Lateral walking gait phase recognition for hip exoskeleton by denoising autoencoder-LSTM
Lateral resistance walk is an effective way to strengthen the abductor muscles of the hip. Accurate lateral walking gait recognition is the prerequisite for exoskeletons to be applied to lateral walking exercises. This paper proposes a denoising autoencoder-LSTM (DAE-LSTM) algorithm for lateral walk...
Saved in:
| Published in: | Computational and structural biotechnology journal Vol. 28; pp. 50 - 62 |
|---|---|
| Main Authors: | , , , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Netherlands
Elsevier B.V
01.01.2025
Research Network of Computational and Structural Biotechnology Elsevier |
| Subjects: | |
| ISSN: | 2001-0370, 2001-0370 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Lateral resistance walk is an effective way to strengthen the abductor muscles of the hip. Accurate lateral walking gait recognition is the prerequisite for exoskeletons to be applied to lateral walking exercises. This paper proposes a denoising autoencoder-LSTM (DAE-LSTM) algorithm for lateral walking gait recognition. Nine sets of IMU data at three speeds and three strides of ten subjects were collected. Four lateral walking gait phases of narrow double support (NDS), guided foot swing (GFS), wide double support (WDS) and following leg swing (FLS) were recognized. The recognition performance of random forest (RF), support vector machine (SVM), k-nearest neighbors (KNN), neural networks (NN) and DAE-LSTM were compared. The average cross-subject recognition accuracy of DAE-LSTM was 90.2 %, which was higher than the other four models and previous work. For each frame of IMU data, the average recognition time of DAE-LSTM is 0.383 ms, which is 5.32 ms higher than the previous work. When the signal-to-noise ratio (SNR) is greater than 100:1, the accuracy of the DAE-LSTM model is higher than 90.0 %, and the accuracy of the other four models were less than 85 %. The results show that the proposed algorithm can achieve the requirements of recognition accuracy, model recognition time and model robustness for application in exoskeleton.
[Display omitted] |
|---|---|
| AbstractList | Lateral resistance walk is an effective way to strengthen the abductor muscles of the hip. Accurate lateral walking gait recognition is the prerequisite for exoskeletons to be applied to lateral walking exercises. This paper proposes a denoising autoencoder-LSTM (DAE-LSTM) algorithm for lateral walking gait recognition. Nine sets of IMU data at three speeds and three strides of ten subjects were collected. Four lateral walking gait phases of narrow double support (NDS), guided foot swing (GFS), wide double support (WDS) and following leg swing (FLS) were recognized. The recognition performance of random forest (RF), support vector machine (SVM), k-nearest neighbors (KNN), neural networks (NN) and DAE-LSTM were compared. The average cross-subject recognition accuracy of DAE-LSTM was 90.2 %, which was higher than the other four models and previous work. For each frame of IMU data, the average recognition time of DAE-LSTM is 0.383 ms, which is 5.32 ms higher than the previous work. When the signal-to-noise ratio (SNR) is greater than 100:1, the accuracy of the DAE-LSTM model is higher than 90.0 %, and the accuracy of the other four models were less than 85 %. The results show that the proposed algorithm can achieve the requirements of recognition accuracy, model recognition time and model robustness for application in exoskeleton.Lateral resistance walk is an effective way to strengthen the abductor muscles of the hip. Accurate lateral walking gait recognition is the prerequisite for exoskeletons to be applied to lateral walking exercises. This paper proposes a denoising autoencoder-LSTM (DAE-LSTM) algorithm for lateral walking gait recognition. Nine sets of IMU data at three speeds and three strides of ten subjects were collected. Four lateral walking gait phases of narrow double support (NDS), guided foot swing (GFS), wide double support (WDS) and following leg swing (FLS) were recognized. The recognition performance of random forest (RF), support vector machine (SVM), k-nearest neighbors (KNN), neural networks (NN) and DAE-LSTM were compared. The average cross-subject recognition accuracy of DAE-LSTM was 90.2 %, which was higher than the other four models and previous work. For each frame of IMU data, the average recognition time of DAE-LSTM is 0.383 ms, which is 5.32 ms higher than the previous work. When the signal-to-noise ratio (SNR) is greater than 100:1, the accuracy of the DAE-LSTM model is higher than 90.0 %, and the accuracy of the other four models were less than 85 %. The results show that the proposed algorithm can achieve the requirements of recognition accuracy, model recognition time and model robustness for application in exoskeleton. Lateral resistance walk is an effective way