Publications

Pollution is a major concern in the present day, causing multiple illnesses and deaths, specifically in developing countries in Asia and Africa. While it has drawn worldwide attention as governments try to issue laws to meet certain criteria for air pollution levels, pollution concentration forecasting has become a major challenge. Particularly, short term forecasting will help to gain information regarding concentrations of harmful pollutants for the upcoming hours and enable better decision-making with regards to controlling air pollution. In this paper, we investigate spatio-temporal graph-based models to determine the best methods for spatial and temporal analysis of data. The models have the additional capacity to perform multi-variate predictions of correlated data, i.e., predicting multiple pollutant concentrations simultaneously, thus requiring lower computational efforts. A real-world pollution dataset measured over Delhi, India, is used to comparing the proposed models with baselines, which shows the Spatio-Temporal Graph Convolution Neural Network (STGCN) models to be performing better than others. For a better understanding of model architectures with the most effective strategies for spatial and temporal data analysis, three models, namely STGCN-A, STGCN-B, STGCN-C have been developed. The models have been compared with 6 other baselines over multiple forecasting horizons of 1 h, 24 h, and 48 h timesteps using various metrics such as mean absolute error (MAE), root mean square error (RMSE), mean absolute percent error (MAPE). On the PM2.5 dataset of Delhi, STGCN-B achieves a performance of 10.53 MAE, 6.92 RMSE and 25.25 MAPE for a 1 h forecast, while STGCN-C achieves 20.18 MAE, 14.73 RMSE and 55.45 MAPE for a 24 h forecast. In general, both structures achieve similar results, with STGCN-C being better in many cases. They are further analysed through observation-prediction graphs and Taylor diagrams, which give an insight into our findings. The models are additionally validated on a benchmark real-world dataset from California, USA for better understanding of the spatio-temporal relations and model performances on a more stable dataset, where STGCN-C performs best for PM2.5 with 4.30 RMSE, 1.98 MAE, 25.96 MAPE for 1 h predictions for univariate data and 3.63 RMSE, 1.88 MAE and 25.91 MAPE in multivariate forecasting. The developed spatio-temporal graph-based models hold promising applications in urban air quality management, aiding policymakers in implementing targeted interventions to mitigate pollution-related health risks. Furthermore, these models can support public health agencies by providing timely and accurate forecasts of pollutant concentrations, enabling proactive measures to safeguard community well-being. Our study showcases the efficacy of spatio-temporal graph-based models in accurately forecasting air pollutant concentrations, with particular emphasis on short-term predictions. By leveraging multi-variate capabilities, our proposed models demonstrate superior performance compared to baseline approaches across various forecasting horizons.

The rise and fall in stock prices are responsible for creating an influence over intra- and inter-sectoral stocks. Through usual market transactions, the mutual dependencies among the stocks/companies are evolved. These kinds of influential effects can be adequately captured by the amount of directional information flow. In this context, attempts have been made to exhibit these kinds of directional influences through segmented entropy networks (e.g., strong, moderate, and weak) using transfer entropy measures. Moreover, these segmentations are required to differentiate different levels of information flow and reduce information loss which might occur for using threshold values during network construction. Naturally, the mutual dependencies among the stocks rely on the dynamic relationships among the influencers and influencees. The existing centralities cannot effectively capture the two aspects of influential nodes. To address the problem, attempts have been made to identify the influencees and influencers in any network through the proposed in-centrality and out-centrality measures. Their performance is compared using the NSE (National Stock Exchange) dataset of India with other existing centralities. It is noted that the financial and energy sectors drive the market as a whole during the period of study. On the other hand, the health care, basic material, and consumer defensive sectors create a moderate impact on the market. Additionally, the influential stocks have high market capitalization and generated high market revenue at that time. The effectiveness of the proposed model has also been compared in terms of its spreading efficacy using a weighted independent cascade model. In addition, the performance results have been validated through the Mann–Whitney U-test. The p-values among the pair of distributions of spreading performance are significantly less than 0.05 for both weak and strong entropy networks which reveal the effectiveness of the models.

The missing readings in various sensors of air pollution monitoring stations is a common issue. Those missing sensor readings may greatly influence the performance of monitoring and analysis of air pollution data. To address this problem, in this paper, a multi-view based missing value (MV) imputation method called MVDI (Multi-View Data Imputation) is proposed for air pollution related time series data. MVDI combines four models namely LSTM (Long-Short Term Memory), IDS (Inverse Distance Squared), SVR (Support Vector Regressor), and KNN (K-Nearest Neighbors) to estimate MVs. These four models are mainly employed to capture the variations in data from different views of the dataset. Here, different views represent different portions (subsets) of the actual dataset. The estimates of MVs from all the views are combined using a kernel function to get an overall result. The proposed model MVDI is evaluated on real-world air pollution dataset in terms of RMSE, MAE, MAPE, and R2. The experimental results show that MVDI dominates over the baseline methods namely AR (AutoRegressive), ARIMA (AutoRegressive Integrated Moving Average), RFR (Random Forest Regressor), ANN (Artificial Neural Network), LI (Linear Interpolation), NN (Nearest Neighbors), MI (Mean Imputation), CNN (Convolutional Neural Network), ConvLSTM (Convolutional LSTM).

The sensors available in the smartphones are useful to explore a diverse range of city dynamics (e.g. noise pollution, road condition, traffic condition, etc.). The potential of the smartphone sensors coupled with their widespread availability help to emerge a new paradigm of sensing known as participatory sensing. It uses the power of smartphone equipped sensors to collect, store, and analyze data with high spatiotemporal granularity. In a participatory sensing based system, a task provider (also known as a crowdsourcer) may have a set of sensing tasks regarding different dynamics of a city. Here, adequate users’ participation is necessary to acquire a sufficient amount of data which is a key factor for the participatory sensing based systems to provide good service quality. The task providers appoint a set of task executors (smartphone users i.e. participants of crowdsensing tasks) to execute those sensing tasks. But, existing works on sensing task allocation suffer from lack of good incentive mechanisms that are attractive for the task executors. In order to address this issue, in this paper, a double auction based incentive mechanism called TATA (Truthful Double Auction for Task Allocation) is proposed for participatory sensing. TATA performs fair allocation of tasks which is leading to efficient incentive mechanism. In the case of TATA, the fair allocation of sensing tasks of the task providers to the task executers indicates that the proposed double auction mechanism is able to satisfy the truthfulness property in order to resist market manipulation (i.e., untruthful bidding and asking). Specifically, TATA achieves all the desirable properties like individual rationality, truthfulness (i.e. incentive compatibility), budget balance, etc. TATA is also computationally efficient and yields high system efficiency. Additionally, the performance of the proposed incentive mechanism is evaluated and compared with the existing mechanisms through extensive simulations based on the real-world data from Amazon Mechanical Turk. TATA yields high utility and satisfaction for the task providers and executors as compared to the existing mechanisms.

As cloud data centers (DCs) have become integral to enterprise computing infrastructure, the upswing in the demand for cloud services has led to significant energy consumption. Thus, efficient energy management techniques have become imperative to address this challenge. Although several methods have been developed for energy reduction through virtual machine consolidation (VMC), they primarily focus on minimizing active hosts, often neglecting the trade-off between energy efficiency and quality of service (QoS) satisfaction. Moreover, optimizing energy efficiency while maintaining QoS becomes increasingly complex in multi-resource environments, especially with diverse workloads. To tackle these issues, we present Resource-Optimized VMC (RO-VMC), a novel VMC framework. It places a primary focus on optimizing resource utilization to balance the energy efficiency-QoS trade-off from the perspectives of both cloud service providers (CSPs) and users. RO-VMC leverages a probabilistic model to capture the inherent stochasticity of workloads and optimizes migration decisions. By considering the complex interplay between energy efficiency and QoS satisfaction, it effectively redistributes the migrating VMs, ensuring the needs and expectations of both CSPs and cloud users are met. Experiments are conducted using the Bitbrains and Google Cloud Cluster traces on a simulated cloud setup to evaluate the effectiveness of RO-VMC. Comparative analysis against state-of-the-art VMC strategies (AFED-EF, EQ-VMC and PEAS) revealed that RO-VMC outperforms them by a significant margin in terms of energy efficiency, QoS satisfaction and resource utilization.

Speech emotion recognition (SER) is one of the most important and active areas of. research in speech processing. Numerous approaches have been proposed to address various limitations in this field, but the sheer diversity of speech emotions, as well as their complexity, continue to make SER a tough nut to crack. This paper attempts to conduct a thorough investigation into speech emotion recognition in order to determine the most appropriate feature set and model for SER. A multi-layer perceptron (MLP) and convolutional neural network (CNN) based ensemble model for SER is proposed, which is a simple yet very powerful model for SER that can greatly improve classification accuracy. The model’s performance is evaluated based on four benchmark datasets, namely RAVDESS (Ryerson Audio-Visual Database of Emotional Speech and Song), EmoDB (Emotional Dat0abase), SAVEE (Surrey Audio-Visual Expressed Emotion), and TESS (Toronto Emotional Speech Set). The proposed model dominates over several baseline methods (decision tree (DT), random forest (RF), support vector machine (SVM), k-nearest neighbour (KNN), and the base learners, i.e., MLP and CNN) in terms of various performance metrics for all the datasets. Furthermore, the proposed model outperforms all previous works for RAVDESS (Acc=73.1%), SAVEE (Acc=83.8%), and TESS (Acc=99.9%) datasets.

Music has always been the most powerful medium to express human emotion and feeling which sometimes mere words cannot express. As a result generating music using machine and deep learning approaches have been quite popular for some time now. It is a very challenging and interesting task to do as imitating human creativity is not easy. This paper attempted to perform effective melody generation using sequential deep learning models particularly LSTMs (Long short-term memory). In this context, note that the previous works exhibit two principal limitations. Firstly, a significant majority of the studies rely on RNN variants that cannot effectively remember long past sequences. Secondly, they often don’t consider the varying temporal context lengths in melody generation during data modeling. In this work, experiments have been performed with different LSTM variants namely Vanilla LSTM, Multi-Layer LSTM, Bidirectional LSTM and different temporal context lengths for each of them to find out the optimal LSTM model and the optimal timestep for efficient melody generation. Moreover, ensembles of the best-performing techniques for each genre (e.g., classical, country, jazz, and pop) are implemented to see if we can generate even better melodies than the corresponding individual models. Finally, a qualitative evaluation is carried out for the generated melodies by conducting a survey that we circulated among fellow colleagues and within the ISMIR community and asked the participants to rate each audio on a scale of 1-5 which helped us in assessing the quality of our generated music samples. All the models have been validated on four datasets that we manually prepared based on their genres namely Classical, Jazz, Country and Pop.

Human activity recognition by the use of smartphone-equipped sensors has gotten a lot of interest in current times because of its large variety of applications.In this regard, this study provides a comprehensive comparative analysis of shallow and deep learning models for smartphone-based HARover high granular daily human activities. Moreover, A robust architecture for smartphone-based HAR is also provided, with stages ranging from data collection to data modelling. A total of seven best performing HAR models namely Decision Tree (DT), Random Forest(RF), DeepNeural Networks (DNN), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Gradient Boosting (GB) and Convolutional Neural Networks (CNN) are investigated. This research work is based on a real-world dataset of 95690 data samples collected from the smartphone sensors of 18 different subjects. The comparative study reveals that three models namely DNN, RF, and GB mostly dominated over the other models in terms of five performance metrics namely accuracy, recall, precision, F1-score, and AUC value.

Physical systems like weather variables, the behavior of oceanic bodies, economic variables, and similar systems possess a considerable amount of chaos, and deducing predictive patterns from them is almost not feasible. Forecasting weather parameters has always been a major objective due to several reasons, but observably not all weather variables are equally influential. Parameters like temperature, humidity, and radiation, though easier to predict due to obvious patterns, are found to be less impactful in practical circumstances. But variables that are more turbulent and difficult to model, like wind flow, cloud cover, sea level pressure, etc. are very influential in the context of managing disasters like cyclones, estimating trades, estimating power generation and many other causes. In this study, the aim is to accurately forecast the horizontal wind velocity field which individually considers the longitudinal and latitudinal components of velocity and sea level pressure over a certain region. Initial attempts in this domain used to be purely mathematical with deterministic results, but predicting real phenomena by overpowering the chaos required enormous computational overhead. The results obtained were not satisfactory. With the evolution of statistical modeling, machine learning and deep learning, these systems were majorly formulated as spatiotemporal forecasting problems. Modified deep learning approaches like ConvLSTM, transformer-based models, CNN-GRU models, and others were applied on the spatiotemporal prediction problem producing more accurate results as compared to the primary methods. But the introduction of reservoir computing framework once again invoked the possibilities of improvements in this domain. An instance of reservoir computing, known as the echo state Network (ESN) was found to simulate and learn the complex dynamics of physical systems with significantly less effort. This boiled down to be a major motivation behind this paper. In this study, we have selected two regions over the Indian peninsula and the Mexican gulf and collected hourly data of horizontal wind velocity and sea level pressure with a spatial granularity of 0.25 degrees on these regions. This data has been used to train our proposed model which is an echo state network and convolution-based encoder–decoder architecture. The model forecasts the same parameters over the same spatial zone for some forecast horizons. The results have been rigorously compared with potential baselines where the ESN was replaced by conventional recurrent networks, and it was observed that our proposed approach outperforms all the other baselines.

Road surfaces can contain a lot of anomalies such as potholes. Understanding and detecting such irregularities are a key towards building a safe road transport system and a step towards building a smart city. This paper makes an attempt to classify road surface images using transfer learning on pre-trained convolution neural network (CNN) based models. In this work, two types of transfer learning approaches namely fine tuning and feature extraction are employed on various state-of-the-art CNN architectures of recent past such as VGG-16 (by Visual Geometry Group), VGG-19, Inception, ResNet-50 (Residual Network), Xception, DenseNet-121, SEResNet-50 (Squeeze-and-Excitation ResNet model), and EfficientNet-B3. The performance of the models are evaluated based on real-world dataset of road surface images collected by the participants. The evaluation metrics considered are test accuracy, precision, recall, F1-score, specificity, area under the receiver operating characteristic curve (ROC-AUC) and also training and inference time measurements. It is observed that among all the deep CNN models, SEResNet-50 (F1-score = 0.954, ROC-AUC = 0.993), Xception (F1-score = 0.943, ROC-AUC = 0.987) and DenseNet-121 (F1-score = 0.941, ROC-AUC = 0.987) achieve the best performance in terms of the evaluation metrics while fine tuning is considered with data augmentation. Effectiveness of the deep CNN models are also evaluated on various benchmark datasets, namely Road Traversing Knowledge (RTK) dataset and pothole dataset.

The term smart city was first coined in the early 1990s. Along with the infrastructure and structural facility, it specifically utilizes a plethora of information technology (IT) innovations and technologies, which are now getting more and more embedded in our daily lives at a breath-taking speed to make cities smarter for the citizens. Smart cities utilize technology-based services and collective knowledge to improve citizens’ efficiency and quality of life (QoL). In this context, the aim of this chapter is to introduce the basic paradigm, tools, and technologies required for monitoring different dynamics of a city (e.g., pollution, traffic condition, road condition, and citizens’ health) using Internet of things (IoT)-based crowd/participatory sensing. There are a variety of smart city applications, some of which are briefly discussed in this chapter. Acquiring data from various dynamics via crowdsensing or participatory sensing is a critical criterion for creating smart environments. Feedback generation over transient data can generate a more efficient system for the smart solution of different technologies. In this chapter, an IoT–cloud-based end-to-end architecture is presented for this purpose. In addition, some open research issues and constraints are also presented to direct future researchers.

