Real-time gait classification for persuasive smartphone apps: Structuring the literature and pushing the limits

Basit Öğe Kaydı
dc.contributor.authorSchneider, Oliver
dc.contributor.authorMacLean, Karon E.
dc.contributor.authorAltun, Kerem
dc.contributor.authorKaruei, Idin
dc.contributor.authorWu, Michael Ming-An
dc.date.accessioned2021-05-15T12:50:27Z
dc.date.available2021-05-15T12:50:27Z
dc.date.issued2013
dc.departmentMühendislik ve Doğa Bilimleri Fakültesi, Makine Mühendisliği Bölümüen_US
dc.descriptionACM SIGART;ACM SIGCHI
dc.description18th International Conference on Intelligent User Interfaces, IUI 2013 -- 19 March 2013 through 22 March 2013 -- Santa Monica, CA -- 96418
dc.description.abstractPersuasive technology is now mobile and context-aware. Intelligent analysis of accelerometer signals in smartphones and other specialized devices has recently been used to classify activity (e.g., distinguishing walking from cycling) to encourage physical activity, sustainable transport, and other social goals. Unfortunately, results vary drastically due to differences in methodology and problem domain. The present report begins by structuring a survey of current work within a new framework, which highlights comparable characteristics between studies; this provided a tool by which we and others can understand the current state-of-the art and guide research towards existing gaps. We then present a new user study, positioned in an identified gap, that pushes limits of current success with a challenging problem: the real-time classification of 15 similar and novel gaits suitable for several persuasive application areas, focused on the growing phenomenon of exercise games. We achieve a mean correct classification rate of 78.1% of all 15 gaits with a minimal amount of personalized training of the classifier for each participant when carried in any of 6 different carrying locations (not known a priori). When narrowed to a subset of four gaits and one location that is known, this improves to means of 92.2% with and 87.2% without personalization. Finally, we group our findings into design guidelines and quantify variation in accuracy when an algorithm is trained for a known location and participant. Copyright © 2013 ACM.en_US
dc.identifier.doi10.1145/2449396.2449418
dc.identifier.endpage172en_US
dc.identifier.isbn9781450320559
dc.identifier.scopus2-s2.0-84875853568
dc.identifier.scopusqualityN/A
dc.identifier.startpage161en_US
dc.identifier.urihttps://doi.org/10.1145/2449396.2449418
dc.identifier.urihttps://hdl.handle.net/20.500.12939/1246
dc.indekslendigikaynakScopus
dc.institutionauthorAltun, Kerem
dc.language.isoen
dc.relation.ispartofInternational Conference on Intelligent User Interfaces, Proceedings IUI
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectActivity Detectionen_US
dc.subjectExercise Gamesen_US
dc.subjectGait Classificationen_US
dc.subjectMobileen_US
dc.subjectPersuasive Computingen_US
dc.subjectSurveyen_US
dc.titleReal-time gait classification for persuasive smartphone apps: Structuring the literature and pushing the limits
dc.typeConference Object

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu
Makine Mühendisliği Bölümü Koleksiyonu