Cargando…

Individual Identification by Late Information Fusion of EmgCNN and EmgLSTM from Electromyogram Signals

This paper is concerned with individual identification by late fusion of two-stream deep networks from Electromyogram (EMG) signals. EMG signal has more advantages on security compared to other biosignals exposed visually, such as the face, iris, and fingerprints, when used for biometrics, at least...

Descripción completa

Detalles Bibliográficos
Autores principales: Byeon, Yeong-Hyeon, Kwak, Keun-Chang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9504259/
https://www.ncbi.nlm.nih.gov/pubmed/36146119
http://dx.doi.org/10.3390/s22186770
_version_ 1784796171109138432
author Byeon, Yeong-Hyeon
Kwak, Keun-Chang
author_facet Byeon, Yeong-Hyeon
Kwak, Keun-Chang
author_sort Byeon, Yeong-Hyeon
collection PubMed
description This paper is concerned with individual identification by late fusion of two-stream deep networks from Electromyogram (EMG) signals. EMG signal has more advantages on security compared to other biosignals exposed visually, such as the face, iris, and fingerprints, when used for biometrics, at least in the aspect of visual exposure, because it is measured through contact without any visual exposure. Thus, we propose an ensemble deep learning model by late information fusion of convolutional neural networks (CNN) and long short-term memory (LSTM) from EMG signals for robust and discriminative biometrics. For this purpose, in the ensemble model’s first stream, one-dimensional EMG signals were converted into time–frequency representation to train a two-dimensional convolutional neural network (EmgCNN). In the second stream, statistical features were extracted from one-dimensional EMG signals to train a long short-term memory (EmgLSTM) that uses sequence input. Here, the EMG signals were divided into fixed lengths, and feature values were calculated for each interval. A late information fusion is performed by the output scores of two deep learning models to obtain a final classification result. To confirm the superiority of the proposed method, we use an EMG database constructed at Chosun University and a public EMG database. The experimental results revealed that the proposed method showed performance improvement by 10.76% on average compared to a single stream and the previous methods.
format Online
Article
Text
id pubmed-9504259
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-95042592022-09-24 Individual Identification by Late Information Fusion of EmgCNN and EmgLSTM from Electromyogram Signals Byeon, Yeong-Hyeon Kwak, Keun-Chang Sensors (Basel) Article This paper is concerned with individual identification by late fusion of two-stream deep networks from Electromyogram (EMG) signals. EMG signal has more advantages on security compared to other biosignals exposed visually, such as the face, iris, and fingerprints, when used for biometrics, at least in the aspect of visual exposure, because it is measured through contact without any visual exposure. Thus, we propose an ensemble deep learning model by late information fusion of convolutional neural networks (CNN) and long short-term memory (LSTM) from EMG signals for robust and discriminative biometrics. For this purpose, in the ensemble model’s first stream, one-dimensional EMG signals were converted into time–frequency representation to train a two-dimensional convolutional neural network (EmgCNN). In the second stream, statistical features were extracted from one-dimensional EMG signals to train a long short-term memory (EmgLSTM) that uses sequence input. Here, the EMG signals were divided into fixed lengths, and feature values were calculated for each interval. A late information fusion is performed by the output scores of two deep learning models to obtain a final classification result. To confirm the superiority of the proposed method, we use an EMG database constructed at Chosun University and a public EMG database. The experimental results revealed that the proposed method showed performance improvement by 10.76% on average compared to a single stream and the previous methods. MDPI 2022-09-07 /pmc/articles/PMC9504259/ /pubmed/36146119 http://dx.doi.org/10.3390/s22186770 Text en © 2022 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
Byeon, Yeong-Hyeon
Kwak, Keun-Chang
Individual Identification by Late Information Fusion of EmgCNN and EmgLSTM from Electromyogram Signals
title Individual Identification by Late Information Fusion of EmgCNN and EmgLSTM from Electromyogram Signals
title_full Individual Identification by Late Information Fusion of EmgCNN and EmgLSTM from Electromyogram Signals
title_fullStr Individual Identification by Late Information Fusion of EmgCNN and EmgLSTM from Electromyogram Signals
title_full_unstemmed Individual Identification by Late Information Fusion of EmgCNN and EmgLSTM from Electromyogram Signals
title_short Individual Identification by Late Information Fusion of EmgCNN and EmgLSTM from Electromyogram Signals
title_sort individual identification by late information fusion of emgcnn and emglstm from electromyogram signals
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9504259/
https://www.ncbi.nlm.nih.gov/pubmed/36146119
http://dx.doi.org/10.3390/s22186770
work_keys_str_mv AT byeonyeonghyeon individualidentificationbylateinformationfusionofemgcnnandemglstmfromelectromyogramsignals
AT kwakkeunchang individualidentificationbylateinformationfusionofemgcnnandemglstmfromelectromyogramsignals