Enhancing biomechanical machine learning with limited data: generating realistic synthetic posture data using generative artificial intelligence
Objective: Biomechanical Machine Learning (ML) models, particularly deep-learning models, demonstrate the best performance when trained using extensive datasets. However, biomechanical data are frequently limited due to diverse challenges. Effective methods for augmenting data in developing ML model...
Uloženo v:
| Vydáno v: | Frontiers in bioengineering and biotechnology Ročník 12; s. 1350135 |
|---|---|
| Hlavní autoři: | , , , , , , , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Switzerland
Frontiers Media SA
14.02.2024
Frontiers Media S.A |
| Témata: | |
| ISSN: | 2296-4185, 2296-4185 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Objective:
Biomechanical Machine Learning (ML) models, particularly deep-learning models, demonstrate the best performance when trained using extensive datasets. However, biomechanical data are frequently limited due to diverse challenges. Effective methods for augmenting data in developing ML models, specifically in the human posture domain, are scarce. Therefore, this study explored the feasibility of leveraging generative artificial intelligence (AI) to produce realistic synthetic posture data by utilizing three-dimensional posture data.
Methods:
Data were collected from 338 subjects through surface topography. A Variational Autoencoder (VAE) architecture was employed to generate and evaluate synthetic posture data, examining its distinguishability from real data by domain experts, ML classifiers, and Statistical Parametric Mapping (SPM). The benefits of incorporating augmented posture data into the learning process were exemplified by a deep autoencoder (AE) for automated feature representation.
Results:
Our findings highlight the challenge of differentiating synthetic data from real data for both experts and ML classifiers, underscoring the quality of synthetic data. This observation was also confirmed by SPM. By integrating synthetic data into AE training, the reconstruction error can be reduced compared to using only real data samples. Moreover, this study demonstrates the potential for reduced latent dimensions, while maintaining a reconstruction accuracy comparable to AEs trained exclusively on real data samples.
Conclusion:
This study emphasizes the prospects of harnessing generative AI to enhance ML tasks in the biomechanics domain. |
|---|---|
| AbstractList | Objective: Biomechanical Machine Learning (ML) models, particularly deep-learning models, demonstrate the best performance when trained using extensive datasets. However, biomechanical data are frequently limited due to diverse challenges. Effective methods for augmenting data in developing ML models, specifically in the human posture domain, are scarce. Therefore, this study explored the feasibility of leveraging generative artificial intelligence (AI) to produce realistic synthetic posture data by utilizing three-dimensional posture data. Methods: Data were collected from 338 subjects through surface topography. A Variational Autoencoder (VAE) architecture was employed to generate and evaluate synthetic posture data, examining its distinguishability from real data by domain experts, ML classifiers, and Statistical Parametric Mapping (SPM). The benefits of incorporating augmented posture data into the learning process were exemplified by a deep autoencoder (AE) for automated feature representation. Results: Our findings highlight the challenge of differentiating synthetic data from real data for both experts and ML classifiers, underscoring the quality of synthetic data. This observation was also confirmed by SPM. By integrating synthetic data into AE training, the reconstruction error can be reduced compared to using only real data samples. Moreover, this study demonstrates the potential for reduced latent dimensions, while maintaining a reconstruction accuracy comparable to AEs trained exclusively on real data samples. Conclusion: This study emphasizes the prospects of harnessing generative AI to enhance ML tasks in the biomechanics domain.Objective: Biomechanical Machine Learning (ML) models, particularly deep-learning models, demonstrate the best performance when trained using extensive datasets. However, biomechanical data are frequently limited due to diverse challenges. Effective methods for augmenting data in developing ML models, specifically in the human posture domain, are scarce. Therefore, this study explored the feasibility of leveraging generative artificial intelligence (AI) to produce realistic synthetic posture data by utilizing three-dimensional posture data. Methods: Data were collected from 338 subjects through surface topography. A Variational Autoencoder (VAE) architecture was employed to generate and evaluate synthetic posture data, examining its distinguishability from real data by domain experts, ML classifiers, and Statistical Parametric Mapping (SPM). The benefits of incorporating augmented posture data into the learning process were exemplified by a deep autoencoder (AE) for automated feature representation. Results: Our findings highlight the challenge of differentiating synthetic data from real data for both experts and ML classifiers, underscoring the quality of synthetic data. This observation was also confirmed by SPM. By integrating synthetic data into AE training, the reconstruction error can be reduced compared to using only real data samples. Moreover, this study demonstrates the potential for reduced latent dimensions, while maintaining a reconstruction accuracy comparable to AEs trained