Lower-Limb Joint Torque Prediction Using LSTM Neural Networks and Transfer Learning

Estimation of joint torque during movement provides important information in several settings, such as effect of athletes' training or of a medical intervention, or analysis of the remaining muscle strength in a wearer of an assistive device. The ability to estimate joint torque during daily ac...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING Ročník 30; s. 600 - 609
Hlavní autoři:	Zhang, Longbin, Soselia, Davit, Wang, Ruoli, Gutierrez-Farewik, Elena M.
Médium:	Journal Article Publikace
Jazyk:	angličtina
Vydáno:	United States IEEE 2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Ankle Ankle Joint Athletes Biomechanical Phenomena Electromyography generalizability Humans inverse dynamics Joints (anatomy) Knee Joint Learning Long short-term memory Lower Extremity LSTM Machine Learning Mean square errors Muscle strength Muscles Neural networks Neural Networks, Computer Performance prediction Plantar flexion Predictive models Root-mean-square errors Task analysis time series Torque Training Transfer learning
ISSN:	1534-4320, 1558-0210, 1558-0210
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Estimation of joint torque during movement provides important information in several settings, such as effect of athletes' training or of a medical intervention, or analysis of the remaining muscle strength in a wearer of an assistive device. The ability to estimate joint torque during daily activities using wearable sensors is increasingly relevant in such settings. In this study, lower limb joint torques during ten daily activities were predicted by long short-term memory (LSTM) neural networks and transfer learning. LSTM models were trained with muscle electromyography signals and lower limb joint angles. Hip flexion/extension, hip abduction/adduction, knee flexion/extension and ankle dorsiflexion/plantarflexion torques were predicted. The LSTM models' performance in predicting torque was investigated in both intra-subject and inter-subject scenarios. Each scenario was further divided into intra-task and inter-task tests. We observed that LSTM models could predict lower limb joint torques during various activities accurately with relatively low error (root mean square error ≤ 0.14 Nm/kg, normalized root mean square error ≤ 8.7%) either through a uniform model or through ten separate models in intra-subject tests. Furthermore, a transfer learning technique was adopted in the inter-task and inter-subject tests to further improve the generalizability of LSTM models by pre-training a model on multiple subjects and/or tasks and transferring the learned knowledge to a target task/subject. Particularly in the inter-subject tests, we could predict joint torques accurately in several movements after training from only a few movements from new subjects.
AbstractList	Estimation of joint torque during movement provides important information in several settings, such as effect of athletes' training or of a medical intervention, or analysis of the remaining muscle strength in a wearer of an assistive device. The ability to estimate joint torque during daily activities using wearable sensors is increasingly relevant in such settings. In this study, lower limb joint torques during ten daily activities were predicted by long short-term memory (LSTM) neural networks and transfer learning. LSTM models were trained with muscle electromyography signals and lower limb joint angles. Hip flexion/extension, hip abduction/adduction, knee flexion/extension and ankle dorsiflexion/plantarflexion torques were predicted. The LSTM models' performance in predicting torque was investigated in both intra-subject and inter-subject scenarios. Each scenario was further divided into intra-task and inter-task tests. We observed that LSTM models could predict lower limb joint torques during various activities accurately with relatively low error (root mean square error ≤ 0.14 Nm/kg, normalized root mean square error ≤ 8.7%) either through a uniform model or through ten separate models in intra-subject tests. Furthermore, a transfer learning technique was adopted in the inter-task and inter-subject tests to further improve the generalizability of LSTM models by pre-training a model on multiple subjects and/or tasks and transferring the learned knowledge to a target task/subject. Particularly in the inter-subject tests, we could predict joint torques accurately in several movements after training from only a few movements from new subjects. Estimation of joint torque during movement provides important information in several settings, such as effect of athletes' training or of a medical intervention, or analysis of the remaining muscle strength in a wearer of an assistive device. The ability to estimate