Big Data Analytics for Internet of Things

Tausifa Jan Saleem is currently pursuing her Doctor of Philosophy (Ph.D) from National Institute of Technology Srinagar, India. She has received the Bachelor of Technology (B. Tech.) degree in Information Technology (IT) from National Institute of Technology Srinagar, India and the M.Tech. degree in Computer Science from University of Jammu, India. She has published more than 10 research articles in reputed journals (indexed by Scopus and SCI) and conferences (indexed by Scopus). Her research areas of interest include Internet of Things, Data Analytics, Machine Learning, and Deep Learning.Mohammad Ahsan Chishti, Ph.D, is Dean at the School of Engineering & Technology and Associate Professor in the Department of Information Technology at the Central University of Kashmir. He has published over 100 scholarly papers and holds 12 patents. He is the recipient of “Young Engineers Award 2015-2016” from IEI and “Young Scientist Award 2009-2010” from the government of Jammu and Kashmir. He is a Senior Member of the IEEE, MIEI, MCSI & MIETE.

• List of Contributors xvList of Abbreviations xix1 Big Data Analytics for the Internet of Things: An Overview 1Tausifa Jan Saleem and Mohammad Ahsan Chishti2 Data, Analytics and Interoperability Between Systems (IoT) is Incongruous with the Economics of Technology: Evolution of Porous Pareto Partition (P3) 7Shoumen Palit Austin Datta, Tausifa Jan Saleem, Molood Barati, María Victoria López López, Marie-Laure Furgala, Diana C. Vanegas, Gérald Santucci, Pramod P. Khargonekar, and Eric S. McLamore2.1 Context 82.2 Models in the Background 122.3 Problem Space: Are We Asking the Correct Questions? 142.4 Solutions Approach: The Elusive Quest to Build Bridges Between Data and Decisions 152.5 Avoid This Space: The Deception Space 172.6 Explore the Solution Space: Necessary to Ask Questions That May Not Have Answers, Yet 172.7 Solution Economy: Will We Ever Get There? 192.8 Is This Faux Naïveté in Its Purest Distillate? 212.9 Reality Check: Data Fusion 222.10 “Double A” Perspective of Data and Tools vs. The Hypothetical Porous Pareto (80/20) Partition 282.11 Conundrums 292.12 Stigma of Partition vs. Astigmatism of Vision 382.13 The Illusion of Data, Delusion of Big Data, and the Absence of Intelligence in AI 402.14 In Service of Society 502.15 Data Science in Service of Society: Knowledge and Performance from PEAS 522.16 Temporary Conclusion 60Acknowledgements 63References 633 Machine Learning Techniques for IoT Data Analytics 89Nailah Afshan and Ranjeet Kumar Rout3.1 Introduction 893.2 Taxonomy of Machine Learning Techniques 943.2.1 Supervised ML Algorithm 953.2.1.1 Classification 963.2.1.2 Regression Analysis 983.2.1.3 Classification and Regression Tasks 993.2.2 Unsupervised Machine Learning Algorithms 1033.2.2.1 Clustering 1033.2.2.2 Feature Extraction 1063.2.3 Conclusion 107References 1074 IoT Data Analytics Using Cloud Computing 115Anjum Sheikh, Sunil Kumar, and Asha Ambhaikar4.1 Introduction 1154.2 IoT Data Analytics 1174.2.1 Process of IoT Analytics 1174.2.2 Types of Analytics 1184.3 Cloud Computing for IoT 1184.3.1 Deployment Models for Cloud 1204.3.1.1 Private Cloud 1204.3.1.2 Public Cloud 1204.3.1.3 Hybrid Cloud 1214.3.1.4 Community Cloud 1214.3.2 Service Models for Cloud Computing 1224.3.2.1 Software as a Service (SaaS) 1224.3.2.2 