to strengthen the abductor muscles of the hip. Accurate lateral walking gait recognition is the prerequisite for exoskeletons to be applied to lateral walking exercises. This paper proposes a denoising autoencoder-LSTM (DAE-LSTM) algorithm for lateral walking gait recognition. Nine sets of IMU data at three speeds and three strides of ten subjects were collected. Four lateral walking gait phases of narrow double support (NDS), guided foot swing (GFS), wide double support (WDS) and following leg swing (FLS) were recognized. The recognition performance of random forest (RF), support vector machine (SVM), k-nearest neighbors (KNN), neural networks (NN) and DAE-LSTM were compared. The average cross-subject recognition accuracy of DAE-LSTM was 90.2%, which was higher than the other four models and previous work. For each frame of IMU data, the average recognition time of DAE-LSTM is 0.383 ms, which is 5.32ms higher than the previous work. When the signal-to-noise ratio (SNR) is greater than 100:1, the accuracy of the DAE-LSTM model is higher than 90.0%, and the accuracy of the other four models were less than 85%. The results show that the proposed algorithm can achieve the requirements of recognition accuracy, model recognition time and model robustness for application in exoskeleton. Lateral resistance walk is an effective way to strengthen the abductor muscles of the hip. Accurate lateral walking gait recognition is the prerequisite for exoskeletons to be applied to lateral walking exercises. This paper proposes a denoising autoencoder-LSTM (DAE-LSTM) algorithm for lateral walking gait recognition. Nine sets of IMU data at three speeds and three strides of ten subjects were collected. Four lateral walking gait phases of narrow double support (NDS), guided foot swing (GFS), wide double support (WDS) and following leg swing (FLS) were recognized. The recognition performance of random forest (RF), support vector machine (SVM), k-nearest neighbors (KNN), neural networks (NN) and DAE-LSTM were compared. The average cross-subject recognition accuracy of DAE-LSTM was 90.2 %, which was higher than the other four models and previous work. For each frame of IMU data, the average recognition time of DAE-LSTM is 0.383 ms, which is 5.32 ms higher than the previous work. When the signal-to-noise ratio (SNR) is greater than 100:1, the accuracy of the DAE-LSTM model is higher than 90.0 %, and the accuracy of the other four models were less than 85 %. The results show that the proposed algorithm can achieve the requirements of recognition accuracy, model recognition time and model robustness for application in exoskeleton. [Display omitted] Lateral resistance walk is an effective way to strengthen the abductor muscles of the hip. Accurate lateral walking gait recognition is the prerequisite for exoskeletons to be applied to lateral walking exercises. This paper proposes a denoising autoencoder-LSTM (DAE-LSTM) algorithm for lateral walking gait recognition. Nine sets of IMU data at three speeds and three strides of ten subjects were collected. Four lateral walking gait phases of narrow double support (NDS), guided foot swing (GFS), wide double support (WDS) and following leg swing (FLS) were recognized. The recognition performance of random forest (RF), support vector machine (SVM), k-nearest neighbors (KNN), neural networks (NN) and DAE-LSTM were compared. The average cross-subject recognition accuracy of DAE-LSTM was 90.2 %, which was higher than the other four models and previous work. For each frame of IMU data, the average recognition time of DAE-LSTM is 0.383 ms, which is 5.32 ms higher than the previous work. When the signal-to-noise ratio (SNR) is greater than 100:1, the accuracy of the DAE-LSTM model is higher than 90.0 %, and the accuracy of the other four models were less than 85 %. The results show that the proposed algorithm can achieve the requirements of recognition accuracy, model recognition time and model robustness for application in exoskeleton. |
| Author | Luo, Mingxiang Kobsiriphat, Worawarit Cao, Wujing Wu, Xinyu Wang, Jing-Xin Yu, Hongliu Dong, Xiaoli Zhang, Mingming |
| Author_xml | – sequence: 1 givenname: Mingxiang surname: Luo fullname: Luo, Mingxiang organization: Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518005, China – sequence: 2 givenname: Xiaoli surname: Dong fullname: Dong, Xiaoli organization: Xinjiang Industrial Vocational and Technical College, Urumqi 830000, China – sequence: 3 givenname: Hongliu surname: Yu fullname: Yu, Hongliu organization: University of Shanghai for Science and Technology, Shanghai 200093, China – sequence: 4 givenname: Mingming orcidid: 0000-0001-8016-1856 surname: Zhang fullname: Zhang, Mingming organization: Southern University of Science and Technology, Shenzhen 518055, China – sequence: 5 givenname: Xinyu surname: Wu fullname: Wu, Xinyu organization: Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518005, China – sequence: 6 givenname: Worawarit orcidid: 0000-0002-2979-3089 surname: Kobsiriphat fullname: Kobsiriphat, Worawarit organization: The National Metal and Materials Technology Center, Pathum Thani 12140, Thailand – sequence: 7 givenname: Jing-Xin surname: Wang fullname: Wang, Jing-Xin organization: Department of Rehabilitation, Zhengzhou Central Hospital Affiliated to Zhengzhou University, Zhengzhou 450000, China – sequence: 8 givenname: Wujing orcidid: 0000-0002-3348-0691 surname: Cao fullname: Cao, Wujing email: caowujing414@126.com organization: Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518005, China |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/40026802$$D View this record in MEDLINE/PubMed |
| BookMark | eNqNUsFu1DAQjVARLaU_wAHlyCVh7DixV0JCqCq00iIOFImbNXEmu06z8WJ7C_17nG6LWg4Vvow1897TaN57mR1MbqIse82gZMCad0NpQjuUHHhdAi8B2LPsiKdSQCXh4MH_MDsJYYD0FGsWFbzIDgUAbxTwo-zHEiN5HPNfOF7ZaZWv0MZ8u8ZAuSfjVpON1k1573y-ttucfrtwRSPF1Gtv8o4mZ8PMw110NBnXkS-W3y6_vMqe9zgGOrmrx9n3T2eXp-fF8uvni9OPy8IIVccCm65fsAo7URnWdjWXUoCQvamZAdNQw0giw0WNnBriQlVtJVWaIauVobY6zi72up3DQW-93aC_0Q6tvm04v9LoozUj6RoV9H0tG4RWdNBjw7DuFaqOFK8rkbQ-7LW2u3ZDnaEpptM8En08mexar9y1ZkxJJpRMCm_vFLz7uaMQ9cYGQ-OIE7ld0BUXHBQX8j-gTFazT0wl6JuHe_1d6N7GBFB7gPEuBE-9NjbibFxa046agZ5Dowc9h0bPodHAdUpIovJ_qPfqT5Le70mUnL225HUwNrlPnU2hien09in6H6cD2uI |
| CitedBy_id | crossref_primary_10_1016_j_bspc_2025_108612 |
| Cites_doi | 10.1109/LRA.2022.3185380 10.1109/JSEN.2024.3406596 10.1109/TNSRE.2024.3365204 10.1109/CAC.2018.8623035 10.1109/TNSRE.2019.2909585 10.1109/TNNLS.2020.3009448 10.1109/TIE.2021.3082067 10.1016/j.neucom.2020.01.098 10.1109/TNSRE.2019.2950096 10.1109/JSEN.2024.3469250 10.1016/j.bspc.2021.102587 10.3389/fnbot.2020.00047 10.1109/JSEN.2023.3343721 10.1109/JBHI.2019.2923209 10.2519/jospt.2009.2796 10.1109/TBME.2017.2718528 10.1109/TPAMI.2020.2998790 10.1109/TNSRE.2021.3133656 10.3390/s19040840 10.1145/2557977.2557993 10.1109/TNSRE.2021.3107780 10.1109/TIFS.2020.2985628 10.1109/IWW-BCI.2016.7457459 10.1109/ACCESS.2019.2922258 10.1109/ACCESS.2020.2967845 10.2519/jospt.2013.4004 10.1109/TIM.2024.3488159 10.1109/TNSRE.2021.3086843 10.1109/ICIP.2018.8451608 10.1109/TNSRE.2021.3076366 10.1109/IJCNN60899.2024.10650106 10.1109/TMRB.2022.3166543 |
| ContentType | Journal Article |
| Copyright | 2025 2025 Published by Elsevier B.V. on behalf of Research Network of Computational and Structural Biotechnology. 2025 Published by Elsevier B.V. on behalf of Research Network of Computational and Structural Biotechnology. 2025 |
| Copyright_xml | – notice: 2025 – notice: 2025 Published by Elsevier B.V. on behalf of Research Network of Computational and Structural Biotechnology. – notice: 2025 Published by Elsevier B.V. on behalf of Research Network of Computational and Structural Biotechnology. 2025 |
| DBID | 6I. AAFTH AAYXX CITATION NPM 7X8 7S9 L.6 5PM DOA |
| DOI | 10.1016/j.csbj.2025.02.001 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef PubMed MEDLINE - Academic AGRICOLA AGRICOLA - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic AGRICOLA AGRICOLA - Academic |
| DatabaseTitleList | MEDLINE - Academic AGRICOLA PubMed |
| 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: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 2001-0370 |
| EndPage | 62 |
| ExternalDocumentID | oai_doaj_org_article_5a80ff576a0b4d0fa61a5f8a8de82534 PMC11871487 40026802 10_1016_j_csbj_2025_02_001 S2001037025000285 |
| Genre | Journal Article |
| GroupedDBID | 0R~ 0SF 457 53G 5VS 6I. AACTN AAEDT AAEDW AAFTH AAHBH AAIKJ AALRI AAXUO ABMAC ACGFS ADBBV ADEZE ADRAZ ADVLN AEXQZ AFTJW AGHFR AITUG AKRWK ALMA_UNASSIGNED_HOLDINGS AMRAJ AOIJS BAWUL BCNDV DIK EBS EJD FDB GROUPED_DOAJ HYE IPNFZ KQ8 M41 M48 M~E NCXOZ O9- OK1 RIG ROL RPM SSZ AAYWO AAYXX ACVFH ADCNI AEUPX AFPUW AIGII AKBMS AKYEP CITATION NPM 7X8 7S9 L.6 5PM |
| ID | FETCH-LOGICAL-c485t-a6df913ad43c1bd52774047fc51c0c6e61e7a1a95a2e6e2483b3781c0a158ceb3 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 5 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001437869500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2001-0370 |
| IngestDate | Fri Oct 03 12:52:57 EDT 2025 Tue Nov 04 02:05:02 EST 2025 Fri Aug 22 20:19:43 EDT 2025 Fri Jul 11 15:59:37 EDT 2025 Mon Jul 21 06:06:21 EDT 2025 Thu Nov 27 01:03:35 EST 2025 Tue Nov 18 22:09:42 EST 2025 Sat Feb 22 15:43:01 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | IMUs Lateral walking gait recognition DAE-LSTM Hip exoskeleton |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. 2025 Published by Elsevier B.V. on behalf of Research Network of Computational and Structural Biotechnology. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c485t-a6df913ad43c1bd52774047fc51c0c6e61e7a1a95a2e6e2483b3781c0a158ceb3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0001-8016-1856 0000-0002-3348-0691 0000-0002-2979-3089 |
| OpenAccessLink | https://doaj.org/article/5a80ff576a0b4d0fa61a5f8a8de82534 |