joint torque during daily activities using wearable sensors is increasingly relevant in such settings. In this study, lower limb joint torques during ten daily activities were predicted by long short-term memory (LSTM) neural networks and transfer learning. LSTM models were trained with muscle electromyography signals and lower limb joint angles. Hip flexion/extension, hip abduction/adduction, knee flexion/extension and ankle dorsiflexion/plantarflexion torques were predicted. The LSTM models' performance in predicting torque was investigated in both intra-subject and inter-subject scenarios. Each scenario was further divided into intra-task and inter-task tests. We observed that LSTM models could predict lower limb joint torques during various activities accurately with relatively low error (root mean square error ≤ 0.14 Nm/kg, normalized root mean square error ≤ 8.7%) either through a uniform model or through ten separate models in intra-subject tests. Furthermore, a transfer learning technique was adopted in the inter-task and inter-subject tests to further improve the generalizability of LSTM models by pre-training a model on multiple subjects and/or tasks and transferring the learned knowledge to a target task/subject. Particularly in the inter-subject tests, we could predict joint torques accurately in several movements after training from only a few movements from new subjects.Estimation of joint torque during movement provides important information in several settings, such as effect of athletes' training or of a medical intervention, or analysis of the remaining muscle strength in a wearer of an assistive device. The ability to estimate joint torque during daily activities using wearable sensors is increasingly relevant in such settings. In this study, lower limb joint torques during ten daily activities were predicted by long short-term memory (LSTM) neural networks and transfer learning. LSTM models were trained with muscle electromyography signals and lower limb joint angles. Hip flexion/extension, hip abduction/adduction, knee flexion/extension and ankle dorsiflexion/plantarflexion torques were predicted. The LSTM models' performance in predicting torque was investigated in both intra-subject and inter-subject scenarios. Each scenario was further divided into intra-task and inter-task tests. We observed that LSTM models could predict lower limb joint torques during various activities accurately with relatively low error (root mean square error ≤ 0.14 Nm/kg, normalized root mean square error ≤ 8.7%) either through a uniform model or through ten separate models in intra-subject tests. Furthermore, a transfer learning technique was adopted in the inter-task and inter-subject tests to further improve the generalizability of LSTM models by pre-training a model on multiple subjects and/or tasks and transferring the learned knowledge to a target task/subject. Particularly in the inter-subject tests, we could predict joint torques accurately in several movements after training from only a few movements from new subjects. Estimation of joint torque during movement provides important information in several settings, such as effect of athletes' training or of a medical intervention, or analysis of the remaining muscle strength in a wearer of an assistive device. The ability to estimate joint torque during daily activities using wearable sensors is increasingly relevant in such settings. In this study, lower limb joint torques during ten daily activities were predicted by long short-term memory (LSTM) neural networks and transfer learning. LSTM models were trained with muscle electromyography signals and lower limb joint angles. Hip flexion/extension, hip abduction/adduction, knee flexion/extension and ankle dorsiflexion/plantarflexion torques were predicted. The LSTM models' performance in predicting torque was investigated in both intra-subject and inter-subject scenarios. Each scenario was further divided into intra-task and inter-task tests. We observed that LSTM models could predict lower limb joint torques during various activities accurately with relatively low error (root mean square error <= 0.14 Nm/kg, normalized root mean square error <= 8.7%) either through a uniform model or through ten separate models in intra-subject tests. Furthermore, a transfer learning technique was adopted in the inter-task and inter-subject tests to further improve the generalizability of LSTM models by pre-training a model on multiple subjects and/or tasks and transferring the learned knowledge to a target task/subject. Particularly in the inter-subject tests, we could predict joint torques accurately in several movements after training from only a few movements from new subjects.
Author	Soselia, Davit Zhang, Longbin Wang, Ruoli Gutierrez-Farewik, Elena M.