Platform as a Service (PaaS) 1224.3.2.3 Infrastructure as a Service (IaaS) 1224.3.3 Data Analytics on Cloud 1234.4 Cloud-Based IoT Data Analytics Platform 1234.4.1 Atos Codex 1254.4.2 AWS IoT 1254.4.3 IBM Watson IoT 1264.4.4 Hitachi Vantara Pentaho, Lumada 1274.4.5 Microsoft Azure IoT 1284.4.6 Oracle IoT Cloud Services 1294.5 Machine Learning for IoT Analytics in Cloud 1324.5.1 ML Algorithms for Data Analytics 1324.5.2 Types of Predictions Supported by ML and Cloud 1364.6 Challenges for Analytics Using Cloud 1374.7 Conclusion 139References 1395 Deep Learning Architectures for IoT Data Analytics 143Snowber Mushtaq and Omkar Singh5.1 Introduction 1435.1.1 Types of Learning Algorithms 1465.1.1.1 Supervised Learning 1465.1.1.2 Unsupervised Learning 1465.1.1.3 Semi-Supervised Learning 1465.1.1.4 Reinforcement Learning 1465.1.2 Steps Involved in Solving a Problem 1465.1.2.1 Basic Terminology 1475.1.2.2 Training Process 1475.1.3 Modeling in Data Science 1475.1.3.1 Generative 1485.1.3.2 Discriminative 1485.1.4 Why DL and IoT? 1485.2 DL Architectures 1495.2.1 Restricted Boltzmann Machine 1495.2.1.1 Training Boltzmann Machine 1505.2.1.2 Applications of RBM 1515.2.2 Deep Belief Networks (DBN) 1515.2.2.1 Training DBN 1525.2.2.2 Applications of DBN 1535.2.3 Autoencoders 1535.2.3.1 Training of AE 1535.2.3.2 Applications of AE 1545.2.4 Convolutional Neural Networks (CNN) 1545.2.4.1 Layers of CNN 1555.2.4.2 Activation Functions Used in CNN 1565.2.4.3 Applications of CNN 1585.2.5 Generative Adversarial Network (GANs) 1585.2.5.1 Training of GANs 1585.2.5.2 Variants of GANs 1595.2.5.3 Applications of GANs 1595.2.6 Recurrent Neural Networks (RNN) 1595.2.6.1 Training of RNN 1605.2.6.2 Applications of RNN 1615.2.7 Long Short-Term Memory (LSTM) 1615.2.7.1 Training of LSTM 1615.2.7.2 Applications of LSTM 1625.3 Conclusion 162References 1636 Adding Personal Touches to IoT: A User-Centric IoT Architecture 167Sarabjeet Kaur Kochhar6.1 Introduction 1676.2 Enabling Technologies for BDA of IoT Systems 1696.3 Personalizing the IoT 1716.3.1 Personalization for Business 1726.3.2 Personalization for Marketing 1726.3.3 Personalization for Product Improvement and Service Optimization 1736.3.4 Personalization for Automated Recommendations 1746.3.5 Personalization for Improved User Experience 1746.4 Related Work 1756.5 User Sensitized IoT Architecture 1766.6 The Tweaked Data Layer 1786.7 The Personalization Layer 1806.7.1 The Characterization Engine 1806.7.2 The Sentiment Analyzer 1826.8 Concerns and Future Directions 1836.9 Conclusions 184References 1857 Smart Cities and the Internet of Things 187Hemant Garg, Sushil Gupta, and Basant Garg7.1 Introduction 1877.2 Development of Smart Cities and the IoT 1887.3 The Combination of the IoT with Development of City Architecture to Form Smart Cities 1897.3.1 Unification of the IoT 1907.3.2 Security of Smart Cities 1907.3.3 Management of Water and Related Amenities 1907.3.4 Power Distribution and Management 1917.3.5 Revenue Collection and Administration 1917.3.6 Management of City Assets and Human Resources 1927.3.7 Environmental Pollution Management 1927.4 How Future Smart Cities Can Improve Their Utilization of the Internet of All Things, with Examples 1937.5 Conclusion 194References 1958 A Roadmap for Application of IoT-Generated Big Data in Environmental Sustainability 197Ankur Kashyap8.1 Background