Machine Learning for Wireless Communications

Dear Colleagues,

The constantly emerging new applications of communications, such as truly immersive multisensory extended reality (XR), wearable devices, unmanned aerial vehicles (UAVs), etc., are progressively improving the quality of our daily life. Meanwhile, these new communication applications are generating a large amount of data traffic with heterogeneous quality-of-service (QoS) requirements. As such, there is an emerging need to integrate machine learning technologies into designing, planning, and optimizing future wireless communications. Recently, modern machine learning technologies, especially deep learning techniques, have been proven to have the powerful data-driven capability to facilitate wireless communications in a variety of scenarios, such as channel modeling, channel estimation, signal detection, resource allocation, network optimization, etc. This Special Issue aims to bring together advances in the research on machine learning for wireless communications across a broad range of applications.

Topics of interest include but are not limited to the following:

• Machine learning (including deep learning, deep reinforcement learning, etc.) for signal detection, classification, compression;
• Machine learning for spectrum sensing, localization, and positioning;
• Machine learning for channel modeling, estimation, and prediction;
• Machine learning for resource allocation and network optimization;
• Machine learning for new emerging applications toward 6G (including intelligent reflection surface, unmanned aerial vehicles, the Internet of Things, etc.)
• Performance analysis and evaluation of machine learning empowered wireless communication systems;
• Machine learning for vehicular networks;
• Distributed machine learning/federated learning and communications.

Dr. Chang Liu
Dr. Shihao Yan
Dr. Qingqing Cheng
Dr. Minghui Min
Dr. Weijie Yuan
Guest Editors