book

Deep Learning and Its Applications for Vehicle Networks

Name: Deep Learning and Its Applications for Vehicle Networks
ISBN: 9781000877250

by Fei Hu, Iftikhar Rasheed

May 2023

Intermediate to advanced

356 pages

13h 58m

English

CRC Press

Read now

Unlock full access

Cover Page
Half Title page
Title Page
Copyright Page
Contents
Preface
About the Editors
List of Contributors
Part I Deep learning for vehicle safety and security
1 Deep learning for vehicle safety
1.1 Introduction1.2 Deep learning for internal vehicle monitoring1.2.1 Camera-based system1.2.2 Wearable sensor-based system1.2.3 Driver behavior monitoring1.3 Deep learning for surrounding environment perception1.3.1 Road detection1.3.2 Vehicle surrounding environment detection1.3.3 Object detection in challenging environments1.4 Deep learning for traffic management1.4.1 Traffic flow modelling1.4.2 Vehicle and infrastructure communications1.5 Deep learning-based route planning and navigation1.5.1 Route planning for travellers1.5.2 Route planning for food transportation1.5.3 Dynamic routing with unknown map1.6 ConclusionsReferences

2 Deep learning for driver drowsiness classification for a safe vehicle application
2.1 Introduction2.1.1 Importance of drowsiness detection2.1.2 Application in future automated vehicles2.2 Driver drowsiness detection methods2.2.1 Subjective measures2.2.2 Objective measures2.2.3 Deep learning methods2.3 Comparison of methods2.4 Summary and outlookNotesReferences
3 A deep learning perspective on Connected Automated Vehicle (CAV) cybersecurity and threat intelligence
3.1 Introduction3.2 CAV technological enablers: automation and connectivity3.3 CAV threat landscape and threat intelligence3.3.1 In-vehicle (low-level sensor) cyber vulnerabilities3.3.2 Vehicle control modules3.3.3 Security analysis of CAV threats3.3.4 Attack surfaces3.3.5 Organizational risks to CAV ecosystem3.4 CAV threat mitigation: anomaly detection and classification with deep learning3.5 Frontiers in deep learning (advancement and future)3.5.1 Meta-learning3.5.2 Federated learning3.6 End-to-end deep CNN-LSTM architecture for CAV cyberattack detection3.6.1 Performance analysis3.6.2 Results and discussions3.7 ConclusionReferences
Part II Deep learning for vehicle communications
4 Deep learning for UAV network optimization
4.1 Introduction4.2 Key categories for UAV networking throughput enhancement4.3 Routing enhancement for UAV networking throughput4.3.1 Position-based routing4.3.2 Topology-based routing4.3.3 Swarm-based routing4.3.4 DL-enabled routing for UAV networking4.4 UAV networking construction4.4.1 UAV swarm networking construction4.4.2 DL-enabled UAV swarm networking enhancement4.5 DL-enabled UAV networking throughput4.5.1 DL-enabled allocation for throughput enhancement4.5.2 DL-enabled scheduling for throughput enhancement4.6 ConclusionsReferences
5 State-of-the-art in PHY layer deep learning for future wireless communication systems and networks
5.1 Introduction5.1.1 Related survey papers5.1.2 Summary of this chapter5.2 Data-driven ML methods for transceiver optimization5.2.1 Data-driven approach for end-to-end transceiver optimization5.2.2 Model-aided data-driven methods for modular transceiver optimization5.3 Deep learning for symbol detection5.3.1 Incorporating expert knowledge into autoencoders5.3.2 Implementing NNs at the receiver5.3.3 Sequential detectors using ML5.4 Channel estimation using ML5.5 Channel prediction in frequency- and time-domain using ML5.6 Channel coding using AI/ML5.7 Intelligent link adaptation5.8 Intelligent radios5.8.1 Intelligent spectrum sensing5.8.2 Automatic signal recognition using CNNs5.8.3 Intelligent radio environment5.9 ML for system-level performance evaluation of wireless networks5.10 ConclusionsNotesReferences