Deep learning methods have become the state of the art for spatio-temporal predictive analysis in a wide range of fields, including environmental management, public health, urban planning, pollution monitoring, and so on. Despite the fact that a variety of powerful deep learning-based models can address various problem-specific issues in different research domain, it has been found that no single optimal model can outperform everywhere. Now, in the last two years, various deep learning-based studies have provided a variety of best-performing techniques for predicting COVID-19 health outcomes. In this context, this study attempts to perform a case study that investigates the spatio-temporal variation in the performance of deep-learning-based methods for predicting COVID-19 health outcomes in India. Various widely applied deep learning models namely CNN (convolutional neural network), RNN (recurrent neural network), Vanilla LSTM (long short-term memory), LSTM Autoencoder, and Bidirectional LSTM are considered to investigate their spatio-temporal performance variation. The effectiveness of the models is assessed using various metrics based on COVID-19 mortality time-series from 36 states and union territories of India.

Existence of several challenges and high cost in the development of monitoring infrastructure have become major reasons for data sparsity by statutory government agencies tasked to study pollution exposure in urban areas. As an effort to mitigate this problem, the recent usage of satellite aerosol optical depth data along with the usage of learning algorithms have become popular in recent times. This paper presents a novel four-staged approach using different machine learning, deep learning and statistical methods to develop a spatio-temporal hybrid model for temporal forecasting using data from existing stations along with satellite aerosol optical depth data for spatial interpolation. Experiments conducted on real-world data belonging to the cities of Kolkata, Bengaluru and Mumbai show that a consistent pattern is not followed in all the cities in all stages except in spatial interpolation where Random Forest Regression is found to surpass all other models used. While a long short-term memory network (LSTM Auto-Encoder) when employed in temporal forecasting inside the hybrid method outperforms others in Mumbai, a random forest regression-based method and a multi-layer perceptron-based method outperform others similarly in Kolkata and Bengaluru, respectively.

Air temperature is one of the most important meteorological parameters related with atmospheric and environmental research. In this context, accurate prediction and forecasting of temperature is crucial due to the current global climate change. Although, the short term temperature forecasting have been more or less conquered in the past by using predictive algorithms, the long-term temperature forecasting is still a challenging task. Long term temperature forecasting is previously attempted by deep learning methods like Recurrent Neural Network (RNN), Long Short Term Memory (LSTM), etc. However, the gradient explosion and gradient vanishing problems of the RNN based networks were the major roadblock in the path of long-term prediction. So, in this paper, an attention-based model called ALTF Net (Attention based Long term Temperature Forecasting Network) approaches this problem using an Encoder–Decoder orientation. The Encoder encodes the relative dependencies of the auto-regressive time-series into an attention tensor which is used by the Decoder to produce the prediction. The Encoder is augmented to incorporate a convolution block to recognize the seasonal patterns. The proposed model ALTF uses a Transformer with an augmented encoder to predict temperature up to 150 days with high accuracy, a feat which would be difficult using RNN and LSTM. The model has been trained with years of data from 5 cities around the globe and the performance have been rigorously evaluated in terms of RMSE, MAE, R2, and correlation values. It is observed that the proposed model dominated over several baselines (ARIMA, RFR, KNN, MLP, RNN, CNN, LSTM, and Transformer) for long term temperature forecasting.

Expeditions on Mars and interest in research orienting around these exploration missions have been accelerating more than ever, recently. Due to lack of active human interference in Mars missions, processing and accurate classification of images taken by the rovers is a very essential part of the system. Proper identification of landforms governs the accessibility of the mobile rovers on Mars’ surface. Moreover, NASA has already collected over two million images from the planet, and more volumes are yet to arrive as these photographs serve as major documents for photogrammetry and studies based on remote sensing. Automatic labeling of incoming images and also making searching of the image database easier in the public interest requires highly accurate image classifiers. Deriving motivation from the above causes, this study intends to implement an efficient supervised multi-class image classifier for identifying Mars imagery. However, this objective is confronted by a major bottleneck. Most datasets that are accurately labeled, portray a highly skewed nature and insufficient data to train a deep model from scratch. The MSL surface imagery labeled dataset captured by the Curiosity rover, that has been considered for this study, is one such dataset with only 6691 images distributed unevenly into 25 classes. These obstacles are less signified in the existing literature and hence this paper addresses these challenges, outperforming the state-of-the-art metrics. Due to the absence of large data volume, a transfer learning based methodology was considered, using very deep convolutional networks pre-trained on ImageNet dataset. But images from Mars often involve a difference in hue, contrast and clarity when compared with images taken on Earth. Hence, the deep model was fine-tuned with our dataset and the extracted feature from the tuned neural network was used for the final classification. It was found that the results obtained from a single pre-trained model were not optimum and that ensemble approaches could unify many such results into a better result. Similar feature vectors were extracted from a few other pre-trained models. The whole setup converges into a dynamic routing module, a novel polling algorithm, which for each image, comes to an agreement about the best set of features while generating the output probability vector. The proposed approach is evaluated by several numeric metrics like accuracy, precision and recall, confusion matrices and roc curves, against the chosen individual pre-trained models and most prominent ensemble methods. Mars-TRP produces a test accuracy of around 88% in the standard test set of MSL surface dataset and an accuracy of 96% in the HiRise dataset, outperforming the individual pre-trained models, all the ensemble baselines and other existing approaches.

Occupancy detection and prediction are two well-established problems which can be improved further to achieve higher accuracy in both cases than the existing solutions. To achieve the desired higher accuracy, proposed OccupancySense model detects human presence and predicts indoor occupancy count by the fusion of Internet of Things (IoT) based indoor air quality () data along with static and dynamic context data which is a unique approach in this domain. This data fusion helps us to achieve higher forecasting accuracy along with the integration of state of the art gradient boosting based categorical features supported CatBoost algorithm. For comparison, other commonly used machine learning classification and regression algorithms, e.g., Multiple Linear Regression (MLR), Decision Tree (DT), Random Forests (RF) and Support Vector Machine (SVM) for regression and Logistic Regression (LR), Naïve Bayes (NB), Decision Tree (DT) and Random Forest (RF), Support Vector Machine (SVM) for classification, were also assessed during this experiment. Out of these, CatBoost outperformed other models when considered in terms of accuracy. Hence, CatBoost is used as the core of the OccupancySense design and we have validated the proposed model by a real-world case study with continuous 91 days of indoor data, having 33 unique external features. These features are collected directly as well as derived from the collected data. To handle these features, feature engineering plays a key role in the OccupancySense model. The speciality of this model is, it is non-intrusive one but have high predictive power. It can detect occupancy and predicts headcount along with occupancy density of the room pretty accurately with 99.85%, 93.2% and 95.6% respectively (with 10 fold cross-validation) which outperforms other state of the art models.

Analysis and prediction on real time air quality data is a critical step in solving various problems related to pollution and finding a genuine solution. However, missing values in air pollution data is a serious issue that may greatly influence the performance of such analysis and prediction. In order to address this problem, a 2-step process is proposed, consisting of a data pre-processing stage using Q-FUZZY (Quantized Fuzzification) model and data imputation stage via a Fuzzy Imputation Model(FIM) to handle this complexity. We have validated the proposed approach using a real world dataset of Kolkata, India containing pollution levels of different air pollutants along with meteorological parameters. Various performance measures are used to determine the effectiveness of FIM. Moreover, the performance of the proposed model is also compared with the baselines namely, FLAR (Fuzzy Least Absolute Regression), ridge regression and EMD-SVR-SARIMA (Empirical Mode Decomposition-Support Vector Regressions-Seasonal Autoregressive Integrated Moving Average). On comparison, it is observed that FIM achieves an overall better performance in terms of distance measures, Mean Similarity Measures (MSM), Mean Inclusion Measures (MIM) and Mean Predictive Ability (MPA).

Emotion identification based on multimodal data (e.g., audio, video, text, etc.) is one of the most demanding and important research fields, with various uses. In this context, this research work has conducted a rigorous exploration of model-level fusion to find out the optimal multimodal model for emotion recognition using audio and video modalities. More specifically, separate novel feature extractor networks for audio and video data are proposed. After that, an optimal multimodal emotion recognition model is created by fusing audio and video features at the model level. The performances of the proposed models are assessed based on two benchmark multimodal datasets namely Ryerson Audio–Visual Database of Emotional Speech and Song (RAVDESS) and Surrey Audio–Visual Expressed Emotion (SAVEE) using various performance metrics. The proposed models achieve high predictive accuracies of 99% and 86% on the SAVEE and RAVDESS datasets, respectively. The effectiveness of the models are also verified by comparing their performances with the existing emotion recognition models. Some case studies are also conducted to explore the model’s ability to capture the variability of emotional states of the speakers in publicly available real-world audio–visual media.

Poor air quality is becoming a critical environmental concern in different countries over the last several years. Most of the air pollutants have serious consequences on human health and wellbeing. In this context, efficient forecasting of air pollutants is currently crucial to predict future events with a view to taking corrective actions and framing effective environmental policies. Although deep learning (DL) as well as statistical forecasting models are investigated in the literature, they have rarely used in air pollutant-specific optimal model building for long-term forecasting. In this paper, our aim is to develop the pollutant-specific optimal forecasting models for the phases spanning from preprocessing to model building by investigating a set of predictive techniques. In this regard, this paper presents a methodology for long-term forecasting of some important air pollutants. More specifically, a total of eight best performing models such as stacked LSTM, LSTM auto-encoder, Bi-LSTM, convLSTM, Holt-Winters, auto-regressive (AR), SARIMA, and Prophet are investigated for developing pollutant-specific optimal forecasting models. The study is carried out based on the real-world data obtained from government-run air quality monitoring units in Kolkata over a period of 4 years. The models such as Holt-Winters, Bi-LSTM, and ConvLSTM achieve high forecasting accuracy with respect to MAE and RMSE values for majority of the pollutants.

One of the most challenging tasks in time-series prediction is a model’s capability to accurately learn the repeating granular trends in the data’s structure to generate effective predictions. Traditionally specially tuned statistical models and deep learning models like recurrent neural networks and long short-term memory networks are used to tackle such problem of sequence modeling. However in practice, factors like inadequate parameters in case of statistical models, random weight initializations, and data inadequacy in case of deep learning models affect the resulting final predictions. As a possible solution to these known problems, this paper introduces a novel method of time-series labeling (TSL) comprising a combination of encoding and decoding methodologies that not only takes into account the granular structure of a time-series data but also its underlying meta-learners for better predictive accuracy. To demonstrate the approach’s effectiveness and capability of handling wide range of scenarios, comparisons are drawn first over different widely used statistical and deep learning models and then applying TSL to each of them in order to showcase the resulting performance improvement when implemented over a wide variety of real-world datasets. The experimental findings reflect an average of 25% increase in overall performance when using TSL along with mostly similar performance of different combinations regardless of model complexity thereby proving its efficacy in predicting periodic data.

Adequate nighttime lighting of city streets is necessary for safe vehicle and pedestrian movement, deterrent of crime, improvement of the citizens’ perceptions of safety, and so on. However, monitoring and mapping of illumination levels in city streets during the nighttime is a tedious activity that is usually based on manual inspection reports. The advancement in smartphone technology comes up with a better way to monitor city illumination using a rich set of smartphone-equipped inexpensive but powerful sensors (e.g., light sensor, GPS, etc). In this context, the main objective of this work is to use the power of smartphone sensors and IoT-cloud-based framework to collect, store, and analyze nighttime illumination data from citizens to generate high granular city illumination map. The development of high granular illumination map is an effective way of visualizing and assessing the illumination of city streets during nighttime. In this article, an illumination mapping algorithm called Street Illumination Mapping is proposed that works on participatory sensing-based illumination data collected using smartphones as IoT devices to generate city illumination map. The proposed method is evaluated on a real-world illumination dataset collected by participants in two different urban areas of city Kolkata. The results are also compared with the baseline mapping techniques, namely, Spatial k-Nearest Neighbors, Inverse Distance Weighting, Random Forest Regressor, Support Vector Regressor, and Artificial Neural Network.

Smart handheld devices such as smartphones are capable of sensing and interacting with surrounding environments. This emerging capability of smartphones has resulted in the utilization of it as input devices and led it to be used as the default physical interface in applications of ubiquitous computing. Mobile crowdsensing is a new paradigm, which utilizes the different sensors in the smart devices to sense data from the surroundings and then transmit large amount of data to the cloud to be analyzed, managed, and stored. Crowdsourcing, on the other hand, can be defined as a model to solve a complex problem that is distributed in nature, where a crowd of unspecific size is utilized through an open call. The usage of smart devices with unique multi-sensing proficiency and context-aware capability will be able to utilize the full potential of crowdsourcing. Hence, the smart devices with the capability of sensing the environment and utilization of the wisdom of the crowd can be utilized for various benefits of the society for a better standard of living. In this survey, we present a comprehensive understanding of mobile crowdsensing and mobile crowdsourcing and how it has helped in improving the standard of living of people, specifically in the context of smart cities. Pertaining challenges have been highlighted which were creating hindrances in smooth implementation of these techniques and a few of the solutions have been discussed.

In any online social media platform, it is necessary to reduce the effect of rumor data from original information as it may cause harm to society. Influential users can be detected through different centrality measures. When the rumor is generated through some influential users, they have more impact on society. Here, we have proposed a prognostic method to distinguish those influential users of online social media, based on network analysis. The susceptible-infectious-recovered (SIR) model has been used for simulation of the propagation of information. For the particular seed nodes which have been chosen by practicing different centrality measures, detailed relative learning in terms of infected nodes is also exhibited. Selection of seed nodes through centrality measure is computationally exhaustive; therefore, we form a composite model, where the original social network is decomposed using the k-core, and centrality nodes are obtained from that decomposed network. Centrality measurements thus derived from the generated network are used as the seed of information propagation. Another important result derived from the empirical study is that not only the influential nodes, but neighbors of the influential nodes also have a greater impact on maximizing the effect of rumors.

Time series forecasting has gained enormous research significance and has vast applications in the field of monitoring environmental air pollution and meteorological conditions. In this context, this work presents a comparative study of some machine learning and deep learning techniques for forecasting two air pollutants (NO2 and O3) and two meteorological parameters (relative humidity and solar radiation). The study is conducted with five well-defined models such as K-nearest neighbour regression (KNN), support vector regression (SVR), hidden Markov models (HMM), convolutional neural networks (CNN) and Long Short-Term Memory (LSTM) networks. The models are evaluated based on the real-world air pollution and meteorological data collected from the government set-up monitoring station in Kolkata, India. The root mean squared error (RMSE) and symmetric mean absolute percentage error (SMAPE) are used as metrics for performance evaluation. The findings reflect that the methods such as SVR and KNN outperform in terms of RMSE and SMAPE values over other methods. The study also shows that HMM fails to capture the pattern in the air pollution and meteorological time series data.

