Machine Learning in Communication Systems and Networks, 2nd Edition

Dear Colleagues,

Recent advances in machine learning, including the availability of powerful computing platforms, have received huge attention from related academic, research, and industry communities. Machine learning is considered a promising tool to tackle the challenge in increasingly complex, heterogeneous, and dynamic communication environments. Machine learning would be able to contribute to the intelligent management and optimization of communication systems and networks by enabling them to predict changes, find patterns of uncertainties in the communication environment, and make data-driven decisions.

This Topic will focus on machine learning-based solutions to manage complex issues in communication systems and networks across various layers and within various ranges of communication applications. The objective of the Topic is to share and discuss recent advances and future trends of machine learning for intelligent communication. Original research (unpublished and not currently under review by another journal) is welcome in relevant areas, including (but not limited to) the following:

• Fundamental limits of machine learning in communication;
• Design and implementation of advanced machine learning algorithms (including distributed learning) in communication;
• Machine learning for physical layer and cross-layer processing (e.g., channel modeling and estimation, interference avoidance, beamforming and antenna configuration, etc.);
• Machine learning for adaptive radio resource allocation and optimization;
• Machine learning for network slicing, virtualization, and software-defined networking;
• Service performance optimization and evaluation of machine learning-based solutions in various vertical applications (e.g., healthcare, transport, aquaculture, farming, etc.);
• Machine learning for anomaly detection in communication systems and networks;
• Security, privacy, and trust of machine learning over communication systems and networks.

Prof. Dr. Yichuang Sun
Dr. Haeyoung Lee
Dr. Oluyomi Simpson
Topic Editors