MACHINE LEARNING-ASSISTED SENSING TECHNIQUES FOR INTEGRATED COMMUNICATIONS AND SENSING IN WLANS: CURRENT STATUS AND FUTURE DIRECTIONS

|Sensing is a key basis for building an intelligent environment. Using channel state information (CSI) from the IEEE 802.11 physical layer in the wireless local access networks, the CSI-based device-free sensing technique has become very promising to the current sensing solutions because of its non-invasion of privacy, non-contact, easy deployment, and low cost. In recent years, the integrated communication and sensing (ICAS) technology has become one of the popular research topics in both wireless communications and computer areas. Given the fruitful advancements of ICAS, it is essential to review these advancements to synthesize and give previous research experiences and references to aid the development of relevant research (cid:12)elds and real-world applications. Motivated by this, this paper aims to provide a comprehensive survey of CSI-based sensing techniques. This study categorizes the surveyed works into model-based methods, data-based methods, and model-data hybrid-driven methods. Some important physical models and machine learning algorithms are also introduced. The sensing functions are classi(cid:12)ed into detection, estimation, and recognition according to speci(cid:12)c application scenarios. Furthermore, future directions and challenges are discussed.