The behaviour of individual users in an online social network is a major contributing factor in determining the outcome of multiple network phenomenon. Group formation, growth of the network, information propagation, and rumour blocking are some of the many network behavioural traits that are influenced by the interaction patterns of the users in the network. Network motifs capture one such interaction pattern between users in online social networks (OSNs). For this work, four second-order (two-edged) network motifs have been considered, namely, message receiving pattern, message broadcasting pattern, message passing pattern, and reciprocal message pattern, to analyse user behaviour in online social networks. This work provides and utilizes a node interaction pattern-finding algorithm to identify the frequency of aforementioned second-order network motifs in six real-life online social networks (Facebook, GPlus, GNU, Twitter, Enron Email, and Wiki-vote). The frequency of network motifs participated in by a node is considered for the relative ranking of all nodes in the online social networks. The highest-rated nodes are considered seeds for information propagation. The performance of using network motifs for ranking nodes as seeds for information propagation is validated using statistical metrics Z-score, concentration, and significance profile and compared with baseline ranking methods in-degree centrality, out-degree centrality, closeness centrality, and PageRank. The comparative study shows the performance of centrality measures to be similar or better than second-order network motifs as seed nodes in information diffusion. The experimental results on finding frequencies and importance of different interaction patterns provide insights on the significance and representation of each such interaction pattern and how it varies from network to network.

From the popular concept of six-degree separation, social networks are generally analyzed in the perspective of small world networks where centrality of nodes play a pivotal role in information propagation. However, working with a large dataset of a scale-free network (which follows power law) may be different due to the nature of the social graph. Moreover, the derivation of centrality may be difficult due to the computational complexity of identifying centrality measures. This study provides a comprehensive and extensive review and comparison of seven centrality measures (clustering coefficients, Node degree, K-core, Betweenness, Closeness, Eigenvector, PageRank) using four information propagation methods (Breadth First Search, Random Walk, Susceptible-Infected-Removed, Forest Fire). Five benchmark similarity measures (Tanimoto, Hamming, Dice, Sorensen, Jaccard) have been used to measure the similarity between the seed nodes identified using the centrality measures with actual source seeds derived through Google's LargeStar-SmallStar algorithm on Twitter Stream Data. MapReduce has been utilized for identifying the seed nodes based on centrality measures and for information propagation simulation. It is observed that most of the centrality measures perform well compared to the actual source in the initial stage but are saturated after a certain level of influence maximization in terms of both affected nodes and propagation level.

In smartphone-based crowd/participatory sensing systems, it is necessary to identify the actual sensor data provider. In this context, this paper attempts to recognize the users’ identity based on their gait patterns (i.e. unique walking patterns). More specifically, a deep convolution neural network (CNN) model is proposed for the user identification with accelerometer data generated from users smartphone sensors. The proposed model is evaluated based on the real-world benchmark dataset (accelerometer biometric competition data) having a total of 387 users accelerometer sensor readings (60 million data samples). The performance of the proposed CNN-based approach is also compared with five baseline methods namely Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Logistic Regression (LR), and K-Nearest Neighbours (KNN). It is observed that the proposed model achieves better results (accuracy = 98.8%, precision = 0.94, recall = 0.97, and F1-score = 0.95) as compared to the baseline methods.

Spatial distributions of data of natural phenomena can be estimated by using different spatial interpolation techniques. These techniques can be used for the purpose of developing urban noise pollution monitoring applications, so they can truly describe the actual urban noise pollution scenario of any region of interest to make effective and informed decisions. In this context, our aim is to use IoT-cloud based framework to generate dynamic (i.e., changes in terms of time and space) noise maps as a service with the help of spatial interpolation techniques. Noise map generation is an effective method for visualizing and assessing urban noise pollution. In this article, we have proposed three spatial interpolation techniques (GLIDW, I-GLIDW, GLIDW-OK) that work on participatory sensing-based noise pollution data collected using smartphones as IoT devices to generate dynamic noise maps. Proposed techniques can address diverse scenarios such as sparse datasets, high accuracy, better response time, and so on. Depending on the situation, we can choose an appropriate technique. We evaluate our proposed methods based on a real-world urban noise pollution dataset collected by participants over a period of two years in an urban area of the city Kolkata. The results are compared with inverse distance weighting (IDW) and Ordinary Kriging (OK) methods. The method GLIDW is proposed for a dense dataset. The results validate that in the case of a dense dataset GLIDW dominates over other methods. But, when the data sparsity level is medium, I-GLIDW performs well. However, if the dataset is very sparse, then GLIDW-OK dominates in terms of predictive accuracy. The results also show that Relative Improvement (RI) of I-GLIDW and GLIDW-OK is always positive compared to baseline methods IDW and OK.

Indoor air pollutants e.g., Carbon dioxide (CO2), Particulate Matter(PM)2.5, PM10, Total Volatile Organic Compounds (TVOC), etc. have a serious impact on human health. Out of these pollutants, CO2 is one of the most dominant one. Hence, proper monitoring and control of this pollutant is an important part of maintaining a healthy indoor. To make this happen, it is required to predict the next moment’s indoor pollutant level at an acceptable accuracy range that ensures necessary steps can be taken beforehand to avoid a rise in the indoor pollution level for maintaining a healthy indoor all the time. It also helps people plan ahead, decreases the adverse effects on health and the costs associated. For this experiment, we have collected three months of real-life time-series data along with proper context information and have gone through feature engineering and feature selection process to create model ready data. Now, since the indoor CO2 concentration is dependent on multiple external factors (context data) which in turn is dependent on time, makes it a time-dependent function. Hence, to predict the indoor pollutant CO2, here we have used the time series forecasting model based on our collected data nature. This is a powerful tool and used in a wide range of research domains for predicting the next moment’s target value. This model ready data is utilized in forecasting different time series models. According to our findings, among the selected popular time series models, the SARIMAX time series model is best suited for this forecasting problem which is utilizing indoor context information along with historical data (with 10 Fold Time-Series Split Cross-Validation score 0.907). We have achieved an average of RMSE 26.45 ppm (i.e., 97.36% accuracy) level based on a three day average for indoor pollutant prediction which is outperforming other relevant models in this domain.

Proper maintenance of roads is an extremely complex task and also an important issue all over the world. One of the most critical road monitoring and maintenance activities is the detection of road anomalies such as potholes. Identification of potholes is necessary to avoid road accidents, prevent damage of vehicles, enhance travelling comforts, etc. Although maintenance of roads is considered to be a serious issue by the authorities over the years, lack of proper detection and mapping of road potholes makes the issue more severe. To overcome this problem, an end-to-end system called PotSpot is built for real-time detection, monitoring, and spatial mapping of potholes across the city A Convolutional Neural Network (CNN) model is proposed and evaluated on real-world dataset for pothole detection. Additionally, real-time pothole-marked maps are generated with the help of Google Maps API (Application Programming Interface). To provide an end-to-end service through this system, both the pothole detection and pothole mapping are integrated through an android application. The proposed model is also compared with six baselines namely Artificial Neural Network (ANN), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and three pre-trained CNN models InceptionV3, VGG19 and VGG16 in terms of performance metrics to verify its effectiveness. The proposed model achieves better accuracy (≈ 97.6 %) as compared to the above-mentioned baseline methods. It is also observed that the Area Under the Curve (AUC) value for the proposed pothole detection model (AUC= 0.97) is higher than the baseline methods.

COVID-19 is a global crisis where India is going to be one of the most heavily affected countries. The variability in the distribution of COVID-19-related health outcomes might be related to many underlying variables, including demographic, socioeconomic, or environmental pollution related factors. The global and local models can be utilized to explore such relations. In this study, ordinary least square (global) and geographically weighted regression (local) methods are employed to explore the geographical relationships between COVID-19 deaths and different driving factors. It is also investigated whether geographical heterogeneity exists in the relationships. More specifically, in this paper, the geographical pattern of COVID-19 deaths and its relationships with different potential driving factors in India are investigated and analysed. Here, better knowledge and insights into geographical targeting of intervention against the COVID-19 pandemic can be generated by investigating the heterogeneity of spatial relationships. The results show that the local method (geographically weighted regression) generates better performance (R2=0.97) with smaller Akaike Information Criterion (AICc =−66.42) as compared to the global method (ordinary least square). The GWR method also comes up with lower spatial autocorrelation (Moran’s I=−0.0395 and p<0.01) in the residuals. It is found that more than 86% of local R2 values are larger than 0.60 and almost 68% of R2 values are within the range 0.80–0.97. Moreover, some interesting local variations in the relationships are also found.

Tackling air pollution has become of utmost importance since the last few decades. Different statistical as well as deep learning methods have been proposed till now, but seldom those have been used to forecast future long-term pollution trends. Forecasting long-term pollution trends into the future is highly important for government bodies around the globe as they help in the framing of efficient environmental policies. This paper presents a comparative study of various statistical and deep learning methods to forecast long-term pollution trends for the two most important categories of particulate matter (PM) which are PM2.5 and PM10. The study is based on Kolkata, a major city on the eastern side of India. The historical pollution data collected from government set-up monitoring stations in Kolkata are used to analyse the underlying patterns with the help of various time-series analysis techniques, which is then used to produce a forecast for the next two years using different statistical and deep learning methods. The findings reflect that statistical methods such as auto-regressive (AR), seasonal auto-regressive integrated moving average (SARIMA) and Holt–Winters outperform deep learning methods such as stacked, bi-directional, auto-encoder and convolution long short-term memory networks based on the limited data available.

Forecasting time series has acquired immense research importance and has vast applications in the area of air pollution monitoring. This work attempts to investigate the abilities of various existing techniques when applied for short term, high granular time series forecasting of PM2.5. More specifically, a comparative study has been provided, taking into account both popularly used models and lesser-used models in this area. The study has been carried out considering ten well defined models that are ARIMA (auto-regressive integrated moving average), SARIMA (seasonal ARIMA), SES (single exponential smoothing), DES (double exponential smoothing), TES (triple exponential smoothing), ANN (artificial neural network), DT (decision tree), kNN (k-nearest neighbor), LSTM (long short-term memory) and MCFO (markov chain first order). A framework has been built that categories the models, implements them under identical execution environment and forecasts succeeding values. Implementation has been carried out over five data sets of real-world air pollution time series, that are collected from five differently located government setup monitoring stations over a period of 1 year (July 2018-June 2019). Rigorous statistical analysis has been performed that yields an insight to the nature and variability of these time series data. Forecasting has been carried out on short term basis, focusing on high granularity whereas, three different lengths of forecast horizon (1 day, 1 week, and 1 month) have been tested. Eventually, the models have been compared in terms of their associated performance measuring units namely, RMSE (root mean of squared error), MAE (mean absolute error) and MAPE (mean absolute percentage error). The comparative results verified with multiple datasets show that all the models posses less error for a shorter forecast horizon, where LSTM providing the best performance. Superiority of machine learning and deep learning models are found in case of longer length of forecast horizon with kNN achieving best accuracy whereas, significant performance degradation of ARIMA is found for longer forecast horizon. Moreover, TES, DT, kNN, LSTM, MCFO are found to be well adopted in relation with shape and variability of the data. Note that the performance on various length of high granular forecast horizon have been studied over multiple datasets that give an added value to this work.

The demand of cloud-based services is growing rapidly due to the high scalability and cost-effective nature of cloud infrastructure. As a result, the size of the data center is increasing drastically, so is the cost of maintenance in terms of resource management and energy consumption. Hence, it is important to develop a proper resource management plan to maximize the profit by reducing the overhead of operational cost. In this paper, we propose a multi-step-ahead workload prediction approach using Machine learning techniques and allocate the resources based on this prediction in a way that allows the resources to be utilized more efficiently and thereby, reducing the data center’s overall energy consumption. We evaluate the effectiveness of our framework based on real workload trace of Bitbrains. Experimental results show that our framework outperforms other state-of-the-art approaches for predicting workload over a long-run and significantly improves resource utilization while enabling substantial energy savings.

As the number of enterprises dispatching their workload to the cloud has increased significantly over the last decade, service level agreements (SLAs) becoming a key element to consider for maintaining the quality of service (QoS). In order to facilitate the perseverance of service quality at a satisfactory level, clouds perform load balancing through migration of virtual machines (VMs) from overloaded physical machines (PMs). However, there are several challenges in achieving effective and efficient load balancing. First, VMs in clouds use different resources to serve a variety of applications, which results in varying levels of resource overutilization in different PMs. Second, due to the application’s time-varying heterogeneous nature of resource requirements, the PM’s resource consumption vary over time, making the profiling of resources difficult. Migration decisions in previous load balancing techniques are mostly based on deterministic resource demand estimation, which treats each resource equally and leads to inefficient migrations, causing severe SLA violations in terms of performance degradation. To address this problem, we propose a SLA-aware stochastic load balancing scheme using VM migrations, namely SLA-LB. It provides probabilistic guarantee against resource overloading, while satisfying the SLA. As opposed to previous methods, SLA-LB dynamically assigns different weights to different resources based on PM’s overload probability and effectively addresses the multidimensional resource requirement with stochastic characterization. Experimental results using PlanetLab and Google Cluster trace show that SLA-LB outperforms previous load balancing methods, i.e., RIAL, Sandpiper and CloudScale in terms of performance degradation by an average margin of 10.8%, 23.53% and 33%, respectively.

Energy harvesting facilitates Wireless Sensor Networks (WSN) to work in perpetual mode. But, the amount and duration of green energy depend on the unpredictable behavior of ambient energy sources. Limited knowledge of future energy availability is the main constraint in designing routing and MAC (Medium Access Control) protocol. If the prediction of future energy availability can be done with fine accuracy, then energy management strategies can be designed accordingly. Predicting solar irradiance value is a challenging issue as it has seasonal and daily temperature variation. Enhanced-Pro, a novel energy prediction strategy is proposed here by considering past energy observations as well as current energy intake, and its effectiveness is also tested. It is a modification of Pro-Energy, which is a landmark solar energy prediction solution in terms of accuracy. In this work, real-life solar traces are used for prediction. The algorithm incorporates two factors tuning factor and fine adjustment index. These two factors help to enhance prediction accuracy. Enhanced-Pro is compared with Pro-Energy, I-Pro-Energy, and QL-SEP. The simulation result proves Enhanced-Pro delivers better performance in the scale of computational complexity and accuracy.

The physiological and psychological well-being of humans depends on an extensive set of factors, of which pollution is the most ubiquitous. Its effects are often latent but extremely detrimental, especially in the case of noise pollution. In pollution monitoring and smart city systems, predicting noise from urban road traffic is of utmost significance. It is a difficult task due to the complexity of spatial correlations among the locations and temporal correlations among the timestamps, coupled with the diverse nature of these spatio-temporal correlations which are also dependent on the type of area in which the locations are situated. As a solution, we propose a participatory sensing-based solution to assess the road traffic noise by attaining a high level of granularity. We subsequently predict the noise values with a hybrid predictor that uses a regression model and ordinary kriging. Our solution outperforms the baseline regression and kriging methods and thus provides a novel method to gain a deeper insight into the levels of road traffic noise pollution. The effectiveness and strength of the proposed method are validated by extensive experiments with a real-world participatory sensing-based road traffic noise dataset.

