A Model-based Optimization Approach for Through-wall Wi-Fi Sensing

This paper focuses on optimizing the Wi-Fi sensing ability for non-line-of-sight (NLOS) environments. Existing Wi-Fi Channel State Information (CSI) based methods are categorized into pattern-based and model-based approaches. Pattern-based methods, relying on machine learning, require extensive training data and are less adaptable to changing scenarios. Conversely, model-based methods utilize physical principles and are more robust, demanding less training data. While most current model-based research targets line-of-sight (LOS) scenarios, effective models for NLOS environments are lacking, where both reflection and refraction are significant. This study introduces the CPR model to quantify the squeezing and stretching effects of Fresnel zones in NLOS scenarios, which enhances spatial resolution. The PASTLBO algorithm, a parameter-Adaptive teaching and learning-based optimization method, is proposed to optimize the deployment of Wi-Fi sensing systems by guiding transmitter and receiver placement for optimal sensing performance. Experimental results show significant improvements in sensing performance, with optimized placement of transmitters and receivers enhancing sensing performance by over 30% compared to standard placements. The study concludes that understanding and quantifying the squeezing and stretching effects in Fresnel zones can significantly improve the accuracy and reliability of Wi-Fi sensing systems in complex NLOS environments.