Author_xml	– sequence: 1 givenname: Longbin orcidid: 0000-0001-8785-5885 surname: Zhang fullname: Zhang, Longbin organization: Department of Engineering Mechanics, KTH MoveAbility Laboratory, KTH BioMEx Center, KTH Royal Institute of Technology, Stockholm, Sweden – sequence: 2 givenname: Davit surname: Soselia fullname: Soselia, Davit organization: Department of Engineering Mechanics, KTH MoveAbility Laboratory, KTH BioMEx Center, KTH Royal Institute of Technology, Stockholm, Sweden – sequence: 3 givenname: Ruoli orcidid: 0000-0002-2232-5258 surname: Wang fullname: Wang, Ruoli organization: Department of Engineering Mechanics, KTH MoveAbility Laboratory, KTH BioMEx Center, KTH Royal Institute of Technology, Stockholm, Sweden – sequence: 4 givenname: Elena M. orcidid: 0000-0001-5417-5939 surname: Gutierrez-Farewik fullname: Gutierrez-Farewik, Elena M. email: lanie@kth.se organization: Department of Engineering Mechanics, KTH MoveAbility Laboratory, KTH BioMEx Center, KTH Royal Institute of Technology, Stockholm, Sweden
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/35239487$$D View this record in MEDLINE/PubMed https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-310875$$DView record from Swedish Publication Index (Kungliga Tekniska Högskolan) http://kipublications.ki.se/Default.aspx?queryparsed=id:$$DView record from Swedish Publication Index (Karolinska Institutet)
BookMark	eNp9kklvFDEQhVsoiCzwB0BCLXHh0oP35RiFAEFNQMyEq-X2EjzpaQ92t0b8ezxLIpFDTlWyvvfKqnqn1dEQB1dVryGYQQjkh8X1_OflDAGEZhhSxgV7Vp1ASkUDEARH2x6ThmAEjqvTnJcAQM4of1EdY4qwJIKfVPM2blxq2rDq6q8xDGO9iOnP5OofydlgxhCH-iaH4bZu54tv9bWbku5LGTcx3eVaD7ZeJD1k71LdOp2Ggr6snnvdZ_fqUM-qm0-Xi4svTfv989XFedsYBvDYWOAwwZY4DawV0HfeS0FJx433AtKuM6JjHjIqvLQd58xzZoDFxkhBONX4rLra-9qol2qdwkqnvyrqoHYPMd0qncZgeqfKIG-9wdpBQiwRwnAPUEcFc9II2xWvZu-VN249df-5HZ7uSucUoxJL9CT_Mfw6302_G38rDIHgtPDv9_w6xbLePKpVyMb1vR5cnLJCDDNIKJeyoO8eocs4paFsslAESlk2sjV8e6CmbuXswwfuT1sAsQdMijkn55UJo94edEw69AoCtU2R2qVIbVOkDikqUvRIeu_-pOjNXhSccw8CyRGHgOB_Ld7Sow
CODEN	ITNSB3
CitedBy_id	crossref_primary_10_1109_TNSRE_2024_3488052 crossref_primary_10_1109_ACCESS_2025_3591227 crossref_primary_10_1111_exsy_13659 crossref_primary_10_1109_TIM_2022_3225023 crossref_primary_10_1109_TII_2024_3353823 crossref_primary_10_3390_s24134217 crossref_primary_10_1016_j_compbiomed_2023_107124 crossref_primary_10_1109_TNSRE_2024_3349639 crossref_primary_10_1016_j_ijhydene_2024_06_282 crossref_primary_10_1109_TNSRE_2023_3315373 crossref_primary_10_1109_TIM_2024_3480203 crossref_primary_10_3390_s23063331 crossref_primary_10_1016_j_bspc_2024_106188 crossref_primary_10_1109_TNSRE_2024_3495530 crossref_primary_10_1109_JSEN_2024_3352005 crossref_primary_10_1145_3699768 crossref_primary_10_1109_TNSRE_2023_3295453 crossref_primary_10_1016_j_neucom_2025_130884 crossref_primary_10_1177_16878132241278508 crossref_primary_10_1016_j_bspc_2024_106551 crossref_primary_10_1088_1741_2552_accd22 crossref_primary_10_1016_j_cmpb_2023_107848 crossref_primary_10_1016_j_bspc_2023_105103 crossref_primary_10_1016_j_bspc_2025_108612 crossref_primary_10_3390_electronics11233848 crossref_primary_10_3390_s24092792 crossref_primary_10_3390_s23239576 crossref_primary_10_1016_j_engappai_2023_107761 crossref_primary_10_1109_ACCESS_2024_3414175 crossref_primary_10_3390_s24227301 crossref_primary_10_3390_s24010211 crossref_primary_10_1109_JSEN_2025_3576709 crossref_primary_10_1109_JSEN_2024_3521896 crossref_primary_10_1186_s12984_024_01398_7 crossref_primary_10_1002_cpe_70248 crossref_primary_10_1016_j_clinbiomech_2023_106074 