11756nam 2200529 450 991067813780332120211014131147.01-119-74077-01-119-74078-91-119-74076-2(CKB)4100000011809498(MiAaPQ)EBC6527616(Au-PeEL)EBL6527616(OCoLC)1244620042(CaSebORM)9781119740759(EXLCZ)99410000001180949820211014d2021 uy 0engurcnu||||||||txtrdacontentcrdamediacrrdacarrierBig data analytics for Internet of things /edited by Tausifa Jan Saleem, Mohammad Ahsan ChishtiHoboken, New Jersey :Wiley,[2021]©20211 online resource (xx, 376 pages) illustrations1-119-74075-4 Includes bibliographical references and index.Cover -- Title Page -- Copyright Page -- Contents -- List of Contributors -- List of Abbreviations -- Chapter 1 Big Data Analytics for the Internet of Things: An Overview -- Chapter 2 Data, Analytics and Interoperability Between Systems (IoT) is Incongruous with the Economics of Technology: Evolution of Porous Pareto Partition (P3) -- 2.1 Context -- 2.2 Models in the Background -- 2.3 Problem Space: Are We Asking the Correct Questions? -- 2.4 Solutions Approach: The Elusive Quest to Build Bridges Between Data and Decisions -- 2.5 Avoid This Space: The Deception Space -- 2.6 Explore the Solution Space: Necessary to Ask Questions That May Not Have Answers, Yet -- 2.7 Solution Economy: Will We Ever Get There? -- 2.8 Is This Faux Naïveté in Its Purest Distillate? -- 2.9 Reality Check: Data Fusion -- 2.10 "Double A" Perspective of Data and Tools vs. The Hypothetical Porous Pareto (80/20) Partition -- 2.11 Conundrums -- 2.12 Stigma of Partition vs. Astigmatism of Vision -- 2.13 The Illusion of Data, Delusion of Big Data, and the Absence of Intelligence in AI -- 2.14 In Service of Society -- 2.15 Data Science in Service of Society: Knowledge and Performance from PEAS -- 2.16 Temporary Conclusion -- Acknowledgements -- References -- Chapter 3 Machine Learning Techniques for IoT Data Analytics -- 3.1 Introduction -- 3.2 Taxonomy of Machine Learning Techniques -- 3.2.1 Supervised ML Algorithm -- 3.2.1.1 Classification -- 3.2.1.2 Regression Analysis -- 3.2.1.3 Classification and Regression Tasks -- 3.2.2 Unsupervised Machine Learning Algorithms -- 3.2.2.1 Clustering -- 3.2.2.2 Feature Extraction -- 3.2.3 Conclusion -- References -- Chapter 4 IoT Data Analytics Using Cloud Computing -- 4.1 Introduction -- 4.2 IoT Data Analytics -- 4.2.1 Process of IoT Analytics -- 4.2.2 Types of Analytics -- 4.3 Cloud Computing for IoT -- 4.3.1 Deployment Models for Cloud.4.3.1.1 Private Cloud -- 4.3.1.2 Public Cloud -- 4.3.1.3 Hybrid Cloud -- 4.3.1.4 Community Cloud -- 4.3.2 Service Models for Cloud Computing -- 4.3.2.1 Software as a Service (SaaS) -- 4.3.2.2 Platform as a Service (PaaS) -- 4.3.2.3 Infrastructure as a Service (IaaS) -- 4.3.3 Data Analytics on Cloud -- 4.4 Cloud-Based IoT Data Analytics Platform -- 4.4.1 Atos Codex -- 4.4.2 AWS IoT -- 4.4.3 IBM Watson IoT -- 4.4.4 Hitachi Vantara Pentaho, Lumada -- 4.4.5 Microsoft Azure IoT -- 4.4.6 Oracle IoT Cloud Services -- 4.5 Machine Learning for IoT Analytics in Cloud -- 4.5.1 ML Algorithms for Data Analytics -- 4.5.2 Types of Predictions Supported by ML and Cloud -- 4.6 Challenges for Analytics Using Cloud -- 4.7 Conclusion -- References -- Chapter 5 Deep Learning Architectures for IoT Data Analytics -- 5.1 Introduction -- 5.1.1 Types of Learning Algorithms -- 5.1.1.1 Supervised Learning -- 5.1.1.2 Unsupervised Learning -- 5.1.1.3 Semi-Supervised Learning -- 5.1.1.4 Reinforcement Learning -- 5.1.2 Steps Involved in Solving a Problem -- 5.1.2.1 Basic Terminology -- 5.1.2.2 Training Process -- 5.1.3 Modeling in Data Science -- 5.1.3.1 Generative -- 5.1.3.2 Discriminative -- 5.1.4 Why DL and IoT? -- 5.2 DL Architectures -- 5.2.1 Restricted