exclusively on real data samples. Conclusion: This study emphasizes the prospects of harnessing generative AI to enhance ML tasks in the biomechanics domain. Objective: Biomechanical Machine Learning (ML) models, particularly deep-learning models, demonstrate the best performance when trained using extensive datasets. However, biomechanical data are frequently limited due to diverse challenges. Effective methods for augmenting data in developing ML models, specifically in the human posture domain, are scarce. Therefore, this study explored the feasibility of leveraging generative artificial intelligence (AI) to produce realistic synthetic posture data by utilizing three-dimensional posture data. Methods: Data were collected from 338 subjects through surface topography. A Variational Autoencoder (VAE) architecture was employed to generate and evaluate synthetic posture data, examining its distinguishability from real data by domain experts, ML classifiers, and Statistical Parametric Mapping (SPM). The benefits of incorporating augmented posture data into the learning process were exemplified by a deep autoencoder (AE) for automated feature representation. Results: Our findings highlight the challenge of differentiating synthetic data from real data for both experts and ML classifiers, underscoring the quality of synthetic data. This observation was also confirmed by SPM. By integrating synthetic data into AE training, the reconstruction error can be reduced compared to using only real data samples. Moreover, this study demonstrates the potential for reduced latent dimensions, while maintaining a reconstruction accuracy comparable to AEs trained exclusively on real data samples. Conclusion: This study emphasizes the prospects of harnessing generative AI to enhance ML tasks in the biomechanics domain. Objective: Biomechanical Machine Learning (ML) models, particularly deep-learning models, demonstrate the best performance when trained using extensive datasets. However, biomechanical data are frequently limited due to diverse challenges. Effective methods for augmenting data in developing ML models, specifically in the human posture domain, are scarce. Therefore, this study explored the feasibility of leveraging generative artificial intelligence (AI) to produce realistic synthetic posture data by utilizing three-dimensional posture data. Methods: Data were collected from 338 subjects through surface topography. A Variational Autoencoder (VAE) architecture was employed to generate and evaluate synthetic posture data, examining its distinguishability from real data by domain experts, ML classifiers, and Statistical Parametric Mapping (SPM). The benefits of incorporating augmented posture data into the learning process were exemplified by a deep autoencoder (AE) for automated feature representation. Results: Our findings highlight the challenge of differentiating synthetic data from real data for both experts and ML classifiers, underscoring the quality of synthetic data. This observation was also confirmed by SPM. By integrating synthetic data into AE training, the reconstruction error can be reduced compared to using only real data samples. Moreover, this study demonstrates the potential for reduced latent dimensions, while maintaining a reconstruction accuracy comparable to AEs trained exclusively on real data samples. Conclusion: This study emphasizes the prospects of harnessing generative AI to enhance ML tasks in the biomechanics domain. Biomechanical Machine Learning (ML) models, particularly deep-learning models, demonstrate the best performance when trained using extensive datasets. However, biomechanical data are frequently limited due to diverse challenges. Effective methods for augmenting data in developing ML models, specifically in the human posture domain, are scarce. Therefore, this study explored the feasibility of leveraging generative artificial intelligence (AI) to produce realistic synthetic posture data by utilizing three-dimensional posture data. Data were collected from 338 subjects through surface topography. A Variational Autoencoder (VAE) architecture was employed to generate and evaluate synthetic posture data, examining its distinguishability from real data by domain experts, ML classifiers, and Statistical Parametric Mapping (SPM). The benefits of incorporating augmented posture data into the learning process were exemplified by a deep autoencoder (AE) for automated feature representation. Our findings highlight the challenge of differentiating synthetic data from real data for both experts and ML classifiers, underscoring the quality of synthetic data. This observation was also confirmed by SPM. By integrating synthetic data into AE training, the reconstruction error can be reduced compared to using only real data samples. Moreover, this study demonstrates the potential for reduced latent dimensions, while maintaining a reconstruction accuracy comparable to AEs trained exclusively on real data samples. This study emphasizes the prospects of harnessing generative AI to enhance ML tasks in the biomechanics domain. Objective: Biomechanical Machine Learning (ML) models, particularly deep-learning models, demonstrate the best performance when trained using extensive datasets. However, biomechanical data are frequently limited due to diverse challenges. Effective methods for augmenting data in developing ML models, specifically in the human posture domain, are scarce. Therefore, this study explored the feasibility of leveraging generative artificial intelligence (AI) to produce realistic synthetic posture data by utilizing three-dimensional posture data.Methods: Data were collected from 338 subjects through surface topography. A Variational Autoencoder (VAE) architecture was employed to generate and evaluate synthetic posture data, examining its distinguishability from real data by domain experts, ML classifiers, and Statistical Parametric Mapping (SPM). The benefits of incorporating augmented posture data into the learning process were exemplified by a deep autoencoder (AE) for automated feature representation.Results: Our findings highlight the challenge of differentiating synthetic data from real data for both experts and ML classifiers, underscoring the quality of synthetic data. This observation was also confirmed by SPM. By integrating synthetic data into AE training, the reconstruction error can be reduced compared to using only real data samples. Moreover, this study demonstrates the potential for reduced latent dimensions, while maintaining a reconstruction accuracy comparable to AEs trained exclusively on real data samples.Conclusion: This study emphasizes the prospects of harnessing generative AI to enhance ML tasks in the biomechanics domain. |
| Author | Simon, Steven Werthmann, Frederike Wolf, Claudia Kniepert, Johanna Konradi, Jürgen Betz, Ulrich Drees, Philipp Dindorf, Carlo Dully, Jonas Becker, Stephan Fröhlich, Michael Huthwelker, Janine |
| AuthorAffiliation | 1 Department of Sports Science , University of Kaiserslautern-Landau , Kaiserslautern , Germany 2 Institute of Physical Therapy , Prevention and Rehabilitation , University Medical Centre , Johannes Gutenberg University Mainz , Mainz , Germany 3 Department of Orthopedics and Trauma Surgery , University Medical Centre , Johannes Gutenberg University Mainz , Mainz , Germany |
| AuthorAffiliation_xml | – name: 2 Institute of Physical Therapy , Prevention and Rehabilitation , University Medical Centre , Johannes Gutenberg University Mainz , Mainz , Germany – name: 1 Department of Sports Science , University of Kaiserslautern-Landau , Kaiserslautern , Germany – name: 3 Department of Orthopedics and Trauma Surgery , University Medical Centre , Johannes Gutenberg University Mainz , Mainz , Germany |
| Author_xml | – sequence: 1 givenname: Carlo surname: Dindorf fullname: Dindorf, Carlo – sequence: 2 givenname: Jonas surname: Dully fullname: Dully, Jonas – sequence: 3 givenname: Jürgen surname: Konradi fullname: Konradi, Jürgen – sequence: 4 givenname: Claudia surname: Wolf fullname: Wolf, Claudia – sequence: 5 givenname: Stephan surname: Becker fullname: Becker, Stephan – sequence: 6 givenname: Steven surname: Simon fullname: Simon, Steven – sequence: 7 givenname: Janine surname: Huthwelker fullname: Huthwelker, Janine – sequence: 8 givenname: Frederike surname: Werthmann fullname: Werthmann, Frederike – sequence: 9 givenname: Johanna surname: Kniepert fullname: Kniepert, Johanna – sequence: 10 givenname: Philipp surname: Drees fullname: Drees, Philipp – sequence: 11 givenname: Ulrich surname: Betz fullname: Betz, Ulrich – sequence: 12 givenname: Michael surname: Fröhlich fullname: Fröhlich, Michael |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/38419724$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9Ustu1DAUjVARLaU_wAJFYsNmBj8Tmw1CVaGVKrGBteXYNzMeJfZgO636F3wyzjxQ20UXlu_1Pff43Mfb6sQHD1X1HqMlpUJ-7jsXYEkQYUtMOSrnVXVGiGwWDAt-8sg-rS5S2iCEMOEtF-RNdUoFw7Il7Kz6e-XX2hvnV3UhHMEUzxk91KM2a-ehHkBHP4fvXV7XgxtdBltbnfWXegUeos5zNIIeXMrO1OnB5zXM1jakPEXYgespzbBjxh3UOmbXO-PKX85nGAZXggbeVa97PSS4ONzn1e_vV78urxe3P3_cXH67XRgm21wK6xpudS8BGSGYBE2BI-gsRbrFfW8QkE42PS6-FVZa1tBGS0Nt22MBiJ5XN3teG_RGbaMbdXxQQTu1ewhxpWaFZgAFSLLOmoZw3rG25Rqo6JDueoQlUNsUrq97ru3UjWAN-Bz18IT0acS7tVqFO4WRkFK0ojB8OjDE8GeClNXokilN0R7ClBSRlLIGYc4L9OMz6CZM0ZdeKUpailjTkLm8D48l_ddynHwBiD3AxJBShF4Zl8tkwqzQDUWamvdM7fZMzXumDntWUsmz1CP7C0n_AD3P20I |
| CitedBy_id | crossref_primary_10_1016_j_foohum_2025_100818 crossref_primary_10_3389_fbioe_2025_1579085 crossref_primary_10_1177_14727978251380798 crossref_primary_10_3389_fspor_2025_1646146 crossref_primary_10_1038_s41598_024_62720_w crossref_primary_10_1108_K_11_2024_3026 crossref_primary_10_3389_fspor_2025_1607600 |
| Cites_doi | 10.1016/j.jbiomech.2022.111301 10.1109/access.2020.3029616 10.1007/s40279-014-0246-y 10.1145/3446374 10.3390/s20185373 10.1007/s00586-021-06918-w 10.1109/JBHI.2015.2450232 10.18653/v1/P17-1061 10.1109/CVPR.2009.5206848 10.1109/jsen.2020.3019053 10.1109/JBHI.2019.2958879 10.2478/bhk-2021-0022 10.1109/ICASSP40776.2020.9053735 10.1609/aaai.v33i01.33015885 10.1109/access.2020.2973898 10.1038/s41597-021-01014-6 10.3390/ijerph19074074 10.1109/MCSE.2007.55 10.1093/jamia/ocaa309 10.1016/j.jneumeth.2020.108885 10.1109/jbhi.2019.2906499 10.1007/s00419-023-02458-5 10.1109/ICMLA.2019.00236 10.1142/S1469026820500029 10.1038/s41598-019-38748-8 10.2307/2529310 10.1016/B978-0-444-63984-4.00005-3 10.1038/nmeth.4642 10.3390/s18103533 10.1109/TNNLS.2021.3132928 10.1186/s40537-023-00727-2 10.1007/s40141-019-00234-7 10.3390/s21186323 10.1007/s40279-019-01110-z 10.1519/jsc.0000000000001279 10.1016/j.humov.2022.103054 10.3390/ijerph20054131 10.1109/EMBC.2019.8856294 10.1080/10255842.2020.1828375 10.1109/ICASSP.2015.7178320 10.1109/CCE.2018.8465714 10.1016/j.humov.2008.12.003 10.1109/CASE49439.2021.9551525 10.1016/j.jbiomech.2020.109684 10.1007/s40846-017-0297-2 10.1016/j.medengphy.2023.104046 10.3390/ijerph20010173 10.1007/s00586-016-4807-7 10.3389/fbioe.2020.00362 10.1007/s13042-022-01553-3 10.1016/j.neunet.2020.09.007 10.1109/AIPR.2018.8707390 10.36730/2022.1.levia.6 10.1016/j.jbiomech.2018.09.009 10.3390/s21175876 |
| ContentType | Journal Article |