| PMID | 40026802 |
| PQID | 3173400218 |
| PQPubID | 23479 |
| PageCount | 13 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_5a80ff576a0b4d0fa61a5f8a8de82534 pubmedcentral_primary_oai_pubmedcentral_nih_gov_11871487 proquest_miscellaneous_3242082477 proquest_miscellaneous_3173400218 pubmed_primary_40026802 crossref_citationtrail_10_1016_j_csbj_2025_02_001 crossref_primary_10_1016_j_csbj_2025_02_001 elsevier_sciencedirect_doi_10_1016_j_csbj_2025_02_001 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-01-01 |
| PublicationDateYYYYMMDD | 2025-01-01 |
| PublicationDate_xml | – month: 01 year: 2025 text: 2025-01-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | Netherlands |
| PublicationPlace_xml | – name: Netherlands |
| PublicationTitle | Computational and structural biotechnology journal |
| PublicationTitleAlternate | Comput Struct Biotechnol J |
| PublicationYear | 2025 |
| Publisher | Elsevier B.V Research Network of Computational and Structural Biotechnology Elsevier |
| Publisher_xml | – name: Elsevier B.V – name: Research Network of Computational and Structural Biotechnology – name: Elsevier |
| References | Stolyarov, Burnett, Herr (bib10) 2018; 65 Zou, Wang, Wang, Zhao, Li (bib20) 2020; 15 Luo, Sun, Zhang, Tang, Wang (bib14) 2020; 28 Mohamed S.A., Martinez-Hernandez U., A Hybrid Bayesian-Heuristic Inference System for Recognition of Gait Phase, International Joint Conference on Neural Networks (IJCNN), Yokohama, Japan; 2024. Liu, Wang, He, Li, Wu (bib25) 2022; 4 Distefano, Blackburn, Marshall, Padua (bib2) 2009; 39 Wei, Ding, Yi, Guo, Wang, Zhu, Jiang (bib13) 2021 Wu, Yuan, Zhang, Wang, Xu, Tao (bib21) 2022; 69 Cheng, Bolívar-Nieto, Gregg (bib5) 2020; 29 Su, Wang, Liu, Sheng, Jiang, Xiang (bib7) 2019; 27 Wang, Zhang, Shen, Du, Zhao, Cui, Wen (bib33) 2022; 44 Yang, Xiang, Pang, Yin, Wu, Cao (bib9) 2023; 72 Gu, Guo, Deligianni, Lo, Yang (bib34) 2021; 32 Chen, Li, Fang, Zhang (bib29) 2024; 24 Liu, Liu, Song, Wu, Jin (bib30) 2024; 24 Park K.-H., Lee S.-W., “Movement intention decoding based on deep learning for multiuser myoelectric interfaces,” Proceedings of the 4th International Winter Conference on Brain-Computer Interface; 2016; p. 1–2. Wu Y., Zheng B., Zhao Y., Dynamic gesture recognition based on LSTM-CNN,” Proceedings of the China Automation Congress. (CAC); 2018. p. 2446-2450, Nov./Dec. Chen, Zhang, Liu, Leng, Fu (bib8) 2021; 29 Xu, Wang (bib26) 2020; 14 Liu, Zhou, He, Li, Wang, Wu (bib22) 2022; 7 Sheng, Li (bib18) 2020; 395 Guo, Hutabarat, Owaki, Hayashibe (bib31) 2024; 24 Willcox, Burden (bib1) 2013; 33 Ryu J.-H., Kim D.-H., “Multiple gait phase recognition using boosted classifiers based on sEMG signal and classification matrix,” In Proceedings of the 8th International Conference on Ubiquitous Information Management and Communication (ICUIMC '14), Jan; 2014. Tu J., Liu H., Meng F., Liu M., Ding R., Spatial-temporal data augmentation based on LSTM autoencoder network for skeleton-based human action recognition,” Processings of the 25th IEEE International Conference on Image Process;2018; p. 3478-3482. Hu, Wang, Mei, Martens, Yang, Lewis, Feng (bib36) 2020; 24 Bruinsma, Carloni (bib12) 2021; 29 Guo, Wu, Fang, Zhang, Long (bib28) 2024; 73 Morbidoni, Cucchiarelli, Agostini, Knaflitz, Fioretti, Di Nardo (bib3) 2021; 29 Rokhmanova, Pearl, Kuchenbecker, Halilaj (bib27) 2024; 32 Bartlett, Goldfarb (bib6) 2018; 65 Zhao, Yang, Okoye, Wang (bib35) 2019; 7 Zhang, Tran, Liu, Liu (bib17) 2022; 44 Wei, Zhang, Tian, Hong (bib4) 2021; 68 Jun, Lee, Lee, Lee, Kim (bib15) 2020; 8 Wang, Ye, Luo, Men, Zhao, Huang (bib19) 2019; 19 Zhao (10.1016/j.csbj.2025.02.001_bib35) 2019; 7 Su (10.1016/j.csbj.2025.02.001_bib7) 2019; 27 Stolyarov (10.1016/j.csbj.2025.02.001_bib10) 2018; 65 Guo (10.1016/j.csbj.2025.02.001_bib31) 2024; 24 Liu (10.1016/j.csbj.2025.02.001_bib22) 2022; 7 Zhang (10.1016/j.csbj.2025.02.001_bib17) 2022; 44 Distefano (10.1016/j.csbj.2025.02.001_bib2) 2009; 39 Willcox (10.1016/j.csbj.2025.02.001_bib1) 2013; 33 Wei (10.1016/j.csbj.2025.02.001_bib13) 2021 Hu (10.1016/j.csbj.2025.02.001_bib36) 2020; 24 Wei (10.1016/j.csbj.2025.02.001_bib4) 2021; 68 Bartlett (10.1016/j.csbj.2025.02.001_bib6) 2018; 65 Wang (10.1016/j.csbj.2025.02.001_bib19) 2019; 19 10.1016/j.csbj.2025.02.001_bib24 Xu (10.1016/j.csbj.2025.02.001_bib26) 2020; 14 Morbidoni (10.1016/j.csbj.2025.02.001_bib3) 2021; 29 Yang (10.1016/j.csbj.2025.02.001_bib9) 2023; 72 10.1016/j.csbj.2025.02.001_bib23 Wang (10.1016/j.csbj.2025.02.001_bib33) 2022; 44 Gu (10.1016/j.csbj.2025.02.001_bib34) 2021; 32 Bruinsma (10.1016/j.csbj.2025.02.001_bib12) 2021; 29 Chen (10.1016/j.csbj.2025.02.001_bib8) 2021; 29 Sheng (10.1016/j.csbj.2025.02.001_bib18) 2020; 395 Zou (10.1016/j.csbj.2025.02.001_bib20) 2020; 15 Chen (10.1016/j.csbj.2025.02.001_bib29) 2024; 24 Liu (10.1016/j.csbj.2025.02.001_bib30) 2024; 24 10.1016/j.csbj.2025.02.001_bib32 Wu (10.1016/j.csbj.2025.02.001_bib21) 2022; 69 Guo (10.1016/j.csbj.2025.02.001_bib28) 2024; 73 Liu (10.1016/j.csbj.2025.02.001_bib25) 2022; 4 Luo (10.1016/j.csbj.2025.02.001_bib14) 2020; 28 Cheng (10.1016/j.csbj.2025.02.001_bib5) 2020; 29 10.1016/j.csbj.2025.02.001_bib16 Rokhmanova (10.1016/j.csbj.2025.02.001_bib27) 2024; 32 10.1016/j.csbj.2025.02.001_bib11 Jun (10.1016/j.csbj.2025.02.001_bib15) 2020; 8 |