and Motivation 1978.2 Execution of the Study 1988.2.1 Role of Big Data in Sustainability 1988.2.2 Present Status and Future Possibilities of IoT in Environmental Sustainability 1998.3 Proposed Roadmap 2028.4 Identification and Prioritizing the Barriers in the Process 2048.4.1 Internet Infrastructure 2048.4.2 High Hardware and Software Cost 2048.4.3 Less Qualified Workforce 2048.5 Conclusion and Discussion 205References 2059 Application of High-Performance Computing in Synchrophasor Data Management and Analysis for Power Grids 209C.M. Thasnimol and R. Rajathy9.1 Introduction 2099.2 Applications of Synchrophasor Data 2109.2.1 Voltage Stability Analysis 2119.2.2 Transient Stability 2129.2.3 Out of Step Splitting Protection 2139.2.4 Multiple Event Detection 2139.2.5 State Estimation 2139.2.6 Fault Detection 2149.2.7 Loss of Main (LOM) Detection 2149.2.8 Topology Update Detection 2149.2.9 Oscillation Detection 2159.3 Utility Big Data Issues Related to PMU-Driven Applications 2159.3.1 Heterogeneous Measurement Integration 2159.3.2 Variety and Interoperability 2169.3.3 Volume and Velocity 2169.3.4 Data Quality and Security 2169.3.5 Utilization and Analytics 2179.3.6 Visualization of Data 2189.4 Big Data Analytics Platforms for PMU Data Processing 2199.4.1 Hadoop 2209.4.2 Apache Spark 2219.4.3 Apache HBase 2229.4.4 Apache Storm 2229.4.5 Cloud-Based Platforms 2239.5 Conclusions 224References 22410 Intelligent Enterprise-Level Big Data Analytics for Modeling and Management in Smart Internet of Roads 231Amin Fadaeddini, Babak Majidi, and Mohammad Eshghi10.1 Introduction 23110.2 Fully Convolutional Deep Neural Network for Autonomous Vehicle Identification 23310.2.1 Detection of the Bounding Box of the License Plate 23310.2.2 Segmentation Objective 23410.2.3 Spatial Invariances 23410.2.4 Model Framework 23410.2.4.1 Increasing the Layer of Transformation 23410.2.4.2 Data Format of Sample Images 23510.2.4.3 Applying Batch Normalization 23610.2.4.4 Network Architecture 23610.2.5 Role of Data 23610.2.6 Synthesizing Samples 23610.2.7 Invariances 23710.2.8 Reducing Number of Features 23710.2.9 Choosing Number of Classes 23810.3 Experimental Setup and Results 23910.3.1 Sparse Softmax Loss 23910.3.2 Mean Intersection Over Union 24010.4 Practical Implementation of Enterprise-Level Big Data Analytics for Smart City 24010.5 Conclusion 244References 24411 Predictive Analysis of Intelligent Sensing and Cloud-Based Integrated Water Management System 247Tanuja Patgar and Ripal Patel11.1 Introduction 24711.2 Literature Survey 24811.3 Proposed Six-Tier Data Framework 25011.3.1 Primary Components 25111.3.2 Contact Unit (FC-37) 25311.3.3 Internet of Things Communicator (ESP8266) 25311.3.4 GSM-Based ARM and Control System 25311.3.5 Methodology 25311.3.6 Proposed Algorithm 25611.4 Implementation and Result Analysis 25711.4.1 Water Report for Home 1 and Home 2 Modules 26311.5 Conclusion 263References 26312 Data Security in the Internet of Things: Challenges and Opportunities 265Shashwati Banerjea, Shashank Srivastava, and Sachin Kumar12.1 Introduction 26512.2 IoT: Brief Introduction 26612.2.1 Challenges in a Secure IoT 26712.2.2 Security Requirements in IoT Architecture 26812.2.2.1 Sensing Layer 26812.2.2.2 Network Layer 26912.2.2.3 Interface Layer 27112.2.3 Common Attacks in IoT 27112.3 IoT Security Classification 27212.3.1 Application