| Copyright | Copyright © 2024 Dindorf, Dully, Konradi, Wolf, Becker, Simon, Huthwelker, Werthmann, Kniepert, Drees, Betz and Fröhlich. 2024. This work is licensed 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. Copyright © 2024 Dindorf, Dully, Konradi, Wolf, Becker, Simon, Huthwelker, Werthmann, Kniepert, Drees, Betz and Fröhlich. 2024 Dindorf, Dully, Konradi, Wolf, Becker, Simon, Huthwelker, Werthmann, Kniepert, Drees, Betz and Fröhlich |
| Copyright_xml | – notice: Copyright © 2024 Dindorf, Dully, Konradi, Wolf, Becker, Simon, Huthwelker, Werthmann, Kniepert, Drees, Betz and Fröhlich. – notice: 2024. This work is licensed 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. – notice: Copyright © 2024 Dindorf, Dully, Konradi, Wolf, Becker, Simon, Huthwelker, Werthmann, Kniepert, Drees, Betz and Fröhlich. 2024 Dindorf, Dully, Konradi, Wolf, Becker, Simon, Huthwelker, Werthmann, Kniepert, Drees, Betz and Fröhlich |
| DBID | AAYXX CITATION NPM 3V. 7X7 7XB 88E 8FE 8FH 8FI 8FJ 8FK ABUWG AFKRA AZQEC BBNVY BENPR BHPHI CCPQU DWQXO FYUFA GHDGH GNUQQ HCIFZ K9. LK8 M0S M1P M7P PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQGLB PQQKQ PQUKI PRINS 7X8 5PM DOA |
| DOI | 10.3389/fbioe.2024.1350135 |
| DatabaseName | CrossRef PubMed ProQuest Central (Corporate) Health & Medical Collection ProQuest Central (purchase pre-March 2016) Medical Database (Alumni Edition) ProQuest SciTech Collection ProQuest Natural Science Collection Hospital Premium Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials Biological Science Collection AUTh Library subscriptions: ProQuest Central Natural Science Collection ProQuest One Community College ProQuest Central Korea Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Central Student SciTech Premium Collection ProQuest Health & Medical Complete (Alumni) ProQuest Biological Science Collection Health & Medical Collection (Alumni Edition) Medical Database Biological Science Database ProQuest Central Premium ProQuest One Academic ProQuest Publicly Available Content ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) ProQuest One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China MEDLINE - Academic PubMed Central (Full Participant titles) Open Access: DOAJ - Directory of Open Access Journals |
| DatabaseTitle | CrossRef PubMed Publicly Available Content Database ProQuest Central Student ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest One Health & Nursing ProQuest Natural Science Collection ProQuest Central China ProQuest Central ProQuest One Applied & Life Sciences ProQuest Health & Medical Research Collection Health Research Premium Collection Health and Medicine Complete (Alumni Edition) Natural Science Collection ProQuest Central Korea Health & Medical Research Collection Biological Science Collection ProQuest Central (New) ProQuest Medical Library (Alumni) ProQuest Biological Science Collection ProQuest One Academic Eastern Edition ProQuest Hospital Collection Health Research Premium Collection (Alumni) Biological Science Database ProQuest SciTech Collection ProQuest Hospital Collection (Alumni) ProQuest Health & Medical Complete ProQuest Medical Library ProQuest One Academic UKI Edition ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic CrossRef PubMed Publicly Available Content Database |
| 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: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| DocumentTitleAlternate | Dindorf et al |
| EISSN | 2296-4185 |
| ExternalDocumentID | oai_doaj_org_article_e094bdc6255b4775ae38b0abf019e3d6 PMC10899878 38419724 10_3389_fbioe_2024_1350135 |
| Genre | Journal Article |
| GeographicLocations | Germany |
| GeographicLocations_xml | – name: Germany |
| GroupedDBID | 53G 5VS 9T4 AAFWJ AAYXX ACGFS ADBBV ADRAZ AFPKN ALMA_UNASSIGNED_HOLDINGS AOIJS BAWUL BCNDV CITATION DIK GROUPED_DOAJ GX1 HYE KQ8 M48 M~E OK1 PGMZT RPM ACXDI IPNFZ NPM RIG 3V. 7X7 7XB 88E 8FE 8FH 8FI 8FJ 8FK ABUWG AFKRA AZQEC BBNVY BENPR BHPHI CCPQU DWQXO FYUFA GNUQQ HCIFZ K9. LK8 M1P M7P PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQGLB PQQKQ PQUKI PRINS 7X8 5PM |
| ID | FETCH-LOGICAL-c497t-41b65daf9e0c8849ea3e50ebd30a71ffc0e2b96f130ad8d9d4636a9c3d7f18e03 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 10 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001174144000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2296-4185 |
| IngestDate | Fri Oct 03 12:43:59 EDT 2025 Tue Sep 30 17:10:04 EDT 2025 Fri Sep 05 11:49:13 EDT 2025 Thu Nov 20 01:07:04 EST 2025 Thu Apr 03 07:01:00 EDT 2025 Sat Nov 29 05:43:18 EST 2025 Tue Nov 18 21:30:57 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | deep learning spine data augmentation machine learning variational autoencoder statistical parametric mapping |
| Language | English |
| License | Copyright © 2024 Dindorf, Dully, Konradi, Wolf, Becker, Simon, Huthwelker, Werthmann, Kniepert, Drees, Betz and Fröhlich. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c497t-41b65daf9e0c8849ea3e50ebd30a71ffc0e2b96f130ad8d9d4636a9c3d7f18e03 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 Edited by: Zhen (Jeff) Luo, University of Technology Sydney, Australia Reviewed by: Tianzhe Bao, University of Health and Rehabilitation Sciences, China These authors have contributed equally to this work and share senior authorship Chang Won Jeong, Wonkwang University, Republic of Korea |
| OpenAccessLink | https://doaj.org/article/e094bdc6255b4775ae38b0abf019e3d6 |
| PMID | 38419724 |
| PQID | 3273046620 |
| PQPubID | 7426804 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_e094bdc6255b4775ae38b0abf019e3d6 pubmedcentral_primary_oai_pubmedcentral_nih_gov_10899878 proquest_miscellaneous_2933460155 proquest_journals_3273046620 pubmed_primary_38419724 crossref_citationtrail_10_3389_fbioe_2024_1350135 crossref_primary_10_3389_fbioe_2024_1350135 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-02-14 |