| References_xml | – volume: 4 start-page: 472 year: 2022 end-page: 479 ident: bib25 article-title: Metric learning for robust gait phase recognition for a lower limb exoskeleton robot based on sEMG publication-title: IEEE Trans Med Robot Bionics – volume: 24 start-page: 5224 year: 2024 end-page: 5236 ident: bib31 article-title: Speed-variable gait phase estimation during ambulation via temporal convolutional network publication-title: IEEE Sens J – volume: 7 start-page: 7779 year: 2022 end-page: 7785 ident: bib22 article-title: A novel method for detecting misclassifications of the locomotion mode in lower-limb exoskeleton robot control publication-title: IEEE Robot Autom Lett – volume: 32 start-page: 1005 year: 2024 end-page: 1012 ident: bib27 article-title: IMU-based kinematics estimation accuracy affects gait retraining using vibrotactile cues publication-title: IEEE Trans Neural Syst Rehabil Eng – volume: 27 start-page: 1032 year: 2019 end-page: 1042 ident: bib7 article-title: A CNN-based method for intent recognition using inertial measurement units and intelligent lower limb prosthesis publication-title: IEEE Trans Neural Syst Rehabil Eng – volume: 39 start-page: 532 year: 2009 end-page: 540 ident: bib2 article-title: Gluteal muscle activation during common therapeutic exercises publication-title: J Orthop Sports Phys Ther – volume: 44 start-page: 345 year: 2022 end-page: 360 ident: bib17 article-title: On learning disentangled representations for gait recognition publication-title: IEEE Trans Pattern Anal Mach Intell – volume: 44 start-page: 3436 year: 2022 end-page: 3449 ident: bib33 article-title: Event-stream representation for human gaits identification using deep neural networks publication-title: IEEE Trans Pattern Anal Mach Intell – volume: 29 start-page: 1827 year: 2020 end-page: 1837 ident: bib5 article-title: Real-time activity recognition with instantaneous characteristic features of thigh kinematics publication-title: IEEE Trans Neural Syst Rehabil Eng – volume: 65 start-page: 763 year: 2018 end-page: 769 ident: bib10 article-title: Translational motion tracking of leg joints for enhanced prediction of walking tasks publication-title: IEEE Trans Biomed Eng – volume: 69 start-page: 4999 year: 2022 end-page: 5008 ident: bib21 article-title: Gait phase classification for a lower limb exoskeleton system based on a graph convolutional network model publication-title: IEEE Trans Ind Electron – volume: 24 start-page: 37986 year: 2024 end-page: 37996 ident: bib29 article-title: A method for real-time prediction of gait events based on walking speed estimation publication-title: IEEE Sens J – volume: 24 start-page: 22685 year: 2024 end-page: 22697 ident: bib30 article-title: Gait event detection based on fuzzy logic model by using IMU signals of lower limbs publication-title: IEEE Sens J – volume: 32 start-page: 546 year: 2021 end-page: 560 ident: bib34 article-title: Cross-subject and cross-modal transfer for generalized abnormal gait pattern recognition publication-title: IEEE Trans Neural Netw Learn Syst – volume: 33 start-page: 325 year: 2013 end-page: 331 ident: bib1 article-title: The influence of varying hip angle and pelvis position on muscle recruitment patterns of the hip abductor muscles during the clam exercise publication-title: J Orthop Sports Phys Ther – reference: Ryu J.-H., Kim D.-H., “Multiple gait phase recognition using boosted classifiers based on sEMG signal and classification matrix,” In Proceedings of the 8th International Conference on Ubiquitous Information Management and Communication (ICUIMC '14), Jan; 2014. – reference: Tu J., Liu H., Meng F., Liu M., Ding R., Spatial-temporal data augmentation based on LSTM autoencoder network for skeleton-based human action recognition,” Processings of the 25th IEEE International Conference on Image Process;2018; p. 3478-3482. – volume: 29 start-page: 819 year: 2021 end-page: 830 ident: bib3 article-title: Machine-learning-based prediction of gait events from EMG in cerebral palsy children publication-title: IEEE Trans Neural Syst Rehabil Eng – volume: 73 start-page: 1 year: 2024 end-page: 15 ident: bib28 article-title: Online transfer learning with pseudo label for gait phase prediction publication-title: IEEE Trans Instrum Meas – volume: 65 start-page: 1330 year: 2018 end-page: 1338 ident: bib6 article-title: A phase variable approach for IMU-based locomotion activity recognition publication-title: IEEE Trans Neural Syst Rehabil Eng – reference: Mohamed S.A., Martinez-Hernandez U., A Hybrid Bayesian-Heuristic Inference System for Recognition of Gait Phase, International Joint Conference on Neural Networks (IJCNN), Yokohama, Japan; 2024. – reference: Park K.