crossref_primary_10_1016_j_joca_2024_02_891 crossref_primary_10_1109_TNSRE_2024_3515966 crossref_primary_10_1016_j_compbiomed_2024_108016 crossref_primary_10_1007_s42452_025_07198_5 crossref_primary_10_1016_j_bspc_2024_106245 crossref_primary_10_1007_s42044_025_00267_3 crossref_primary_10_1007_s11517_023_03011_w crossref_primary_10_1109_TIM_2024_3384565 crossref_primary_10_1016_j_bspc_2025_108282 crossref_primary_10_1177_09544062251332155 crossref_primary_10_3390_pr12050924 crossref_primary_10_1016_j_jbiomech_2024_111997 crossref_primary_10_1016_j_ijmecsci_2025_110519 crossref_primary_10_1016_j_robot_2025_105178
Cites_doi	10.1016/j.neunet.2020.07.033 10.1016/j.jbiomech.2019.109533 10.1109/BioRob49111.2020.9224286 10.1016/j.jbiomech.2021.110698 10.3389/fnbot.2018.00016 10.1109/TBME.2017.2704085 10.1146/annurev.bioeng.3.1.245 10.1310/sci1701-16 10.1162/neco.1997.9.8.1735 10.1016/j.medengphy.2007.05.005 10.3390/s20247127 10.1016/j.gaitpost.2019.04.015 10.1109/TBME.2016.2538296 10.1109/TMI.2016.2528162 10.1109/TCYB.2015.2422785 10.1016/j.jbiomech.2009.01.033 10.21105/joss.00568 10.1080/10255840701552036 10.1016/j.jbiomech.2015.09.021 10.3389/fnbot.2019.00097 10.1016/j.neucom.2020.10.056 10.1002/cphy.cp120108 10.1519/JSC.0000000000001323 10.1007/s11044-019-09685-1 10.1016/j.jbiomech.2008.01.014 10.1523/JNEUROSCI.5792-11.2012 10.1016/j.jbiomech.2018.08.023 10.3390/s19132974 10.1126/science.1127647 10.1109/JAS.2021.1004243 10.1109/ACCESS.2019.2900591 10.1519/SSC.0b013e318213afa8 10.1109/TASE.2020.3033664 10.1016/0021-9290(74)90056-6 10.1186/s40537-016-0043-6 10.1007/s11517-018-1940-y 10.1186/s13029-015-0044-4 10.1088/1741-2552/aae26b 10.1109/ICRA40945.2020.9197441 10.1589/jpts.29.2160
ContentType	Journal Article Publication
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID	97E ESBDL RIA RIE AAYXX CITATION CGR CUY CVF ECM EIF NPM 7QF 7QO 7QQ 7SC 7SE 7SP 7SR 7TA 7TB 7TK 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D NAPCQ P64 7X8 ADTPV AFDQA AOWAS D8T D8V ZZAVC BZJLE STUKM DOA
DOI	10.1109/TNSRE.2022.3156786
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Aluminium Industry Abstracts Biotechnology Research Abstracts Ceramic Abstracts Computer and Information Systems Abstracts Corrosion Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts Materials Business File Mechanical & Transportation Engineering Abstracts Neurosciences Abstracts Solid State and Superconductivity Abstracts METADEX Technology Research Database ANTE: Abstracts in New Technology & Engineering Engineering Research Database Aerospace Database Materials Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Nursing & Allied Health Premium Biotechnology and BioEngineering Abstracts MEDLINE - Academic SwePub SWEPUB Kungliga Tekniska Högskolan full text SwePub Articles SWEPUB Freely available online SWEPUB Kungliga Tekniska Högskolan SwePub Articles full text SwePub Other SwePub Other full text DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) Materials Research Database Civil Engineering Abstracts Aluminium Industry Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Ceramic Abstracts Neurosciences Abstracts Materials Business File METADEX Biotechnology and BioEngineering Abstracts Computer and Information Systems Abstracts Professional Aerospace Database Nursing & Allied Health Premium Engineered Materials Abstracts Biotechnology Research Abstracts Solid State and Superconductivity Abstracts Engineering Research Database Corrosion Abstracts Advanced Technologies Database with Aerospace ANTE: Abstracts in New Technology & Engineering MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic Materials Research Database MEDLINE