6 Deep learning-based index modulation systems for vehicle communications
6.1 Introduction6.2 V2V and V2I Communications6.3 Deep learning-based index modulation systems6.3.1 Multicarrier-based index modulation systems6.3.2 Single-carrier based index modulation systems6.3.3 Multi-input multi-output based index modulation systems6.4 ConclusionsReferences
7 Deep reinforcement learning applications in connected-automated transportation systems
7.1 Introduction7.1.1 Chapter organization7.2 Deep reinforcement learning: theory and background7.2.1 (Deep) reinforcement learning: a brief history7.2.2 Classical reinforcement learning7.2.3 Deep reinforcement learning7.2.4 Formulating (deep) reinforcement learning for CAV application7.3 Data environment in CAV networks7.3.1 Benefits7.3.2 Data generated by AVs7.4 Deep reinforcement learning applications: connected vehicles7.4.1 Lane changing and assistance7.4.2 Traffic signal control7.4.3 Traffic flow optimization7.4.4 Rail and maritime transportation7.4.5 Data communications, computing, and networking7.4.6 DRL applications for cybersecurity7.5 Deep reinforcement learning applications: automated driving systems7.5.1 Motion planning7.5.2 Lateral control7.5.3 Safety7.6 Challenges and future directions7.6.1 Transferability to real-world applications7.6.2 Representation of traffic environment7.6.3 Formulating reward functions7.6.4 Multi-agent DRL in CAV environment7.6.5 Partial state observabilityREFERENCES
Part III Deep learning for vehicle control
8 Vehicle emission control on road with temporal traffic information using deep reinforcement learning
8.1 Introduction8.2 Related work8.3 Overview8.3.1 Preliminary8.3.2 Traffic data insight8.3.3 Problem formulation8.4 Methodology8.4.1 Framework8.4.2 EFRL model8.5 Experiments8.5.1 Data and setup8.5.2 Baselines and metric8.5.3 Results8.6 ConclusionReferences
9 Load prediction of an electric vehicle charging pile
9.1 Introduction9.2 Charging load characteristic analysis of electric vehicles9.3 Quantile regression model of dilated causal convolutional9.3.1 Dilated causal convolutional9.3.2 Kernel density estimation9.3.3 Dilated causal convolutional quantile regression9.3.4 Model evaluation index9.3.5 Example simulation based on python9.4 Spatio-temporal dynamic load prediction of charging pile load based on deep learning9.4.1 Spatio-temporal dynamic load prediction of the charging pile9.4.2 Spatio-temporal dynamic load matrix construction9.4.3 Spatio-temporal convolutional networks model9.4.4 Spatio-temporal dynamic load forecasting based on dilated causal convolution-2D9.4.5 Spatio-temporal dynamic load forecasting based on Spatio-temporal neural network9.4.6 Example simulation based on python9.5 ConclusionsReferences
10 Deep learning for autonomous vehicles: A vision-based approach to self-adapted robust control
10.1 Introduction10.2 References selection via deep learning image processing10.2.1 CNN analytic outcomes as control references10.2.2 Experimental data10.2.3 Multi-objective evaluation10.2.4 Control state variable10.3 Robust control design10.3.1 System identification10.3.2 Robust Linear Quadratic Regulator (RLQR)10.3.3 ℋ∞ Controller10.4 Case study for hybrid controller10.4.1 Simulation environment and problem objective10.4.2 Machine learning design10.4.3 Hybrid control design10.4.4 Performance evaluation10.5 ConclusionsNoteReferences
Part IV DL for information management
11 A natural language processing-based approach for automating IoT search
11.1 Introduction11.2 IoT search engine11.2.1 Architecture11.2.2 Key components11.2.3 Research challenges11.3 NLP-based query processing11.3.1 Design rationale11.3.2 Basic components of NLP11.3.3 NLP tools11.3.4 Comparison of NLTK and spaCy11.4 The ACQUISE approach11.4.1 Baseline strategy11.4.2 Enhanced static strategy11.4.3 Enhanced dynamic strategy11.5 Performance evaluation11.5.1 Methodology11.5.2 Results11.6 Discussion11.6.1 Machine learning11.6.2 Protocols and algorithms11.6.3 Security and privacy11.7 Related work11.8 Final remarksAcknowledgementReferences
