Key points are not available for this paper at this time.
Wireless sensing has emerged as an innovative technology that enables many smart applications such as indoor localization, activity recognition, and user tracking. However, achieving reliable and precise results in wireless sensing requires an accurate distinction between line-of-sight and non-line-of-sight transmissions. This paper introduces PEiD, a novel method that utilizes low-cost WiFi devices for transmission path identification, offering real-time measurements with high accuracy through the application of machine-learning-based classifiers. To overcome the deficiencies of commodity WiFi in bandwidth, PEiD explores the peak energy index distribution extracted from the channel impulse responses. Our approach effectively captures the inherent randomness of channel properties and significantly reduces the number of samples required for identification, thus surpassing previous methods. Additionally, to tackle the challenge of mobility, a sliding window technique is also adopted to achieve continuous monitoring of transmission path status. According to our extensive experiments, PEiD can attain a best path identification accuracy of 97.5% for line-of-sight scenarios and 94.3% for non-line-of-sight scenarios, with an average delay of under 300 ms (92% accuracy) even in dynamic environments.
Xiao et al. (Fri,) studied this question.