-H., Lee S.-W., “Movement intention decoding based on deep learning for multiuser myoelectric interfaces,” Proceedings of the 4th International Winter Conference on Brain-Computer Interface; 2016; p. 1–2. – volume: 15 start-page: 3197 year: 2020 end-page: 3212 ident: bib20 article-title: Deep learning-based gait recognition using smartphones in the wild publication-title: IEEE Trans Inf Forensics Secur – volume: 68 start-page: 1746 year: 2021 end-page: 8094 ident: bib4 article-title: A comparison of neural networks algorithms for EEG and sEMG features based gait phases recognition publication-title: Biomed Signal Process Control – volume: 29 start-page: 2595 year: 2021 end-page: 2604 ident: bib8 article-title: A probability distribution model-based approach for foot placement prediction in the early swing phase with a wearable IMU sensor publication-title: IEEE Trans Neural Syst Rehabil Eng – volume: 29 start-page: 1079 year: 2021 end-page: 1088 ident: bib12 article-title: IMU-based deep neural networks: prediction of locomotor and transition intentions of an osseointegrated transfemoral amputee publication-title: IEEE Trans Neural Syst Rehabil Eng – volume: 19 start-page: 840 year: 2019 ident: bib19 article-title: Pedestrian stride-length estimation based on LSTM and |oencoders publication-title: Sensors – volume: 72 start-page: 1 year: 2023 end-page: 14 ident: bib9 article-title: Inertial sensing for lateral walking gait detection and application in lateral resistance exoskeleton publication-title: IEEE Trans Instrum Meas – start-page: 107 year: 2021 ident: bib13 article-title: A novel sEMG-based gait phase-kinematics-coupled predictor and its interaction with exoskeletons publication-title: Front Neurorobotics – volume: 395 start-page: 86 year: 2020 end-page: 94 ident: bib18 article-title: Siamese denoising autoencoders for joints trajectories reconstruction and robust gait recognition publication-title: Neurocomputing – volume: 14 start-page: 47 year: 2020 ident: bib26 article-title: On-board Training Strategy for IMU-Based Real-Time Locomotion Recognition of Transtibial Amputees With Robotic Prostheses publication-title: Front neurorobotics – volume: 7 start-page: 76741 year: 2019 end-page: 76753 ident: bib35 article-title: Walking assist robot: a novel non-contact abnormal gait recognition approach based on extended set membership filter publication-title: IEEE Access – volume: 28 start-page: 267 year: 2020 end-page: 276 ident: bib14 article-title: A low-cost end-to-end semg-based gait sub-phase reco gnition system publication-title: IEEE Trans Neural Syst Rehabil Eng – volume: 8 start-page: 19196 year: 2020 end-page: 19207 ident: bib15 article-title: Feature extraction using an rnn autoencoder for skeleton-based abnormal gait recognition publication-title: IEEE Access – volume: 24 start-page: 1215 year: 2020 end-page: 1225 ident: bib36 article-title: Vision-based freezing of gait detection with anatomic directed graph representation publication-title: IEEE J Biomed Health Inform – reference: Wu Y., Zheng B., Zhao Y., Dynamic gesture recognition based on LSTM-CNN,” Proceedings of the China Automation Congress. (CAC); 2018. p. 2446-2450, Nov./Dec. – volume: 7 start-page: 7779 issue: 3 year: 2022 ident: 10.1016/j.csbj.2025.02.001_bib22 article-title: A novel method for detecting misclassifications of the locomotion mode in lower-limb exoskeleton robot control publication-title: IEEE Robot Autom Lett doi: 10.1109/LRA.2022.3185380 – volume: 24 start-page: 22685 issue: 14 year: 2024 ident: 10.1016/j.csbj.2025.02.001_bib30 article-title: Gait event detection based on fuzzy logic model by using IMU signals of lower limbs publication-title: IEEE Sens J doi: 10.1109/JSEN.2024.3406596 – volume: 32 start-page: 1005 year: 2024 ident: 10.1016/j.csbj.2025.02.001_bib27 article-title: IMU-based kinematics estimation accuracy affects gait retraining using vibrotactile cues publication-title: IEEE Trans Neural Syst Rehabil Eng doi: 10.1109/TNSRE.2024.3365204 – ident: 10.1016/j.csbj.2025.02.001_bib23 doi: 10.1109/CAC.2018.8623035 – volume: 27 start-page: 1032 issue: 5 year: 2019 ident: 10.1016/j.csbj.2025.02.001_bib7 article-title: A CNN-based method for intent recognition using inertial measurement units and intelligent lower limb prosthesis publication-title: IEEE Trans Neural Syst Rehabil Eng doi: 10.1109/TNSRE.2019.2909585 – volume: 32 start-page: 546 issue: 2 year: 2021 ident: 10.1016/j.csbj.2025.02.001_bib34 article-title: Cross-subject and cross-modal transfer for generalized abnormal gait pattern recognition publication-title: IEEE Trans Neural Netw Learn Syst doi: 10.1109/TNNLS.2020.3009448 – volume: 72 start-page: 1 year: 2023 ident: 10.1016/j.csbj.2025.02.001_bib9 