Computing Technologies and Applications: Paving Path Towards Society 5.0

Description

Making use of digital technology for social care is a major responsibility of the computing domain. Social care services require attention for ease in social systems, e-farming, and automation, etc. Thus, the book focuses on suggesting software solutions for supporting social issues, such as health care, learning about and monitoring for disabilities, and providing technical solutions for better living. Technology is enabling people to have access to advances so that they can have better health. To undergo the digital transformation, the current processes need to be completely re-engineered to make use of technologies like the Internet of Things (IoT), big data analytics, artificial intelligence, and others. Furthermore, it is also important to consider digital initiatives in tandem with their cloud strategy instead of treating them in isolation. At present, the world is going through another, possibly even stronger revolution: the use of recent computing models to perform complex cognitive tasks to solve social problems in ways that were previously either highly complicated or extremely resource intensive. This book not only focuses the computing technologies, basic theories, challenges, and implementation but also covers case studies. It focuses on core theories, architectures, and technologies necessary to develop and understand the computing models and their applications. The book also has a high potential to be used as a recommended textbook for research scholars and post-graduate programs. The book deals with a problem-solving approach using recent tools and technology for problems in health care, social care, etc. Interdisciplinary studies are emerging as both necessary and practical in universities. This book helps to improve computational thinking to "understand and change the world’. It will be a link between computing and a variety of other fields. Case studies on social aspects of modern societies and smart cities add to the contents of the book to enhance book adoption potential. This book will be useful to undergraduates, postgraduates, researchers, and industry professionals. Every chapter covers one possible solution in detail, along with results. Cover Half Title Series Page Title Page Copyright Page Contents Preface Acknowledgments Editors Contributors Section I: Cloud Computing 1. Cloud Technology and Management 1.1 Introduction to Cloud Technology 1.1.1 Definition 1.1.2 History of Cloud Computing 1.1.2.1 Evolution of Cloud Computing 1.1.2.2 What Are the Advantages of the Cloud? 1.1.3 Cloud Computing Architecture 1.1.3.1 Front End 1.1.3.2 Middleware 1.1.3.3 Back End 1.1.4 Types of Cloud Services 1.1.4.1 Deployment Model 1.1.4.1.1 Public Cloud 1.1.4.1.2 Private Cloud 1.1.4.1.3 Hybrid Cloud 1.1.4.1.4 Community Cloud 1.1.4.2 Service Model 1.1.4.2.1 IAAS (Infrastructure-as-a-Service) 1.1.4.2.2 PAAS (Platform-as-a-Service) 1.1.4.2.3 SAAS (Software-as-a-Service) 1.1.5 Attributes of Cloud Computing 1.1.6 Obstacles for Cloud Technology 1.2 Cloud Management and Operations 1.2.1 Advantages of Cloud Management 1.2.2 Cloud Infrastructure 1.2.3 Components of Cloud Management 1.2.3.1 Resource Management 1.2.3.2 Cost Management 1.2.3.3 Governance and Compliance 1.2.3.4 Security 1.2.3.5 Case Study on Cloud Storage Service 1.2.3.6 Amazon S3 1.2.3.7 Amazon EBS 1.2.3.8 Amazon Elastic File System References 2. Real Time Edge Computing: An Edge of Automation 2.1 Introduction 2.1.1 Comparison of Cloud and Edge Computing 2.2 Literature Review 2.3 Architecture of Real Time Edge Computing 2.4 Case Study on Edge Computing: Industrial Automation 2.4.1 Industrial Automation Edge Computing Use Cases 2.4.2 Industrial Automation Using Edge Computing Architecture 2.4.3 Industrial Automation Real Time Tasks Allocations on Edge Cloud 2.4.4 Edge Computing Solution for Industrial Automation 2.4.5 Real Time Case Study of Industries Using Edge Computing 2.5 Challenges in