Deep Learning and Big Data for Intelligent Transportation: Enabling Technologies and Future Trends (Studies in Computational Intelligence, 945)

✍ Scribed by Khaled R. Ahmed (editor), Aboul Ella Hassanien (editor)

• Publisher: Springer
• Year: 2021
• Tongue: English
• Leaves: 264
• Category: Library

✦ Synopsis

This book contributes to the progress towards intelligent transportation. It emphasizes new data management and machine learning approaches such as big data, deep learning and reinforcement learning. Deep learning and big data are very energetic and vital research topics of today’s technology. Road sensors, UAVs, GPS, CCTV and incident reports are sources of massive amount of data which are crucial to make serious traffic decisions. Herewith this substantial volume and velocity of data, it is challenging to build reliable prediction models based on machine learning methods and traditional relational database. Therefore, this book includes recent research works on big data, deep convolution networks and IoT-based smart solutions to limit the vehicle’s speed in a particular region, to support autonomous safe driving and to detect animals on roads for mitigating animal-vehicle accidents. This book serves broad readers including researchers, academicians, students and working professional in vehicles manufacturing, health and transportation departments and networking companies.

✦ Table of Contents

Preface
Big Data and Autonomous Vehicles
Deep Learning and Object Detection for Safe Driving
AI and IoT for Intelligent Transportation
Contents
Big Data and Autonomous Vehicles
Big Data Technologies with Computational Model Computing Using Hadoop with Scheduling Challenges
1 Introduction
2 Relationship Between IoT and Big Data Analyitcs
3 Big Data Analytics Methods
4 Big Data Challenges and Future Prespectives
5 Mapreduce Model for Dynamic Modeling Towards Scheduled Computing
6 Conclusions
References
Big Data for Autonomous Vehicles
1 Introduction
2 Vehicular Communication
3 Protocols and Standards for Vehicular Communication:
3.1 Dedicated Short-Range Communication (DSRC)
3.2 Cellular V2X
3.3 Bluetooth
3.4 Visible Light Communication (VLC)
3.5 In-vehicle Communication Protocols
4 Autonomous Vehicles (AVs)
4.1 Levels of Automation
4.2 Big Data Sources for Autonomous Vehicle
5 Big Data in AV
5.1 Big Data Acquisition
5.2 Big Data Preprocessing
5.3 Big Data Storage
5.4 Big Data Analysis
5.5 Big Data Computing
5.6 Big Data Transmission
6 AV Security
7 Research Avenues
7.1 Big Data Transmission
7.2 Machine Learning (ML) for Vehicular Networks
7.3 Vehicular Network Security
8 Conclusion
References
Deep Learning and Object Detection for Safe Driving
Analysis of Target Detection and Tracking for Intelligent Vision System
1 Introduction
1.1 Major Challenges Involved in Object Detection and Tracking
2 Moving Object Detection Methods
2.1 Temporal Difference Method
2.2 Simple Background Subtraction
2.3 Background Modeling Approach
2.4 Optical Flow Method
2.5 Feature Point Detectors
2.6 Segmentation Based Approaches
2.7 Supervised Learning Approaches
2.8 Object Detection Based on Feature Extraction
2.9 Shape Based Moving Object Detection
3 Related Works
4 Motivation
5 System Overview
5.1 Feature Extraction Based on 2D Cross-Correlation
5.2 Robust Skin Color Based Approach
5.3 Fusion Based Approach
6 Performance Evaluation
6.1 Evaluation Metrics
6.2 Novelty of the Proposed Approaches
7 Conclusion and Future Directions
References
Enhanced End-to-End System for Autonomous Driving Using Deep Convolutional Networks
1 Introduction
2 Previous Deep Learning Methods for Autonomous Driving
2.1 Alvinn
2.2 DAVE
2.3 DAVE-2
3 Proposed System
3.1 Prediction of Steering Angle
3.2 Road Detection Using Image Processing
3.3 Object Detection Using YOLO-V3
3.4 Combined Pipeline Output
