|
IEEE
Transactions on Intelligent Transportation Systems
Special Issue on
Deep Learning
Models for Safe and Secure Intelligent Transportation Systems
Scheduled
Publication Time: 2021
Aim and Scope
Autonomous vehicular technology is
approaching a level of maturity that gives confidence to the end users in
many cities around the world for their usage so as to share the roads with
manual vehicles. Autonomous and manual vehicles have different capabilities
which may result in surprising safety, security and resilience impacts when
mixed together as a part of Intelligent Transportation System (ITS). For
example, autonomous vehicles are able to communicate electronically with
one another, make fast decisions and associated actuation, and generally
act deterministically. In contrast, manual vehicles cannot communicate
electronically, are limited by the capabilities and slow reaction of human
drivers, and may show some uncertainty and even irrationality in behaviour
due to the involvement of human. At the same time, humans can react
properly to more complex situations than autonomous vehicles. Unlike manual
vehicles, the security of computing and communications of autonomous
vehicles can be compromised thereby precluding them from achieving
individual or group goals. Given the expected mixture of autonomous and
manual vehicles that is expected to persist for many decades, safety and
security issues for a mixture of autonomous and manual vehicles are crucial
to investigate before autonomous vehicles enter our roadways in numbers. To
improve the safety and security of the transportation system, the
artificial intelligence (AI) based techniques and deep learning models have
extensively been applied to data-driven ITS model. Despite the pioneering
works on the integration of ITS data with deep learning techniques, such
techniques still require more accurate perception since the false positives
generated during the execution of the algorithms can perturb the utility
real-time data analytics particularly for safety applications in ITS. More
importantly, the recent breakthrough in generative adversarial networks in
machine learning better demonstrates the criticality of the safety problems
in ITS in the presence of advanced persistent threats as that adversarial
models can be generated at an accelerating pace. Therefore, it is crucial
to understand how both types of vehicles will fare in terms of safety
(avoidance of dangerous situations), performance (acceptable delays and
throughput), and resilience (fast recovery from dangerous situations) under
a variety of uncertain situations without and with attacks on autonomous
vehicle communications in in the presence of hidden advertises who exploit
machine learning security loop holes. Despite the existing research on
cyber-attacks on the functions of individual vehicles, the focus on the
interplay of different types of vehicles under the influence of
cyber-adversaries is missing. To address the above-mentioned challenges,
there is a need for new algorithmic developments beyond traditional topics
in big data, deep neural networks, and cyber security. The aim of this
special issue is to provide a multi-aspect up-to-date reference for
theoretical development of deep learning models and techniques for
improving security and safety in ITS.
Topics
The topics of interest for this special issue include,
but are not limited to
·
Deep learning based
security, integrity and privacy solutions for ITS.
·
Deep learning based
energy-aware traffic management solutions
·
Deep learning based
5G communication for ITS
·
Deep learning based
physical layer design techniques for autonomous vehicles
·
Deep learning based
object detection for autonomous vehicles
·
Deep learning based
SDN-enabled network management for ITS
·
Deep learning based
intrusion detection/prevention techniques
·
Low power based
deep learning techniques for autonomous vehicles
·
Trusted
machine/deep learning for ITS
·
Security hardening
of ITS
·
Artificial
intelligence for the integration of communications and sensing in ITS
·
Deep learning
models for trusted ITS
·
Artificial
intelligence safety for ITS
·
Explainable
artificial intelligence for ITS
·
Explainable
decision making for autonomous vehicles operating in uncertain and evolving
environments
·
Optimizing safety
and security of ITS using Artificial intelligence
·
Deep learning
models for resilient ITS
·
Innovative deep
learning techniques for attacks detection, prevention, and mitigation in
ITS
·
Nature-inspired
artificial intelligence for ITS
Submission
Paper submission should conform to
the information for authors available at https://mc.manuscriptcentral.com/t-its.
Timeline
First submission deadline: May 30, 2020
Notification of first decision: August 30, 2020
First revision submission deadline: October 30, 2020
Notification of final decision: February 30, 2021
Final manuscript (camera ready) submission deadline: March 30, 2021
Issue of Publication: May 30, 2021
Guest Editors
Alireza Jolfaei, Macquarie University, Sydney, Australia
(alireza.jolfaei@mq.edu.au)
Neeraj Kumar, Thapar
Institute of Engineering and Technology, India (neeraj.kumar@thapar.edu)
Min Chen, Huazhong University
of Science and Technology, Wuhan, China (minchen@ieee.org)
Krishna Kant, Temple University, PA, USA
(kkant@temple.edu)
|