| PublicationDateYYYYMMDD | 2024-02-14 |
| PublicationDate_xml | – month: 02 year: 2024 text: 2024-02-14 day: 14 |
| PublicationDecade | 2020 |
| PublicationPlace | Switzerland |
| PublicationPlace_xml | – name: Switzerland – name: Lausanne |
| PublicationTitle | Frontiers in bioengineering and biotechnology |
| PublicationTitleAlternate | Front Bioeng Biotechnol |
| PublicationYear | 2024 |
| Publisher | Frontiers Media SA Frontiers Media S.A |
| Publisher_xml | – name: Frontiers Media SA – name: Frontiers Media S.A |
| References | Lashgari (B32) 2020; 346 Yang (B58) 2021; 21 Huang (B22) 2023; 120 Lau (B33) 2009; 28 Liu (B34) 2020; 8 Halilaj (B18) 2018; 81 Pandit (B44) 2019 Luo (B36) 2020; 8 Takeishi (B52) 2021 Tu (B53) 2020 Chollet (B9) 2015 Zhao (B65) 2017 Yukawa (B61) 2018; 27 Barnes (B4) 2015; 45 Kiprijanovska (B28) 2020; 20 Kneifl (B29) 2023; 93 Kang (B27) 2021; 28 Zaroug (B62) 2020; 8 Dindorf (B15); 13 Saxena (B49) 2022; 54 Abadi (B1) 2016 Mohan (B42) 2019; 7 Yang (B59) 2022; 33 Dindorf (B13); 24 Horst (B20) 2019; 9 Tunca (B54) 2020; 24 Nguyen (B43) 2018 Hernandez (B19) 2020; 103 Yee (B60) 2021 Ceyssens (B8) 2019; 49 Horst (B21) 2021; 8 Martinez (B39) 2020; 24 Wahid (B56) 2015; 19 Zhou (B67) 2019 Bzdok (B7) 2018; 15 Ballabio (B3) 2019; 31 Deng (B10) 2009 Hussain (B24) 2020; 132 Zhao (B64) 2017 Valamatos (B55) 2022; 19 Phinyomark (B47) 2018; 38 Zhao (B66) 2019; 33 Dindorf (B12); 21 Landis (B31) 1977; 33 Alzubaidi (B2) 2023; 10 Dindorf (B11); 20 Paragliola (B45) 2021 Song (B51) 2020 Marchi (B38) 2015 Sharifi Renani (B50) 2021; 21 Bicer (B6) 2022; 144 Huthwelker (B25) 2023; 88 Mahmud (B37) 2020; 19 Wan (B57) 2017 Mohammadian Rad (B41) 2018; 18 Bayer (B5) 2023; 14 Elkholy (B16) 2019 Ferreira (B17) 2016; 30 Hunter (B23) 2007; 9 Prost (B48) 2021; 30 Dindorf (B14) Pedregosa (B46) 2011 Zhao (B63) 2015 Kornish (B30) 2018 McInnes (B40) 2018 Ludwig (B35) 2023; 20 Iglesias (B26) 2023 |
| References_xml | – volume: 144 start-page: 111301 year: 2022 ident: B6 article-title: Generative deep learning applied to biomechanics: a new augmentation technique for motion capture datasets publication-title: J. Biomech. doi: 10.1016/j.jbiomech.2022.111301 – volume: 8 start-page: 188429 year: 2020 ident: B34 article-title: Synthesizing foot and ankle kinematic characteristics for lateral collateral ligament injuries detection publication-title: IEEE Access doi: 10.1109/access.2020.3029616 – volume: 45 start-page: 37 year: 2015 ident: B4 article-title: Strategies to improve running economy publication-title: Sports Med. doi: 10.1007/s40279-014-0246-y – volume: 54 start-page: 1 year: 2022 ident: B49 article-title: Generative adversarial networks (GANs) publication-title: ACM Comput. Surv. doi: 10.1145/3446374 – volume: 20 start-page: 5373 year: 2020 ident: B28 article-title: Detection of gait abnormalities for fall risk assessment using wrist-worn inertial sensors and deep learning publication-title: Sensors doi: 10.3390/s20185373 – volume: 30 start-page: 2520 year: 2021 ident: B48 article-title: Description of spine motion during gait in normal adolescents and young adults publication-title: Eur. Spine J. doi: 10.1007/s00586-021-06918-w – volume: 19 start-page: 1794 year: 2015 ident: B56 article-title: Classification of Parkinson's disease gait using spatial-temporal gait features publication-title: IEEE J. Biomed. Health Inf. doi: 10.1109/JBHI.2015.2450232 – year: 2017 ident: B65 article-title: Learning discourse-level diversity for neural dialog models using conditional variational autoencoders doi: 10.18653/v1/P17-1061 – year: 2017 ident: B64 article-title: Towards deeper understanding of variational autoencoding models – volume-title: ImageNet: a large-scale hierarchical image database year: 2009 ident: B10 article-title: ImageNet: a large-scale hierarchical image database doi: 10.1109/CVPR.2009.5206848 – volume: 21 start-page: 1906 year: 2021 ident: B58 article-title: Novel soft smart shoes for motion intent learning of lower limbs using LSTM with a convolutional autoencoder publication-title: IEEE Sensors J. doi: 10.1109/jsen.2020.3019053 – volume: 24 start-page: 1994 year: 2020 ident: B54 article-title: Deep learning for fall risk assessment with inertial sensors: utilizing domain knowledge in spatio-temporal gait parameters publication-title: IEEE J. Biomed. Health Inf. doi: 10.1109/JBHI.2019.2958879 – volume: 13 start-page: 177 ident: B15 article-title: Feature extraction and gait classification in hip replacement patients on the basis of kinematic waveform data publication-title: Biomed. Hum. Kinet. doi: 10.2478/bhk-2021-0022 – volume-title: Information maximized variational domain adversarial learning for speaker verification year: 2020 ident: B53 article-title: Information maximized variational domain adversarial learning for speaker verification doi: 10.1109/ICASSP40776.2020.9053735 – volume: 33 start-page: 5885 year: 2019 ident: B66 article-title: InfoVAE: balancing learning and inference in variational autoencoders publication-title: AAAI doi: 10.1609/aaai.v33i01.33015885 – volume: 8 start-page: 32485 year: 2020 ident: B36 article-title: Multi-set canonical correlation analysis for 3D abnormal gait behaviour recognition based on virtual sample generation publication-title: IEEE Access doi: 10.1109/access.2020.2973898 – start-page: 452 volume-title: A deep learning-based approach for the classification of gait dynamics in subjects with a neurodegenerative disease year: 2021 ident: B45 article-title: A deep learning-based approach for the classification of gait