Cargando…

CSI-Based Human Activity Recognition Using Multi-Input Multi-Output Autoencoder and Fine-Tuning

Wi-Fi-based human activity recognition (HAR) has gained considerable attention recently due to its ease of use and the availability of its infrastructures and sensors. Channel state information (CSI) captures how Wi-Fi signals are transmitted through the environment. Using channel state information...

Descripción completa

Detalles Bibliográficos
Autores principales: Chahoushi, Mahnaz, Nabati, Mohammad, Asvadi, Reza, Ghorashi, Seyed Ali
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10099367/
https://www.ncbi.nlm.nih.gov/pubmed/37050651
http://dx.doi.org/10.3390/s23073591
_version_ 1785025036397051904
author Chahoushi, Mahnaz
Nabati, Mohammad
Asvadi, Reza
Ghorashi, Seyed Ali
author_facet Chahoushi, Mahnaz
Nabati, Mohammad
Asvadi, Reza
Ghorashi, Seyed Ali
author_sort Chahoushi, Mahnaz
collection PubMed
description Wi-Fi-based human activity recognition (HAR) has gained considerable attention recently due to its ease of use and the availability of its infrastructures and sensors. Channel state information (CSI) captures how Wi-Fi signals are transmitted through the environment. Using channel state information of the received signals transmitted from Wi-Fi access points, human activity can be recognized with more accuracy compared with the received signal strength indicator (RSSI). However, in many scenarios and applications, there is a serious limit in the volume of training data because of cost, time, or resource constraints. In this study, multiple deep learning models have been trained for HAR to achieve an acceptable accuracy level while using less training data compared to other machine learning techniques. To do so, a pretrained encoder which is trained using only a limited number of data samples, is utilized for feature extraction. Then, by using fine-tuning, this encoder is utilized in the classifier, which is trained by a fraction of the rest of the data, and the training is continued alongside the rest of the classifier’s layers. Simulation results show that by using only 50% of the training data, there is a 20% improvement compared with the case where the encoder is not used. We also showed that by using an untrainable encoder, an accuracy improvement of 11% using 50% of the training data is achievable with a lower complexity level.
format Online
Article
Text
id pubmed-10099367
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-100993672023-04-14 CSI-Based Human Activity Recognition Using Multi-Input Multi-Output Autoencoder and Fine-Tuning Chahoushi, Mahnaz Nabati, Mohammad Asvadi, Reza Ghorashi, Seyed Ali Sensors (Basel) Article Wi-Fi-based human activity recognition (HAR) has gained considerable attention recently due to its ease of use and the availability of its infrastructures and sensors. Channel state information (CSI) captures how Wi-Fi signals are transmitted through the environment. Using channel state information of the received signals transmitted from Wi-Fi access points, human activity can be recognized with more accuracy compared with the received signal strength indicator (RSSI). However, in many scenarios and applications, there is a serious limit in the volume of training data because of cost, time, or resource constraints. In this study, multiple deep learning models have been trained for HAR to achieve an acceptable accuracy level while using less training data compared to other machine learning techniques. To do so, a pretrained encoder which is trained using only a limited number of data samples, is utilized for feature extraction. Then, by using fine-tuning, this encoder is utilized in the classifier, which is trained by a fraction of the rest of the data, and the training is continued alongside the rest of the classifier’s layers. Simulation results show that by using only 50% of the training data, there is a 20% improvement compared with the case where the encoder is not used. We also showed that by using an untrainable encoder, an accuracy improvement of 11% using 50% of the training data is achievable with a lower complexity level. MDPI 2023-03-30 /pmc/articles/PMC10099367/ /pubmed/37050651 http://dx.doi.org/10.3390/s23073591 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Chahoushi, Mahnaz
Nabati, Mohammad
Asvadi, Reza
Ghorashi, Seyed Ali
CSI-Based Human Activity Recognition Using Multi-Input Multi-Output Autoencoder and Fine-Tuning
title CSI-Based Human Activity Recognition Using Multi-Input Multi-Output Autoencoder and Fine-Tuning
title_full CSI-Based Human Activity Recognition Using Multi-Input Multi-Output Autoencoder and Fine-Tuning
title_fullStr CSI-Based Human Activity Recognition Using Multi-Input Multi-Output Autoencoder and Fine-Tuning
title_full_unstemmed CSI-Based Human Activity Recognition Using Multi-Input Multi-Output Autoencoder and Fine-Tuning
title_short CSI-Based Human Activity Recognition Using Multi-Input Multi-Output Autoencoder and Fine-Tuning
title_sort csi-based human activity recognition using multi-input multi-output autoencoder and fine-tuning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10099367/
https://www.ncbi.nlm.nih.gov/pubmed/37050651
http://dx.doi.org/10.3390/s23073591
work_keys_str_mv AT chahoushimahnaz csibasedhumanactivityrecognitionusingmultiinputmultioutputautoencoderandfinetuning
AT nabatimohammad csibasedhumanactivityrecognitionusingmultiinputmultioutputautoencoderandfinetuning
AT asvadireza csibasedhumanactivityrecognitionusingmultiinputmultioutputautoencoderandfinetuning
AT ghorashiseyedali csibasedhumanactivityrecognitionusingmultiinputmultioutputautoencoderandfinetuning