Human Activity Recognition Using MSHNet Based on Wi-Fi CSI

Wang, Fuchao; Duan, Pengsong; Cao, Yangjie; Kong, Jinsheng; Li, Hao

doi:10.1007/978-3-030-64002-6_4

Cited by 1 publication

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reference [17], in the context of monitoring the daily activities of the elderly, used the transceiver characteristics of wireless signals to aggregate the CSI streams of the same receiving antenna and used the method of deep learning for training, verified on the public data set and the data set collected by ourselves, and the average recognition rate could reach more than 95%. Reference [18] designed a long short-term memory convolutional neural network framework that recognizes different activities through CSI from commercial Wi-Fi devices.…”

Section: Introductionmentioning

confidence: 99%

Wi-CAL: A Cross-Scene Human Motion Recognition Method Based on Domain Adaptation in a Wi-Fi Environment

et al. 2022

View full text Add to dashboard Cite

In recent years, research on Wi-Fi sensing technology has developed rapidly. This technology automatically senses human activities through commercial Wi-Fi devices, such as lying down, falling, walking, waving, sitting down, and standing up. Because the movement of human parts affects the transmission of Wi-Fi signals, resulting in changes in CSI. In the context of indoor monitoring of human health through daily behavior, we propose Wi-CAL. More precisely, CSI fingerprints were collected at six events in two indoor locations, and data enhancement technology Dynamic Time Warping Barycentric Averaging (DBA) was used to expand the data. Then the feature weighting algorithm and convolution layer are combined to select the most representative CSI data features of human action. Finally, a classification model suitable for multiple scenes was obtained by blending the softmax classifier and CORrelation ALignment (CORAL) loss. Experiments are carried out on public data sets and the data sets before and after the expansion collected in this paper. Through comparative experiments, it can be seen that our method can achieve good recognition performance.

show abstract

Section: Introductionmentioning

confidence: 99%