Activity Recognition Using the Joint of Wi-Fi 2.4G and 5G Frequency Bands

Human activity recognition based on Wi-Fi Channel State Information (CSI) is playing an increasingly important role in various fields such as security, medical care, etc. Most existing CSI-based activity identification methods rely on a single frequency band of Wi-Fi signals. In addition, the use of...

Full description

Saved in:
Bibliographic Details
Main Authors: Yan, BeiMing, Cheng, Wei, Huang, GeTong, Zhu, Zhong Shang, Gao, Xiang
Format: Conference Proceeding
Language:English
Subjects:
2.4G
5G mobile communication
Activity recognition
Convolutional neural networks
CSI
Deep learning
Feature extraction
Medical services
Performance evaluation
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Human activity recognition based on Wi-Fi Channel State Information (CSI) is playing an increasingly important role in various fields such as security, medical care, etc. Most existing CSI-based activity identification methods rely on a single frequency band of Wi-Fi signals. In addition, the use of deep learning methods for CSI-based activity recognition is still in its infancy. In this paper, we propose a scheme of activity recognition using the joint CSI of the 2.4G frequency band and the 5G frequency band (ARJF), which takes advantage of a novel convolutional neural network (CNN) to automatically extract deep features from the CSI data, to realize the detection and classification of 7 actions. Compared with the recognition result of a single frequency band, the proposed method has better recognition accuracy.
ISSN:2576-7828
DOI:10.1109/ICCT52962.2021.9657966