article-title: Inertial sensing for lateral walking gait detection and application in lateral resistance exoskeleton publication-title: IEEE Trans Instrum Meas – volume: 69 start-page: 4999 issue: 5 year: 2022 ident: 10.1016/j.csbj.2025.02.001_bib21 article-title: Gait phase classification for a lower limb exoskeleton system based on a graph convolutional network model publication-title: IEEE Trans Ind Electron doi: 10.1109/TIE.2021.3082067 – volume: 395 start-page: 86 year: 2020 ident: 10.1016/j.csbj.2025.02.001_bib18 article-title: Siamese denoising autoencoders for joints trajectories reconstruction and robust gait recognition publication-title: Neurocomputing doi: 10.1016/j.neucom.2020.01.098 – volume: 28 start-page: 267 issue: 1 year: 2020 ident: 10.1016/j.csbj.2025.02.001_bib14 article-title: A low-cost end-to-end semg-based gait sub-phase reco gnition system publication-title: IEEE Trans Neural Syst Rehabil Eng doi: 10.1109/TNSRE.2019.2950096 – volume: 24 start-page: 37986 issue: 22 year: 2024 ident: 10.1016/j.csbj.2025.02.001_bib29 article-title: A method for real-time prediction of gait events based on walking speed estimation publication-title: IEEE Sens J doi: 10.1109/JSEN.2024.3469250 – volume: 68 start-page: 1746 year: 2021 ident: 10.1016/j.csbj.2025.02.001_bib4 article-title: A comparison of neural networks algorithms for EEG and sEMG features based gait phases recognition publication-title: Biomed Signal Process Control doi: 10.1016/j.bspc.2021.102587 – volume: 14 start-page: 47 year: 2020 ident: 10.1016/j.csbj.2025.02.001_bib26 article-title: On-board Training Strategy for IMU-Based Real-Time Locomotion Recognition of Transtibial Amputees With Robotic Prostheses publication-title: Front neurorobotics doi: 10.3389/fnbot.2020.00047 – volume: 24 start-page: 5224 issue: 4 year: 2024 ident: 10.1016/j.csbj.2025.02.001_bib31 article-title: Speed-variable gait phase estimation during ambulation via temporal convolutional network publication-title: IEEE Sens J doi: 10.1109/JSEN.2023.3343721 – volume: 24 start-page: 1215 issue: 4 year: 2020 ident: 10.1016/j.csbj.2025.02.001_bib36 article-title: Vision-based freezing of gait detection with anatomic directed graph representation publication-title: IEEE J Biomed Health Inform doi: 10.1109/JBHI.2019.2923209 – volume: 39 start-page: 532 issue: 7 year: 2009 ident: 10.1016/j.csbj.2025.02.001_bib2 article-title: Gluteal muscle activation during common therapeutic exercises publication-title: J Orthop Sports Phys Ther doi: 10.2519/jospt.2009.2796 – volume: 65 start-page: 763 issue: 4 year: 2018 ident: 10.1016/j.csbj.2025.02.001_bib10 article-title: Translational motion tracking of leg joints for enhanced prediction of walking tasks publication-title: IEEE Trans Biomed Eng doi: 10.1109/TBME.2017.2718528 – volume: 44 start-page: 345 issue: 1 year: 2022 ident: 10.1016/j.csbj.2025.02.001_bib17 article-title: On learning disentangled representations for gait recognition publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2020.2998790 – volume: 29 start-page: 2595 year: 2021 ident: 10.1016/j.csbj.2025.02.001_bib8 article-title: A probability distribution model-based approach for foot placement prediction in the early swing phase with a wearable IMU sensor publication-title: IEEE Trans Neural Syst Rehabil Eng doi: 10.1109/TNSRE.2021.3133656 – volume: 19 start-page: 840 issue: 4 year: 2019 ident: 10.1016/j.csbj.2025.02.001_bib19 article-title: Pedestrian stride-length estimation based on LSTM and |oencoders publication-title: Sensors doi: 10.3390/s19040840 – ident: 10.1016/j.csbj.2025.02.001_bib11 doi: 10.1145/2557977.2557993 – volume: 29 start-page: 1827 year: 2020 ident: 10.1016/j.csbj.2025.02.001_bib5 article-title: Real-time activity recognition with instantaneous characteristic features of thigh kinematics publication-title: IEEE Trans Neural Syst Rehabil Eng doi: 10.1109/TNSRE.2021.3107780 – volume: 15 start-page: 3197 year: 2020 ident: 10.1016/j.csbj.2025.02.001_bib20 article-title: Deep learning-based gait recognition using smartphones in the wild publication-title: IEEE Trans Inf Forensics Secur doi: 10.1109/TIFS.2020.2985628 – ident: 10.1016/j.csbj.2025.02.001_bib24 doi: 10.1109/IWW-BCI.2016.7457459 – volume: 7 start-page: 76741 year: 2019 ident: 10.1016/j.csbj.2025.02.001_bib35 article-title: Walking assist robot: a novel non-contact abnormal gait recognition approach based on extended set membership filter publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2922258 – volume: 8 start-page: 19196 year: 2020 ident: 10.1016/j.csbj.2025.02.001_bib15 article-title: Feature extraction using an rnn autoencoder for skeleton-based abnormal gait recognition publication-title: IEEE Access doi: 10.1109/ACCESS.2020.2967845 – volume: 33 start-page: 325 issue: 5 year: 2013 ident: 10.1016/j.csbj.2025.02.001_bib1 article-title: The influence of varying hip angle and pelvis position on muscle