WiLDAR: WiFi Signal-Based Lightweight Deep Learning Model for Human Activity Recognition
Author(s) | Deng, Fuxiang | |
Author(s) | Jovanov, Emil | |
Author(s) | Song, Houbing | |
Author(s) | Shi, Weisong | |
Author(s) | Zhang, Yuan | |
Author(s) | Xu, Wenyao | |
Date Accessioned | 2023-07-18T19:52:31Z | |
Date Available | 2023-07-18T19:52:31Z | |
Publication Date | 2023-07-11 | |
Description | This article was originally published in IEEE Internet of Things Journal. The version of record is available at: https://doi.org/10.1109/JIOT.2023.3294004. © 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | |
Abstract | In recent years, the WiFi channel state information (CSI) has been increasingly used for human activity recognition (HAR) during activities of daily living, because of non-intrusiveness and privacy preserving properties. However, most previous works require complex processing of CSI signals, and the large number of classification network parameters significantly increases the recognition time and deployment costs. Accordingly, a WiFi signal based lightweight deep learning (WiLDAR) network is developed in this study to ensure systematic operation on edge computing devices. We combine the random convolution kernel with deep separable convolution and residual structure, so that WiLDAR can easily extract CSI signal features without filtering and denoising. The parameter number and training time of WiLDAR are thus much less than those of previous neural networks. In addition, a tiny HAR system using only Raspberry Pi and router is implemented. Experiments verify that WiLDAR can achieve real-time HAR on IoT devices, which makes HAR deployment more convenient. We test WiLDAR on three different fine-grained action datasets to achieve 99%, 93.5% and 97.5% recognition accuracy, respectively. The demonstrated learning capability of WiLDAR makes it an excellent option for the remote HAR. | |
Sponsor | The authors acknowledge supports from National Natural Science Foundation of China (62172340). | |
Citation | F. Deng, E. Jovanov, H. Song, W. Shi, Y. Zhang and W. Xu, "WiLDAR: WiFi Signal-Based Lightweight Deep Learning Model for Human Activity Recognition," in IEEE Internet of Things Journal, doi: 10.1109/JIOT.2023.3294004. | |
ISSN | 2327-4662 | |
URL | https://udspace.udel.edu/handle/19716/33021 | |
Language | en_US | |
Publisher | IEEE Internet of Things Journal | |
Keywords | human activity recognition | |
Keywords | WiFi sensing | |
Keywords | Channel state information (CSI) | |
Keywords | IoT | |
Keywords | neural network | |
Keywords | Edge Computing | |
Title | WiLDAR: WiFi Signal-Based Lightweight Deep Learning Model for Human Activity Recognition | |
Type | Article |