Edge Computing 2.6 Scope of Research in Edge Computing 2.7 Conclusions Acknowledgement References 3. Fog Computing: Architecture, Issues, Applications, and Case Study 3.1 Introduction 3.2 Federation 3.3 Benefits of Fog Computing 3.4 Existing Security System in Fog 3.5 IoT Challenges and Their Solutions with Fog Computing 3.6 Some of the Major Issues with Fog Computing 3.7 Other Applications 3.8 Case Studies References 4. Mobile Web Service Architecture in the Cloud Environment 4.1 Introduction 4.2 Mobile Cloud Computing (MCC) 4.3 Web Services 4.3.1 SOAP Web Services 4.3.2 RESTful Web Services 4.3.3 Technological Impact of Mobile Application Development 4.3.4 IoT 4.3.5 Virtual Reality 4.3.6 M-Commerce 4.3.7 Cross-Platform Mobile App Development 4.3.8 Blockchain 4.4 MCC Architectures 4.4.1 Reliable Web Service Architecture 4.4.1.1 Reliable Web Service Through Middleware Component 4.4.2 A Framework of Mobile Cloudlet 4.4.3 Virtual Caching Service Architecture 4.5 Conclusion References Section II: Internet of Things 5. Internet of Things - Essential IoT Business Guide with Different Case Studies 5.1 Introduction to the Internet of Things 5.2 Phrases of the Internet of Things 5.3 Working of the Internet of Things 5.4 Protocols Used in the Internet of Things 5.5 Criticality of the Internet of Things 5.6 Benefits and Detriments 5.7 Applications of the Internet of Things 5.8 Design Methodology for the Internet of Things 5.9 Various Types of Sensors 5.10 Design Methodologies 5.11 Case Studies 5.11.1 Case Study 1: Single Axis Solar Tracker Using Arduino 5.11.2 Case Study 2: Plant Monitoring System using Raspberry-Pi References 6. Research Issues in IoT 6.1 Introduction 6.2 Internet of Things (IoT) 6.2.1 Introduction 6.2.2 Examples of IoT 6.2.3 IoT Challenges 6.3 Tools and Techniques for IoT Challenges 6.3.1 Data Analytics 6.3.2 Decision Analysis and Support Systems 6.3.3 Game Theory 6.3.4 Simulation 6.4 Probable Solutions to Address IoT Research Challenges 6.4.1 Simulation for IoT Scalability 6.4.2 Reliability Theory for IoT Robustness 6.4.3 Self-organizing Systems 6.4.4 Context Awareness 6.5 Case Study 6.6 Conclusion References 7. Intrusion Detection Systems in IoT: Techniques, Datasets, and Challenges 7.1 The IoT and Security 7.1.1 IoT Architecture 7.1.2 Classification of IoT Threats 7.1.3 Traditional Defense Mechanisms 7.2 Intrusion Detection Systems Based on Learning Techniques 7.2.1 Design Choices of Machine Learning Based IDSs 7.2.2 Machine Learning Techniques for IDSs 7.2.3 Metrics for IDS Evaluation 7.3 Tools for NIDS Implementation 7.3.1 Free Data Set Available for IoT Security 7.3.2 Free Open-Source Network Sniffers 7.3.3 Open-source NIDS 7.3.4 Case Study 7.4 Challenges and Future Research Directions 7.5 Conclusion References 8. Case Study of Smart Farming Using IoT 8.1 Introduction 8.2 Literature Review 8.3 Problems with Existing Systems 8.3.1 Agricultural Issues 8.3.2 Farmer Issues and Monitoring Issues 8.4 Proposed Solution 8.5 Components and Sensors 8.5.1 DHT11 - Temperature and Humidity Sensor 8.5.1.1 Working of DHT11 8.5.2 Solenoid Valve 8.5.3 NodeMCU (ESP 8266) 8.6 IoT System Architecture 8.6.1 Communication between DHT11 and Microcontroller 8.6.2 Communication between Solenoid Valve and Microcontroller 8.6.3 Communication between Microcontroller and AWS IoT Platform 8.7 Field Implementation 8.7.1 Agricultural Land Preparation for Crop 8.7.2 Planting the Crop 8.7.3 Crop Selection According to Climate 8.7.3.1 Climate Requirement for Carrot Farming 8.7.4 IoT System Implementation 8.8 Future Scope 8.9 Conclusion References Section III: Data Science, Deep Learning, and Machine Learning 9. Stochastic Computing for Deep Neural Networks 9.1 Introduction 9.2 Theoretical Background 9.2.1 Related Work 9.2.2 Deep Neural Networks 9.2.2.1 Overview of Feedforward Neural Networks 9.2.2.2 Overview of Deep Neural Networks 9.2.3 Principles of Digital Arithmetic 9.2.3.1 Fixed-Value Representation 9.2.3.2 Floating Value Representation 9.2.4 Stochastic