A CSI-Based Human Activity Recognition Using Deep Learning
Article
Fard Moshiri, P., Shahbazian, R., Nabati, M. and Ghorashi, S. A. 2021. A CSI-Based Human Activity Recognition Using Deep Learning. Sensors. https://doi.org/10.3390/s21217225
Authors | Fard Moshiri, P., Shahbazian, R., Nabati, M. and Ghorashi, S. A. |
---|---|
Abstract | The Internet of Things (IoT) has become quite popular due to advancements in Information and Communications technologies and has revolutionized the entire research area in Human Activity Recognition (HAR). For the HAR task, vision-based and sensor-based methods can present better data but at the cost of users’ inconvenience and social constraints such as privacy issues. Due to the ubiquity of WiFi devices, the use of WiFi in intelligent daily activity monitoring for elderly persons has gained popularity in modern healthcare applications. Channel State Information (CSI) as one of the characteristics ofWiFi signals, can be utilized to recognize different human activities. We have employed a Raspberry Pi 4 to collect CSI data for seven different human daily activities, and converted CSI data to images and then used these images as inputs of a 2D Convolutional Neural Network (CNN) classifier. Our experiments have shown that the proposed CSI-based HAR outperforms other competitor methods including 1D-CNN, Long Short-Term Memory (LSTM), and Bi-directional LSTM, and achieves an accuracy of around 95% for seven activities. |
Keywords | activity recognition; Internet of Things; smart house; deep learning; channel state information |
Journal | Sensors |
ISSN | 1424-8220 |
Year | 2021 |
Publisher | MDPI |
Publisher's version | License File Access Level Anyone |
Digital Object Identifier (DOI) | https://doi.org/10.3390/s21217225 |
Publication dates | |
Online | 30 Oct 2021 |
Publication process dates | |
Accepted | 22 Oct 2021 |
Deposited | 01 Nov 2021 |
Copyright holder | © 2021 The Authors |
https://repository.uel.ac.uk/item/89y6v
Download files
264
total views120
total downloads5
views this month1
downloads this month