Indoor Air Pollution is one of the most ignored topics that require serious investigation. People spend most of their lives in either closed AC offices or within AC bedrooms which are not monitored at all. Several indoor air pollutants can affect human health out of which CO2 is most dominant. Time series forecasting is a very powerful tool which has been successfully used in a wide range of research domain for predicting next moment’s value if it is time-dependent. Here, we have found this tool fits well in the present scenario and thus used for solving this issue. Out of the different time series models present in the domain, using the SARIMA model, we have achieved a prediction accuracy of 102.2 parts per million (ppm), i.e., 89.78% for the indoor pollutant prediction which is outperforming other forecasting models.

Street garbage monitoring is important for ensuring a clean and healthy civic environment. In this context, automatic detection and classification of waste/litter objects on the streets is necessary for proper garbage disposal. Specifically, such detection and classification of waste objects could be utilized in developing automated waste sorting applications. This paper attempts to build a Faster R-CNN based predictive model for automatic classification of ten different types of waste/litter objects. Two pre-trained networks namely Inception-V2 and ResNet-101 are investigated as backbone networks for feature extraction. The performance of the proposed model is also compared with two baselines namely RFCN (region-based fully convolutional network) and SSD (single shot multibox detector). It is observed that the Faster R-CNN configured with InceptionV2 achieves the highest mAP (mean average precision) of 92%.

In mobile crowd-sensing, smartphone users take part in sensing and then share the data to the server (cloud) and get an incentive. These data can be utilized for providing better services to improve quality of life. Batteries used in smartphones constrain the usability of these devices for longer charge cycles. Hence, maintaining a balance between energy consumption due to crowd-sensing application and that due to the current computational load on the device is the need of the hour. Consequently, in this paper, we formulate strategies applying Markov Decision Process (MDP) by which a smart handheld would crowd-sense while keeping the device active for a longer period of time. MDP used here helps to decide when a device would lend itself to crowd-sense considering the remaining energy of the device, it’s recharging probability, current computational load,and the incentive it receives. In this work, we have considered indoor localization as an example of a smartphone based crowd sensing application. The strategies found by solving MDP formulation are implemented for a smartphone application for crowd-sensed indoor localization. We have experimented using 5 smart handheld devices for different use cases. Our scheme is found to perform better than the state-of-the-art works.

Participatory sensing has become an effective way of sensing urban dynamics due to the widespread availability of smartphones among citizens. Traditionally, separate urban sensing applications are designed to monitor different urban dynamics like environment, transportation, mobility, etc. However, combining these applications to aggregate information can lead to various new inferences. The main objective of this work is to improve urban sensing applications by overcoming their individual limitations. A unified framework called JUSense (Judicious Urban Sensing) is proposed that can derive benefits from these applications by combining their functionalities. JUSense provides the opportunity for applications to tackle the challenges associated with data collection, aggregation of data in cloud, calibration, data cleaning, and prediction. A multi-view fusion model is proposed for spatiotemporal urban air and noise pollution map generation. Further, a random forest classifier is built to classify the driving events. Here, large scale experiments are performed to evaluate the efficacy of JUSense on real-world dataset. Both the fusion model and the random forest classifier yield better accuracies compared to the baseline methods. Additionally, case studies are conducted to show the advantages that can arise out of the mutual interactions among the applications.

Cloud federation is a new computing paradigm that has paved the way for cloud service providers (CSPs) to offer their unused resources (virtual machine) to other CSPs when their resource demands are low. Federation also allows CSPs to outsource their resource requests to other CSPs when their computing resources' demands are high. Thus, in cloud federation environment reliability and availability of services offered by service providers increase as the CSPs are able to share their resources among themselves. Moreover, to maintain the reliability and availability of cloud services offered through federation, it is important that the computational environment of member CSPs within the federation is fault tolerant. Therefore, there is a need for fault tolerant system to guarantee cloud service reliability and availability in cloud federation environment. In this paper, we propose a proactive fault tolerance system that preempts faults within the federation on the basis of CPU temperature. The fault tolerance system within the federation is modeled as a multi-objective optimization problem of maximizing profit and minimizing migration cost while redistributing resources (virtual machine) from faulty CSPs to non-faulty CSPs within the federation. To address this issue, we have also proposed an algorithm called Preference Based Fault Management (PBFM) to manage the federation in the event of faults. We perform extensive experiments to evaluate the effectiveness of our proposed mechanism and compare it with two other mechanisms MCAFM (Migration Cost Assured Fault Management) and PAFM (Profit Assured Fault Management). Results show that our proposed mechanism PBFM yields an optimized solution to the general problem of profit and migration cost trade-off in presence of faulty CSPs.

Computation offloading effectively expands the usability of mobile terminals beyond their physical limits, and also greatly extends their battery charging intervals. Offloading or cyber foraging is a technique by which large and complex computational jobs are relocated from lightweight portable devices (such as smartphones) called offloadee to powerful servers (such as nearby laptops/desktops or cloud server over the Internet) called surrogates, and getting the output back at the offloadee. Many research works have been done so far on the architecture of offloading systems, but only few works can be found on fault detection and tolerance. So this paper concentrates on categorizing different failures that may affect the benefit of offloading computation and proposes a fault-tolerance approach to alleviate those faults. The checkpoint based fault-tolerance approach proposed in this paper is able to handle crash, omission and transient failures altogether. Fault prevention is obtained by utilizing historical data for choosing worthy surrogate from known neighborhood. This fault tolerance model is evaluated by applying a real application named πcalculator and Scimark benchmark suite. The system is implemented and the proposed approach is found to be effective with respect to energy consumption and resource utilization even in case of crash and omission failure.

Online Social Networks (OSNs) are largely popular. People interact daily on networks such as Facebook, Twitter, YouTube, Email, Messenger, WhatsApp, Google+, Quora, LiveJournal etc. and the types of interaction on these networks are different. The types of content that people share on these networks are also different. Each of the OSNs serves a different purpose, such as sharing multimedia, microblogging, serving as a Question and Answer forum etc. Moreover, the community structure of these networks is also different. However, currently, all OSNs are considered as scale-free network based on the power-law degree distribution nature of these networks. In this paper, the effect of network properties such as density, diameter, degree distribution, global clustering coefficient, local clustering coefficient, homophily, assortativity and other centrality measures such as power-law exponent, eigenvector centrality and closeness centrality on seven online social networks, namely, Facebook, Twitter, YouTube, Email, Google+, Epinions and Gowalla networks are studied. The differences and similarities in the empirical results are analyzed, and the OSNs are divided categories based on the observed differences and similarities in network properties and centrality measures.

The governance for smart cities will be more citizen-centric and government policies will be based on the demand of the citizen. Social network has the potential of elevating the governance process to new levels. It enables government for instantaneous transmission of information to the targeted citizen, processing large scale data available through social media and can enable to take decisions based on that data in judicial way to increase transparency and accountability. For smart governance, it is required that within a limited budget government can propagate information to the maximum people. Social media analysis provides knowledge to ensure maximize the influence. Similarly for misinformation/rumour, influence can be minimized and SNA helps to identify communities and locations affected by this information. Moreover it can be used to identify those influential users who are able to spread information. This knowledge will empower Government agencies to take necessary precautionary measures such as targeted campaigning against the rumour, identified the source of information, block the source node or delayed rumour propagation. In this chapter we will study an conceptual framework for generating a governance system which will be able to identify the citizens those have maximum influence in the social network, campaigning of government policies through them for the maximum propagation to the citizen with minimum budget, detect rumour, found the source of misinformation, block the source node of rumour, detection of community, generating anti-spreading model for already propagated rumour.

Information propagation in the network is probabilistic in nature; simultaneously, it depends on the connecting paths of the propagation. Selection of seed nodes plays an important role in determining the levels and depth of the contagion in the network. This paper presents a comparative study when seed nodes for information propagation are selected through the properties of different centrality measures in the social network. This study captures the interaction measures of nodes in the social network, selects seed nodes based on five centrality measures, i.e. degree distribution, betweenness centrality, closeness centrality, Eigenvector and PageRank, and compares the affected nodes and levels of propagation within the network. We demonstrate the performance of the different centrality measures by processing three datasets of social network: Twitter network, Bitcoin network and author collaborative network. For the propagation of the information, we use breadth-first search (BFS) and susceptible–infectious–recovered (SIR) model and a detailed comparative study is also presented for each of the seed nodes selected using aforementioned network properties. Results show that the Eigenvector centrality and PageRank centrality measures outperform other centrality measures in all test cases in terms of propagation level and affected nodes during information propagation. Both Eigenvector and PageRank network data processing required a high computational overhead. For this reason we propose a hybrid model where using k-core the network is degenerated into a smaller network and centrality nodes are extracted from the smaller network. These centrality nodes, as compared to original centrality nodes, perform almost in the same manner in terms of influence maximization when k is chosen in a rational way.

Changes in the BAN topology are caused due to the body movement induced by repeated activities like walking, running, twisting, turning and waving arms. In such activities, individual nodes may move relative to each other and along with this, the entire BAN may move its absolute location, which can induce several complexities in the network like re-transmission, collision, overhearing and changing interference. This paper presents a scheme referred as, posture based data transmission (PBDT) with the objective of efficient data transmission. PBDT is based on the occurrence of potential (best) posture over time in repeated activities. In PBDT, each node follows the procedures: (a) recognized the sequence of postures by observing the variation of received signal strength indicator (RSSI) from neighbor nodes over time, (b) finds the best posture from posture sequence for data transmission, (c) maintains a dynamic active/sleep schedule in order to reduce lossy transmission, collision and overhearing. Here, we consider walking as a repeated action over time to check the validity of the proposed mechanism. PBDT is implemented using Castalia simulator and compared with selected MAC protocols. The results are analyzed in respect to the energy consumption and throughput.

The application of wireless sensor networks (WSNs) technology in monitoring systems is demanding more efficient services to fulfill the requirements of the monitoring task. For this purpose, the simultaneous presence of features such as different communication mediums (air and water) used by nodes and various sizes of data generated by heterogeneous nodes are the key obstacles to build a communication protocol, which can ensure the reliable data delivery. This work terms such WSNs as mixed wireless sensor networks (MWSNs) which contains the aforementioned features. In this paper, we introduce a new cross-layer protocol for mixed wireless sensor network (XMSN) which can adapt these features. The proposed cross layer protocol XMSN for such mixed environment is implemented and analyzed extensively in Castalia simulator. The performance of XMSN is compared with composition of well-known protocols, namely, CTP plus BoX-MAC-2. The result shows that XMSN has better efficiency in terms of end-to-end delay, energy consumption, and goodput than that of CTP plus BoX-MAC-2 protocol.

The technology, cloud computing, in present days, is vastly used due to the services it provides and the ease with which they can be availed. The enormous development of the Internet technology is due to the advent of the concept of cloud. Along with its benefits, cloud computing brings along itself a detrimental side effect, i.e., carbon emission. This is due to the massive energy consumption in the cloud data centers. Reduction in energy consumption in cloud is thus one of the major challenges among the researchers. This work conducts a thorough study of the various techniques that help in minimization of energy consumption in data centers. It also explores and proposes approaches to reduce the same, eventually making the environment greener. In the proposed work, prediction mechanism has been adopted and implemented on the existing Minimization of Migration (MM) policy for large history data set, followed by dynamic thresholding mechanism in place of static thresholds. Rigorous simulations have been conducted, and the results show reduction in cloud data center energy consumption.

By embracing the potential of IoT and smartphones, traditional cities can be transformed to smart cities. The success of such smart city mission is firmly vested in populace and thus it should have a bottom-up nature, initiated by the citizens. This paper focuses on the design and development of a unified framework, which can provide a platform to empower all the applications across different dimensions of urban life in a smart city. The aim of this framework is to connect citizens, data, knowledge and services related to IoT as well as smartphone based applications. Here, we categorize all the applications for the smart city in three representative types, viz. IoT based, IoT and smartphone based and smartphone as IoT based applications. We have also developed and tested one prototype following this architecture for each of these three representative category type, i.e, IoT based smart classroom, IoT and smartphone based air quality monitoring system and only smartphone based noise monitoring system to demonstrate the effectiveness of the proposed framework for the smart city scenario.

A clear knowledge about human travel patterns is significantly important in the domains of science as well as commerce. In this paper an approach is proposed to identify the travel patterns of individuals. More specifically, the travel patterns of individuals including students and professionals are investigated by analyzing their smartphone sensing data (e.g. GPS trajectories). In this work, the travel patterns are explored by performing staypoint detection and frequent sequence mining. The proposed approach is also evaluated with a real-world smartphone sensing dataset collected by volunteers of diverse demographic characteristics (e.g. occupation, age, gender, place of residence, etc).

No one knows the exact moment when sleep overcomes the senses. A drowsy driver at the wheel of a vehicle on the street can give rise to highly unsafe traffic situations and lead to extremely severe accidents. So being alert during driving becomes one of the key factors to a safe drive. Our proposed system can be used to monitor the state of driver's alertness by taking into account his behavioral as well as physiological factors. While the behavioral part is monitored in real time through image processing with the help of the camera on smartphones, the physiological monitoring relies on a heartbeat monitoring device called Zephyr. With the help of machine learning, we have identified patterns in the behavioral and physiological factors that together helps to identify drowsy states from alert states for explicitly during driving.

Community detection or formation of clustering is a well defined problem of pattern recognition where interaction pattern of the members is measured. The detection of well defined communities are based on the fact that interaction within the community will be maximum whereas the interaction with the other communities will be minimum. Though several numbers of good community detection algorithms are present for well defined clustering, time complexity of these algorithm is quiet high and thus cannot be treated as the good measures of detection of community where number of nodes in the network is too large. In this paper, we are proposing a novel algorithm of community detection based on hierarchical ego based algorithm. In a network, ego is defined as the highest node degree centrality node and this node is treated as the cluster center of the community in our algorithm. The nodes closely connected with the ego node formed the community and from the remaining network the same process is iterated for community detection. For the result, dataset is extracted using Node-XL from a Twitter account, R based Hadoop network is used for the analysis of the network. For the visualization of the network I-graph is used.

Cloud federation has paved the way for cloud service providers (CSP) to collaborate with other CSPs to serve users’ resource requests, which are prohibitively high for any single CSP during peak time. Moreover, to entice different CSPs to participate in federation, it is necessary to maximize the profit of all CSPs involved in the federation. Further, federation enables overloaded CSPs to distribute their load among other underloaded member CSPs of federation by migrating the virtual machines (VM). Migration of VM among member CSPs of federation, also enables to increase the reliability and availability of cloud services on occurrence of faults in the datacenters of CSPs. Thus it becomes important for CSPs to form a federation with other CSPs, in such a way that the migration cost of VMs between CSPs of the same federation is minimized and simultaneously profit of CSPs in federation is maximized. In this paper, we model the problem of forming federation among CSPs as a hedonic coalition game, with a utility function depending on profit and migration cost, with the objective of maximizing the former and minimizing the latter. We propose an algorithm to solve this hedonic game and compare its performance with other existing game-theory based cloud federation formation mechanisms.