Computing Overview 9.3 Stochastic Processing Elements 9.3.1 Combinational Processing-based Elements 9.3.1.1 Multiplication 9.3.1.2 Addition and Subtraction 9.3.2 FSM-based Computational Elements 9.3.2.1 Stochastic Hyperbolic Function 9.3.2.2 Stochastic Max Pooling 9.4 Neural Network Training and Inference in Stochastic Computing 9.5 SC Elements Implementation 9.6 Experiments and Results 9.6.1 Stochastic Computing-based Neural Network Inference 9.6.2 Stochastic Computing-based Neural Network Training 9.7 Case Study 9.8 Conclusion and Further Work References 10. Convolutional Neural Network and Its Advances: Overview and Applications 10.1 Introduction 10.2 Elements of Convolutional Neural Networks 10.2.1 Preliminary Mathematical Concepts 1. Vector and Tensors 2. Chain Rule and Vector Calculus 10.2.2 Basic Components of Convolutional Neural Networks 1. Convolution Layer 2. Pooling Layer 3. Fully Connected Layer 4. Activation Function 10.3 Advances in CNNs 10.3.1 Convolution Layer 1. Tiled Convolution 2. Transposed Convolution 3. Dilated Convolution 10.3.2 Pooling 1. Lp Pooling 2. Mixed Pooling 3. Stochastic Pooling 4. Spectral Pooling 10.3.3 Activation Function 1. ReLU 2. Leaky ReLU 3. Parametric ReLU 10.3.4 Loss Function 1. Softmax Loss 2. Hinge Loss 10.3.5 Regularization 1. Dropout 2. DropConnect 10.3.6 Optimization 1. Weight Initialization 2. Stochastic Gradient Descent 10.4 Classic CNN models 10.4.1 LeNet-5 10.4.2 AlexNet 10.4.3 VGGNets 10.4.4 GoogLeNet 1. Inception v1 2. Inception v2 3. Inception v3 4. Inception v4 and Inception-ResNet 10.5 Applications of CNN 10.5.1 Applications of One-dimensional CNN 10.5.2 Applications of Two-dimensional CNN 1. Image Classification 2. Object Detection 3. Face Recognition 4. Image Segmentation 5. Object Tracking 6. Pose Estimation 10.5.3 Applications of Multi-dimensional CNN 10.6 Conclusion References 11. Convolutional Neural Network: A Systematic Review and Its Application using Keras 11.1 Introduction 11.2 Convolutional Neural Network (CNN) 11.2.1 CNN Architecture 11.2.1.1 Convolutional Layer 11.2.1.2 Classification 11.2.2 Workings of the CNN 11.3 Implementation of CNN 11.3.1 Dataset CIFAR-10 11.3.2 Loading the Dataset and Importing Required Packages 11.3.3 Data Pre-processing 11.3.4 Construction of a CNN 11.4 Latest Research Trends in CNN 11.5 Conclusion References 12. Big Data Analytics: Applications, Issues and Challenges 12.1 Introduction to Big Data Sources of Big Data 12.2 Big Data Analytics and Its Issues and Challenges 12.3 Big Data Analytics using Hadoop Big Data Analytics Challenges with Hadoop Major Components of Hadoop 12.4 Applications I Healthcare [14] [15] II Grid Computing [16,17,18,19] III Flight Safety [23] IV Satellites [25] V Quality of Experience (QoE) Monitoring [26] VI Government VII Social Media Analytics VIII Technology IX Fraud Detection X Call Center Analytics XI Banking XII Agriculture XIII Marketing XIV Smartphones XV Crowd Flow Prediction [27] 12.5 Case Study of Big Data Analytics for Vehicle Tracking 12.6 Conclusion References 13. AR-Powered Computer Science Education 13.1 Introduction 13.2 Augmented Reality 13.3 Data Structure Visualization 13.4 Software Design and Development 13.5 Practical Implementation and Results 13.6 Conclusion Notes References 14. Information Technology for Student Decision Support in College Planning 14.1 Introduction 14.2 Challenges and Opportunities in College Planning 14.2.1 College Planning Is Hard for Undecided Students 14.2.2 Information Technology (IT) Tools for College Planning 14.3 Interest-aligned (IA) Planning: Extending Holland's Theory to College Courses for Decision Support 14.3.1 An Overview of Holland's Theory and Its Applications 14.3.2 The Six Holland Personality Types and Their Assessment 14.3.2.1 Personality Types 14.3.2.2 Personality Assessment and Holland Profile 14.3.3 The Six Environmental Types and Their Assessment 14.3.3.1 Environmental Types 14.3.3.2 Assessing Holland Profiles for Courses and Sets of Courses 14.4 