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: RIE name: IEEE/IET Electronic Library url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 4 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Occupational Therapy & Rehabilitation
EISSN	1558-0210
EndPage	609
ExternalDocumentID	oai_doaj_org_article_343fdfc3ae144d488c7f02b586e9c8db oai_swepub_ki_se_659392 oai_DiVA_org_kth_310875 35239487 10_1109_TNSRE_2022_3156786 9727104
Genre	orig-research Research Support, Non-U.S. Gov't Journal Article
GrantInformation_xml	– fundername: Promobilia Foundation grantid: 18200; 18014; 18202; 19302; 21302 funderid: 10.13039/100009389 – fundername: Swedish Research Council grantid: 2018-00750; 2018-04902 funderid: 10.13039/501100004359
GroupedDBID	--- -~X 0R~ 29I 4.4 53G 5GY 5VS 6IK 97E AAFWJ AAJGR AASAJ AAWTH ABAZT ABVLG ACGFO ACGFS ACIWK ACPRK AENEX AETIX AFPKN AFRAH AGSQL AIBXA ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD ESBDL F5P GROUPED_DOAJ HZ~ H~9 IFIPE IPLJI JAVBF LAI M43 O9- OCL OK1 P2P RIA RIE RNS AAYXX CITATION CGR CUY CVF ECM EIF NPM RIG 7QF 7QO 7QQ 7SC 7SE 7SP 7SR 7TA 7TB 7TK 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D NAPCQ P64 7X8 ADTPV AFDQA AOWAS D8T D8V ZZAVC BZJLE STUKM
ID	FETCH-LOGICAL-c603t-d0e343d4ea0dd81fbff9854b7cff815bbc8b6f1658f9db776f76c0d3cc98475a3
IEDL.DBID	DOA
ISICitedReferencesCount	57
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000772417400005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1534-4320 1558-0210
IngestDate	Fri Oct 03 12:53:31 EDT 2025 Tue Nov 25 03:34:03 EST 2025 Tue Nov 04 17:21:02 EST 2025 Thu Oct 02 07:40:14 EDT 2025 Sun Nov 30 04:16:26 EST 2025 Wed Feb 19 02:27:21 EST 2025 Tue Nov 18 22:11:38 EST 2025 Sat Nov 29 01:47:13 EST 2025 Wed Aug 27 02:40:15 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://creativecommons.org/licenses/by-nc-nd/4.0
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c603t-d0e343d4ea0dd81fbff9854b7cff815bbc8b6f1658f9db776f76c0d3cc98475a3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0001-5417-5939 0000-0002-2232-5258 0000-0001-8785-5885
OpenAccessLink	https://doaj.org/article/343fdfc3ae144d488c7f02b586e9c8db
PMID	35239487
PQID	2641996585
PQPubID	85423
PageCount	10
ParticipantIDs	doaj_primary_oai_doaj_org_article_343fdfc3ae144d488c7f02b586e9c8db proquest_journals_2641996585 pubmed_primary_35239487 swepub_primary_oai_DiVA_org_kth_310875 swepub_primary_oai_swepub_ki_se_659392 proquest_miscellaneous_2636145799 crossref_citationtrail_10_1109_TNSRE_2022_3156786 crossref_primary_10_1109_TNSRE_2022_3156786 ieee_primary_9727104
PublicationCentury	2000
PublicationDate	20220000 2022-00-00 20220101 2022 2022-01-01
PublicationDateYYYYMMDD	2022-01-01
PublicationDate_xml	– year: 2022 text: 20220000
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: New York
PublicationTitle	IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
PublicationTitleAbbrev	TNSRE
PublicationTitleAlternate	IEEE Trans Neural Syst Rehabil Eng
PublicationYear	2022
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref34 ref12 ref37 ref15 ref14 ref30 ref11 ref10 ref2 ref1 ref39 bergstra (ref35) 2012; 13 ref17 ref38 ref16 ref19 ref18 srivastava (ref31) 2014; 15 woolson (ref36) 2007 harrison (ref4) 2004; 18 ref46 ref45 ref23 ref48 ref26 ref47 ref25 ref20 ref42 ref41 ref22 ref44 ref21 ref43 ref28 ref27 molnar (ref32) 2020 ref29 ref8 ref7 myer (ref3) 2005; 19 hermens (ref24) 1999; 8 ref9 ref6 ref5 brownlee (ref33) 2019 ref40
