CALL FOR PAPER
IEEE Open Journal of Vehicular Technology
Special Issue on
Machine Learning/Deep Learning for Wireless Communications

Download Call for Papers

Recently, discussions of the sixth generation (6G) systems have just been started and artificial intelligence (AI) is considered as a powerful driving force to boost its development. Due to the penetrations of AI, data-driven and computing-intensive services are emerging such as mobile high-definition interactive augmented reality/virtual reality (AR/VR). To support the user experience of these services, it requires the fusion of AI and big data in wireless communications. As such, machine learning/deep learning for wireless communications has become a research hotspot and draws a lot of attention from both academia and industry.

However, unlike the existing research fields of AI, the implementation of machine learning/deep learning for wireless communications faces several unique and critical challenges: In the data level, the data of wireless networks is usually collected by spatially distributed edge nodes, and thus the data set usually follows a nonindependent and identically distribution. As a result, the accuracy of learning models is lowered due to error propagation caused by the distribution divergence. In the model level, centralized existing learning paradigms cannot fully explore the potential of dispersive computation resource located at the edge of networks. Moreover, the issues of convergence and interpretability with respect to machine learning/deep learning are not well
understood, and thus the efficiency and robustness cannot be guaranteed in the case of unreliable wireless communication circumstances. In the application level, the implementation of machine learning/deep learning for wireless communications is still in the germination stage. There is a need to fully integrate the communication, computation, and storage capability of wireless networks so as to augment our networks to allow efficient implementation of machine learning/deep learning algorithms in wireless communications.

Motivated by providing feasible solutions and inspirable insights of the aforementioned issues, this special issue focuses on the fundamental theory, frameworks, techniques and applications of machine learning/deep learning for wireless communications, which aims to share and discuss the recent advances and future trends. The topics of interest include, but are not limited to the following:

  • Machine learning/deep learning-enabled intelligent wireless network architecture
  • New machine learning/deep learning paradigms and algorithms for wireless communications
  • Information-theoretic modeling and analysis of machine learning/deep learning for wireless
    communications
  • Machine learning/deep learning-based signal processing techniques for wireless communications
  • Machine learning/deep learning-based network management and resource allocation mechanisms
  • New application scenarios of machine learning/deep learning for wireless communications
  • Datasets for machine learning/deep learning experiments in wireless communications
  • Security and privacy issues of machine learning/deep learning for wireless communications
  • Prototypes and testbeds with respect to machine learning/deep learning for wireless communications

Important Dates:
Manuscript submission: December 1, 2019
Notification of authors: January 15, 2020
Revised manuscripts due: February 1, 2020
Final editorial decision: February 15, 2020
Final papers due: March 1, 2020
Estimated publication date: Second Quarter 2020

Guest Editors:
Tony Q. S. Quek
Singapore University of Technology and Design, Singapore
Email: tonyquek@sutd.edu.sg

Yu-Chee Tseng
National Chiao Tung University, Taiwan
Email: yctseng@cs.nctu.edu.tw

Zhongyuan Zhao
Beijing University of Posts and Telecommunications, China
Email: zyzhao@bupt.edu.cn

Marios Kountouris
Eurecom, France
Email: Marios.Kountouris@eurecom.fr

Shiwen Mao
Auburn Univ., USA
Email: smao@auburn.edu