Towards CSI-based diversity activity recognition via LSTM-CNN encoder-decoder neural network

Human activity recognition using WiFi signals is widespread for smart-environment sensing domain in recent years. Existing researches use learning-based methods to obtain several features of activity data and then recognize human activities. As we know, propagation characteristics of WiFi signals ar...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) Vol. 444; pp. 260 - 273
Main Authors: Guo, Linlin, Zhang, Hang, Wang, Chao, Guo, Weiyu, Diao, Guangqiang, Lu, Bingxian, Lin, Chuang, Wang, Lei
Format: Journal Article
Language:English
Published: Elsevier B.V 15.07.2021
Subjects:
Channel state information
Convolutional neural network
Human activity recognition
Long short term memory
WiFi signals
WiFi signals
Human activity recognition
Convolutional neural network
Channel state information
Long short term memory
ISSN:0925-2312, 1872-8286
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Human activity recognition using WiFi signals is widespread for smart-environment sensing domain in recent years. Existing researches use learning-based methods to obtain several features of activity data and then recognize human activities. As we know, propagation characteristics of WiFi signals are different for individuals under different place conditions even in the same environment. In this paper, we focus on how to weaken the accuracy differences among individuals on activity recognition and improve the robustness in one indoor environment. Based on this, we design a novel deep learning model called LCED which consists of one LSTM-based Encoder, features image presentation, and one CNN-based Decoder to weaken the accuracy differences among individuals on activity recognition. We first use a low-pass filter to remove high-frequency noise data in time-sequence signal data and design variance-based window method to determine the start and the end of time-sequence signal data corresponding to an activity. After that, we utilize the proposed LCED model to learn informative features space of activity data and improve the accuracy of sixteen activities. Experimental results show that the average accuracy of sixteen activities is high 95% and the accuracy differences among individuals on activity recognition averagely decreases by 3%.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2020.02.137