recruitment patterns of the hip abductor muscles during the clam exercise publication-title: J Orthop Sports Phys Ther doi: 10.2519/jospt.2013.4004 – volume: 65 start-page: 1330 issue: 6 year: 2018 ident: 10.1016/j.csbj.2025.02.001_bib6 article-title: A phase variable approach for IMU-based locomotion activity recognition publication-title: IEEE Trans Neural Syst Rehabil Eng – start-page: 107 year: 2021 ident: 10.1016/j.csbj.2025.02.001_bib13 article-title: A novel sEMG-based gait phase-kinematics-coupled predictor and its interaction with exoskeletons publication-title: Front Neurorobotics – volume: 73 start-page: 1 year: 2024 ident: 10.1016/j.csbj.2025.02.001_bib28 article-title: Online transfer learning with pseudo label for gait phase prediction publication-title: IEEE Trans Instrum Meas doi: 10.1109/TIM.2024.3488159 – volume: 29 start-page: 1079 year: 2021 ident: 10.1016/j.csbj.2025.02.001_bib12 article-title: IMU-based deep neural networks: prediction of locomotor and transition intentions of an osseointegrated transfemoral amputee publication-title: IEEE Trans Neural Syst Rehabil Eng doi: 10.1109/TNSRE.2021.3086843 – volume: 44 start-page: 3436 issue: 7 year: 2022 ident: 10.1016/j.csbj.2025.02.001_bib33 article-title: Event-stream representation for human gaits identification using deep neural networks publication-title: IEEE Trans Pattern Anal Mach Intell – ident: 10.1016/j.csbj.2025.02.001_bib16 doi: 10.1109/ICIP.2018.8451608 – volume: 29 start-page: 819 year: 2021 ident: 10.1016/j.csbj.2025.02.001_bib3 article-title: Machine-learning-based prediction of gait events from EMG in cerebral palsy children publication-title: IEEE Trans Neural Syst Rehabil Eng doi: 10.1109/TNSRE.2021.3076366 – ident: 10.1016/j.csbj.2025.02.001_bib32 doi: 10.1109/IJCNN60899.2024.10650106 – volume: 4 start-page: 472 issue: 2 year: 2022 ident: 10.1016/j.csbj.2025.02.001_bib25 article-title: Metric learning for robust gait phase recognition for a lower limb exoskeleton robot based on sEMG publication-title: IEEE Trans Med Robot Bionics doi: 10.1109/TMRB.2022.3166543 |
| SSID | ssj0000816930 |
| Score | 2.3497572 |
| Snippet | Lateral resistance walk is an effective way to strengthen the abductor muscles of the hip. Accurate lateral walking gait recognition is the prerequisite for... |
| SourceID | doaj pubmedcentral proquest pubmed crossref elsevier |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 50 |
| SubjectTerms | biotechnology DAE-LSTM exoskeleton gait Hip exoskeleton hips IMUs Lateral walking gait recognition signal-to-noise ratio support vector machines |
| Title | Lateral walking gait phase recognition for hip exoskeleton by denoising autoencoder-LSTM |
| URI | https://dx.doi.org/10.1016/j.csbj.2025.02.001 https://www.ncbi.nlm.nih.gov/pubmed/40026802 https://www.proquest.com/docview/3173400218 https://www.proquest.com/docview/3242082477 https://pubmed.ncbi.nlm.nih.gov/PMC11871487 https://doaj.org/article/5a80ff576a0b4d0fa61a5f8a8de82534 |
| Volume | 28 |
| WOSCitedRecordID | wos001437869500001&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: 2001-0370 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816930 issn: 2001-0370 databaseCode: DOA dateStart: 20120101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2001-0370 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816930 issn: 2001-0370 databaseCode: M~E dateStart: 20110101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3Pb9MwFLZg4gAHxG-yjclI3FCE7dixfRzTJg7dhMRAvVm249CMKqnalMGFv53nJK0akMqFSw6xncR-z37fc56_h9AbAWbPawbeCWDxlDsqUsWdS2mhS6W0U7ILxvwykVdXajrVH3dSfcWYsJ4euB-4d8IqUpaAii1xvCClzakVpbKqCODcZB0TKJF6x5nq1mAVSUbIcEqmD-jyK3cDDiETPUknHVmijrB_ZJD-Bpx_xk3uGKKLR-jhgCDxaf_lj9GdUD9BD3Z4BZ-i6cTGg8VzfGvncSscf7VVixczsFh4GzHU1BgAK55VCxx-NKtvYH8AB2L3E8NS1FRxDwHbddtEpssiLNPJp-vLZ-jzxfn12Yd0SKGQeq5Em9q8KDXNbMEzT10hGKA9wmXpBfXE5yGnQVpqtbAs5IFxlblMKiizVCgPjvZzdFA3dXiJcOZZBujIlUELzgvnnLSZVZ7owApKQoLoZjiNH_jFY5qLudkEkt2YKAITRWAIi9F0CXq7bbPo2TX21n4fpbStGZmxuxugL2bQF_MvfUmQ2MjYDCCjBw_wqGrvy19vFMLADIy_VWwdmvXKAALLeIeV9tRhMYyBcSkT9KJXom03YttcEZYgNVKvUT_HJXU165jAY6548Gfl4f8YmSN0P_a33186Rgftch1eoXv-e1utliforpyqk26WwfXy1_lvmxItyQ |
| linkProvider | Directory of Open Access Journals |
| 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=Lateral+walking+gait+phase+recognition+for+hip+exoskeleton+by+denoising+autoencoder-LSTM&rft.jtitle=Computational+and+structural+biotechnology+journal&rft.au=Luo%2C+Mingxiang&rft.au=Dong%2C+Xiaoli&rft.au=Yu%2C+Hongliu&rft.au=Zhang%2C+Mingming&rft.date=2025-01-01&rft.pub=Research+Network+of+Computational+and+Structural+Biotechnology&rft.eissn=2001-0370&rft.volume=28&rft.spage=50&rft.epage=62&rft_id=info:doi/10.1016%2Fj.csbj.2025.02.001&rft.externalDocID=PMC11871487 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2001-0370&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2001-0370&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2001-0370&client=summon |