Cargando…

A Hand-Modeled Feature Extraction-Based Learning Network to Detect Grasps Using sEMG Signal

Recently, deep models have been very popular because they achieve excellent performance with many classification problems. Deep networks have high computational complexities and require specific hardware. To overcome this problem (without decreasing classification ability), a hand-modeled feature se...

Descripción completa

Detalles Bibliográficos
Autores principales: Baygin, Mehmet, Barua, Prabal Datta, Dogan, Sengul, Tuncer, Turker, Key, Sefa, Acharya, U. Rajendra, Cheong, Kang Hao
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8914690/
https://www.ncbi.nlm.nih.gov/pubmed/35271154
http://dx.doi.org/10.3390/s22052007
_version_ 1784667784046706688
author Baygin, Mehmet
Barua, Prabal Datta
Dogan, Sengul
Tuncer, Turker
Key, Sefa
Acharya, U. Rajendra
Cheong, Kang Hao
author_facet Baygin, Mehmet
Barua, Prabal Datta
Dogan, Sengul
Tuncer, Turker
Key, Sefa
Acharya, U. Rajendra
Cheong, Kang Hao
author_sort Baygin, Mehmet
collection PubMed
description Recently, deep models have been very popular because they achieve excellent performance with many classification problems. Deep networks have high computational complexities and require specific hardware. To overcome this problem (without decreasing classification ability), a hand-modeled feature selection method is proposed in this paper. A new shape-based local feature extractor is presented which uses the geometric shape of the frustum. By using a frustum pattern, textural features are generated. Moreover, statistical features have been extracted in this model. Textures and statistics features are fused, and a hybrid feature extraction phase is obtained; these features are low-level. To generate high level features, tunable Q factor wavelet transform (TQWT) is used. The presented hybrid feature generator creates 154 feature vectors; hence, it is named Frustum154. In the multilevel feature creation phase, this model can select the appropriate feature vectors automatically and create the final feature vector by merging the appropriate feature vectors. Iterative neighborhood component analysis (INCA) chooses the best feature vector, and shallow classifiers are then used. Frustum154 has been tested on three basic hand-movement sEMG datasets. Hand-movement sEMG datasets are commonly used in biomedical engineering, but there are some problems in this area. The presented models generally required one dataset to achieve high classification ability. In this work, three sEMG datasets have been used to test the performance of Frustum154. The presented model is self-organized and selects the most informative subbands and features automatically. It achieved 98.89%, 94.94%, and 95.30% classification accuracies using shallow classifiers, indicating that Frustum154 can improve classification accuracy.
format Online
Article
Text
id pubmed-8914690
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-89146902022-03-12 A Hand-Modeled Feature Extraction-Based Learning Network to Detect Grasps Using sEMG Signal Baygin, Mehmet Barua, Prabal Datta Dogan, Sengul Tuncer, Turker Key, Sefa Acharya, U. Rajendra Cheong, Kang Hao Sensors (Basel) Article Recently, deep models have been very popular because they achieve excellent performance with many classification problems. Deep networks have high computational complexities and require specific hardware. To overcome this problem (without decreasing classification ability), a hand-modeled feature selection method is proposed in this paper. A new shape-based local feature extractor is presented which uses the geometric shape of the frustum. By using a frustum pattern, textural features are generated. Moreover, statistical features have been extracted in this model. Textures and statistics features are fused, and a hybrid feature extraction phase is obtained; these features are low-level. To generate high level features, tunable Q factor wavelet transform (TQWT) is used. The presented hybrid feature generator creates 154 feature vectors; hence, it is named Frustum154. In the multilevel feature creation phase, this model can select the appropriate feature vectors automatically and create the final feature vector by merging the appropriate feature vectors. Iterative neighborhood component analysis (INCA) chooses the best feature vector, and shallow classifiers are then used. Frustum154 has been tested on three basic hand-movement sEMG datasets. Hand-movement sEMG datasets are commonly used in biomedical engineering, but there are some problems in this area. The presented models generally required one dataset to achieve high classification ability. In this work, three sEMG datasets have been used to test the performance of Frustum154. The presented model is self-organized and selects the most informative subbands and features automatically. It achieved 98.89%, 94.94%, and 95.30% classification accuracies using shallow classifiers, indicating that Frustum154 can improve classification accuracy. MDPI 2022-03-04 /pmc/articles/PMC8914690/ /pubmed/35271154 http://dx.doi.org/10.3390/s22052007 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
Baygin, Mehmet
Barua, Prabal Datta
Dogan, Sengul
Tuncer, Turker
Key, Sefa
Acharya, U. Rajendra
Cheong, Kang Hao
A Hand-Modeled Feature Extraction-Based Learning Network to Detect Grasps Using sEMG Signal
title A Hand-Modeled Feature Extraction-Based Learning Network to Detect Grasps Using sEMG Signal
title_full A Hand-Modeled Feature Extraction-Based Learning Network to Detect Grasps Using sEMG Signal
title_fullStr A Hand-Modeled Feature Extraction-Based Learning Network to Detect Grasps Using sEMG Signal
title_full_unstemmed A Hand-Modeled Feature Extraction-Based Learning Network to Detect Grasps Using sEMG Signal
title_short A Hand-Modeled Feature Extraction-Based Learning Network to Detect Grasps Using sEMG Signal
title_sort hand-modeled feature extraction-based learning network to detect grasps using semg signal
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8914690/
https://www.ncbi.nlm.nih.gov/pubmed/35271154
http://dx.doi.org/10.3390/s22052007
work_keys_str_mv AT bayginmehmet ahandmodeledfeatureextractionbasedlearningnetworktodetectgraspsusingsemgsignal
AT baruaprabaldatta ahandmodeledfeatureextractionbasedlearningnetworktodetectgraspsusingsemgsignal
AT dogansengul ahandmodeledfeatureextractionbasedlearningnetworktodetectgraspsusingsemgsignal
AT tuncerturker ahandmodeledfeatureextractionbasedlearningnetworktodetectgraspsusingsemgsignal
AT keysefa ahandmodeledfeatureextractionbasedlearningnetworktodetectgraspsusingsemgsignal
AT acharyaurajendra ahandmodeledfeatureextractionbasedlearningnetworktodetectgraspsusingsemgsignal
AT cheongkanghao ahandmodeledfeatureextractionbasedlearningnetworktodetectgraspsusingsemgsignal
AT bayginmehmet handmodeledfeatureextractionbasedlearningnetworktodetectgraspsusingsemgsignal
AT baruaprabaldatta handmodeledfeatureextractionbasedlearningnetworktodetectgraspsusingsemgsignal
AT dogansengul handmodeledfeatureextractionbasedlearningnetworktodetectgraspsusingsemgsignal
AT tuncerturker handmodeledfeatureextractionbasedlearningnetworktodetectgraspsusingsemgsignal
AT keysefa handmodeledfeatureextractionbasedlearningnetworktodetectgraspsusingsemgsignal
AT acharyaurajendra handmodeledfeatureextractionbasedlearningnetworktodetectgraspsusingsemgsignal
AT cheongkanghao handmodeledfeatureextractionbasedlearningnetworktodetectgraspsusingsemgsignal