dynamics in subjects with a neurodegenerative disease – volume: 8 start-page: 232 year: 2021 ident: B21 article-title: Gutenberg Gait Database, a ground reaction force database of level overground walking in healthy individuals publication-title: Sci. Data doi: 10.1038/s41597-021-01014-6 – volume: 19 start-page: 4074 year: 2022 ident: B55 article-title: Biomechanical performance factors in the track and field sprint start: a systematic review publication-title: Int. J. Environ. Res. Public Health doi: 10.3390/ijerph19074074 – volume: 9 start-page: 90 year: 2007 ident: B23 article-title: Matplotlib: a 2D graphics environment publication-title: Comput. Sci. Eng. doi: 10.1109/MCSE.2007.55 – volume: 28 start-page: 812 year: 2021 ident: B27 article-title: UMLS-based data augmentation for natural language processing of clinical research literature publication-title: J. Am. Med. Inf. Assoc. doi: 10.1093/jamia/ocaa309 – volume: 346 start-page: 108885 year: 2020 ident: B32 article-title: Data augmentation for deep-learning-based electroencephalography publication-title: J. Neurosci. Methods doi: 10.1016/j.jneumeth.2020.108885 – volume: 24 start-page: 144 year: 2020 ident: B39 article-title: Falls risk classification of older adults using deep neural networks and transfer learning publication-title: IEEE J. Biomed. Health Inf. doi: 10.1109/jbhi.2019.2906499 – volume: 93 start-page: 3637 year: 2023 ident: B29 article-title: Low-dimensional data-based surrogate model of a continuum-mechanical musculoskeletal system based on non-intrusive model order reduction publication-title: Arch. Appl. Mech. doi: 10.1007/s00419-023-02458-5 – volume-title: Abnormal gait detection by classifying inertial sensor data using transfer learning year: 2019 ident: B44 article-title: Abnormal gait detection by classifying inertial sensor data using transfer learning doi: 10.1109/ICMLA.2019.00236 – year: 2021 ident: B52 article-title: Variational autoencoder with differentiable physics engine for human gait analysis and synthesis – volume: 19 year: 2020 ident: B37 article-title: Variational autoencoder-based dimensionality reduction for high-dimensional small-sample data classification publication-title: Int. J. Comp. Intel. Appl. doi: 10.1142/S1469026820500029 – volume: 9 start-page: 2391 year: 2019 ident: B20 article-title: Explaining the unique nature of individual gait patterns with deep learning publication-title: Sci. Rep. doi: 10.1038/s41598-019-38748-8 – volume: 33 start-page: 159 year: 1977 ident: B31 article-title: The measurement of observer agreement for categorical data publication-title: Biometrics doi: 10.2307/2529310 – volume: 31 start-page: 129 year: 2019 ident: B3 article-title: Recent advances in high-level fusion methods to classify multiple analytical chemical data publication-title: Data Handl. Sci. Technol. doi: 10.1016/B978-0-444-63984-4.00005-3 – volume: 15 start-page: 233 year: 2018 ident: B7 article-title: Statistics versus machine learning publication-title: Nat. Methods doi: 10.1038/nmeth.4642 – volume: 18 start-page: 3533 year: 2018 ident: B41 article-title: Novelty detection using deep normative modeling for IMU-based abnormal movement monitoring in Parkinson's disease and autism spectrum disorders publication-title: Sensors doi: 10.3390/s18103533 – volume: 33 start-page: 2324 year: 2022 ident: B59 article-title: Memory-augmented generative adversarial networks for anomaly detection publication-title: IEEE Trans. Neural Netw. Learn Syst. doi: 10.1109/TNNLS.2021.3132928 – volume: 10 start-page: 46 year: 2023 ident: B2 article-title: A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications publication-title: J. Big Data doi: 10.1186/s40537-023-00727-2 – year: 2023 ident: B26 article-title: Data Augmentation techniques in time series domain: a survey and taxonomy 2023 – volume: 7 start-page: 246 year: 2019 ident: B42 article-title: Sex differences in the spine publication-title: Curr. Phys. Med. Rehabil. Rep. doi: 10.1007/s40141-019-00234-7 – volume: 21 start-page: 6323 ident: B12 article-title: Classification and automated interpretation of spinal posture data using a pathology-independent classifier and explainable artificial intelligence (XAI) publication-title: Sensors doi: 10.3390/s21186323 – volume: 49 start-page: 1095 year: 2019 ident: B8 article-title: Biomechanical risk factors associated with running-related injuries: a systematic review publication-title: Sports Med. doi: 10.1007/s40279-019-01110-z – volume: 30 start-page: 2069 year: 2016 ident: B17 article-title: Energetics, biomechanics, and performance in masters' swimmers: a systematic review publication-title: J. Strength Cond. Res. doi: 10.1519/jsc.0000000000001279 – year: 2018 ident: B40 article-title: UMAP: Uniform Manifold approximation and projection for dimension reduction – volume: 88 start-page: 103054 year: 2023 ident: B25 article-title: Reference values and functional descriptions of transverse plane spinal dynamics during gait based on surface topography publication-title: Hum. Mov. Sci. doi: 10.1016/j.humov.2022.103054 – volume: 20 start-page: 4131 year: 2023 ident: B35 article-title: Reference values for sagittal clinical posture assessment in people aged 10 to 69 years publication-title: Int. J. Environ. Res. Public Health doi: 10.3390/ijerph20054131 – volume-title: Unsupervised GEI-based gait disorders detection from different views year: 2019 ident: B16 article-title: Unsupervised GEI-based gait disorders detection from different views doi: 10.1109/EMBC.2019.8856294 – start-page: 265 volume-title: {TensorFlow}: a system for {Large-Scale} machine learning year: 2016 ident: B1 article-title: {TensorFlow}: a system for {Large-Scale} machine learning – volume: 24 start-page: 299 ident: B13 article-title: General method for automated feature extraction and selection and its application for gender classification and biomechanical knowledge discovery of sex differences in spinal posture during stance and gait publication-title: Comput. Methods Biomech. Biomed. Engin doi: 10.1080/10255842.2020.1828375 – start-page: 1 year: 2017 ident: B57 article-title: Variational autoencoder based synthetic data generation for imbalanced learning – volume-title: A novel approach for automatic acoustic novelty detection using a denoising autoencoder with bidirectional LSTM neural networks year: 2015 ident: B38 article-title: A novel approach for automatic acoustic novelty detection using a denoising autoencoder with bidirectional LSTM neural networks doi: 10.1109/ICASSP.2015.7178320 – year: 2015 ident: B9 publication-title: Keras – volume-title: Estimating skeleton-based gait abnormality index by sparse deep auto-encoder year: 2018 ident: B43 article-title: Estimating skeleton-based gait abnormality index by sparse deep auto-encoder doi: 10.1109/CCE.2018.8465714 – year: 2019 ident: B67 article-title: HYPE: a benchmark for human eYe perceptual evaluation of generative models – start-page: 3 volume-title: A novel approach to abnormal gait recognition based on generative adversarial networks year: 2020 ident: B51 article-title: A novel approach to abnormal gait recognition based on generative adversarial networks – year: 2015 ident: B63 article-title: Stacked what-where auto-encoders – volume: 28 start-page: 504 year: 2009 ident: B33 article-title: Support vector machine for classification of walking conditions of persons after stroke with dropped foot publication-title: Hum. Mov. Sci. doi: 10.1016/j.humov.2008.12.003 – volume-title: Systematic development of machine for abnormal muscle activity detection year: 2021 ident: B60 article-title: Systematic development of machine for abnormal muscle activity detection doi: 10.1109/CASE49439.2021.9551525 – volume: 103 start-page: 109684 year: 2020 ident: B19 article-title: Adversarial autoencoder for visualization and classification of human activity: application to a low-cost commercial force plate publication-title: J. Biomech. doi: 10.1016/j.jbiomech.2020.109684 – volume: 38 start-page: 244 year: 2018 ident: B47 article-title: Analysis of big data in gait biomechanics: current trends and future directions publication-title: J. Med. Biol. Eng. doi: 10.1007/s40846-017-0297-2 – volume: 120 start-page: 104046 year: 2023 ident: B22 article-title: Three-dimensional lumbar spine generation using variational autoencoder publication-title: Med. Eng. Phys. doi: 10.1016/j.medengphy.2023.104046 – volume: 20 start-page: 173 ident: B11 article-title: Conceptual structure and current trends in artificial intelligence, machine learning, and deep learning research in sports: a bibliometric review publication-title: Int. J. Environ. Res. Public Health doi: 10.3390/ijerph20010173 – volume: 27 start-page: 426 year: 2018 ident: B61 article-title: Normative data for parameters of sagittal spinal alignment in healthy subjects: an analysis of gender specific differences and changes with aging in 626 asymptomatic individuals publication-title: Eur. Spine J. doi: 10.1007/s00586-016-4807-7 – volume: 8 start-page: 362 year: 2020 ident: B62 article-title: Lower limb kinematics trajectory prediction using long short-term memory neural networks publication-title: Front. Bioeng. Biotechnol. doi: 10.3389/fbioe.2020.00362 – volume: 14 start-page: 135 year: 2023 ident: B5 article-title: Data augmentation in natural language processing: a novel text generation approach for long and short text classifiers publication-title: Int. J. Mach. Learn Cybern. doi: 10.1007/s13042-022-01553-3 – volume: 132 start-page: 353 year: 2020 ident: B24 article-title: High-content image generation for drug discovery using generative adversarial networks publication-title: Neural Netw. doi: 10.1016/j.neunet.2020.09.007 – volume-title: DCNN augmentation via synthetic data from variational autoencoders and generative adversarial networks year: 2018 ident: B30 article-title: DCNN augmentation via synthetic data from variational autoencoders and generative adversarial networks doi: 10.1109/AIPR.2018.8707390 – year: 2011 ident: B46 article-title: Scikit-learn: machine learning in Python – volume-title: Visualization of interindividual differences in spinal dynamics in the presence of intraindividual variabilities ident: B14 article-title: Visualization of interindividual differences in spinal dynamics in the presence of intraindividual variabilities doi: 10.36730/2022.1.levia.6 – volume: 81 start-page: 1 year: 2018 ident: B18 article-title: Machine learning in human movement biomechanics: best practices, common pitfalls, and new opportunities publication-title: J. Biomech. doi: 10.1016/j.jbiomech.2018.09.009 – volume: 21 start-page: 5876 year: 2021 ident: B50 article-title: The use of synthetic IMU signals in the training of deep learning models significantly improves the accuracy of joint kinematic predictions publication-title: Sensors doi: 10.3390/s21175876 |
| SSID | ssj0001257582 |
| Score | 2.3270307 |
| Snippet | Objective:
Biomechanical Machine Learning (ML) models, particularly deep-learning models, demonstrate the best performance when trained using extensive... Biomechanical Machine Learning (ML) models, particularly deep-learning models, demonstrate the best performance when trained using extensive datasets. However,... Objective: Biomechanical Machine Learning (ML) models, particularly deep-learning models, demonstrate the best performance when trained using extensive... |