Boltzmann Machine -- 5.2.1.1 Training Boltzmann Machine -- 5.2.1.2 Applications of RBM -- 5.2.2 Deep Belief Networks (DBN) -- 5.2.2.1 Training DBN -- 5.2.2.2 Applications of DBN -- 5.2.3 Autoencoders -- 5.2.3.1 Training of AE -- 5.2.3.2 Applications of AE -- 5.2.4 Convolutional Neural Networks (CNN) -- 5.2.4.1 Layers of CNN -- 5.2.4.2 Activation Functions Used in CNN -- 5.2.5 Generative Adversarial Network (GANs) -- 5.2.5.1 Training of GANs -- 5.2.5.2 Variants of GANs -- 5.2.5.3 Applications of GANs -- 5.2.6 Recurrent Neural Networks (RNN) -- 5.2.6.1 Training of RNN -- 5.2.6.2 Applications of RNN.5.2.7 Long Short-Term Memory (LSTM) -- 5.2.7.1 Training of LSTM -- 5.2.7.2 Applications of LSTM -- 5.3 Conclusion -- References -- Chapter 6 Adding Personal Touches to IoT: A User-Centric IoT Architecture -- 6.1 Introduction -- 6.2 Enabling Technologies for BDA of IoT Systems -- 6.3 Personalizing the IoT -- 6.3.1 Personalization for Business -- 6.3.2 Personalization for Marketing -- 6.3.3 Personalization for Product Improvement and Service Optimization -- 6.3.4 Personalization for Automated Recommendations -- 6.3.5 Personalization for Improved User Experience -- 6.4 Related Work -- 6.5 User Sensitized IoT Architecture -- 6.6 The Tweaked Data Layer -- 6.7 The Personalization Layer -- 6.7.1 The Characterization Engine -- 6.7.2 The Sentiment Analyzer -- 6.8 Concerns and Future Directions -- 6.9 Conclusions -- References -- Chapter 7 Smart Cities and the Internet of Things -- 7.1 Introduction -- 7.2 Development of Smart Cities and the IoT -- 7.3 The Combination of the IoT with Development of City Architecture to Form Smart Cities -- 7.3.1 Unification of the IoT -- 7.3.2 Security of Smart Cities -- 7.3.3 Management of Water and Related Amenities -- 7.3.4 Power Distribution and Management -- 7.3.5 Revenue Collection and Administration -- 7.3.6 Management of City Assets and Human Resources -- 7.3.7 Environmental Pollution Management -- 7.4 How Future Smart Cities Can Improve Their Utilization of the Internet of All Things, with Examples -- 7.5 Conclusion -- References -- Chapter 8 A Roadmap for Application of IoT-Generated Big Data in Environmental Sustainability -- 8.1 Background and Motivation -- 8.2 Execution of the Study -- 8.2.1 Role of Big Data in Sustainability -- 8.2.2 Present Status and Future Possibilities of IoT in Environmental Sustainability -- 8.3 Proposed Roadmap -- 8.4 Identification and Prioritizing the Barriers in the Process.8.4.1 Internet Infrastructure -- 8.4.2 High Hardware and Software Cost -- 8.4.3 Less Qualified Workforce -- 8.5 Conclusion and Discussion -- References -- Chapter 9 Application of High-Performance Computing in Synchrophasor Data Management and Analysis for Power Grids -- 9.1 Introduction -- 9.2 Applications of Synchrophasor Data -- 9.2.1 Voltage Stability Analysis -- 9.2.2 Transient Stability -- 9.2.3 Out of Step Splitting Protection -- 9.2.4 Multiple Event Detection -- 9.2.5 State Estimation -- 9.2.6 Fault Detection -- 9.2.7 Loss of Main (LOM) Detection -- 9.2.8 Topology Update Detection -- 9.2.9 Oscillation Detection -- 9.3 Utility Big Data Issues Related to PMU-Driven Applications -- 9.3.1 Heterogeneous Measurement Integration -- 9.3.2 Variety and Interoperability -- 9.3.3 Volume and Velocity -- 9.3.4 Data Quality and Security -- 9.3.5 Utilization and Analytics -- 9.3.6 Visualization of Data -- 9.4 Big Data Analytics Platforms for PMU Data Processing -- 9.4.1 Hadoop -- 9.4.2 Apache Spark -- 9.4.3 Apache HBase -- 9.4.4 Apache Storm -- 9.4.5 Cloud-Based Platforms -- 9.5 Conclusions -- References -- Chapter 10 Intelligent Enterprise-Level Big Data