With more awareness and growth in the cloud market, demands for computational resources have increased in order to provide services to the cloud users. Sometimes it is difficult for an individual cloud service provider (CSP) to meet the level of promised quality of service (QoS) and to fulfill all types of resource requests dynamically. Cloud federation has become a consolidated paradigm in which group of cooperative CSPs share their unused resources with peers to gain some economic benefit. Hence, the cloud federation overcomes the limitation of each CSP for maintaining QoS during sudden spikes in resource demand. However, the presence of untrusted CSPs degrades the QoS of the services delivered through federation. Trusted CSPs are highly reputed in the federation as they can extend their resources and services to maintain the level of committed QoS by the member CSPs of the federation. Therefore, to guarantee delivery of committed QoS, it will be necessary to form a federation with trusted CSPs only. In this paper, we present a broker based cloud federation architecture. The cloud federation formation is modeled as a hedonic coalitional game. The main objective of this work is to find the most suitable and stable federation of trusted CSPs that will maximize the satisfaction level of each individual CSP on the basis of QoS and profit. The proposed coalitional game inspired cloud federation formation (CGCFF) algorithm has been extensively compared with selected existing techniques. Simulation results show that the set of federation formed by CGCFF is Nash-stable and performs better than these techniques in terms of satisfaction, quality and profit.

This paper proposes an alternate ranking system based on social network metrics and their evaluation in a composite distributed framework. The most important aspect of social network domain is voluminous data. In order to know key trends, predictive analysis of huge sets of raw data can be effective. Again these analytics are generally very compute intensive. The most efficient solution of such compute-intensive analysis is to map such problems in a distributed domain. The main contributions of this paper are twofold. First, the analysis of cricket community from the viewpoint of social network and finding ranking of players and countries based on the properties of graph centrality measures. Second, the paper proposes a comprehensive distributed framework to offer infrastructural support for the large data analysis as well as graph processing. Hadoop is an open-source framework to store and process large data sets in a cloud environment. MapReduce is a popular programming model for processing that data in a distributed manner. However, MapReduce alone is not efficient for graph processing. Giraph is an alternative programming paradigm for graph processing in Hadoop. Using a practical case study of social network analysis of cricket community, this paper captures the significance of the alternate ranking in this sport, as well as shows effectiveness of the proposed framework in the process of analyzing voluminous data.

These days mobile phones are having advanced onboard sensors embedded in it which makes connecting and computing much easier. This has led to realizing novel application paradigms such as crowd sensing and crowd computing. Crowd sensing relies on the sensing capabilities of the mobile devices as well as its communication efficiency to send collected sensed data to the cloud for further processing. On the other hand, mobile crowd computing is an amalgamation of the machine and human intelligence to achieve a given set of tasks in a distributed manner. Thus, crowd computing utilizes the computation and communication capability of the devices. Here in our work, we have come up with a novel approach integrating these two paradigms in a framework that have addressed both the issues of mobile sensing and crowd computing at the same time and utilized the ability of the crowd to solve problems without involving cloud servers in the backend. We have implemented our framework using 4 smart handheld devices for a route-finding application. The devices are connected to each other through BLE (Bluetooth Low Energy) technology. The results obtained can be received both online (using the machine intelligence) and offline (using human intelligence) when no devices are connected to the internet. The device hence receiving the information, in turn, can itself be a contributor in the crowd for other route-finding queries solicited by another user in the crowd.

Driving style analysis and road anomaly detection have a remarkable impact on road safety. They directly influence road accidents and have been a vital area of research in order to address road safety problems. In this paper, a system called D&RSense have been proposed that uses GPS and accelerometer of smartphones to categorize driving style of drivers, assess the road quality as well as to give real-time warnings to drivers in order to make driving safer. D&RSense does the categorization through detection of driving events like acceleration and braking and road anomalies like bumps and potholes by using the popular machine learning technique, Support Vector Machine (SVM) and gives real-time warning and instructions to drivers using a locally running Fast Dynamic Time Warping (FastDTW) algorithm. Extensive experiments have been conducted to evaluate the effectiveness of the proposed system.

Energy harvesting facility becomes an aid to sensor nodes in prolonging their lifetime. Most of the routing protocols are designed to take into consideration the battery powered sensor network and are not useful in the case of energy harvesting sensor networks. So here, we propose a harvested profile aware multi hop clustered routing protocol (HPAMC) that takes care of the energy profile of different sensor nodes and split the whole network into clusters. The algorithm is suitable for long runs of the simulation. The initial energy of the battery has been kept very low so that the nodes mostly depend on the harvested energy. Dense nodes with a healthy energy profile are chosen as the cluster head. A distributed approach has been followed for cluster head selection. Extensive simulations are carried out in network simulator Castalia to check the effectiveness of the routing protocol and compare its performance with commonly known clustered routing protocol.

In this paper, we present a case study on sentiment and social network analysis of opinions on Twitter. We have used Twitter data as a corpus to find opinions about GST (Good and Service Tax) among Indians applied from July 1st, 2017. Tweets, retweets and mentions are collected to extract the opinions of Indian citizens in the form of positive and negative opinions. In order to find out how users, who posted about GST are connected to each other we have generated a directed network based on the data collected, where users are the node of the graph and there exists an edge between them if they have mentioned replies or retweeted the posts. The network of users tweeted about GST form a small world network.

In recent years, advancement in mobile phone technology along with their exhaustive use in daily life leads towards a new paradigm of sensing called participatory sensing. Using the power of participatory sensing, we can develop people and environment centric sensing societal applications that helps citizen and policy maker in better decision making. In this paper, we present a participatory sensing based application called SenseDCity that discover travel pattern of the individual user, crowd flow of the city from the citizen's GPS trajectories. The system notifies users about the congestion, and current popular places near them. It takes the power of "people as a sensor" for identifying the road condition of the city, common health related symptoms among the citizen which in turn coming as a feedback and is a very valuable knowledge for both the citizen and the city administrator. The system is tested in the real-world scenarios and outcomes of the system are showing a glimpse of the huge potential of the proposed approach.

Integration of the physical world with the computerized world has led to the manifestation of Cyber-Physical Systems (CPSs) in an attempt to build a better and smarter world. In this paper, such a CPS named D&RSense has been proposed to promote smart transportation in order to make travelling more comfortable and safe. By studying driving patterns of drivers, D&RSense can get valuable insights to their braking and accelerating styles which can help to give them real-time warnings when they drive aggressively. Detection of rash driving prone areas across the city can help to recommend which areas of the city need stricter surveillance. D&RSense involves smartphones of commuters and utilizes their accelerometer and GPS sensors to detect driving events like braking and acceleration as well as poor road conditions like bumps and potholes by applying the ensemble learning method for classification, Random Forest (RF). The accuracy of the same has been compared to other supervised machine learning classifiers like Naive Bayes, k-Nearest Neighbours (k-NN), Decision Trees (DT), Support Vector Machine (SVM) and Artificial Neural Networks (ANN). Rash-driving prone areas and poor road segments during the course of the experiment have been plotted using Density-based spatial clustering of applications with noise (DBSCAN) algorithm. Effectiveness of the proposed application has been evaluated through extensive testing.

In this paper a hierarchy of knowledge community detection is proposed which is able to identify most impactful topics from a Twitter stream, analyze and generate a social network leading to the formation of knowledge-based communities. Data is crawled, in a region-specific manner, to ensure, cohesiveness of content. An aggregated score consisting of a sentiment score(in the range of [-1,1]) and an outreach score is assigned to each tweet, following which the knowledge network is generated, based on the score-wise proximity of tweets. Three community detection algorithms, Leading Eigenvector, Fast Greedy and Walktrap are used to detect communities from the derived knowledge network. Their efficiencies are compared on the basis of the number of communities generated and the modularity. Quality benchmark evaluation to test the network partition is applied for analysing and finally the impact of trending topics on the social stream is measured.

Social network can be represented by a graph, where individual users are represented as nodes/vertices and connections between them are represented as edges of the graph. The classification of people based on their tastes, choices, likes or dislikes are associated with each other, forms a virtual cluster or community. The basis of a better community detection algorithm refers to within the community the interaction will be maximized and with other community the interaction will be minimized. In this paper, we are proposing an ego based community detection algorithm and compared with three most popular hierarchical community detection algorithms, namely edge betweenness, label propagation and walktrap and compare them in terms of modularity, transitivity, average path length and time complexity. A network is formed based on the data collected from a Twitter account, using Node-XL and I-graph and data are processed in R based Hadoop framework.

Node-wise suitable posture-based data transmission reduces the energy consumption and prolongs the network lifetime. But, the challenging task is to classify and identify the posture sequence for a repeated activity such as walk, freehand exercise, and run in body area network (BAN) with low-cost (without using motion-detecting sensors like accelerometer) solution. This study proposes a solution to identify and classify the posture-based movements in repeated activity like a freehand exercise in BAN after observing the variation of received signal strength indicator (RSSI) over time. Analysis through simulation results shows that proposed solution can achieve the goal.

GPS is one of the most used services in any location-based app in our smartphone, and almost a quarter of all Android apps available in the Google Play store are using this GPS. There are many apps which require monitoring your locations in a continuous fashion because of the application’s nature, and those kinds of apps consume the highest power from the smartphones. Because of the high-power draining nature of this GPS, we hesitate to take part in different crowd-sourced applications which are very much important for the smart city realization as maximum of these applications use GPS in real time or in a very frequent manner for the realization of participatory sensing in a smart city scenario. To resolve this, we have introduced an energy-efficient context-aware approach which utilizes user’s mobility information from the user’s context and as well smartphone’s sensing values from the inbuilt accelerometer, magnetometer, and gyroscope of the smartphone to provide us a very close estimation of the present location of the user without using continuous GPS. It is an energy-efficient solution without sacrificing the accuracy compared to energy saving which will boost the crowd to take part in the smartphone-based crowd-sourced applications that depend on participatory sensing for the smart city environment.

Cloud federation has become a consolidated paradigm in which set of cooperative service providers share their unused computing resources with other members of the federation to gain some extra revenue. Due to increase in consciousness about cloud computing, demand for cloud services among cloud users have increased, thus making it hard for any single cloud service provider to cope up with cloud users demands and satisfying the promised quality of service. Hence, the cloud federation overcomes the limitation of each cloud service provider for maintaining their individual cloud resources. This chapter emphasizes on different approaches for cloud federation formation based on game theory and also highlights the importance of trust (soft security) in federated cloud environment. Different models for cloud federation formation using coalition game and the role of a cloud service broker in cloud federation are presented in this chapter.

This paper proposes and evaluates the novel utilization of small world network properties for the formation of team of players with both best performances and best belongingness within the team network. To verify this concept, this methodology is applied to T-20 cricket teams. The players are treated as nodes of the network, whereas the number of interactions between team members is denoted as the edges between those nodes. All intra country networks form the cricket network for this case study. Analysis of the networks depicts that T-20 cricket network inherits all characteristics of small world network. Making a quantitative measure for an individual performance in the team sports is important with respect to the fact that for team selection of an International match, from pool of best players, only eleven players can be selected for the team. The statistical record of each player considered as a traditional way of quantifying the performance of a player. But the other criteria such as performing against a strong opponent or performance as an effective team member such as fielding, running between the wickets, good partnership deserves more credential. In this paper a revised method based on social networking is presented to quantify the quality of team belongingness and efficiency of each player. The application of Social Network Analysis (SNA) is explored to measure performances and the rank of the players. A bidirectional weighted network of players is generated using the information collected from T-20 cricket (2014–2016) and used for network analysis. Thus team was formed based on that ranking and compared with their IPL (Indian Premier League) performances of 2016.

Energy efficiency is one of the key challenges for designing routing algorithms for wireless sensor networks (WSN). Fast data delivery from source node to sink node is also required for many applications. Sometimes data transmission towards the sink may be interrupted because of failure of nodes in a particular area. The various such requirements of routing data in a WSN are sometimes contradictory and routing algorithms must be designed keeping in mind all these requirements. In this paper three routing algorithms are proposed for multi-sink partitioned network. In these three algorithms, the source nodes or intermediate nodes select a next node to forward the data to the destination or sink. This process repeats until the data reaches the sink. In the first technique, the next node is chosen considering its distance from sink node as a criterion. In the second technique, remaining energy of the neighboring nodes is used as a criterion for selection of the next node. The combination of these two criteria is considered in the third technique and a multiple criteria decision analysis technique is used. A recovery technique from area failure is also proposed and incorporated in the above mentioned algorithms. The algorithms are designed and implemented in multi-sink environment for partitioned wireless sensor networks. Performances of the algorithms are studied in a simulation environment and compared with other well-known algorithms to understand their effectiveness.

With the surging of smartphone sensing and wireless networking, Mobile Crowd Sensing (MCS) has become a promising paradigm for cross-space and large scale sensing. In the smart city context, MCS can be extremely useful in pulling crowd data for better monitoring resource demand and planning. Since these devices are portable it is carried by almost every citizen thus making it ubiquitous. However, portability comes at the cost of limited energy consumption. Thus, the problem is that, how frequently a smartphone would lend itself for crowd-sensing while striking a balance between energy and incentive. In order to solve this problem, we propose a Markov decision process formulation of the problem and solve it to identify an optimal strategy for crowd-sensing depending on remaining energy, recharging probability and current load. Results are taken in R for different real world scenarios.

Social network data are stored in the form of a graph where nodes and edges represent users and their interactions respectively. Sometime it becomes important to block some nodes or edges due to some social welfare like restricting panic attack, propaganda etc. for the benefit of the society. It will be more beneficial if we can restrict this in their source, but as it takes some time to notice the phenomenon, it will be better to block the nodes which have maximum influence in the network. The centrality nodes play an important role to determine the levels and depth of the information propagation in the network. This paper presents an approach to select the influential nodes for information blocking in the social network. This paper captures the interaction measures of nodes in the social network and selects influential nodes based on three important network properties, i.e. degree distribution, betweenness centrality and closeness centrality. We demonstrate the performance of the centrality nodes for information blocking by processing Twitter network extracted using Node-XL and I-graph and processed through R. For simulating the propagation of the information, we are using Random Walk and a detailed comparative study is presented for each of the seed nodes selected using above mentioned network properties. Edge betweenness, which is used to find the important edges of the network is compared with the propagation and show better result than important node selection criterion in terms of information blocking.

Noise pollution in urban areas is a subject of grave concern and it is being recognized globally in different countries and cities. People are facing many health-related problems because of this. Therefore, in the proposed work, we envisioned to tackle the challenge of acquiring real time and spatially fine-grained noise pollution data with a community-driven sensing infrastructure. Mobile crowdsourcing over smartphones presents a new paradigm for collecting context aware sensing data of a vast area like a city. Thus, the proposed system exploits the power of mobile crowdsourcing. The proposed system monitors the present noise level in the surroundings of the user and also generates city's noise pollution footprints. The noise map reflects the real-time pollution scenario of the city which changes with time. The prototype of the system has been evaluated with extensive experiments based on crowdsourced sensing data collected by volunteers in Kolkata city.

Information propagation in online social media draw attention in different research domains due to it's influence and importance in public domain. The complexity of this research problem arises due to its huge volume and transient nature. For different user domain data processing, methodologies and derivations of information spreading are quite different in nature. In this paper, we study information propagation in online social network twitter, considering different centrality measures and simulate through random walk. Assuming that the structure of these websites is a kind of scale free network but exhibits the property of small world network, we compare information propagation to sight the most pivotal nodes in the network in aspect of information propagation.

