Repository logo
 
Publication

Interactive hybrid approach to combine machine and human intelligence for personalized rehabilitation assessment

2020Conference object Open access
Simple item page
dc.contributor.authorLee, Min Hun
dc.contributor.authorSiewiorek, Daniel P.
dc.contributor.authorSmailagic, Asim
dc.contributor.authorBernardino, Alexandre
dc.contributor.authorBermúdez i Badia, Sergi
dc.date.accessioned2022-07-20T14:52:03Z
dc.date.available2022-07-20T14:52:03Z
dc.date.issued2020
dc.description.abstractAutomated assessment of rehabilitation exercises using machine learning has a potential to improve current rehabilitation practices. However, it is challenging to completely replicate therapist’s deci sion making on the assessment of patients with various physical conditions. This paper describes an interactive machine learning approach that iteratively integrates a data-driven model with ex pert’s knowledge to assess the quality of rehabilitation exercises. Among a large set of kinematic features of the exercise motions, our approach identifies the most salient features for assessment using reinforcement learning and generates a user-specific analysis to elicit feature relevance from a therapist for personalized rehabilita tion assessment. While accommodating therapist’s feedback on fea ture relevance, our approach can tune a generic assessment model into a personalized model. Specifically, our approach improves performance to predict assessment from 0.8279 to 0.9116 average F1-scores of three upper-limb rehabilitation exercises (𝑝 < 0.01). Our work demonstrates that machine learning models with feature selection can generate kinematic feature-based analysis as expla nations on predictions of a model to elicit expert’s knowledge of assessment, and how machine learning models can augment with expert’s knowledge for personalized rehabilitation assessment.pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.citationLee, M. H., Siewiorek, D. P., Smailagic, A., Bernardino, A., & Bermúdez i Badia, S. (2020, April). Interactive hybrid approach to combine machine and human intelligence for personalized rehabilitation assessment. In Proceedings of the ACM Conference on Health, Inference, and Learning (pp. 160-169).pt_PT
dc.identifier.doi10.1145/3368555.3384452pt_PT
dc.identifier.urihttp://hdl.handle.net/10400.13/4439
dc.language.isoengpt_PT
dc.publisherACMpt_PT
dc.relationAHA: Augmented Human Assistance
dc.relationThe AHA project aims to develop a robotic assistance plataform for supporting healthy lifestyle and sustain active aging.
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/pt_PT
dc.subjectHuman-AI interactionpt_PT
dc.subjectExplainable AIpt_PT
dc.subjectInteractive machine learningpt_PT
dc.subjectPersonalizationpt_PT
dc.subjectDecision support systemspt_PT
dc.subjectStroke rehabilitation assessmentpt_PT
dc.subject.pt_PT
dc.subjectFaculdade de Ciências Exatas e da Engenhariapt_PT
dc.titleInteractive hybrid approach to combine machine and human intelligence for personalized rehabilitation assessmentpt_PT
dc.typeconference object
dspace.entity.typePublication
oaire.awardTitleAHA: Augmented Human Assistance
oaire.awardTitleThe AHA project aims to develop a robotic assistance plataform for supporting healthy lifestyle and sustain active aging.
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/5665-PICT/CMUP-ERI%2FHCI%2F0046%2F2013/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT//SFRH%2FBD%2F113694%2F2015/PT
oaire.citation.endPage169pt_PT
oaire.citation.startPage160pt_PT
oaire.citation.titleProceedings of the ACM Conference on Health, Inference, and Learningpt_PT
oaire.fundingStream5665-PICT
person.familyNameBermúdez i Badia
person.givenNameSergi
person.identifier239789
person.identifier.ciencia-idCA17-5E88-2B37
person.identifier.orcid0000-0003-4452-0414
person.identifier.ridC-8681-2018
person.identifier.scopus-author-id6506360007
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsopenAccesspt_PT
rcaap.typeconferenceObjectpt_PT
relation.isAuthorOfPublicationef8f1e3b-3c09-4817-80d0-d96aa88051a2
relation.isAuthorOfPublication.latestForDiscoveryef8f1e3b-3c09-4817-80d0-d96aa88051a2
relation.isProjectOfPublication15913ce4-5392-4ce6-ab2f-1b155da9c18d
relation.isProjectOfPublicationa7d87d10-aada-456c-8552-7896d28a2552
relation.isProjectOfPublication.latestForDiscoverya7d87d10-aada-456c-8552-7896d28a2552

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Interactive hybrid approach to combine machine and human intelligence for personalized rehabilitation assessment.pdf
Size:
998.7 KB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Publicações em Atas de Congressos/Conferências, etc.