References_xml	– ident: ref16 doi: 10.1016/j.neunet.2020.07.033 – volume: 19 start-page: 51 year: 2005 ident: ref3 article-title: Neuromuscular training improves performance and lower-extremity biomechanics in female athletes publication-title: The Journal of Strength and Conditioning Research – ident: ref28 doi: 10.1016/j.jbiomech.2019.109533 – ident: ref21 doi: 10.1109/BioRob49111.2020.9224286 – ident: ref44 doi: 10.1016/j.jbiomech.2021.110698 – ident: ref10 doi: 10.3389/fnbot.2018.00016 – ident: ref11 doi: 10.1109/TBME.2017.2704085 – volume: 8 start-page: 13 year: 1999 ident: ref24 article-title: European recommendations for surface electromyography publication-title: Roessingh Res Develop – ident: ref29 doi: 10.1146/annurev.bioeng.3.1.245 – ident: ref41 doi: 10.1310/sci1701-16 – ident: ref19 doi: 10.1162/neco.1997.9.8.1735 – ident: ref5 doi: 10.1016/j.medengphy.2007.05.005 – ident: ref22 doi: 10.3390/s20247127 – ident: ref25 doi: 10.1016/j.gaitpost.2019.04.015 – volume: 13 start-page: 1 year: 2012 ident: ref35 article-title: Random search for hyper-parameter optimization publication-title: J Mach Learn Res – ident: ref12 doi: 10.1109/TBME.2016.2538296 – year: 2019 ident: ref33 publication-title: Deep learning for computer vision image classification object detection and face recognition in python – ident: ref34 doi: 10.1109/TMI.2016.2528162 – ident: ref17 doi: 10.1109/TCYB.2015.2422785 – ident: ref2 doi: 10.1016/j.jbiomech.2009.01.033 – ident: ref37 doi: 10.21105/joss.00568 – volume: 18 start-page: 473 year: 2004 ident: ref4 article-title: Force-velocity relationship and stretch-shortening cycle function in sprint and endurance athletes publication-title: The Journal of Strength and Conditioning Research – ident: ref7 doi: 10.1080/10255840701552036 – ident: ref30 doi: 10.1016/j.jbiomech.2015.09.021 – ident: ref8 doi: 10.3389/fnbot.2019.00097 – ident: ref23 doi: 10.1016/j.neucom.2020.10.056 – ident: ref1 doi: 10.1002/cphy.cp120108 – ident: ref42 doi: 10.1519/JSC.0000000000001323 – volume: 15 start-page: 1929 year: 2014 ident: ref31 article-title: Dropout: A simple way to prevent neural networks from overfitting publication-title: J Mach Learn Res – ident: ref13 doi: 10.1007/s11044-019-09685-1 – ident: ref6 doi: 10.1016/j.jbiomech.2008.01.014 – ident: ref40 doi: 10.1523/JNEUROSCI.5792-11.2012 – ident: ref38 doi: 10.1016/j.jbiomech.2018.08.023 – ident: ref15 doi: 10.3390/s19132974 – ident: ref46 doi: 10.1126/science.1127647 – year: 2020 ident: ref32 publication-title: Interpretable Machine Learning A Guide for Making Black Box Models Explainable – ident: ref18 doi: 10.1109/JAS.2021.1004243 – ident: ref39 doi: 10.1109/ACCESS.2019.2900591 – ident: ref48 doi: 10.1519/SSC.0b013e318213afa8 – ident: ref14 doi: 10.1109/TASE.2020.3033664 – ident: ref26 doi: 10.1016/0021-9290(74)90056-6 – ident: ref43 doi: 10.1186/s40537-016-0043-6 – ident: ref45 doi: 10.1007/s11517-018-1940-y – start-page: 1 year: 2007 ident: ref36 article-title: Wilcoxon signed-rank test publication-title: Wiley Encyclopedia of Clinical Trials – ident: ref27 doi: 10.1186/s13029-015-0044-4 – ident: ref9 doi: 10.1088/1741-2552/aae26b – ident: ref20 doi: 10.1109/ICRA40945.2020.9197441 – ident: ref47 doi: 10.1589/jpts.29.2160
SSID	ssj0017657
Score	2.5546923
Snippet	Estimation of joint torque during movement provides important information in several settings, such as effect of athletes' training or of a medical... Estimation of joint torque during movement provides important information in several settings, such as effect of athletes’ training or of a medical...
