A Meta-Bayesian Approach for Rapid Online Parametric Optimization for Wrist-based Interactions

dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorLiao, Yi-Chien_US
dc.contributor.authorDesai, Rutaen_US
dc.contributor.authorPierce, Alex M.en_US
dc.contributor.authorTaylor, Krista E.en_US
dc.contributor.authorBenko, Hrvojeen_US
dc.contributor.authorJonker, Tanya R.en_US
dc.contributor.authorGupta, Aakaren_US
dc.contributor.departmentDepartment of Information and Communications Engineeringen
dc.contributor.editorMueller, Florian Floyden_US
dc.contributor.editorKyburz, Pennyen_US
dc.contributor.editorWilliamson, Julie R.en_US
dc.contributor.editorSas, Corinaen_US
dc.contributor.editorWilson, Max L.en_US
dc.contributor.editorToups Dugas, Phoebeen_US
dc.contributor.editorShklovski, Irinaen_US
dc.contributor.groupauthorUser Interfacesen
dc.contributor.organizationMeta AI Researchen_US
dc.contributor.organizationMeta Reality Labsen_US
dc.date.accessioned2024-05-22T05:51:01Z
dc.date.available2024-05-22T05:51:01Z
dc.date.issued2024-05-11en_US
dc.description.abstractWrist-based input often requires tuning parameter settings in correspondence to between-user and between-session differences, such as variations in hand anatomy, wearing position, posture, etc. Traditionally, users either work with predefined parameter values not optimized for individuals or undergo time-consuming calibration processes. We propose an online Bayesian Optimization (BO)-based method for rapidly determining the user-specific optimal settings of wrist-based pointing. Specifically, we develop a meta-Bayesian optimization (meta-BO) method, differing from traditional human-in-the-loop BO: By incorporating meta-learning of prior optimization data from a user population with BO, meta-BO enables rapid calibration of parameters for new users with a handful of trials. We evaluate our method with two representative and distinct wrist-based interactions: absolute and relative pointing. On a weighted-sum metric that consists of completion time, aiming error, and trajectory quality, meta-BO improves absolute pointing performance by 22.92% and 21.35% compared to BO and manual calibration, and improves relative pointing performance by 25.43% and 13.60%.en
dc.description.versionPeer revieweden
dc.format.extent38
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationLiao, Y-C, Desai, R, Pierce, A M, Taylor, K E, Benko, H, Jonker, T R & Gupta, A 2024, A Meta-Bayesian Approach for Rapid Online Parametric Optimization for Wrist-based Interactions . in F F Mueller, P Kyburz, J R Williamson, C Sas, M L Wilson, P Toups Dugas & I Shklovski (eds), CHI '24: Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems ., 410, ACM, ACM SIGCHI Annual Conference on Human Factors in Computing Systems, Honolulu, Hawaii, United States, 11/05/2024 . https://doi.org/10.1145/3613904.3642071en
dc.identifier.doi10.1145/3613904.3642071en_US
dc.identifier.isbn979-8-4007-0330-0
dc.identifier.otherPURE UUID: 5d32137c-e16f-4a9b-8eed-220f0f3b3790en_US
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/5d32137c-e16f-4a9b-8eed-220f0f3b3790en_US
dc.identifier.otherPURE LINK: http://www.scopus.com/inward/record.url?scp=85194880854&partnerID=8YFLogxKen_US
dc.identifier.otherPURE FILEURL: https://research.aalto.fi/files/146008506/3613904.3642071.pdfen_US
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/127906
dc.identifier.urnURN:NBN:fi:aalto-202405223511
dc.language.isoenen
dc.relation.ispartofCHI '24: Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems
dc.relation.ispartofACM SIGCHI Annual Conference on Human Factors in Computing Systemsen
dc.rightsopenAccessen
dc.subject.keywordmeta-learningen_US
dc.subject.keywordtarget selectionen_US
dc.subject.keywordwrist-based interactionen_US
dc.subject.keywordhuman-in-the-loop optimizationen_US
dc.subject.keywordmeta-Bayesian optimizationen_US
dc.subject.keywordBayesian optimizationen_US
dc.subject.keywordadaptive interfaceen_US
dc.subject.keywordcalibrationen_US
dc.titleA Meta-Bayesian Approach for Rapid Online Parametric Optimization for Wrist-based Interactionsen
dc.typeA4 Artikkeli konferenssijulkaisussafi
dc.type.versionpublishedVersion

Files