Intelligent Cyber-Physical Systems for Autonomous Transportation

Foreword
Preface
Contents
Contributors
Part I Overview of Transportation Systems
1 Transportation Systems
1.1 Background of Transportation Systems
1.1.1 Roads
1.1.2 Rails
1.1.3 Air
1.2 Growth of Transportation Industry
1.2.1 Importance of Transportation Industry
1.2.2 Growth Factors in Transportation Industry
1.3 Challenges to Transportation Industry
1.3.1 Social and Political Challenges to Transportation Industry
1.3.2 Technical Challenges to Transportation Industry
1.4 Impact of Intelligent Transportation Systems
1.4.1 Overview of ITS
1.4.2 Applications of ITS
1.4.3 Challenges Overcome by Intelligent Transportation Systems
1.5 Conclusion and Future Directions
References
2 Future Autonomous Transportation: Challenges and Prospective Dimensions
2.1 Introduction
2.2 State-of-the-Art System on Autonomous Vehicles
2.3 Technical Feasibility
2.4 Autonomous Transportation on Earth
2.4.1 Challenges
2.5 Autonomous Transportation in Air
2.5.1 Challenges
2.6 Autonomous Transportation in Sea
2.6.1 Challenges
2.7 Potential Technologies for Autonomous Transportation Systems
2.7.1 Blockchain
2.7.2 Artificial Intelligence and Machine Learning
2.7.3 Edge/Fog Computing
2.8 Conclusion
References
Part II Artificial Intelligence
3 Artificial Intelligence
3.1 AI Conception
3.1.1 Cognitive AI
3.1.2 Machine Learning AI
3.1.3 Deep Learning AI
3.2 Need and Evolution of AI
3.2.1 Origin and Development About AI
3.2.2 Common Approaches and Technologies
3.2.2.1 Natural Language Processing (NLP)
3.2.2.2 Artificial Neural Networks (ANN)
3.2.2.3 Computer Vision
3.2.2.4 Expert System
3.2.3 Successive Cross-Field Solutions
3.2.3.1 Smart Manufacturing
3.2.3.2 Smart City
3.2.3.3 Smart Care
3.2.3.4 Smart Education
3.2.3.5 Smart Workflow
3.3 AI for Transportation Systems
3.3.1 Motivations
3.3.2 Application Status
3.3.2.1 Vehicle Identification
3.3.2.2 Vehicle Retrieval
3.3.2.3 Traffic Signal System
3.3.2.4 Driverless
3.3.3 Challenges
References
4 Artificial Intelligence: Evolution, Benefits, and Challenges
4.1 Introduction to Artificial Intelligence
4.1.1 Types of Artificial Intelligence
4.2 Needs and Evolution
4.2.1 Needs of Artificial Intelligence
4.2.2 Evolution of Artificial Intelligence
4.3 AI for Transportation System
4.3.1 Introduction
4.3.2 Benefits of AI in Transportation System
4.3.3 Challenges and Future Research Directions
References
5 Artificial Intelligence: Need, Evolution, and Applications for Transportation Systems
5.1 Overview of Artificial Intelligence
5.1.1 Evolution of Artificial Intelligence
5.1.2 Machine Learning
5.1.3 Reinforcement Learning
5.1.4 Other State-of-the-Art AI Algorithms
5.2 Artificial Intelligence-Empowered Transportation Network
5.2.1 Artificial Intelligence for V2X
5.2.2 Artificial Intelligence for Vehicular Edge Computing
5.2.3 Artificial Intelligence for Unmanned Aerial Vehicle
5.3 AI-Based Applications in Transportation System
5.3.1 Autonomous Driving
5.3.2 Traffic Prediction and Control
5.3.3 UAV Path Planning
References
6 Artificial Intelligence Deployment in Transportation Systems
6.1 Review for AI-Deployment Transportation Systems
6.1.1 Overview
6.1.2 Prevalence
6.1.3 Development Status
6.2 Architecture for AI-Deployment Transportation Systems
6.2.1 AI-Deployment Sensing Layer
6.2.2 AI-Deployment Networking Layer
6.2.3 AI-Deployment Application Layer
6.3 Business Situations for AI-Deployment Transportation Systems
6.3.1 Autonomous Transportation Management
6.3.2 Vehicular Control
6.3.2.1 Intelligent Connected Car (ICV)
6.3.2.2 Intelligent Vehicle–Road Collaboration System (IVRCS)
6.3.2.3 Driverless
6.3.3 Public Transportation Scheduling
6.3.3.1 Public Transportation Scheduling Center
6.3.3.2 Sub-scheduling Center
6.3.3.3 Vehicle Mobile Station
6.3.3.4 Electronic Stop Sign
6.3.4 Transportation Information Service
6.3.4.1 Traveler Information Service Needs
6.3.4.2 The Content of Travel Information Services
6.3.4.3 Construction Content of Public Travel Information Service Platform
6.3.4.4 Travel Chain Analysis
References
Part III Cyber-Physical Systems
7 Cyber-Physical Systems: Historical Evolution and Role in Future Autonomous Transportation
7.1 Introduction
7.2 Internet of Things: Communication
7.3 Vehicle Communication
7.4 Applications
7.4.1 Intelligent Transportation
7.4.2 Supply Chain Management
7.5 Case Study