Massive technological advancements has promoted rise in energy costs, cloud computing being one of the key contributors. The cloud datacenters consume huge amount of energy which lead to carbon emissions, detrimental for our environment. Design of resource scheduling, load balancing and migration schemes for virtual machines (VM) in the cloud environment is one of the ways by which energy consumption can be minimized. This work proposes a prediction based VM migration approach (PMM) and explores how the proposed approach can affect the total energy consumption of a datacenter; with the aim to make the technology more environment friendly. PMM has been designed keeping the concept of the well-known Markov chain model in mind. Substantial amount of simulation has been conducted in this work to conclude how a prediction based resource management technique can play vital role in influencing the energy consumption of a cloud datacenter, in comparison to the existing and popular minimization of migrations (MM) policy.

Here, we present a prototype of a smart building using newly surfacing technologies like IoT (Internet of Things), fog and cloud for the smart city. The demand for everything smart is increasing daily, but the main stumbling block is its high price. So, our aim is to improve the standard of living in home and in office with newly improved working facilities where the whole system will be automatic, efficient and will be under the control of the user via his/her smartphone or computer but the cost will stay within the budget of a common man. All these are done by the incorporation of IoT, fog and cloud. The assimilation is done using open source hardwares and softwares to reduce the cost dramatically than the other existing solutions and implement it in an impressive and ingenious way without compromising QoS (Quality of Service) of any of the functionalities provided by other existing solutions.

Cities are expanding and more and more citizens are exposed to air pollutants both indoors and outdoors. This may have adverse effects on citizens' health. In this paper, we present AirSense, an opportunistic crowd-sensing based air quality monitoring system, aimed at collecting and aggregating sensor data to monitor air pollution in the vicinity (building/neighbourhood) and the city. We introduce a light weight, low power and low cost air quality monitoring device (AQMD) and demonstrate how AQMD and smartphones in a crowd collaboratively gather and share data of interest to the cloud. In cloud, collected data are analyzed and an aggregate view is generated from data collected from various sensors and from different users for providing an air pollution heat map of the city. Unlike previous works, both micro and macro level air quality monitoring is possible with Airsense. End user can view his/her pollution footprint for the whole day, the neighborhood (local) air quality and AQImap (air quality index map) of the city on his/her smartphone. The system is implemented and the prototype is also evaluated.

Secure communication in a continuous patient monitoring system (PMS) through body sensors is required to keep privacy on user's and sensors' secret information and data respectively. This paper presents a secure communication protocol for PMS (SecPMS) in order to get efficient and secure services in such environment. Robustness of the proposed protocol is analyzed using random oracle and it shows that SecPMS provides strong security against possible known attacks. Furthermore, performance comparison is given as an evidence which establishes the efficiency of SecPMS than related existing protocols with respect to time complexity of computation.

Cloud federation has emerged as a new paradigm in which different service providers collaborate to overcome limitation of cloud resource during sudden spikes in demand and improve quality of service (QoS) for delivered cloud services. The growing number of cloud federation to provide cloud services has made service selection a complex task due to varied nature of parameters like price, QoS and trust of different federations. In this context, formal decision making methodology is required to find the best federation which can deliver a services with high QoS and trust in a cost effective way. The proposed model conducts a multi-criteria decision analysis to select best cloud federation in specific time period in accordance with user preference over each parameter. The experimental result and analysis validate the effectiveness of our proposed model.

The motivation of this paper is formation of sports network and characterization of the small world network phenomenon by analyzing the data of individual players of a team. Analysis of the network suggests that sports network can be considered as small world and inherits all characteristics of small world network. Making a quantitative measure for an individual performance in the team sports is important in respect to the fact that for team selection of International football matches, from a pool of best players, only 11 players can be selected for the team. The statistical record of each player is considered as a traditional way of quantifying the performance of a player. But other criteria like performing against a strong opponent or executing a brilliant performance against a strong team deserves more credit. In this paper, a method based on social networking is presented to quantify the quality of player’s efficiency and is defined as the total matches played between each team members of individual teams and the members of different teams. The application of Social Network Analysis (SNA) is explored to measure performances and rank of the players. A bidirectional weighted network of players is generated using the information collected from English Premier League (2014–2015) and used for network formation.

In today's world, social media is a powerful tool: spreading information, and changing the way we receive news. It often reaches faster and farther than any any other channel. The availability of large scale data on online social media motivates our questions on social behavior in spreading information on the network. We conduct extensive experiments on Twitter data, to determine how important some people are in spreading information to the world. The Twitter data used in this study is stored on an HDFS and manipulated using algorithms framed in the MapReduce paradigm of Hadoop. An information flow network is generated from the Twitter data (81540798 tweets) based on the hashtags #Brexit, #Euro and #Rio. We study the effectiveness of K-core and PageRank algorithms in identifying important seeds in social networks, by comparing their outputs against the true seeds obtained from the two-phase algorithm. K-core performs better by most similarity indices, when compared to PageRank.

This chapter reviews the literature of mobile crowd-sensing (MCS) for smart cities is reviewed thoroughly including motivation, possible applications, and issues that are key to successful deployment of such services. It discusses the challenges of crowd-sensing in the context of smart city followed by a brief overview of existing frameworks. The chapter also discusses the issues regarding task assignment, user profiling and trustworthiness, design of incentive mechanisms, localized analytics, and security and privacy. While crowd-sourcing is aimed to utilize collective intelligence of the crowd to solve complex tasks by breaking them down to smaller tasks, crowd-sensing splits the responsibility of gathering correct information to the crowd. Toward this, a geo-social model of MCS is proposed. This model is based on a distributed architecture for task design, assessment, and execution. McSense is a framework that is also proposed for MCS. This framework talks about monetary or service incentives given to users.

This chapter presents a roadmap of key developments in IoT-Cloud research in the context of different application domains and its applicability to IoE. IoT can be extended to IoE, if it is possible to connect everything to the Internet. Different layers of IoT protocol stack are discussed in this chapter. In IoT, physical objects connected to the Internet generate huge amount of data. Here, one of the main challenges is to move these data from the underlying IoT to the cloud. Cloud technologies are appealing due to the fact that the requirements for developing such IoE environment match very closely what cloud can offer in terms of computational and storage resources. Various application areas and existing works are also discussed.

Offloading or cyber foraging is a technique to overcome resource constraints of mobile devices by migrating heavy computation to remote more resourceful surrogates (such as PDAs, desktop PCs). Many research works have been done so far on the architecture of offloading systems, what to offload (partitioning of offloadable code) and when to offload (based on energy constraint, execution time). However, only a few works can be found on fault detection and tolerance. So this paper concentrates on designing a robust offloading framework that can survive a surrogate crash through the notion of redundancy and rollback recovery. Fault prevention can be achieved by using historical data while selecting suitable surrogate at a familiar neighborhood. We have evaluated this framework using a real application named `Π-calculator' based on resource utilization and energy consumption. The mechanism is implemented using different Tabs and smartphone as offloadee and 3 HP laptops as surrogates. Fault tolerant offloading is found to be efficient in terms of energy consumption and resource utilization.

Citizens are exposed to air pollutants both indoors and outdoors due to their activities, which may result in a variety of health effects. In this paper, we present AirSense, an opportunistic crowd-sensing based air quality monitoring system, aimed at collecting and aggregating sensor data to monitor air pollution in the vicinity and the city. We introduce a light weight, low power and low cost air quality monitoring device (AQMD) and demonstrate how AQMD and smart phone devices in a crowd collaboratively (through offloading) gather and share data of interest to the cloud. In cloud, collected data will be analyzed and an aggregated view will be generated for providing an air pollution heat map of the city. End user can view both the neighborhood (local) air quality and AQImap (air quality index map) of the city on his/her smartphone.

Wireless sensor network (WSN) is a dynamic and infra-structure less communication system. These are used for any specific target monitoring. The meaningful data returned by the sensor nodes are used for significant decision making. So the quality of data plays a significant role in correctness of decision. Resource scarcity of WSN makes it vulnerable and prone to faults. Faults in WSN are unintended errors, which may lead to wrong decision making. Moreover, due to faults, the reliability and performance of the WSN may get affected; hence, fault tolerance is necessary over here. This paper aims to design a built-in learning-based link quality estimation approach for WSN. This will enable each sensor node to select an appropriate parent through a good-quality link for forwarding data to the base station (BS). Parameters for link quality estimation over here mainly include received signal strength (RSS), signal to interference plus noise ratio (SINR), and packet reception rate (PRR). Simulation results along with discussion are also presented here.

Green computing has acquired significant amount of importance in the present research scenario as with mammoth advancements in the field of Information and Communications Technology (ICT), energy consumption has increased manifold over the last decade. With development in services provided by cloud providers, a large amount of energy is being consumed by the cloud data centers distributed all over the world. These data centers have a major contribution to the carbon footprints that is being generated, which in turn is detrimental for the environment. This paper studies the current researches that are being conducted to build energy efficient cloud networks and explores strategies that can be adopted to reduce the energy consumption of cloud data centers, thus opening new avenues towards building a ‘green’ cloud network.

In energy harvesting wireless sensor networks (EH-WSNs) sensor nodes are capable of harvesting energy from environmental sources. Usually, knowledge about the link quality improves the performance of WSNs. During data routing, selection of good quality links are important to maintain stable communication. Thus helps to reduce the unnecessary energy wastage. Obtaining the link state information is more challenging for EH-WSN as different nodes has different energy profiles and state of the node depends on several environmental conditions. In this paper, we have studied different factors affecting the link quality and model it using finite state Markov Model. Energy availability of the harvesting devices through real time traces is considered for modeling the network. This model can significantly provide relevant information which is very effective to improve the routing decisions as the next hop decision will be more accurate. The usefulness and validity of the proposed approach is illustrated through simulations for specific examples.

This work investigates the impact of different postures in the wireless sensor network (WSN) deployed on human body. Distance among these sensors varies when it changes posture. As a result the topology of the body area network (BAN) also gets changed and that affects the connectivity among the nodes. A set of postures during exercises in a repeated fashion for investigating different performance metrics of BAN has been considered here. The said BAN environment is simulated using Castalia. Initially T-MAC is used as a link layer protocol to examine different network metrics. It is observed from the simulation results that the network performance varies with the changes in posture. To map T-MAC in BAN environment, an enhancement is required. Hence, a load distributed MAC protocol (LD-MAC) is proposed to distribute the load of data transmission among the nodes in each posture. The proposed LD-MAC is also extensively compared with T-MAC.

With rapid development of mobile networking and increasing demands of heavy computation on handheld devices, energy efficiency becomes an important design consideration. Offloading heavy computation-intensive tasks to remote machines provides the opportunity to save processing energy in the handheld devices. In this paper, a general purpose framework for offloading computation task to save energy in the handheld devices has been proposed. Given a number of resourceful hosts available, a handheld device can offload some computation on-the-fly to a desired device in the P2P network of smart devices. The framework chooses the application that is most cost-effective in terms of energy consumption. To evaluate the proposed approach, 0xbench an integrated Android benchmark suite by 0xLab has been considered. The framework is implemented and tested on P2P network of Android based handheld devices and found to be performing well with these benchmark codes regarding energy saving of the handheld devices.

Nowadays wireless sensor network (WSN) of mobile nodes is used in most of the sensor applications especially in event-driven applications. The choice of mobile nodes are obvious as they are much more versatile than static sensors. Mobile nodes can be deployed in any scenario and cope with rapid changes in the environment. One of the fundamental problem of mobile WSN is energy consumption and this is a more serious issue than in static WSN because all sensors are moving continuously and as a result they are prone to consume more energy. Network lifetime is inversely dependent on the overall energy consumption of nodes in the network. In this paper, we present an energy efficient and event driven mobility model (E3DM) where mobile sensors inform each other about a static event and adjust their route to reach to the nearest point of that event. Sensors exchange some useful information between themselves by packet transmissions. Through this information exchange, movement of one sensor influences the movements of its neighbors. The objective is to minimize the energy consumption and thus increase the network lifetime. Although some overhead involved due to packet exchange between nodes, an enhanced version of energy efficient and event driven mobility model (E4DM) is also introduced to reduce this complexity. The effectiveness of the proposed approaches are evaluated and compared with random way-point mobility model (RWP), one variant of RWP where constant velocity (RWPCV) and Gauss Markov mobility model (GMKV) using NS-3 simulation.

A game theoretic approach is proposed for joint power control and route adaptations for wireless sensor networks to improve the network lifetime. A data collecting sensor network is assumed that employs asynchronous duty-cycling for energy conservation. In such networks, overhearing dominates the energy consumption, which can be controlled by adapting the transmit power levels as well as the route selections. The goal of this work is to determine assignments of transmit power levels and parent selections for all sensor nodes to maximize the lifetime of the network by controlling the overhearing in the nodes, while maintaining acceptable quality of routes. Performance results of the proposed schemes from computer simulations are presented.

Wireless Sensor Networks are widely used in today's world in several applications ranging from environmental and health monitoring to military uses. Data Collection is one of the most important aspects of WSN and this topic has witnessed significant amount of research over the year. Traditionally static sensors were used in the data gathering process but later on mobile nodes were introduced with goal of achieving energy efficiency. This paper mainly deals with Data Collection techniques which uses mobile nodes. Different types of mobile nodes used in data collection have been discussed. A review of recent literature on data collection protocols using mobile nodes has also been presented.

Nowadays WSNs are expected to be an integral part of the extensive computing environment. But because of limited resource of the sensor nodes, it requires to manage an everincreasing need for efficient energy and resource management for both the sensor nodes as well as the overall sensor network. In sensor network, to provide the energy efficiency across all the sensor nodes, finding of efficient route is very important. Our algorithm proposes an efficient and multi-hop routing algorithm which is able to choose an efficient route between available routes by considering multiple important criteria for taking routing decision and at the same time to provide balanced energy consumption across all the sensor nodes.

Target tracking is one of the most popular applications of mobile wireless sensor networks (MWSNs), where coverage and data gathering algorithms are foundations to achieve successful target tracking. Since the mobility of sensor nodes is of great importance in this particular class of application, it is crucial to design efficient techniques that can manage the mobility. In this paper, we particularly concentrate on military surveillance area where intruder tracking is one of the critical task. Many mobility models proposed so far in the literature are used to simulate and evaluate the performance of the networks. At times group mobility model is preferred over individual mobility model to simulate the nature of the application such as military surveillance, disaster relief, tactical environment etc. Usually, groups are formed at the time of sensor node deployment and become fixed. However, this is not appropriate for the application scenario under consideration. This motivates us to design a Cooperative Group Mobility model (CGM) where groups of nodes are formed dynamically. Depending on the current situation, a node can detach itself from its current group and can join into another group. Moreover, all group members may not communicate with each other in 1-hop, though there should exist a path between any pair of nodes in order to achieve their common goal which is tracking of a mobile intruder. The effectiveness of the proposed scheme is evaluated and compared with Reference Point Group Mobility Model (RPGM) using NS-3 simulation.

The main objective of this work is to study network parameters commonly used to explain social structures. In this paper, we extract data from a real-time Facebook account using Netvizz application, analyze and evaluate network parameters on some widely recognized graph topology using GEPHI software.

