IEEE Access Special Section Editorial: Artificial Intelligence (AI)-Empowered Intelligent Transportation Systems

Edith Ngai, Chao Chen, Amr M. Tolba, Mohammad S. Obaidat, Fanzhao Wang
2021 IEEE Access  
EDITORIAL IEEE ACCESS SPECIAL SECTION EDITORIAL: ARTIFICIAL INTELLIGENCE (AI)-EMPOWERED INTELLIGENT TRANSPORTATION SYSTEMS The topic of Artificial Intelligence (AI)-Empowered Intelligent Transportation Systems (ITS) has drawn more attention recently, with the rapid development of ubiquitous networks and smart vehicles. Researchers around the world have been working on new automotive applications to create a comfortable and safer driving environment. Current challenges include: how to run
more » ... ng-intensive applications on vehicles; how to enable real-time feedback between vehicles and the traffic management server based on the current Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) communication modes; and how to provide efficient computing capabilities for resource-consumption applications and reasonable resource allocation for vehicles and infrastructures. Recently, AI has made remarkable achievements in many fields such as image processing, pattern recognition, and natural language processing. It is also involved in computing-intensive applications, such as autopilot and real-time navigation through V2V or V2I. However, AI-Empowered ITS is still in its infancy. How can AI be integrated with ITS and function well in dynamic vehicular network scenarios? In addition, there are still questions on how to design more efficient AI solutions for resource management and coordination in ITS. The objective of this Special Section in IEEE ACCESS is to introduce the current developments and advancements of technical elements in AI-Empowered ITS, from both theoretical and practical perspectives. Our Special Section received an enthusiastic response and many high-quality submissions. All articles were reviewed by at least two independent referees. After a rigorous review process, we accepted 58 articles to form this Special Section. In the article "nLSALog: An anomaly detection framework for log sequence in security management," by Yang et al., a general anomaly detection framework is proposed. By modeling the log template sequence as a natural language sequence, and using the stacked long short-term memory (LSTM) with a self-attention mechanism, the framework can effectively extract the hidden pattern of the log template sequence and express the dependencies inside the log template sequence. In the article "A distributed network intrusion detection system for distributed denial of service attacks in vehicular 69492 This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/ VOLUME 9, 2021
doi:10.1109/access.2021.3074996 fatcat:dfyrghfswff6vmdlpa55jxtkjm