7.6 Connected Vehicle Challenges
7.7 Summary
References
8 Cyber-Physical Systems in Transportation
8.1 Introduction to Cyber-Physical Systems
8.2 Design and Modeling
8.2.1 CPS Architecture
8.2.2 TCPS Architecture
8.3 The Roles of CPS in ITS
8.4 Challenges and Solutions
8.4.1 Standardization and Availability
8.4.2 Efficiency and Reliability
8.4.3 Security and Privacy
8.5 Concluding Remarks
References
Part IV Application Use Cases of Autonomous Transportation Systems
9 Correlation Between Traffic Lights and Emergency Vehicles in Intelligent Transportation System
9.1 Introduction
9.2 Architecture
9.2.1 Hardware Layer
9.2.1.1 Intrusive Sensors
9.2.1.2 Non-intrusive Sensors
9.2.2 Network Layer
9.2.3 Analytical Layer
9.2.4 Application Layer
9.3 Proposed Scheme
9.3.1 Centralised Light-Weight Reporting
9.3.2 Real-Time Route Information Dissemination to Emergency Vehicles
9.3.3 Multiple Emergency Vehicles Intersection Crossing
9.4 Conclusion and Future Scope
References
10 Use Case for Underwater Transportation
10.1 Introduction
10.2 Related Work
10.3 Proposed Scheme
10.3.1 Network Architecture
10.3.2 Depth Threshold
10.3.3 Cluster Formation
10.3.4 Skipping Nodes
10.3.5 Inter-Cluster and Intra-Cluster Communication
10.3.6 Aggregation Techniques
10.3.6.1 Flow Chart
10.4 Conclusions and Future Work
References
11 Advanced Signal Processing for Autonomous Transportation Big Data
11.1 Introduction
11.2 Related Work
11.3 Method
11.3.1 Industrial Big Data
11.3.2 Signal Processing Technology
11.3.3 Realization and Application of Autonomous Driving Based on Signal Processing
11.3.4 The Advanced Signal Processing System for Industrial Big Data
11.3.5 Simulation Analysis
11.4 Results and Discussions
11.4.1 Analysis of the Transmission Accuracy of Signal Processing
11.4.2 Performance Analysis of Different Algorithm Libraries
11.4.3 Performance Analysis of Packet Loss Rate in the Data Signal Processing System
11.5 Conclusions
References
12 Deep Neural Network-Based Prediction of High-Speed Train-Induced Subway Track Vibration
12.1 Introduction
12.2 Deep Neural Network Model
12.2.1 Architecture
12.2.2 Model Training
12.3 Numerical Experiments
12.3.1 Searching for the Best Time Step
12.3.2 How Far in the Future Can We Correctly Predict?
12.3.3 Computing the Overall Accuracy Based on Error Margin
12.3.4 Training Times
12.3.5 Possible Applications of Proposed Deep Learning Vibration Estimation
12.4 Final Remarks
References
13 Advanced Complex Data Analysis of Autonomous Transportation for Smart City Industrial Environment
13.1 Introduction
13.2 Related Works
13.3 Method
13.3.1 Architecture and Key Technologies of IIoT
13.3.2 Spectrum-Based SDN Deployment Algorithm
13.3.3 Industrial Complex Events and Data Processing
13.3.4 Independent Transportation Mode in Industrial Environment
13.3.5 Industrial Advanced Complex Data Analytics
13.3.6 Simulation Experiment of Industrial Complex Data Analytics
13.4 Results and Discussions
13.4.1 Comparison of Different Data Coordination Methods
13.4.2 Analysis of the Operation Effect of Complex Event Mode Based on Industrial Data
13.5 Conclusions
References
14 A Meta Sensor-Based Autonomous Vehicle Safety System for Collision Avoidance Using Li-Fi Technology
14.1 Introduction
14.2 Literature Review
14.3 Proposed Framework
14.3.1 Proposed System Flowchart
14.3.2 Description of LV & FV Scenario and Li-Fi Communication
14.3.3 Case Study of the Need of the Meta Sensor
14.3.4 Importance of Brake Sensor
14.3.5 Meta Sensor
14.3.6 Proposed Algorithm
14.4 Simulation and Results
14.5 Conclusions
References
Part V Security Perspective in Intelligent Transportation Systems
15 Secure Information Transmission in Intelligent Transportation Systems Using Blockchain Technique
15.1 Introduction
15.1.1 Motivation and Research Objective
15.2 Related Work
15.3 Proposed Approach
15.3.1 IPFS Algorithm
15.4 Results and Analysis
15.5 Conclusion
References
16 Privacy-Preserved Mobile Crowdsensing for Intelligent Transportation Systems
16.1 Introduction
16.2 Related Work
16.3 System Model
16.4 Crowdsensing Based on Federated Learning
16.4.1 Data Aggregation with Team Participation
16.4.2 Data Model Aggregation Process
16.4.3 Team Credit Management
16.5 Performance Evaluation
16.5.1 Simulation Setup
16.5.2 Experimental Results
16.5.2.1 Model Training
16.5.2.2 System Performance
16.6 Conclusion
References
Index