دانلود کتاب Deep Learning for Internet of Things Infrastructure

فهرست مطالب :

Cover
Half Title
Title Page
Copyright Page
Dedication
Table of Contents
Acknowledgments
Editors
Contributors
Chapter 1 Data Caching at Fog Nodes under IoT Networks: Review of Machine Learning Approaches
1.1 Introduction
1.1.1 Importance of Caching at Fog Nodes
1.2 Applications of Data Caching at Fog Nodes for IoT Devices
1.3 Life Cycle of Fog Data
1.4 Machine Learning for Data Caching and Replacement
1.5 Future Research Directions
1.6 Conclusion
References
Chapter 2 ECC-Based Privacy-Preserving Mechanisms Using Deep Learning for Industrial IoT: A State-of-the-Art Approaches
2.1 Introduction of Industrial IoT
2.2 Background and Related Works
2.2.1 Evolution of Industrial IoT
2.2.2 Literature Study on Authentication, Privacy, and Security in IIoT
2.3 Objectives and Mathematical Background
2.3.1 Objectives of the Proposed Work
2.3.2 Symbols Used and Its Description
2.3.3 Groundworks
2.4 Security Issues in Industrial IoT
2.5 Industrial Internet of Things System Architecture
2.5.1 Three Tier Architecture of IIoT
2.5.2 Security Issues
2.5.3 Security Framework in Industrial IoT
2.6 Proposed Scheme
2.6.1 ECC-Based Privacy-Preserving Deep Learning via Re-encryption (ECCRE)
2.6.2 ECC-Based Privacy-Preserving Deep Learning (ECCAL)
2.7 Security Analysis
2.7.1 Security Analysis of ECC Based Re-encryption
2.7.2 Security Analysis of ECC Base Encryption
2.8 Experimentation and Results
2.9 Conclusion
References
Chapter 3 Contemporary Developments and Technologies in Deep Learning–Based IoT
3.1 Introduction
3.2 DL Architecture
3.2.1 Neural Network
3.2.2 Multilayer Perceptron and Convolutional Neural Networks
3.2.3 Learning Methods
3.3 Internet of Things (IoT)
3.3.1 At the Intersection of DL and IoT
3.3.2 Recent Trends in DL-Based IoT
3.4 Popular Frameworks and Models
3.4.1 Models
3.4.2 Frameworks
3.4.3 Applications
3.5 Conclusion
References
Chapter 4 Deep Learning–Assisted Vehicle Counting for Intersection and Traffic Management in Smart Cities
4.1 Introduction
4.2 System Model
4.3 The Proposed Approach
4.3.1 Centroid Tracking Using Euclidean Distance
4.3.2 The Virtual Line Double Crossing Algorithm (VLDCA)
4.4 Performance Evaluation
4.5 Conclusion
References
Chapter 5 Toward Rapid Development and Deployment of Machine Learning Pipelines across Cloud-Edge
5.1 Introduction
5.1.1 Emerging Trends
5.1.2 Challenges and State-of-the-Art Solutions
5.1.3 Overview of Technical Contributions
5.1.4 Organization of the Chapter
5.2 Related Work
5.3 Problem Formulation
5.3.1 Motivating Case Study
5.3.2 ML Model Development
5.3.2.1 Challenges
5.3.2.2 Requirements
5.3.3 ML Pipeline Deployment
5.3.3.1 Challenges
5.3.3.2 Requirements
5.3.4 Infrastructure for Resource Management
5.3.4.1 Challenges
5.3.4.2 Requirements
5.4 Design and Implementation of Stratum
5.4.1 Addressing Requirement 1: Rapid AI/ML Model Prototyping Kit
5.4.1.1 Overview of the ML Model Development
5.4.1.2 Metamodel for ML Algorithms
5.4.1.3 Generative Capabilities
5.4.2 Addressing Requirement 2: Automated Deployment of Application Components on Heterogeneous Resources
5.4.2.1 Metamodel for Data Ingestion Frameworks
5.4.2.2 Metamodel for Data Analytics Applications
5.4.2.3 Metamodel for Heterogeneous Resources
5.4.2.4 Metamodel for Data Storage Services
5.4.3 Addressing Requirement 3: Framework for Performance Monitoring and Intelligent Resource Management
5.4.3.1 Performance Monitoring
5.4.3.2 Resource Management
5.4.4 Support for Collaboration and Versioning
5.4.5 Discussion and Current Limitations
5.5 Evaluation of Stratum
5.5.1 Evaluating the Rapid Model Development Framework
5.5.2 Evaluation of Rapid Application Prototyping Framework
5.5.3 Performance Monitoring on Heterogeneous Hardware
5.5.4 Resource Management