Congruence Measures for Determining Person-environment Alignment 14.5 Decision Support for Major Selection and College Degree Planning 14.5.1 Major Selection (MS) 14.5.2 Optimization Models for College Degree Planning (CDP) 14.5.2.1 Shortest-path and Interest-aligned CDP 14.5.3 An Implementation of CDP via Visualization Models for IA and SP 14.6 Conclusions and Future Research References 15. Attention-based Image Captioning and Evaluation Methods 15.1 Introduction 15.2 Benchmark Datasets 15.3 Attention-based Image Captioning Techniques 15.3.1 Spatial Attention 15.3.2 Semantic Attention 15.3.3 Adaptive Attention 15.3.4 Cascade Attention 15.3.5 Fusion Techniques 15.3.6 Scene Graph Based 15.3.7 Reinforcement Learning Based 15.4 Performance Comparison and Discussions 15.5 Evaluation Metrics and Discussion 15.5.1 BiLingual Evaluation Understudy (BLEU) 15.5.2 METEOR 15.5.3 ROUGE (Recall-Oriented Understudy for Gisting Evaluation) 15.5.4 CIDEr (Consensus-based Image Description Evaluation) 15.6 Image Captioning on Industrial Images: Case Study 15.7 Conclusion References 16. Smart Vehicle Monitoring and Control System using Arduino and Speed Gun: A Case Study 16.1 Introduction 16.2 Motivation 16.3 Existing Technology 16.4 Related Work 16.5 Technologies Important for Smart Cities 16.5.1 Information and Communication Technology (ICT) 16.5.2 Internet of Things (IoT) 16.5.3 Sensors 16.5.4 Geospatial Technology (GT) 16.5.5 Artificial Intelligence (AI) 16.6 Benefits of Smart Cities and Technologies 1. Environmental Impact 2. Optimized Energy and Water Management 3. Transportation 4. Security 16.7 Smart City Solutions 1. Digital Water Management 2. Citizen Emergency Response Devices 3. IoT and Traffic Management 4. Smart Vehicles 16.8 Case Study A. Objective B. Vehicle Speed Detection Using Arduino Speed Gun C. Arduino and Sensor Device D. Methodology 16.9 Algorithm 16.10 Implementation 16.11 Summary References 17. Deep Learning Approaches to Pedestrian Detection: State of the Art 17.1 Introduction 17.2 Pedestrian Datasets 17.2.1 Caltech Pedestrian Dataset 17.2.2 MIT Pedestrian Dataset 17.2.3 Tsinghua-Daimler Pedestrian Dataset 17.2.4 Advanced Technical Center (ATCI) Pedestrian Dataset 17.2.5 National Information and Communication Technology Australia (NICTA) Pedestrian Dataset 17.2.6 ETH Pedestrian Dataset 17.2.7 TUD-Brussels Pedestrian Dataset 17.2.8 National Institute for Research in Computer Science and Automation (INRIA) Pedestrian Dataset 17.2.9 PASCAL Visual Object Classes (VOC) 2017 and 2007 Dataset 17.2.10 Microsoft Common Object in Context (COCO) 2018 Dataset 17.2.11 Mapillary Vistas Research Dataset 17.2.12 Proposed Pedestrian Dataset in Academic Institution 17.3 Pedestrian Detection - Issues and Challenges 17.3.1 Problems Related to the Camera 17.3.1.1 Camera Motion 17.3.1.2 Non-rigid Object Deformation 17.3.2 Challenges in Video Acquisition in the Real World 17.3.2.1 Illumination Variation Scenarios 17.3.2.2 Presence of Abrupt Motion 17.3.2.3 Complex Background 17.3.2.4 Shadows 17.3.3 Challenges of Detecting Pedestrians in the Real World 17.3.3.1 Object Occlusion 17.3.3.2 Moving Object View Angle Changes - Pose Variation 17.4 Recent Developments and Architectural Innovations in CNN 17.5 Recent Open-Source Libraries and Platforms for Deep Learning 17.5.1 TensorFlow 17.5.2 Keras 17.5.3 PyTorch 17.5.4 Scikit-Learn 17.5.5 Pandas 17.5.6 Spark MLlib 17.5.7 Theano 17.5.8 MXNet 17.5.9 Google Colab 17.6 Case Study 17.7 Conclusions and Future Directions References 18. Crop Yield Forecast Using a Hybrid Framework of Deep CNN with RNN Technique 18.1 Introduction 18.2 Literature Review 18.3 Data 18.4 Methodology 18.4.1 Data Preprocessing 18.4.2 Hybrid Deep CNN with RNN Framework 18.4.2.1 Weather Prediction Using the Hybrid Model 18.4.2.2 Yield Prediction Using the Hybrid Model 18.5 Results and Discussion 18.5.1 Performance Estimation 18.5.2 Evaluation Metrics 18.5.3 Data Distribution Properties 18.5.4 Accuracy Measures 18.6 Conclusion References Index