Domain 27212.3.1.1 Authentication 27212.3.1.2 Authorization 27412.3.1.3 Depletion of Resources 27412.3.1.4 Establishment of Trust 27512.3.2 Architectural Domain 27512.3.2.1 Authentication in IoT Architecture 27512.3.2.2 Authorization in IoT Architecture 27612.3.3 Communication Channel 27612.4 Security in IoT Data 27712.4.1 IoT Data Security: Requirements 27712.4.1.1 Data: Confidentiality, Integrity, and Authentication 27812.4.1.2 Data Privacy 27912.4.2 IoT Data Security: Research Directions 28012.5 Conclusion 280References 28113 DDoS Attacks: Tools, Mitigation Approaches, and Probable Impact on Private Cloud Environment 285R. K. Deka, D. K. Bhattacharyya, and J. K. Kalita13.1 Introduction 28513.1.1 State of the Art 28713.1.2 Contribution 28813.1.3 Organization 29013.2 Cloud and DDoS Attack 29013.2.1 Cloud Deployment Models 29013.2.1.1 Differences Between Private Cloud and Public Cloud 29313.2.2 DDoS Attacks 29413.2.2.1 Attacks on Infrastructure Level 29413.2.2.2 Attacks on Application Level 29613.2.3 DoS/DDoS Attack on Cloud: Probable Impact 29713.3 Mitigation Approaches 29813.3.1 Discussion 30913.4 Challenges and Issues with Recommendations 30913.5 A Generic Framework 31013.6 Conclusion and Future Work 312References 31214 Securing the Defense Data for Making Better Decisions Using Data Fusion 321Syed Rameem Zahra14.1 Introduction 32114.2 Analysis of Big Data 32214.2.1 Existing IoT Big Data Analytics Systems 32214.2.2 Big Data Analytical Methods 32414.2.3 Challenges in IoT Big Data Analytics 32414.3 Data Fusion 32514.3.1 Opportunities Provided by Data Fusion 32614.3.2 Data Fusion Challenges 32614.3.3 Stages at Which Data Fusion Can Happen 32614.3.4 Mathematical Methods for Data Fusion 32614.4 Data Fusion for IoT Security 32714.4.1 Defense Use Case 32914.5 Conclusion 329References 33015 New Age Journalism and Big Data (Understanding Big Data and Its Influence on Journalism) 333Asif Khan and Heeba Din15.1 Introduction 33315.1.1 Big Data Journalism: The Next Big Thing 33415.1.2 All About Data 33615.1.3 Accessing Data for Journalism 33715.1.4 Data Analytics: Tools for Journalists 33815.1.5 Case Studies – Big Data 34015.1.5.1 BBC Big Data 34015.1.5.2 The Guardian Data Blog 34215.1.5.3 Wikileaks 34415.1.5.4 World Economic Forum 34415.1.6 Big Data – Indian Scenario 34515.1.7 Internet of Things and Journalism 34615.1.8 Impact on Media/Journalism 347References 34816 Two Decades of Big Data in Finance: Systematic Literature Review and Future Research Agenda 351Nufazil Altaf16.1 Introduction 35116.2 Methodology 35316.3 Article Identification and Selection 35316.4 Description and Classification of Literature 35416.4.1 Research Method Employed 35416.4.2 Articles Published Year Wise 35516.4.3 Journal of Publication 35616.5 Content and Citation Analysis of Articles 35616.5.1 Citation Analysis 35616.5.2 Content Analysis 35716.5.2.1 Big Data in Financial Markets 35816.5.2.2 Big Data in Internet Finance 35916.5.2.3 Big Data in Financial Services 35916.5.2.4 Big Data and Other Financial Issues 36016.6 Reporting of Findings and Research Gaps 36016.6.1 Findings from the Literature Review 36116.6.1.1 Lack of Symmetry 36116.6.1.2 Dominance of Research on Financial Markets, Internet Finance, and Financial Services 36116.6.1.3 Dominance of Empirical Research 36116.6.2 Directions for Future Research 362References 362Index 367