With the advent of Smart City, health-care delivery solutions should be smarter to serve huge population. Earlier, we proposed a Sensor-Cloud framework aiming at proper delivery of the remote health-care services. While implementing the health sensors, we faced with the challenge of making the communication seamless across different communication technologies. In this paper, a solution is presented for the tiny sensor nodes with the help of vertical handover.

In social network analysis (SNA), using online social media, it is possible to collect large open source information and to analyze those data for knowing the characteristics of these networks. The main objective of this work is to study online social network parameters commonly used to explain social structures. In this paper, we have extracted data from the three real-time facebook accounts using Netvizz application. Gephi, a open source free software, is used for analysis and evaluation of these network parameters. This analysis shows some well-known network parameters like calculating clustering coefficient (CC) of clusters, group formation, finding node degree distribution (NDD), identifying influential node etc., which can be used for further feature extraction.

In recent years the Internet learners can freely absorb new knowledge without restrictions on time or place. At present, most E-Learning environment architectures use single computers or servers as their structural foundations. Traditional E-Learning systems have major drawback because of their limitations in scalability, availability, distribution of computing power and huge storage systems, as well as sharing information between users. In this context, the use of Grid technology reveals its utility and availability, as scalable, flexible coordinated and secure resource sharing among geographically distributed individuals or institutions, in the perspective of E-Learning system. The major focus of this paper is to design and develop different types of E-Learning services in Computational Grid Environment. This proposed system is able to handle large multimedia learning materials using the features of Grid Technology.

In recent years, game theory has become a popular research topic in the field of wireless sensor network. It provides strategic approach to address some well known issues of mobile wireless sensor network (MWSN). Participating players or nodes either sequentially or simultaneously decide and affect the outcome of the game. Our objective is to apply this decision to find an optimum solution in area coverage and data collection issues of MWSN. Here all the sensor nodes are visualized as players and their association are designed to produce desired outcome. The contributions of this research work are (a) cooperative game based area coverage (b) network game based data collection.

We consider large-scale asynchronous wireless sensor networks (WSN) for environmental monitoring applications, where overhearing severely affects the energy consumption of the nodes. To mitigate energy wastage from overhearing and to improve the network lifetime, we propose multi-channel operation where each node is assigned any one of a small set of channels. We propose a game theoretic framework for solving the channel selection problem that maximizes the network lifetime. The proposed approach largely reduces the computation complexity of channel selection. Computer simulated results are presented, evaluating the performance with this approach.

Wireless Sensor Network (WSN) is one of the most demanding research topics prevalent in the modern research domain. WSN consists of densely deployed sensor nodes in the area which is to be sensed or monitored. Every tiny sensor node needs to transmit the sensed data to more powerful sink nodes. Sensed data may reach sink node through multiple hops. As the sensor nodes are resource constrained, most of the data forwarding algorithms employ threshold values of key parameters and implement event driven routes. Instead, we consider multiple parameters simultaneously for determining route to send the data to sink. In this paper, we propose routing scheme using Multi Criteria Decision Making technique where each criterion is assigned with a weight. An adaptive learning method is used to determine the weights. This routing scheme ensures robust packet reception ratio.

In wireless sensor networks (WSNs) localization systems are required to provide position information of sensor nodes. Location information of sensor nodes with unknown physical coordinates is acquired with the help of beacons or anchors. Beacon placement is one of the prominent factors that shape the localization performance in sensor networks. Placing more beacons in a network is generally not a cost-effective idea. However, a carefully designed technique can increase the accuracy by placing a limited number of beacons. This paper presents an integer linear programming(ILP) formulation of optimal beacon placement (OBP) and also prove that the OBP problem is NP-hard. Requirement based beacon placement algorithm is proposed to optimize number of beacons to cover the entire WSN. Simulation result shows that the proposed beacon placement scheme is effective in a sensor network with high node density.

Identifying faulty nodes in Wireless Sensor Networks (WSNs) is important for proper functioning of WSN. This paper presents low-cost agent-based fault detection approaches which work independently without creating any hindrance for actual data packet routing in WSNs.

Enterprise cloud computing has emerged as a promising technology, where on-demand provisioning of services like storage, infrastructure, software and platform are provided. Growing market of cloud computing, resulted in a variety of heterogeneous cloud services. This leads to a difficult problem for Cloud Service Consumer (SC) when selecting their best fitting Cloud Service Providers (SP), who can provide best quality resource at negotiated price. Thus we propose a middleware based Cloud Service Broker (SB) architecture for enterprise cloud computing. The objective of SB is to find the most suitable SP for a SC based on negotiation with Service Level Agreement (SLA) parameters like price and quality. Second we propose game theory model for automatic SLA negotiation between SC and SP where CSB provides optimal value of price and quality to both the parties.

In the current scenario, wireless sensor network (WSN) is used in substantial number of applications. Mobile WSN (MWSN) is preferred over static WSN in many applications especially in mobile object tracking and trapping system. Coverage is strongly related to object trapping as it is easier to trap an object in fully covered area compare to partially covered area. MWSN becomes default selection when it comes to trap a mobile object in a partially covered area because mobility of sensor nodes can be utilized to enhance the coverage of the network and thus able to detect and trap target. One of the fundamental problems of MWSN is how to coordinate these mobile sensors in such a way that they can move together in order to achieve their common goal. In this paper, we present a game theory inspired mobile object trapping system (GT-MOTS) where mobile nodes form a coalition such that they trap a mobile object by exchanging some key information between themselves. Through this information exchange movement of one sensor influence the movements of its neighbours. The objective of the proposed scheme is to minimize the trapping time by reducing travel distance of each sensor node. The concept of cooperative game theory is used for coalition and concept of pursuer evasion game is used for mobile target trapping. The effectiveness of the proposed approach is evaluated and compared with random way-point mobility model (RWP) and three other variants of RWP using NS-3 simulation.

In the present scenario, there are substantial amount of application where mobile wireless sensor network (MWSN) would be better choice over the static wireless sensor network. The very nature of the MWSN environment requires sensor nodes to interact opportunistically to address a common goal. Coverage is one of those areas where MWSN provides better solution. Coverage in static WSN depends on the initial deployment strategy. Most of the recent works in MWSN propose re-deployment strategy with the help of mobile nodes. In MWSN, the mobility of sensor nodes can be utilized to enhance the coverage of the network. One of the fundamental problems of MWSN is how to coordinate these mobile sensors in such a way that they can move together to accomplish the given task. Here, we study a generalized case of this problem. In this paper, we present a coordination based motion control (CBMC) scheme where all mobile nodes form a cooperative group such that they cover an area by exchanging some key information between themselves. The proposed scheme has two objectives: (i) each sensor node travels a minimum distance, (ii) minimum overlap in the coverage path of sensor nodes. NS-3 simulation shows the effectiveness of CBMC scheme. The proposed scheme is compared with random way-point mobility model (RWP) and three other variants of RWP.

The communication between Wireless Sensor Nodes and the Internet would require a gateway as these two network works on different standards. Mobile phone may be utilized to bridge this gap. It may act as a gateway for Wireless Sensor Nodes to connect with Internet and vice versa. Also this approach allows the smartphone to enrich the data collected from the Wireless Sensor Nodes before sending it to the Internet. In this paper, a low-cost solution is presented with open-source software and hardware that allows a wide range of smartphones to connect with sensors in a pervasive manner.

This chapter presents how Grid can be used to build an e-learning framework which is flexible, convenient, cost-effective, and adaptable. Grid technologies are appealing due to the fact that the requirements for developing such framework match very closely what a Grid can offer in terms of computational and storage resources. On the other hand, agent-based technology can make e-learning Grid more efficient. A few autonomous, co-operative agents with predefined functionalities and responsibilities provide more powerful and reliable e-learning system. The objective of this chapter is to accomplish a blended e-learning Grid framework, where the framework is designed as a multi-agent system integrated with Grid. This chapter also presents the implementation of an e-learning system as Grid services and analysis of the benefits of e-learning Grid system.

In order to maintain the QoS requirements of jobs running on a large distributed system, like Cloud and Grid environments, resource requirements of jobs should be predicted prior to their submission, and on the basis of this prediction, appropriate resources can be selected for their execution. However, because of the dynamic and heterogeneous nature of the modern distributed systems, estimation of resource requirements is a challenging task. This paper presents a feedback-based job modeling scheme based on clone detection technique. In this scheme, the execution data for each job which runs in the environment is stored in Execution History. A newly submitted job is analyzed to find its clones from the execution history and on the basis of the data stored in the execution history, the resource requirement of the new job is predicted. Different levels of clones are discussed in this paper and a metric-based clone detection technique is presented. An automatic resource requirement prediction scheme for jobs is proposed. The paper also evaluates a preliminary implementation of the scheme and discusses the results of using the scheme for some test codes.

TinyOS is a popular event driven operating system for wireless sensor network (WSN). However TinyOS 2.x framework lacks proper visualization approach for simulator TOSSIM and also for real-time network. In this paper we present approaches to add support for two visualizers in TinyOS framework. One such graphical addition is for simulator TOSSIM and another is for real- time network. The main contributions of this paper are 1) Visualizer for TOSSIM 2) 3D visualizer for real time data collection in WSN.

In this paper, we present a resource broker architecture for a computational Grid which uses Genetic Algorithm (GA) for brokering. Resource brokering implies selection of appropriate resource providers for jobs submitted to the Grid. Resource brokering is normally done with the objective of optimizing some performance parameter such as minimizing the total cost of running the jobs or maximizing the utilization of Grid resources. It is a challenging task since the search space for the problem consists of all possible allocations of submitted jobs to available resource providers in a Grid and may be very large. GAs are found to be efficient for such optimization problems. Moreover, the configuration and workload of a Grid is dynamic in nature. Our GA based resource broker tries to address these issues so that jobs are scheduled efficiently.

Wireless sensor network (WSN) is drawing interest in various areas as they have great potential for many distributed applications in different scenarios. This paper demonstrates iSENSE, which provides a web-based sensor monitoring service and a sensor network test-bed. iSENSE uses heterogeneous wireless sensors that are capable of measuring temperature, humidity and light. Gateway nodes collect the sensed data from their respective network area and store the data in MySQL database for analysis and visualization through a portal. Through the test-bed user can remotely submit a sensor application (programs written in NesC) for compiling it using required softwares (TinyOS and NesC) and evaluating the performance of the application by downloading and executing them on dedicated sensing devices which form the test-bed.

Grid represents an environment over a distributed area, incorporating heterogeneous elements such as server nodes, storage devices, and network components in a scalable, wide-area spanning compute infrastructure. Since a Grid requires large scale resource sharing, efficient resource management system (RMS) is required to manage the Quality of Service (QoS). One of the chief tasks of an RMS for Grid is selecting an appropriate and most suitable resource provider for execution of a particular job submitted by a user. This is also known as resource brokering. This paper presents a survey of resource brokering paradigms based on Machine Learning (ML). Three major ML techniques applied in Grid resource management for this purpose have been discussed.

Resource requirement estimation in large distributed systems is a difficult job because of the heterogeneity and dynamism of the environment involving modern distributed systems. A feedback-based job modeling scheme based on clone detection technique was proposed in [6]. This paper extends the taxonomy of clones proposed by other researchers [1] in order to make resource requirement prediction more effective. It also presents a hybrid clone-detection technique, consisting of metrics-based, PDG-based and AST-based clone detection, to make the clone detection process more reliable and robust.

In Wireless Sensor Network all sensor nodes have the equal probability to fail and therefore the data delivery in sensor networks is inherently faulty and unpredictable. Most of the sensor network applications need reliable data delivery to sink instead of point-to-point reliability. Therefore, it is vital to provide fault tolerant techniques for distributed sensor network applications. This paper presents a robust recovery mechanism of nodes failure in a certain region of the network during data delivery. It dynamically finds new node to route data from source nodes to sink. The proposed algorithm is integrated easily in data delivery mechanisms [11] where area failure in a certain geographical region is not considered. This recovery mechanism is focused on multiple-sink partitioned network. It is found that it quickly selects alternative node from its 1-hop neighbor list when there are no forwarding nodes available and establishes route from source to sink. Simulations are done in Matlab environment.

Energy consumption is the key design criterion for routing data in WSN. However, some applications of WSN like disaster management, battlefield control etc. demand fast data delivery. In this paper, three data forwarding techniques are proposed. Here, the source nodes or intermediate nodes select a next node to forward the data to the destination based on different criteria. The process repeats until data reach the destination. In the first technique, neighbor node nearer to the sink is chosen considering its distance from sink node as a criterion. In the second technique remaining energy of the neighboring nodes is used as a criterion to select the next node. The combination of these two criteria is considered in the third technique based on Multiple Criteria Decision Analysis. A comparative study of the performance of these techniques has been carried out and results are presented in this paper.

Multiple sinks are deployed in large-scale wireless sensor networks (WSNs) to minimize transmission delay and energy consumption and also to extend the network life time. Since the data collected by sensor nodes are forwarded to the sink, therefore proper placement of sinks has a great impact on the performance of the WSNs. This paper introduces two sink placement strategies and discusses their advantages and disadvantages in comparison with an existing strategy. The two strategies are compared with the Geographic Sink Placement (GSP) [3] strategy which is used as a benchmark. Both GSP and proposed two strategies are implemented and evaluated in a simulation environment. Performances of these strategies are analyzed and analysis results are presented in this paper. It has been observed that the proposed strategies exhibit better performances with respect to energy usage and lifetime in comparison with GSP.

Resource requirement prediction of jobs prior to their submission in the dynamic and heterogeneous natured modern distributed systems is a difficult task. A feedback-based job modelling scheme based on clone detection technique was proposed in [1, 2] and an extended taxonomy of clones to facilitate prediction was proposed in [3]. In this paper, we propose the resource requirement prediction scheme for different Near Miss clones. The Near Miss clone jobs differ only in some aspects like data type of input data, input data size and operations performed in job. So, resource requirement prediction of a new job from traits of its Near Miss clones previously executed in the system can provide a good estimate. This paper focuses on the issue of resource requirement prediction of different types of Near Miss clone jobs.

As the world is moving towards the “Internet of Things” [1], Internet Protocol enabled Wireless Sensor Network is becoming an important research area. In order to make it possible and to facilitate transmission of IPv6 packets over low powered networks, 6LoWPAN [2,3] has been introduced. In this paper, we study mobility issues and scenarios which may occur in the 6LoWPAN network. We also propose an approach to manage the mobility of nodes efficiently based on received signal strength and link quality. Simple load-balancing technique is also incorporated. The 6LoWPAN based Wireless Sensor Network can be integrated with grid computing establishing a Sensor-Grid which may also be used in various applications.

Mobility management is one of the most important research issues in 6LoWPAN which is a standardized IP based Wireless Sensor Networks (IP-WSN) protocol. Since the IP-WSN application domain is expanded to real-time applications such as health-care and surveillance systems, a fast and seamless handover becomes an important criterion for supporting mobility in 6LoWPAN. In this paper, we have studied mobility characteristics along with design issues and different mobility scenarios. Also, two approaches are incorporated for mobility management namely timer driven and message driven approaches. Both of these are implemented using TinyOS.