SourceID	doaj swepub proquest pubmed crossref ieee
SourceType	Open Website Open Access Repository Aggregation Database Index Database Enrichment Source Publisher
StartPage	600
SubjectTerms	Ankle Ankle Joint Athletes Biomechanical Phenomena Electromyography generalizability Humans inverse dynamics Joints (anatomy) Knee Joint Learning Long short-term memory Lower Extremity LSTM Machine Learning Mean square errors Muscle strength Muscles Neural networks Neural Networks, Computer Performance prediction Plantar flexion Predictive models Root-mean-square errors Task analysis time series Torque Training Transfer learning
SummonAdditionalLinks	– databaseName: IEEE Electronic Library (IEL) dbid: RIE link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwELZKxYELr_IIFGQk6AVC4ziJ7WOBVggtq6obUG-Wn7Bqm6Bslt_P2MlGLVohcYucieXJjD0z9vgbhF5nWlGIK2zKqeFpkTuTakfK1BDFlckUWMxYtWTG5nN-fi5Od9C76S6Mcy4mn7n34TGe5dvWrMNW2aEAY0sC-OctxthwV2s6MWBVRPWECVykBc2zzQWZTBzW88XZMYSCeQ4Ragmrc6hbBI4HFUXIpLtmjyJs_1hnZZvL-ReeaLRBJ_f-b_T30d3R18RHg3I8QDuueYjeXMcVxvUAKoAP8NkNyO49tJiF-mnpbHml8Zd22fS4bjsYJz7twtlOIMIx3wDPFvVXHEA-oL_5kFW-wqqxONpB7zo8grj-eIS-nRzXHz-nYwWG1FQZ7VObOVpQWziVWcuJ194LXhaaGe85KbU2XFeegBfjhdWMVZ5VJrPUGAFWr1T0Mdpt2sY9RVgTcD0K7rQmvrCugq6Up8QQz4j2NE8Q2chBmpHXUCXjUsYwJRMyilEGMcpRjAl6O33zawDn-Cf1hyDeiTIAa8cGkJIc56kEdr31hioHkaaF1c0wn-W65JUThludoL0g2amTUagJ2t8oixwXgZUEXzPkeENAlqBX02uYvuFMRjWuXQcaCg5SyYRI0JNByaa-NyqaoINB624M_dPy-1Ec-kX_E1gMlQm2E45NF_DkZFUK8IifbefiOboTftiww7SPdvtu7V6g2-Z3v1x1L-N8-wNk8SgA priority: 102 providerName: IEEE
Title	Lower-Limb Joint Torque Prediction Using LSTM Neural Networks and Transfer Learning
URI	https://ieeexplore.ieee.org/document/9727104 https://www.ncbi.nlm.nih.gov/pubmed/35239487 https://www.proquest.com/docview/2641996585 https://www.proquest.com/docview/2636145799 https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-310875 http://kipublications.ki.se/Default.aspx?queryparsed=id https://doaj.org/article/343fdfc3ae144d488c7f02b586e9c8db
Volume	30
WOSCitedRecordID	wos000772417400005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1558-0210 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017657 issn: 1558-0210 databaseCode: DOA dateStart: 20210101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVIEE databaseName: IEEE/IET Electronic Library customDbUrl: eissn: 1558-0210 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017657 