DC Field | Value | Language |
---|---|---|
dc.contributor.author | 김지하 | - |
dc.contributor.author | 남윤호 | - |
dc.contributor.author | 이정은 | - |
dc.contributor.author | 서영주 | - |
dc.contributor.author | 황인석 | - |
dc.date.accessioned | 2023-11-02T00:20:55Z | - |
dc.date.available | 2023-11-02T00:20:55Z | - |
dc.date.created | 2023-10-31 | - |
dc.date.issued | 2023-09 | - |
dc.identifier.issn | 2474-9567 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/119014 | - |
dc.description.abstract | Although many works bring exercise monitoring to smartphone and smartwatch, inertial sensors used in such systems require device to be in motion to detect exercises. We introduce ProxiFit, a highly practical on-device exercise monitoring system capable of classifying and counting exercises even if the device stays still. Utilizing novel proximity sensing of natural magnetism in exercise equipment, ProxiFit brings (1) a new category of exercise not involving device motion such as lower-body machine exercise, and (2) a new off-body exercise monitoring mode where a smartphone can be conveniently viewed in front of the user during workouts. ProxiFit addresses common issues of faint magnetic sensing by choosing appropriate preprocessing, negating adversarial motion artifacts, and designing a lightweight yet noise-tolerant classifier. Also, application-specific challenges such as a wide variety of equipment and the impracticality of obtaining large datasets are overcome by devising a unique yet challenging training policy. We evaluate ProxiFit on up to 10 weight machines (5 lower- and 5 upper-body) and 4 free-weight exercises, on both wearable and signage mode, with 19 users, at 3 gyms, over 14 months, and verify robustness against user and weather variations, spatial and rotational device location deviations, and neighboring machine interference. | - |
dc.language | English | - |
dc.publisher | Association for Computing Machinery (ACM) | - |
dc.relation.isPartOf | Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies | - |
dc.title | ProxiFit: Proximity Magnetic Sensing Using a Single Commodity Mobile toward HolisticWeight Exercise Monitoring | - |
dc.type | Article | - |
dc.identifier.doi | 10.1145/3610920 | - |
dc.type.rims | ART | - |
dc.identifier.bibliographicCitation | Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, v.7, no.3, pp.1 - 32 | - |
dc.citation.endPage | 32 | - |
dc.citation.number | 3 | - |
dc.citation.startPage | 1 | - |
dc.citation.title | Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies | - |
dc.citation.volume | 7 | - |
dc.contributor.affiliatedAuthor | 김지하 | - |
dc.contributor.affiliatedAuthor | 남윤호 | - |
dc.contributor.affiliatedAuthor | 이정은 | - |
dc.contributor.affiliatedAuthor | 서영주 | - |
dc.contributor.affiliatedAuthor | 황인석 | - |
dc.identifier.scopusid | 2-s2.0-85173631226 | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.type.docType | Article | - |
dc.description.journalRegisteredClass | scopus | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.