As the world is moving towards the “Internet of Things” [1], Internet Protocol enabled wireless sensor network is becoming an important research area. In order to make it possible and to facilitate transmission of IPv6 packets over low powered networks, 6LoWPAN [9,11] has been introduced. 6LoWPAN incorporates an adaptation layer between network and data link layers. Two routing schemes are used in 6LoWPAN depending on which layer takes routing, forwarding decisions. If adaptation layer takes the decision, then it is called mesh under, whereas if the network layer is involved, then the scheme is route over. In this paper, we present a comparative study of these two schemes. Various performance metrics, such as average round-trip time delay, end to end delay and packet delivery ratio are compared and suitability of the two schemes are analyzed for a Sensor-Grid infrastructure. We also propose a technique which improves the route-over scheme. Our ultimate goal is to apply this Sensor-Grid infrastructure in health-care applications.

Wireless Sensor Networks (WSN) has gathered a considerable amount of attention because of its manifold application in various fields like defense, health monitoring, environment monitoring and disaster management. Though WSN has conquered the world due to its dynamicity still it is very much fault prone because of the reason that the sensors and actuators of the sensor node has to interact directly with the unpredictable environment, where it may be subjected to various physical, chemical and biological forces. To make a WSN more reliable and dependable various fault management systems are employed. Better the fault management higher is the reliability of the WSN. The aim of our paper is to review the functionality of some of the existing fault management systems including their architecture and present a comparative study.

In wireless sensor networks (WSNs) localization systems are required to provide position information of sensor nodes. Position information of sensor nodes with unknown physical positions is acquired with the help of beacons or anchors. Beacon placement is one of the prominent factors that shape the localization performance in sensor networks. Placing more beacons in a network is generally not a cost-effective idea. However, a carefully designed technique can increase the accuracy by placing a limited number of beacons. This paper presents a requirement based beacon placement algorithm to optimize number of beacons to cover the entire WSN. A novel algorithm for routing towards the mobile sink is also proposed, which utilizes the beacon nodes more than sensor nodes to route data towards a mobile sink. This strategy helps to reduce the energy consumption of the WSN and increase the network lifetime. Simulation result shows that the proposed beacon placement scheme is effective in a sensor network with high node density and also evaluates the proposed routing algorithm.

Wireless Sensor Network (WSN) is one of the most demanding research topics prevalent in the modern research domain. WSN consists of densely deployed sensor nodes in the area which is to be sensed or monitored. Each sensor node is a tiny and power constrained device which is assigned the task of monitoring. Sensor networks have a very wide range of application and so they are much in demand. Every tiny sensor node needs to transmit the sensed data to more powerful sink nodes or base station. Thus as communication is an important aspect of WSN, so the underlying technologies being used should also be competent enough to enable better functionalities. This paper deals WSN technologies. A successful WSN has been designed with heterogeneous sensing devices using the most popular and efficient technology, namely the IP technology.

In many applications large scale Wireless Sensor Networks (WSNs) use multiple sinks for fast data dissemination and energy efficiency. A WSN may be divided into a number of partitions and each partition may contain a sink, thereby reducing the distance between source nodes and sink node. This paper focuses on partitioning algorithms for WSN. Some existing graph partitioning algorithms are studied that can be applied for partitioning a WSN. A novel partitioning approach for WSN is proposed along with its modification. Simulation of the proposed algorithms has been carried out and their performances are compared with some existing algorithms. It is demonstrated that the proposed algorithms perform better than the existing algorithms.

India lacks proper health-care delivery solutions to serve its huge population. Major objective of this paper is to propose technical solution for enabling people, communities, health-care organizations to collect and transmit health information as and when required. An integrated infrastructure based on advanced technologies like Sensor Networks and Grid Computing can be built for improved health-care services for the rural and urban India. An architecture of Sensor-Grid infrastructure is presented in this paper to deliver health-care services efficiently.

The design of 2D wireless sensor network (WSN) has been mostly considered in recent research approaches, while the case of 3D sensor network has not been so much explored. In reality, most wireless sensor networks operate in three-dimensions. Moreover, the 3D scenarios of WSN represent more accurately the network design for real world applications. One of the main design challenges in WSNs is energy efficiency to prolong the network operable lifetime. An efficient planning of WSN can control the energy consumption of the whole network. In this paper, by using computational geometry theoretic, we propose a framework for dynamic topology construction of 3D WSN for a given 3D space monitoring application.

One of the important issues for proper usage of Grid is selection of suitable resources for jobs. Precise estimation of resource requirements for jobs is important in order to ensure efficient use of Grid resources. This paper gives an overview of an efficient job modeling technique for allocation of jobs onto the resource providers in Grid. The proposed job modeling depends on the feedback gathered from the previous executions of different jobs. The paper mainly focuses on the technical implementation details of collection of hardware performance monitoring data using the PAPI tool. The performance monitoring data are later used as feedback while analyzing the resource requirements of the job.

Energy consumption is the key design criterion for routing data in wireless sensor Network. Recently the use of multiple sinks instead of single is considered as a research topic for energy saving. The objective is to maximize the network lifetime by reducing distance from source node to sink during data transmission. This paper proposes a network partitioning algorithm based on selection of farthest node from k-Nearest Neighbour Graph. After partitioning, a restricted flooding-based routing protocol is used for data transmission. It is shown that the network lifetime significantly increases in a partitioned network in comparison with a non-partitioned network.

In the present scenario, mobile communication is being widely used in the areas where infrastructure-based telecommunication systems are unavailable or to deploy one is not cost effective. However, often users suffer due to the fact that mobile devices have very low computational capability and thus are incapable of executing many applications with higher resource requirements. In a Mobile Ad-hoc Network (MANET) environment, when a node (a mobile device) is unable to accomplish a job, the job may be transferred to other nodes, which can fulfill its requirements in terms of resources. In ad-hoc network-based environments, such nodes should be found on demand, i.e. an algorithm should reach every node and match the requirements of a job with the capability of each node. This paper particularly emphasizes on the potentials of using PDAs or laptops of users within an office or in a meeting place. Users can submit their job requirements and then the request will pass through the MANET in order to search for a suitable node that would be able to respond back to the user. This paper proposes a Capability Searching Algorithm (CSA) for using in such scenario. CSA gathers information regarding the capability of a node during route discovery and users later can use this information in selecting the node and the best route to that node.

As far the global warming or climatic change is concerned not only emissions but also wastage of energy in buildings are responsible. So proper indoor management is the need of the hour but manually it seems to be an impossible task to do. This paper presents a framework for Indoor Environment Monitoring System (IEMS) to serve this purpose. Wireless sensor network (WSN) is deployed in every nook and hook of the targeted building. Nodes sense environmental parameters and transfer data by Zigbee radio protocol wirelessly. Utilizing the sensor web enablement (SWE) this framework eases the surveillance effectively.

Data transmission is one of the major challenges in wireless sensor network (WSN). Different routing protocols have been proposed to save energy during data transmission in WSN. Routing protocols based on data-centric approach are suitable in this context that performs in-network aggregation of data to yield energy saving data dissemination. In this paper we propose a modified version of SPIN protocol named M-SPIN and compare its performance with traditional SPIN protocol using broadcast communication, which is a well known protocol as benchmark. We evaluate the M-SPIN protocol using simulation in TOSSIM environment. We find that, M-SPIN exhibits significant performance gains than traditional SPIN routing.

Nature of the resource pool in a Grid environment is heterogeneous and dynamic. Availability, load and status of the resources may change at the time of execution of an application. Therefore, in order to maintain the performance guarantee (as has been agreed upon through service level agreements (SLAs) between the client and the resource providers), an application may need to adapt to its run-time environment on the basis of resource availability and application demands. Often it may be required to migrate the application components to a new set of resources during their execution so that performance guarantee can be maintained. Objective of this paper is to present an adaptive execution scheme for achieving guaranteed performance on the basis of the SLAs. The scheme has been implemented based on the notion of performance properties and by deploying a set of autonomous agents within an integrated performance-based resource management framework.

Resource management is one of the focus areas in Grid computing research. One major objective of resource management in a computational Grid environment is to allocate jobs to make efficient use of the computational resources under different resource providers and, thereby, achieve high performance of the jobs. Therefore, performance analysis is also an important issue in Grid resource management. This paper aims at providing an integrated framework for performance-based resource management in computational Grid environment. The framework is supported by a multi-agent system (MAS) which has been developed using a firm software engineering approach based on Gaia methodology. The MAS provides adaptive execution facility either by rescheduling the jobs onto different resource providers or through application of local tuning techniques to jobs in case of any performance problem (may be due to some change in the resource availability or usage scenario). Thus it always guarantees to maintain the quality of service as desired by the client.

Resource management system in Grid environment manages dynamic, heterogeneous pool of resources and allocates the resources to the jobs in most effective manner. A proper job modeling technique can be helpful in allocating jobs to their most suitable resource providers in Grid. Consequently, it assists to manage the execution of jobs as well as helps to achieve high performance. This paper presents a feedback-guided job modeling technique that describes the process required to identify the most suitable resource provider for a particular job using history-based prediction.

In this paper we present the simulation result of Sensor Protocol for Information via Negotiation (SPIN), a wireless sensor routing protocol, using TinyOS and nesC. TinyOS is a widely used operating system for modern wireless sensors, as its modular system is flexible and powerful. But programming with TinyOS can be challenging because it requires a new language, nesC. SPIN protocol is a data-centric routing protocol for Wireless Sensor Network (WSN). SPIN fits under event-driven delivery model. For implementing SPIN we divide the protocol into three phases. These are Initialization phase, DataCollection phase and Negotiation phase. The protocol is simulated in TOSSIM simulator which is an integral part of nesC.

Resource management is one of the focus areas of Grid which identifies Job Modeling to be a very important part of it. A proper Job Modeling can be helpful in allocating jobs to their most suitable resource providers in Grid. This paper presents a feedback-guided Automatic Job Modeling technique that describes the process required to identify the most suitable resource provider for a particular job.

In this paper we discuss different wireless routing algorithms. We compare the efficiency of those routing algorithms. The basic criterion for the comparison is to determine the time to reach a message from source to destination. In this paper we have also shown that the most efficient WSN routing algorithm may not perform best in case of every application. Different routing algorithms are suitable for different application areas. We also discuss about the limitations of WSN.

MANETs are typically characterized by the dynamic nature of their topology. To select a node and the best route to it in a MANET, an existing routing algorithm called the Capability aware routing algorithm, gathers all the details regarding the capability of that node during route discovery before a new job is submitted every time. However, it may so happen that the service provider may move out of position before the client request actually reaches it, or even after the job has been submitted. The client also may move out of range after submitting a service request. In this paper, we propose a Jini based MANET and extend the CAODV algorithm to accommodate the above mentioned scenarios.

Grid is a distributed, dynamic, heterogeneous environment. Selection of appropriate resources for jobs in such an environment is complicated and challenging task. In order to support proper resource selection and high performance job execution, resource management is essential. Resource management identifies job modeling to be a very important part of it. A proper job modeling can be helpful to allocate jobs into their most suitable resource providers in Grid. Consequently, it assists to manage the execution of jobs as well as helps to achieve the desired level of high performance. This paper presents technical implementation details of job modeling technique which is based on execution history. Proposed job modeling technique utilizes PAPI features to gather hardware performance monitoring data of a job, which are later used for analyzing that job. Job modeling technique describes the process required to identify the most suitable source rovider for a particular job.

Scheduling dependent tasks onto Grid resources is an important area in Grid computing research. One major objective of the problem is to allocate tasks to make efficient use of the computational resources by combining the benefits of parallelisms available among those tasks. Identification of the communication requirements among the tasks and grouping them in order to reduce communication overhead are the major issues related to task scheduling problem. This paper proposes a scheme for task scheduling and identifies the different kinds of task dependencies. A novel technique is introduced which works with a metric called performance ratio and checks the possibilities of parallel execution of a set of dependent tasks, so that the dependent tasks with heavy communication overhead can be scheduled on the same Grid resource provider and communication overhead is reduced.

Geocasting is a special variant of multicasting, where a data packet is destined for a particular geographic region. For many applications in wireless ad hoc and sensor networks, geocasting is an important and widely used communication service. Many geocast routing protocols with different approachability have been developed. Amongst them the geometry driven approach addresses the usage of an optimum path through the Fermat point of a triangle for packet forwarding. However, the geometry driven scheme faces some practical problems while determining the Fermat point for a polygonal region. Moreover, the method proposed can not be generalized for triangles with an angle more than 120°. In this paper we discuss a global minima based scheme for finding the Fermat point of a n sided polygonal geographic region, which is more general in its approach and is free from some of the constraints present in the geometry based scheme for finding the Fermat point. Along with that, the present scheme outplays the geometry driven scheme when it comes to the distance traveled by a packet and the energy consumed therefore.

Wireless Sensor Network (WSN) technology is considered as one of the key technology for 21st Century. These networks are widely used in environmental applications, like military application, habitat monitoring, forest fire detection, agricultural research etc. In order to use WSN effectively in various disaster situations, a lot of research has been carried out in the areas like WSN architecture, routing protocols, naming and addressing the sensor nodes etc. In particular, existing routing protocols in WSN are application specific. In other words, based on the type of application, suitable routing protocol must be chosen to run the application efficiently in the network. This paper investigates the suitable routing protocol for forest fire detection using WSN. In general, sensor nodes sense, aggregate and/or suppress sensing data and forward them to the sink. For real life forest fire detection, parameters like temperature etc. can be sensed and when the sensed data exceeds a certain value, then that particular reading is sent to the sink to generate alert. We have carried out a simulation study of SPIN (Sensor Protocols for Information via Negotiation) protocol to route the environmental data from the active region to the sink wirelessly. In our simulated environment, each sensor node in the network measures a certain number of parameters to which we will refer as attributes (e.g. temperature). Each sensor periodically measures these attributes. First the sensed data from active region are compared with a certain threshold value. If the measured data exceeds the threshold value, a short message (an adv message) is forwarded. The messages are transferred to other sensor nodes towards the sink using multi-hop technique. When the sink receives multiple messages from different direction, it realizes that there is a chance of forest fire. Thus, it sends a requirement packet to the originating nodes and receives actual data along with the location of the originating node in response. These data is used to generate a map of the location of the forest fire. Currently, we have only simulated the protocol using TOSSIM

In a dynamic environment like Grid, it is difficult to manage resources at application or user level. In order to support application execution in the context of Grid, a Resource Broker is essential and the task of resource brokering in such a heterogeneous, fast changing, distributed environment is non-trivial. In this paper we present the design and implementation of resource brokering strategies within a multi-agent framework. These strategies help in finding out an optimal allocation of resources for executing multiple concurrent jobs in a Grid environment. We discuss the different stages in resource brokering and their implementation within the framework. The paper also presents results of a preliminary implementation and demonstrates the effectiveness of our strategies.

Jini is able to support applications in heterogeneous, dynamic computing environments and is also being used to develop agent-based applications. This paper presents the design of a multiagent framework for resource brokering and management in a Grid environment and implementation of a part of it utilizing Jini features. The multiagent framework provides services like resource brokering and allocation, analysis of performance-monitoring data, local tuning of applications and also rescheduling in case of any performance problem on a specific resource provider. Part of the framework makes use of mobile agents for scheduling and rescheduling purposes.