LiteHAR: Lightweight Human Activity Recognition from WIFI Signals with Random Convolution Kernels
Authors:
- 23 May 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4068-4072
Abstract
Anatomical movements of the human body can change the channel state information (CSI) of wireless signals in an indoor environment. These changes in the CSI signals can be used for human activity recognition (HAR), which is a pre-dominant and unique approach due to preserving privacy and flexibility of capturing motions in non-line-of-sight environments. Existing models for HAR generally have a high computational complexity, contain very large number of trainable parameters, and require extensive computational resources. This issue is particularly important for implementation of these solutions on devices with limited resources, such as edge devices. In this paper, we propose a lightweight human activity recognition (LiteHAR) approach which, unlike the state-of-the-art deep learning models, does not require extensive training of a large number of parameters. This approach uses randomly initialized convolution kernels for feature extraction from CSI signals without training the kernels. The extracted features are then classified using Ridge regression classifier, which has a linear computational complexity and is very fast. LiteHAR is evaluated on a public benchmark dataset and the results show its high classification performance with a much lower computational complexity in comparison with the complex deep learning models.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Single-Trial Recognition of Video Gamer’s Expertise from Brain Haemodynamic and Facial Emotion ResponsesBrain Sciences, 2021
- ROCKET: exceptionally fast and accurate time series classification using random convolutional kernelsData Mining and Knowledge Discovery, 2020
- Synthesizing Chest X-Ray Pathology for Training Deep Convolutional Neural NetworksIEEE Transactions on Medical Imaging, 2018
- WiFi CSI Based Passive Human Activity Recognition Using Attention Based BLSTMIEEE Transactions on Mobile Computing, 2018
- Image Augmentation Using Radial Transform for Training Deep Neural Networks2018
- A Survey on Behavior Recognition Using WiFi Channel State InformationIEEE Communications Magazine, 2017
- ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression2017
- CSI-Based Device-Free Wireless Localization and Activity Recognition Using Radio Image FeaturesIEEE Transactions on Vehicular Technology, 2017
- Training deep neural networks on imbalanced data sets2016
- Understanding and Modeling of WiFi Signal Based Human Activity Recognition2015