issn: 1558-0210 databaseCode: RIE dateStart: 20010101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELag4sAFFcojpayMBL2gqHGcxPaxQCuEllXVDWhvlp-wKmTRbsrvZ-x4oy6q4MItSiaOPTPOfBM73yD0qtCKQl5hc04Nz6vSmVw7UueGKK5MoSBixqolUzab8cVCXNwo9RX2hA30wIPiTmhFvfWGKgfQ34K7GeaLUte8ccJwq8PbF1DPNplK6wesqdn2F5lCnLSz-eUZJINlCTlqDe_nZicMRbb-VF7lNqT5B41oDD3n--hBwoz4dOjrQ3THdY_Q65v8wLgdyAHwMb7cod4-QPNpqIOWT5c_NP64WnY9bldreDC-WIc1miCE474BPJ23n3Ag64D2ZsPu8A1WncUxnnm3xomM9etj9Pn8rH33IU-VFHLTFLTPbeFAj7ZyqrCWE6-9F7yuNDPec1JrbbhuPAE04oXVjDWeNaaw1BgB0atW9Ana61ade4awJgAhKu60Jr6yroGmlKfEEM-I9rTMENkqVpo01lDt4ruM6UYhZDSGDMaQyRgZejPe83Mg2fir9Ntgr1EyEGTHE-A2MrmN_JfbZOggWHtsRACOg8w0Q0db68s0mTcSMGPYqw2JVYZejpdhGoa1FdW51XWQoQB0aiZEhp4OXjO2DRiXCkgMM3Q8uNFO198vv5zGrl_132CIocLA7YLp1BUcOdnUApDt4f9QxXN0P6h3-K50hPb69bV7ge6ZX_1ys56gu2zBJ3F2TeLfkb8BbiIqMw
linkProvider	Directory of Open Access Journals
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwELaqggQXXuURKGAk6AVC49hJ7GOBVgXSVdUNqDcrfsGqkKBslt_P2MlGLVohcYucieXJjD0z9vgbhF4mqqYQV5iYU81jllodK0uyWJOa1zqpwWKGqiVlMZvx83NxuoXeTHdhrLUh-cy-9Y_hLN-0euW3yvYFGFviwT-vZYylZLitNZ0ZFHnA9YQpzGJG02R9RSYR-9VsfnYIwWCaQoyawfrsKxeB60EF87l0lyxSAO4fK61scjr_QhQNVujo9v-N_w66NXqb-GBQj7toyzb30KvLyMK4GmAF8B4-uwLavYPmpa-gFpeLnwp_ahdNj6u2g3Hi086f7ngiHDIOcDmvTrCH-YD-ZkNe-RLXjcHBEjrb4RHG9dt99OXosHp_HI81GGKdJ7SPTWIpo4bZOjGGE6ecEzxjqtDOcZIppbnKHQE_xgmjiiJ3Ra4TQ7UWYPeymj5A203b2EcIKwLOB-NWKeKYsTl0VTtKNHEFUY6mESJrOUg98urrZPyQIVBJhAxilF6MchRjhF5P3_wa4Dn-Sf3Oi3ei9NDaoQGkJMeZKoFdZ5ymtYVY08D6pguXpCrjuRWaGxWhHS_ZqZNRqBHaXSuLHJeBpQRv02d5Q0gWoRfTa5jA_lSmbmy78jQUXKSsECJCDwclm_peq2iE9gatuzL0D4uvB2HoF_13YNHXJthMODZdwJOVeSbAJ368mYvn6MZxdVLK8uPs8xN00_-8Yb9pF2333co-Rdf1736x7J6FufcH32grRw
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Lower-Limb+Joint+Torque+Prediction+Using+LSTM+Neural+Networks+and+Transfer+Learning&rft.jtitle=IEEE+transactions+on+neural+systems+and+rehabilitation+engineering&rft.au=Zhang%2C+Longbin&rft.au=Soselia%2C+Davit&rft.au=Wang%2C+Ruoli&rft.au=Gutierrez-Farewik%2C+Elena+M&rft.date=2022&rft.eissn=1558-0210&rft.volume=30&rft.spage=600&rft_id=info:doi/10.1109%2FTNSRE.2022.3156786&rft_id=info%3Apmid%2F35239487&rft.externalDocID=35239487
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1534-4320&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1534-4320&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1534-4320&client=summon