Analytics for Modeling and Management in Smart Internet of Roads -- 10.1 Introduction -- 10.2 Fully Convolutional Deep Neural Network for Autonomous Vehicle Identification -- 10.2.1 Detection of the Bounding Box of the License Plate -- 10.2.2 Segmentation Objective -- 10.2.3 Spatial Invariances -- 10.2.4 Model Framework -- 10.2.4.1 Increasing the Layer of Transformation -- 10.2.4.2 Data Format of Sample Images -- 10.2.4.3 Applying Batch Normalization -- 10.2.4.4 Network Architecture -- 10.2.5 Role of Data -- 10.2.6 Synthesizing Samples -- 10.2.7 Invariances -- 10.2.8 Reducing Number of Features -- 10.2.9 Choosing Number of Classes -- 10.3 Experimental Setup and Results -- 10.3.1 Sparse Softmax Loss.10.3.2 Mean Intersection Over Union -- 10.4 Practical Implementation of Enterprise-Level Big Data Analytics for Smart City -- 10.5 Conclusion -- References -- Chapter 11 Predictive Analysis of Intelligent Sensing and Cloud-Based Integrated Water Management System -- 11.1 Introduction -- 11.2 Literature Survey -- 11.3 Proposed Six-Tier Data Framework -- 11.3.1 Primary Components -- 11.3.2 Contact Unit (FC-37) -- 11.3.3 Internet of Things Communicator (ESP8266) -- 11.3.4 GSM-Based ARM and Control System -- 11.3.5 Methodology -- 11.3.6 Proposed Algorithm -- 11.4 Implementation and Result Analysis -- 11.4.1 Water Report for Home 1 and Home 2 Modules -- 11.5 Conclusion -- References -- Chapter 12 Data Security in the Internet of Things: Challenges and Opportunities -- 12.1 Introduction -- 12.2 IoT: Brief Introduction -- 12.2.1 Challenges in a Secure IoT -- 12.2.2 Security Requirements in IoT Architecture -- 12.2.2.1 Sensing Layer -- 12.2.2.2 Network Layer -- 12.2.2.3 Interface Layer -- 12.2.3 Common Attacks in IoT -- 12.3 IoT Security Classification -- 12.3.1 Application Domain -- 12.3.1.1 Authentication -- 12.3.1.2 Authorization -- 12.3.1.3 Depletion of Resources -- 12.3.1.4 Establishment of Trust -- 12.3.2 Architectural Domain -- 12.3.2.1 Authentication in IoT Architecture -- 12.3.2.2 Authorization in IoT Architecture -- 12.3.3 Communication Channel -- 12.4 Security in IoT Data -- 12.4.1 IoT Data Security: Requirements -- 12.4.1.1 Data: Confidentiality, Integrity, and Authentication -- 12.4.1.2 Data Privacy -- 12.4.2 IoT Data Security: Research Directions -- 12.5 Conclusion -- References -- Chapter 13 DDoS Attacks: Tools, Mitigation Approaches, and Probable Impact on Private Cloud Environment -- 13.1 Introduction -- 13.1.1 State of the Art -- 13.1.2 Contribution -- 13.1.3 Organization -- 13.2 Cloud and DDoS Attack -- 13.2.1 Cloud Deployment Models.13.2.1.1 Differences Between Private Cloud and Public Cloud."Big Data Analytics is a briskly expanding research area spanning diverse fields. The efficacy of Big Data Analytics is found mainly in the domain of Internet of Things (IoT). The number of IoT devices is anticipated to amount to several billion in the next few years. This unpredictable growth in the number of devices connected to IoT and the exponential rise in data consumption manifest how the expansion of big data seamlessly coincides with that of IoT. The main objective of Big Data Analytics in IoT is to identify trends in the data, extract concealed information and to dig out valuable information from the raw data generated by IoT systems. This is crucial for dispensing elite services to IoT users. In this regard, investigating the recent technological advancements in the said area becomes indispensable."--Provided by publisher.Big dataBig data.005.7Saleem Tausifa JanChishti Mohammad AhsanMiAaPQMiAaPQMiAaPQBOOK9910678137803321Big data analytics for Internet of things3072016UNINA