12 Toward incentive-compatible vehicular crowdsensing: A reinforcement learning-based approach
12.1 Introduction12.2 Edge-assisted vehicular crowdsensing12.2.1 Architecture design12.2.2 Workflow12.3 Incentive mechanism for vehicle recruitment12.3.1 Stackelberg game12.3.2 Strategy of the SSP12.3.3 Strategies of vehicles12.4 Case study12.5 ConclusionsAppendix AReferences
13 Sub-signal detection from noisy complex signals using deep learning and mathematical morphology
13.1 Introduction13.2 LSTM-RNN and mathematical morphology-based algorithm to detect sub-signals from noisy complex signals13.2.1 Data preparation and pre-processing13.2.2 LSTM-RNN local sub-signal learning13.2.3 Mathematical morphological global sub-signal detection13.3 Experimental results13.4 ConclusionAcknowledgmentNotesReferences
Part V Miscellaneous
14 The basics of deep learning algorithms and their effect on driving behavior and vehicle communications
14.1 Introduction14.2 Basics of deep learning algorithms and supervised learning14.2.1 Linear regression and logistic regression14.2.2 Artificial Neural Networks14.2.3 Convolutional Neural Networks14.2.4 Recurrent Neural Networks14.2.5 Deep learning architectures14.3 Deep unsupervised and semi-supervised learning14.3.1 Restricted Boltzmann Machines and deep belief nets14.3.2 Autoencoders & variational autoencoders14.3.3 Generative adversarial networks14.3.4 Transformers14.4 Hyperparameters, pre-processing and optimization14.4.1 Data augmentation and transfer learning14.4.2 Weight initialization, activation functions and optimizers14.4.3 Training time, pre-processing and architectural refinements14.5 Applications of deep learning in driving behavior analysis and vehicle communication14.6 ConclusionsReferences
15 Integrated simulation of deep learning, computer vision and physical layer of UAV and ground vehicle networks
15.1 Introduction15.2 Applications that can benefit from CAVIAR simulations15.2.1 Simulation of UAV-enabled AI/ML15.2.2 Beam-selection for V2I15.3 Multi-domain integrated simulators15.3.1 Wireless channel generation with Raymobtime15.3.2 Caviar simulations15.4 Simulations results15.4.1 Beam selection for V2I with lidar as input15.4.2 In-loop CAVIAR simulation of a computer vision application15.4.3 Impact of 3D model accuracy on wireless channels15.5 ConclusionsAcknowledgmentsNotesReferences

Content preview from Deep Learning and Its Applications for Vehicle Networks

Deep Learning and Its Applications for Vehicle Networks

Deep Learning (DL) is an effective approach for AI-based vehicular networks and can deliver a powerful set of tools for such vehicular network dynamics. In various domains of vehicular networks, DL can be used for learning-based channel estimation, traffic flow prediction, vehicle trajectory prediction, location-prediction-based scheduling and routing, intelligent network congestion control mechanisms, smart load balancing and vertical handoff control, intelligent network security strategies, virtual smart and efficient resource allocation and intelligent distributed resource allocation methods.

This book is based on the work of world-famous experts on the application of DL to vehicle networks. ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Artificial Intelligent Techniques for Wireless Communication and Networking

Publisher Resources

ISBN: 9781000877250

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Deep Learning and Its Applications for Vehicle Networks

by Fei Hu, Iftikhar Rasheed

Deep Learning and Its Applications for Vehicle Networks

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.