4 Conclusion and Future Work
References
Deep Learning Technologies to Mitigate Deer-Vehicle Collisions
1 Introduction
2 Related Works
2.1 Traditional DVCs Mitigation Approaches
2.2 Machine Learning Deer Detection
3 Deer Detection Methodology
3.1 Deer Detection Using YOLO
4 Experimental Setup and Results
4.1 Setup
4.2 Performance Evaluation Metrics
4.3 Results and Discussions
5 Conclusion and Future Work
References
Night-to-Day Road Scene Translation Using Generative Adversarial Network with Structural Similarity Loss for Night Driving Safety
1 Introduction
2 Image-to-Image Translation
3 GAN with Structural Similarity Loss
4 Results
4.1 Dataset
4.2 Effects of SSIM Loss
4.3 Ablation Studies
5 Conclusion
References
Safer-Driving: Application of Deep Transfer Learning to Build Intelligent Transportation Systems
1 Introduction
2 Deep Learning in Computer Vision
2.1 CNNs Architecture
3 Transfer Learning
4 Deep Learning in Transportation
5 Case Study: Using Transfer Learning to Create Object Classification Model
6 Conclusion
References
Leveraging CNN Deep Learning Model for Smart Parking
1 Motivation
2 Related Work
2.1 Lessons Learnt
3 Context of the Work
3.1 Machine Learning
3.2 Deep Learning
3.3 Comparison of Various Models for Image Classification
3.4 Mathematical Model
4 Conceptual Architecture
4.1 Algorithm
5 Assessment
5.1 Recall and Precision Metrics
5.2 Visualising Recall and Precision
6 Discussion and Conclusion
Appendix 1
References
Estimating Crowd Size for Public Place Surveillance Using Deep Learning
1 Introduction
1.1 Why Do We Need Automated Crowd Count?
1.2 Crowd Count: Definition and Background
2 Convolutional Neural Network for Crowd Counting
2.1 Why CNN?
2.2 CNN Architecture
3 State of the Art CNN Models for Crowd Counting
3.1 Multicolumn CNN
3.2 Switching CNN
3.3 Cascaded CNN
3.4 CSRNet
4 Performance Analysis
5 Conclusion
References
AI and IoT for Intelligent Transportation
IoT Based Regional Speed Restriction Using Smart Sign Boards
1 Introduction
2 Background
3 Problem Statement
4 Literature Survey
5 Proposed Methodology
6 Circuit Diagram of the Proposed System
7 System Implementation
7.1 System Prototype
7.2 Motor Driver
7.3 Bluetooth Low Energy
7.4 BLE Packet Format
8 Results and Discussion
8.1 Real Time Implementation
8.2 Discussion
9 Conclusion
10 Future Scope
References
Synergy of Internet of Things with Cloud, Artificial Intelligence and Blockchain for Empowering Autonomous Vehicles
1 Introduction
2 IoT
2.1 What Is IoT
2.2 Process Involved in IoT
2.3 Applications of IoT
2.4 Challenges of IoT in Autonomous Vehicles
3 Synergy of IoT with Other Technology
3.1 Cloud Centric IoT
3.2 AI Centric IoT
3.3 Blockchain Centric IoT
4 Cloud Centric IoT
4.1 Device Virtualization
4.2 Network Virtualization
4.3 Applications
5 IoT with AI
5.1 Synergy of IoT and Artificial Intelligence
5.2 Components of AI with the IoT
5.3 Applications of IoT with AI
5.4 Advantages of IoT Powered AI
6 IoT with Blockchain
6.1 Grounds of Blockchain
6.2 Need for Blockchain in IoT
6.3 Blockchain of Things
6.4 Applications of Blockchain with IoT in Autonomous Vehicles
7 Conclusion
References
Combining Artificial Intelligence with Robotic Process Automation—An Intelligent Automation Approach
1 Introduction
2 Implementation Technique of RPA + AI
2.1 Exception Handling in the Combination of RPA + AI
3 Robotic Process Automation in Industries
3.1 Polarization of Labour Market
4 Human Intervention Is Still Needed
5 Basics of RPA
5.1 TA versus RPA versus Cognitive RPA
5.2 How to Implement RPA
6 Challenges of RPA
7 Artificial Intelligence
7.1 Major Concepts of Artificial Intelligence
7.2 Limitations of Artificial Intelligence
8 AI-Based Cloud
9 Robotics 2.0
9.1 Data Management with Respect to Robotics 2.0
9.2 Applications of Robotics 2.0
10 Conclusion
References