| SourceID | doaj pubmedcentral proquest pubmed crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source |
| StartPage | 1350135 |
| SubjectTerms | Accuracy Artificial intelligence Asymptomatic Bioengineering and Biotechnology Biomechanics Data analysis data augmentation Data collection Datasets Deep learning Feasibility studies Gait Generative artificial intelligence Human mechanics Kinematics Learning algorithms Machine learning Posture spine statistical parametric mapping variational autoencoder |
| SummonAdditionalLinks | – databaseName: Biological Science Database dbid: M7P link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwELagcIAD70egICNxQ1GT2ElsLghQK05VDyD1ZvmZrrQky2ZbiX_BT2bG8YZdhHrhFsV2NMqM7W88428IecusNho8NnBTC5tzVpW5bgDIaS4tbypra-NisYn29FScn8uzdOA2prTK7ZoYF2o3WDwjP2Kwz4Iv11TFh9WPHKtGYXQ1ldC4SW4hSwKLqXtnO2csAEZENd2VAV9MHgWzGJAcs-JY8AHgT723H0Xa_n9hzb9TJnf2oJP7_yv9A3IvoU_6cTKXh-SG7x-RuzuchI_Jr-P-Ajk4-o7Gq_l4MxgVSb_HtEtPU52JjuIRLl1OF6QoZpq-p10kscZMagpgdBlJoOn4sweUiU-rYcSARexMMeO-m0dceYpGPPFZ0MUOUegT8u3k-OvnL3kq25BbLttNzkvT1E4H6QsrBJdeM18X3jhW6LYMwRa-MrIJsHtqJ5x0yFmmpWWuDaXwBXtKDvqh988JheUE3DnRVkG08CErhQi68Bi8tVyLJiPlVnnKJk5zLK2xVODboMJVVLhChauk8Iy8m8esJkaPa3t_QpuYeyIbd3wxrDuVJrcCgbhxFlzJ2vC2rbVnwhTaBMDPnjkQ83BrFSotEaP6YxIZeTM3w-TGiI3u_XA5KsBijDcIazPybDLAWRImOJaM4xkRe6a5J-p-S7-4iATiJcZ6RSteXC_XS3IHfwXmqJf8kBxs1pf-FbltrzaLcf06TrXfUDw32A priority: 102 providerName: ProQuest |
| Title | Enhancing biomechanical machine learning with limited data: generating realistic synthetic posture data using generative artificial intelligence |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/38419724 https://www.proquest.com/docview/3273046620 https://www.proquest.com/docview/2933460155 https://pubmed.ncbi.nlm.nih.gov/PMC10899878 https://doaj.org/article/e094bdc6255b4775ae38b0abf019e3d6 |
| Volume | 12 |
| WOSCitedRecordID | wos001174144000001&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: 2296-4185 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001257582 issn: 2296-4185 databaseCode: DOA dateStart: 20130101 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: 2296-4185 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001257582 issn: 2296-4185 databaseCode: M~E dateStart: 20130101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Biological Science Database customDbUrl: eissn: 2296-4185 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001257582 issn: 2296-4185 databaseCode: M7P dateStart: 20220101 isFulltext: true titleUrlDefault: http://search.proquest.com/biologicalscijournals providerName: ProQuest – providerCode: PRVPQU databaseName: Health & Medical Collection customDbUrl: eissn: 2296-4185 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001257582 issn: 2296-4185 databaseCode: 7X7 dateStart: 20220101 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2296-4185 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001257582 issn: 2296-4185 databaseCode: BENPR dateStart: 20220101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 2296-4185 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001257582 issn: 2296-4185 databaseCode: PIMPY dateStart: 20220101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Nb9QwELWgcIAD4ptAWRmJG4rqxE5sc6NoKziwihBIy8myHWe70pKtmm2l_ov-ZGacNMoiBBcuURTbkeMZx2884zeEvOXeOgsWG5ipzKeC51lqSwByVmgvytz7wtUx2YRcLNRyqatJqi-MCevpgfuBOwpgf7jaA0wvnJCysIErx6xrAJsEXkeybUA9E2Oq310BGKLy_pQMWGH6qHHrLdJi5gJTPQDwKfZWokjY_yeU-Xuw5GT1OXlIHgywkX7ou_uI3ArtY3J_Qib4hFzP21Mkz2hXNJ6pxyO9KAH6M8ZLBjokiFhR3Hulm_5kE8UQ0fd0FdmnMQSaAorcRPZm2l21AA_x7mzboachVqYYKr8aW1wGioPYE1HQ9YTh8yn5fjL_9vFTOuRbSL3QcpeKzJVFbRsdmFdK6GB5KFhwNWdWZk3jWcidLhtY9mytal0j2ZjVnteyyVRg_Bk5aLdteEEo_AfADlMyb5SEF3mtVGNZQK-rF1aVCcluxt74gYwcc2JsDBglKC8T5WVQXmaQV0LejW3OeiqOv9Y-RpGONZFGOz4A5TKDcpl_KVdCDm8UwgxzuzMcEB8TZZmzhLwZi2FWoqvFtmF70RkAUVyUiEcT8rzXn7EnXAnM9SYSovY0a6-r-yXt-jQyf2fopFVSvfwfH_eK3MMBwxD0TBySg935RXhN7vrL3bo7n5HbcinjVc3IneP5ovo6i3NshuGxFTyrPn-pfvwCDtswWg |
| linkProvider | Directory of Open Access Journals |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6VggQceD8CBYwEJxQ1iZ3EQUKIR6tWLaseitSb6zhOutKSLJttUf8Fv4TfyIyTLLsI9dYDtyhxIsv5ZjzjmfkG4BU3OtfosaGbGhhf8Cj0dYKGnBaZEUlkTJwXrtlEOhrJo6PsYA1-DbUwlFY56ESnqIvG0Bn5Jsd9Fn25JAreT7_71DWKoqtDC40OFnv2_Ae6bO273c_4f19H0fbW4acdv-8q4BuRpXNfhHkSF7rMbGCkFJnV3MaBzQse6DQsSxPYKM-SEpW7LmSRFUSppTPDi7QMpQ04fvcKXEUzIpIuVfBg6UwHjR8ZdbU56Ptlm2U-boiMMxLUYALNrXhl_3NtAv5l2_6dorm0523f_t9W6w7c6q1r9qETh7uwZut7cHOJc_E-_NyqT4hjpK6Yox6gymcCKvvm0kot6_toVIyOqNmkKwBjlEn7llWOpJsyxRka2xNHcs3a8xqtaLqaNi0FZNxgRhUF1eKNM8tISDu-DjZeIkJ9AF8vZUkewnrd1PYxMFSX6K7KNCplih8ymZSlDiwFp43QMvEgHMCiTM_ZTq1DJgp9NwKYcgBTBDDVA8yDN4t3ph1jyYWjPxIGFyOJbdzdaGaV6pWXwgmJvDDoKse5SNNYWy7zQOcl-geWFzjNjQGFqleBrfoDQQ9eLh6j8qKIlK5tc9oqtDW5SMhs9-BRB_jFTLgU1BJPeCBXRGFlqqtP6vGJI0gPKZYtU_nk4nm9gOs7h1_21f7uaO8p3KBloXz8UGzA-nx2ap_BNXM2H7ez507MGRxftqT8Boo5ltM |
| 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=Enhancing+biomechanical+machine+learning+with+limited+data%3A+generating+realistic+synthetic+posture+data+using+generative+artificial+intelligence&rft.jtitle=Frontiers+in+bioengineering+and+biotechnology&rft.au=Carlo+Dindorf&rft.au=Jonas+Dully&rft.au=J%C3%BCrgen+Konradi&rft.au=Claudia+Wolf&rft.date=2024-02-14&rft.pub=Frontiers+Media+S.A&rft.eissn=2296-4185&rft.volume=12&rft_id=info:doi/10.3389%2Ffbioe.2024.1350135&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_e094bdc6255b4775ae38b0abf019e3d6 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2296-4185&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2296-4185&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2296-4185&client=summon |