TY - GEN
T1 - An WiFi-Based Human Activity Recognition System Under Multi-source Interference
AU - Li, Jiapeng
AU - Jiang, Ting
AU - Yu, Jiacheng
AU - Ding, Xue
AU - Zhong, Yi
AU - Liu, Yang
N1 - Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
PY - 2022
Y1 - 2022
N2 - WiFi-based human activity recognition in simple scenes has made exciting progress driven by deep learning methods, but current applications are focused on recognition without interference. When the channel state information(CSI) matrix of the receiver contains both the features of the target activities and other interference, the neural network often needs a deeper model structure if deep features of the activities are desired. But a deep network model is often difficult to converge, resulting in a decline in accuracy. And the model size is too large to be deployed in the real world. In this study, an ultra-lightweight neural network recognition system with a group communication(GC) named GC-LSTM is proposed. This design can easily convert a large model into a lightweight counterpart and improve network performance under multi-source interference via reducing network size and complexity. The experimental results show that the optimal recognition rate of the proposed method is 98.6% in the classification of four kinds of activities under six different interferences. By further adjusting the parameters, the model size is reduced to 4.1% of that of plain Long Short-Term Memory(LSTM), while the identification accuracy remains at 96.4%.
AB - WiFi-based human activity recognition in simple scenes has made exciting progress driven by deep learning methods, but current applications are focused on recognition without interference. When the channel state information(CSI) matrix of the receiver contains both the features of the target activities and other interference, the neural network often needs a deeper model structure if deep features of the activities are desired. But a deep network model is often difficult to converge, resulting in a decline in accuracy. And the model size is too large to be deployed in the real world. In this study, an ultra-lightweight neural network recognition system with a group communication(GC) named GC-LSTM is proposed. This design can easily convert a large model into a lightweight counterpart and improve network performance under multi-source interference via reducing network size and complexity. The experimental results show that the optimal recognition rate of the proposed method is 98.6% in the classification of four kinds of activities under six different interferences. By further adjusting the parameters, the model size is reduced to 4.1% of that of plain Long Short-Term Memory(LSTM), while the identification accuracy remains at 96.4%.
KW - Activity recognition
KW - Channel state information (CSI)
KW - Group Communication (GC)
KW - Model size
KW - Multi-source interference
UR - http://www.scopus.com/inward/record.url?scp=85128736879&partnerID=8YFLogxK
U2 - 10.1007/978-981-19-0390-8_118
DO - 10.1007/978-981-19-0390-8_118
M3 - Conference contribution
AN - SCOPUS:85128736879
SN - 9789811903892
T3 - Lecture Notes in Electrical Engineering
SP - 937
EP - 944
BT - Communications, Signal Processing, and Systems - Proceedings of the 10th International Conference on Communications, Signal Processing, and Systems
A2 - Liang, Qilian
A2 - Wang, Wei
A2 - Liu, Xin
A2 - Na, Zhenyu
A2 - Zhang, Baoju
PB - Springer Science and Business Media Deutschland GmbH
T2 - 10th International Conference on Communications, Signal Processing, and Systems, CSPS 2021
Y2 - 24 July 2021 through 25 July 2021
ER -