5.6 Conclusion
Acknowledgments
References
Chapter 6 Category Identification Technique by a Semantic Feature Generation Algorithm
6.1 Introduction
6.2 Literature Review
6.3 Proposed Approach
6.3.1 Image Feature Generation
6.3.2 The MPEG-7 Visual Descriptors
6.3.3 Color Descriptors
6.3.3.1 Scalable Color Descriptor (SCD)
6.3.3.2 Color Layout Descriptor (CLD)
6.3.3.3 Color Structure Descriptor (CSD)
6.3.4 Texture Descriptors
6.3.5 Shape Descriptors
6.4 Understanding Machine Learning
6.4.1 Supervised Learning Model
6.4.1.1 Classification
6.4.1.2 Regression
6.4.2 Unsupervised Learning Model
6.4.3 Semi-Supervised Learning Model
6.4.4 Reinforcement Learning Model
6.5 Support Vector Machine (SVM)
6.5.1 Tuning Parameters: Kernel, Regularization, Gamma, and Margin
6.6 Experimental Results
6.7 Conclusion and Future Work
References
Chapter 7 Role of Deep Learning Algorithms in Securing Internet of Things Applications
7.1 Introduction
7.2 Literature Survey of Security Threats in IoT
7.3 ML Algorithms for Attack Detection and Mitigation
7.3.1 Linear Regression
7.3.2 Principal Component Analysis
7.3.3 Q-Learning
7.3.4 K-Means Clustering
7.4 DL Algorithms and IoT Devices
7.4.1 Multilayer Perceptron Neural Network (MLPNN)
7.4.2 Convolutional Neural Network (CNN)
7.4.3 Restricted Boltzmann Machine (RBM)
7.4.4 Deep Belief Network (DBN)
7.5 Requirements of Secured IoT System
7.6 Ideology
7.7 Summary
References
Chapter 8 Deep Learning and IoT in Ophthalmology
8.1 Introduction
8.1.1 Chapter Roadmap
8.2 Internet of Things
8.2.1 Applications in Healthcare
8.2.2 Role of Cloud Computing
8.3 Deep Learning
8.3.1 Applications in Healthcare
8.4 DL- and IoT-Based Infrastructure
8.4.1 Proposed Architecture
8.4.2 Components of the Architecture
8.4.3 Types of Ocular Disease Diagnoses
8.4.4 Business Operations Model
8.5 Privacy, Security, and Ethical Considerations
8.6 Research Challenges
8.7 Conclusions and Future Directions
References
Chapter 9 Deep Learning in IoT-Based Healthcare Applications
9.1 Introduction
9.2 Healthcare and Internet of Things
9.2.1 IoT Medical Devices
9.2.2 IoT-Aware Healthcare System
9.2.3 Emergence of IoMT in Healthcare
9.3 Prospects of Deep Learning
9.4 Challenges of Healthcare IoT Analytics
9.5 Deep Learning Techniques in Healthcare Applications
9.5.1 Health Monitoring
9.5.2 Human Activity Recognition
9.5.3 Disease Analysis
9.5.4 Security
9.6 Conclusion and Future Research
References
Chapter 10 Authentication and Access Control for IoT Devices and Its Applications
10.1 Introduction
10.2 Authentication in IoT
10.2.1 Authentication of IoT Devices
10.2.1.1 Security Issues in IoT Devices
10.2.1.2 Authentication Schemes in IoT
10.2.2 Authentication in IoT-Based Applications
10.2.2.1 Authentication in IoT-Based Smart Cities
10.2.2.2 Authentication in IoT-Based Smart Healthcare
10.2.2.3 Authentication for IIoT
10.2.3 Deep Learning–Based Authentication Techniques
10.2.3.1 Neural Networks for ECG-Based Authentication
10.2.3.2 Convolutional Neural Networks – Deep Face Biometric Authentication
10.3 Access Control in IoT
10.3.1 Blockchain-Based Access Control in IoT
10.3.2 Access Control for IoT Applications
10.3.2.1 Access Control for IoT-Based Healthcare Applications
10.3.2.2 Access Control for IoT-Based Smart Home
10.3.2.3 Access Control for IoT-Based Smart City
10.3.2.4 Access Control for IoT-Based Vehicle Tracking
10.4 Conclusion
References
Chapter 11 Deep Neural Network–Based Security Model for IoT Device Network
11.1 Introduction
11.2 Literature Review
11.3 Proposed Method
11.4 Dataset Description
11.4.1 IoT-Device-Network-Logs Dataset
11.4.2 OPCUA Dataset
11.4.2.1 Data Preprocessing
11.5 Experimental Configuration and Result Analysis
11.5.1 Performance Evaluation
11.5.2 Parameter Setting
11.5.3 Result Analysis
11.6 Conclusion
References
Index