A CSI-Based Human Activity Recognition Using Deep Learning

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 cos...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Parisa Fard Moshiri, Reza Shahbazian, Mohammad Nabati, Seyed Ali Ghorashi
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	activity recognition Internet of Things smart house deep learning channel state information Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/6c7a4b49c07e48fc96f6e35592b85b54
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6c7a4b49c07e48fc96f6e35592b85b54
record_format	dspace
spelling	oai:doaj.org-article:6c7a4b49c07e48fc96f6e35592b85b542021-11-11T19:12:06ZA CSI-Based Human Activity Recognition Using Deep Learning10.3390/s212172251424-8220https://doaj.org/article/6c7a4b49c07e48fc96f6e35592b85b542021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7225https://doaj.org/toc/1424-8220The 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 of WiFi 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.Parisa Fard MoshiriReza ShahbazianMohammad NabatiSeyed Ali GhorashiMDPI AGarticleactivity recognitionInternet of Thingssmart housedeep learningchannel state informationChemical technologyTP1-1185ENSensors, Vol 21, Iss 7225, p 7225 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	activity recognition Internet of Things smart house deep learning channel state information Chemical technology TP1-1185
spellingShingle	activity recognition Internet of Things smart house deep learning channel state information Chemical technology TP1-1185 Parisa Fard Moshiri Reza Shahbazian Mohammad Nabati Seyed Ali Ghorashi A CSI-Based Human Activity Recognition Using Deep Learning
description	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 of WiFi 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.
format	article
author	Parisa Fard Moshiri Reza Shahbazian Mohammad Nabati Seyed Ali Ghorashi
author_facet	Parisa Fard Moshiri Reza Shahbazian Mohammad Nabati Seyed Ali Ghorashi
author_sort	Parisa Fard Moshiri
title	A CSI-Based Human Activity Recognition Using Deep Learning
title_short	A CSI-Based Human Activity Recognition Using Deep Learning
title_full	A CSI-Based Human Activity Recognition Using Deep Learning
title_fullStr	A CSI-Based Human Activity Recognition Using Deep Learning
title_full_unstemmed	A CSI-Based Human Activity Recognition Using Deep Learning
title_sort	csi-based human activity recognition using deep learning
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/6c7a4b49c07e48fc96f6e35592b85b54
work_keys_str_mv	AT parisafardmoshiri acsibasedhumanactivityrecognitionusingdeeplearning AT rezashahbazian acsibasedhumanactivityrecognitionusingdeeplearning AT mohammadnabati acsibasedhumanactivityrecognitionusingdeeplearning AT seyedalighorashi acsibasedhumanactivityrecognitionusingdeeplearning AT parisafardmoshiri csibasedhumanactivityrecognitionusingdeeplearning AT rezashahbazian csibasedhumanactivityrecognitionusingdeeplearning AT mohammadnabati csibasedhumanactivityrecognitionusingdeeplearning AT seyedalighorashi csibasedhumanactivityrecognitionusingdeeplearning
_version_	1718431589579358208

A CSI-Based Human Activity Recognition Using Deep Learning

Ejemplares similares