A force levels and gestures integrated multi-task strategy for neural decoding
This paper discusses the problem of decoding gestures represented by surface electromyography (sEMG) signals in the presence of variable force levels. It is an attempt that multi-task learning (MTL) is proposed to recognize gestures and force levels synchronously. First, methods of gesture recogniti...
Gespeichert in:
| Veröffentlicht in: | Complex & Intelligent Systems 2020-10, Vol.6 (3), p.469-478 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 478 |
|---|---|
| container_issue | 3 |
| container_start_page | 469 |
| container_title | Complex & Intelligent Systems |
| container_volume | 6 |
| creator | Hua, Shaoyang Wang, Congqing Xie, Zuoshu Wu, Xuewei |
| description | This paper discusses the problem of decoding gestures represented by surface electromyography (sEMG) signals in the presence of variable force levels. It is an attempt that multi-task learning (MTL) is proposed to recognize gestures and force levels synchronously. First, methods of gesture recognition with different force levels are investigated. Then, MTL framework is presented to improve the gesture recognition performance and give information about force levels. Last but not least, to solve the problem that using the greedy principle in MTL, a modified pseudo-task augmentation (PTA) trajectory is introduced. Experiments conducted on two representative datasets demonstrate that compared with other methods, frequency domain information with convolutional neural network (CNN) is more suitable for gesture recognition with variable force levels. Besides, the feasibility of extracting features that are closely related to both gestures and force levels is verified via MTL. By influencing learning dynamics, the proposed PTA method can improve the results of all tasks, and make it applicable to the case where the main tasks and auxiliary tasks are clear. |
| doi_str_mv | 10.1007/s40747-020-00140-9 |
| format | Article |
| fullrecord | <record><control><sourceid>gale_proqu</sourceid><recordid>TN_cdi_proquest_journals_2440211550</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A634554922</galeid><sourcerecordid>A634554922</sourcerecordid><originalsourceid>FETCH-LOGICAL-c366t-6176a52096644cff126c8b969942d1dbd09a7f2305313f064b71b42173f14acd3</originalsourceid><addsrcrecordid>eNp9kMtqwzAQRU1poSHND3Ql6Frp6GEpWobQF4R2066FrIdx6tipZBfy91XiQndlFjMM98xcblHcElgSAHmfOEguMVDAAIQDVhfFjBK1wgJKdnmeFeYlE9fFIqUdZJWUKwZ0VryuUeij9aj1375NyHQO1T4NY_QJNd3g62gG79B-bIcGDyZ9ojScVvXxBKLOj9G0yHnbu6arb4qrYNrkF799Xnw8PrxvnvH27ells95iy4QYsCBSmJKCEoJzGwKhwq4qJZTi1BFXOVBGBsqyfcICCF5JUnFKJAuEG-vYvLib7h5i_zVmv3rXj7HLLzXlHCghZQlZtZxUtWm9brrQZ-s2l_P7xvadD03erwXjZckVpRmgE2Bjn1L0QR9iszfxqAnoU9Z6ylrnrPU5a60yxCYoZXFX-_jn5R_qB_Xsf7c</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2440211550</pqid></control><display><type>article</type><title>A force levels and gestures integrated multi-task strategy for neural decoding</title><source>DOAJ Directory of Open Access Journals</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>SpringerLink Journals - AutoHoldings</source><source>Springer Nature OA Free Journals</source><creator>Hua, Shaoyang ; Wang, Congqing ; Xie, Zuoshu ; Wu, Xuewei</creator><creatorcontrib>Hua, Shaoyang ; Wang, Congqing ; Xie, Zuoshu ; Wu, Xuewei</creatorcontrib><description>This paper discusses the problem of decoding gestures represented by surface electromyography (sEMG) signals in the presence of variable force levels. It is an attempt that multi-task learning (MTL) is proposed to recognize gestures and force levels synchronously. First, methods of gesture recognition with different force levels are investigated. Then, MTL framework is presented to improve the gesture recognition performance and give information about force levels. Last but not least, to solve the problem that using the greedy principle in MTL, a modified pseudo-task augmentation (PTA) trajectory is introduced. Experiments conducted on two representative datasets demonstrate that compared with other methods, frequency domain information with convolutional neural network (CNN) is more suitable for gesture recognition with variable force levels. Besides, the feasibility of extracting features that are closely related to both gestures and force levels is verified via MTL. By influencing learning dynamics, the proposed PTA method can improve the results of all tasks, and make it applicable to the case where the main tasks and auxiliary tasks are clear.