Log-likelihood Clustering Enabled Passive RF Sensing for Residential Activity Recognition

Physical activity recognition is an important research area in pervasive computing because its importance for in e-healthcare, security and human machine interaction. Among various approaches, passive RF sensing on the basis of well-tried radar principle has potential to provides unique non-invasive human activity detection and recognition solution, and draws more attention. However, this thechnology is far from mature. This paper presents a novel HMM-log-likelihood matrix based feacture characterizing to breack the fixed sliding window limitation in traditional feature extraction approaches. We prove the effectiveness of proposed feature extraction method in K-means&K-medoids clustering algorithms with experimental Doppler data gathered collected from a passive radar system. The time adaptive log-likelihood matrix based approach is proven outperforming the traditional SVD, PCA and physical feature based approaches by 80% regarding activity recognizing rate.