Efficient Wi-Fi-Based Human Activity Recognition Using Adaptive Antenna Elimination

Abstract

Recently, Wi-Fi-based human activity recognition using channel state information (CSI) signals has gained popularity due to its potential features, such as passive sensing and adequate privacy. The movement of various body parts in between Wi-Fi signals' propagation path generates changes in the signal reflections and refraction, which is evident from the CSI variations. In this paper, we analyzed the relationship between human activities and properties (amplitude and phase) of Wi-Fi CSI signals on multiple receiving antennas and discovered the signal properties which vary remarkably in response to human movement. The variation of the received signal among multiple antennas shows different sensitivity to human activities, directly impacting the recognition performance. Therefore, to recognize human activities with better efficiency, we proposed an adaptive antenna elimination algorithm that automatically eliminates the non-sensitive antenna and keeps the sensitive antennas following different human activities. Furthermore, the correlation of the statistical features extracted from the amplitude and phase of the selected antennas' CSI signal was analyzed, and a sequential forward selection was utilized to find the best subset of features. Using such a subset, three machine learning algorithms were employed on two available online datasets to classify various human activities. The experimental results revealed that even when using easy-toimplement, non-deep machine learning, such as random forest, the recognition system based on the proposed adaptive antenna elimination algorithm achieved a superior classification accuracy of 99.84% (line of sight) on the StanWiFi dataset and 97.65% (line-of-sight) / 93.33% (non-line-of-sight) on another widely applied multi-environmental dataset at a fraction of the time cost, demonstrating the robustness of the proposed algorithm.

Distinguish different sensorimotor performance of the hand between the individuals with diabetes mellitus and chronic kidney disease through deep learning models

“…Neuropathy in both DM and CKD typically manifests as neural system damage that impairs sensorimotor performance ( Tesfaye et al, 2010 ; Baumgaertel et al, 2014 ), but research on distinctions between DM and CKD in this context is limited. Our proposed models suggest that deep learning models can uncover variations in sensorimotor patterns between DM and CKD ( Figure 5 ) and marked the sample numbers in Figure 5 because of the imbalanced sample size between different groups ( Jannat et al, 2023 ). The confusion matrix generated by the dil-CNN model implies potential differences in PHUA-based sensorimotor performance between DM and CKD, aligning with previous findings ( Moorthi et al, 2019 ).…”

A new pilot shared method for saving bandwidth cost of OFDM

“…To provide a basis for explaining the PS method, we refer back to the concept of channel frequency response 18 along with the utilization of the interpolation technique 11 , 19 . The LS method is employed for channel estimations in this context.…”

MAG-Res2Net: a novel deep learning network for human activity recognition

“…We trained multiple deep learning models and conducted a comprehensive analysis and interpretation of the experimental results. The confusion matrix format we used was designed and displayed according to the format proposed in literature (Jannat et al 2023).…”