</description><identifier>ISSN: 2199-4536</identifier><identifier>EISSN: 2198-6053</identifier><identifier>DOI: 10.1007/s40747-020-00140-9</identifier><language>eng</language><publisher>Cham: Springer International Publishing</publisher><subject>Artificial neural networks ; Comparative analysis ; Complexity ; Computational Intelligence ; Data Structures and Information Theory ; Electromyography ; Engineering ; Feature extraction ; Gesture recognition ; Learning ; Military readiness ; Military strategy ; Original Article</subject><ispartof>Complex & Intelligent Systems, 2020-10, Vol.6 (3), p.469-478</ispartof><rights>The Author(s) 2020</rights><rights>COPYRIGHT 2020 Springer</rights><rights>The Author(s) 2020. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c366t-6176a52096644cff126c8b969942d1dbd09a7f2305313f064b71b42173f14acd3</citedby><cites>FETCH-LOGICAL-c366t-6176a52096644cff126c8b969942d1dbd09a7f2305313f064b71b42173f14acd3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s40747-020-00140-9$$EPDF$$P50$$Gspringer$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://doi.org/10.1007/s40747-020-00140-9$$EHTML$$P50$$Gspringer$$Hfree_for_read</linktohtml><link.rule.ids>314,776,780,860,27901,27902,41096,41464,42165,42533,51294,51551</link.rule.ids></links><search><creatorcontrib>Hua, Shaoyang</creatorcontrib><creatorcontrib>Wang, Congqing</creatorcontrib><creatorcontrib>Xie, Zuoshu</creatorcontrib><creatorcontrib>Wu, Xuewei</creatorcontrib><title>A force levels and gestures integrated multi-task strategy for neural decoding</title><title>Complex & Intelligent Systems</title><addtitle>Complex Intell. Syst</addtitle><description>This paper discusses the problem of decoding gestures represented by surface electromyography (sEMG) signals in the presence of variable force levels. It is an attempt that multi-task learning (MTL) is proposed to recognize gestures and force levels synchronously. First, methods of gesture recognition with different force levels are investigated. Then, MTL framework is presented to improve the gesture recognition performance and give information about force levels. Last but not least, to solve the problem that using the greedy principle in MTL, a modified pseudo-task augmentation (PTA) trajectory is introduced. Experiments conducted on two representative datasets demonstrate that compared with other methods, frequency domain information with convolutional neural network (CNN) is more suitable for gesture recognition with variable force levels. Besides, the feasibility of extracting features that are closely related to both gestures and force levels is verified via MTL. By influencing learning dynamics, the proposed PTA method can improve the results of all tasks, and make it applicable to the case where the main tasks and auxiliary tasks are clear.</description><subject>Artificial neural networks</subject><subject>Comparative analysis</subject><subject>Complexity</subject><subject>Computational Intelligence</subject><subject>Data Structures and Information Theory</subject><subject>Electromyography</subject><subject>Engineering</subject><subject>Feature extraction</subject><subject>Gesture recognition</subject><subject>Learning</subject><subject>Military readiness</subject><subject>Military strategy</subject><subject>Original Article</subject><issn>2199-4536</issn><issn>2198-6053</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>C6C</sourceid><sourceid>BENPR</sourceid><recordid>eNp9kMtqwzAQRU1poSHND3Ql6Frp6GEpWobQF4R2066FrIdx6tipZBfy91XiQndlFjMM98xcblHcElgSAHmfOEguMVDAAIQDVhfFjBK1wgJKdnmeFeYlE9fFIqUdZJWUKwZ0VryuUeij9aj1375NyHQO1T4NY_QJNd3g62gG79B-bIcGDyZ9ojScVvXxBKLOj9G0yHnbu6arb4qrYNrkF799Xnw8PrxvnvH27ells95iy4QYsCBSmJKCEoJzGwKhwq4qJZTi1BFXOVBGBsqyfcICCF5JUnFKJAuEG-vYvLib7h5i_zVmv3rXj7HLLzXlHCghZQlZtZxUtWm9brrQZ-s2l_P7xvadD03erwXjZckVpRmgE2Bjn1L0QR9iszfxqAnoU9Z6ylrnrPU5a60yxCYoZXFX-_jn5R_qB_Xsf7c</recordid><startdate>20201001</startdate><enddate>20201001</enddate><creator>Hua, Shaoyang</creator><creator>Wang, Congqing</creator><creator>Xie, Zuoshu</creator><creator>Wu, Xuewei</creator><general>Springer International Publishing</general><general>Springer</general><general>Springer Nature B.V</general><scope>C6C</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>IAO</scope><scope>8FE</scope><scope>8FG</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>P5Z</scope><scope>P62</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope></search><sort><creationdate>20201001</creationdate><title>A force levels and gestures integrated multi-task strategy for neural decoding</title><author>Hua, Shaoyang ; Wang, Congqing ; Xie, Zuoshu ; Wu, Xuewei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c366t-6176a52096644cff126c8b969942d1dbd09a7f2305313f064b71b42173f14acd3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Artificial neural networks</topic><topic>Comparative analysis</topic><topic>Complexity</topic><topic>Computational Intelligence</topic><topic>Data Structures and Information Theory</topic><topic>Electromyography</topic><topic>Engineering</topic><topic>Feature extraction</topic><topic>Gesture recognition</topic><topic>Learning</topic><topic>Military readiness</topic><topic>Military strategy</topic><topic>Original Article</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Hua, Shaoyang</creatorcontrib><creatorcontrib>Wang, Congqing</creatorcontrib><creatorcontrib>Xie, Zuoshu</creatorcontrib><creatorcontrib>Wu, Xuewei</creatorcontrib><collection>Springer Nature OA Free Journals</collection><collection>CrossRef</collection><collection>Gale Academic OneFile</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies & Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>Advanced Technologies & Aerospace Database</collection><collection>ProQuest Advanced Technologies & Aerospace Collection</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><jtitle>Complex & Intelligent Systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Hua, Shaoyang</au><au>Wang, Congqing</au><au>Xie, Zuoshu</au><au>Wu, Xuewei</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A force levels and gestures integrated multi-task strategy for neural decoding</atitle><jtitle>Complex & Intelligent Systems</jtitle><stitle>Complex Intell. Syst</stitle><date>2020-10-01</date><risdate>2020</risdate><volume>6</volume><issue>3</issue><spage>469</spage><epage>478</epage><pages>469-478</pages><issn>2199-4536</issn><eissn>2198-6053</eissn><abstract>This paper discusses the problem of decoding gestures represented by surface electromyography (sEMG) signals in the presence of variable force levels. It is an attempt that multi-task learning (MTL) is proposed to recognize gestures and force levels synchronously. First, methods of gesture recognition with different force levels are investigated. Then, MTL framework is presented to improve the gesture recognition performance and give information about force levels. Last but not least, to solve the problem that using the greedy principle in MTL, a modified pseudo-task augmentation (PTA) trajectory is introduced. Experiments conducted on two representative datasets demonstrate that compared with other methods, frequency domain information with convolutional neural network (CNN) is more suitable for gesture recognition with variable force levels. Besides, the feasibility of extracting features that are closely related to both gestures and force levels is verified via MTL. By influencing learning dynamics, the proposed PTA method can improve the results of all tasks, and make it applicable to the case where the main tasks and auxiliary tasks are clear.</abstract><cop>Cham</cop><pub>Springer International Publishing</pub><doi>10.1007/s40747-020-00140-9</doi><tpages>10</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2199-4536 |
| ispartof | Complex & Intelligent Systems, 2020-10, Vol.6 (3), p.469-478 |
| issn | 2199-4536 2198-6053 |
| language | eng |
| recordid | cdi_proquest_journals_2440211550 |
| source | DOAJ Directory of Open Access Journals; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; SpringerLink Journals - AutoHoldings; Springer Nature OA Free Journals |
| subjects | Artificial neural networks Comparative analysis Complexity Computational Intelligence Data Structures and Information Theory Electromyography Engineering Feature extraction Gesture recognition Learning Military readiness Military strategy Original Article |
| title | A force levels and gestures integrated multi-task strategy for neural decoding |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-03T15%3A09%3A14IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_proqu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20force%20levels%20and%20gestures%20integrated%20multi-task%20strategy%20for%20neural%20decoding&rft.jtitle=Complex%20&%20Intelligent%20Systems&rft.au=Hua,%20Shaoyang&rft.date=2020-10-01&rft.volume=6&rft.issue=3&rft.spage=469&rft.epage=478&rft.pages=469-478&rft.issn=2199-4536&rft.eissn=2198-6053&rft_id=info:doi/10.1007/s40747-020-00140-9&rft_dat=%3Cgale_proqu%3EA634554922%3C/gale_proqu%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2440211550&rft_id=info:pmid/&rft_galeid=A634554922&rfr_iscdi=true |