DC Field | Value | Language |
---|---|---|
dc.contributor.author | An, Sungtae | ko |
dc.contributor.author | Gazi, Asim H. | ko |
dc.contributor.author | Inan, Omer T. | ko |
dc.date.accessioned | 2022-11-28T08:01:21Z | - |
dc.date.available | 2022-11-28T08:01:21Z | - |
dc.date.created | 2022-11-28 | - |
dc.date.created | 2022-11-28 | - |
dc.date.issued | 2022-09 | - |
dc.identifier.citation | IEEE SENSORS JOURNAL, v.22, no.18, pp.17963 - 17976 | - |
dc.identifier.issn | 1530-437X | - |
dc.identifier.uri | http://hdl.handle.net/10203/301161 | - |
dc.description.abstract | Learning the route and order of tasks can be critical to human activity recognition (HAR) for fixed protocols of movement. In this article, we propose a novel framework, DynaLAP, a semi-supervised variational recurrent neural network (VRNN) with a dynamic prior distribution, to perform activity recognition in fixed protocols. DynaLAP takes single tri-axial accelerometry data as input and causally classifies the activity of 10-30-s windows at a time. DynaLAP learns not only a window-specific short-term state, but also a long-term dynamic state iteratively updated throughout the protocol's measurements. Additionally, instead of using a stationary prior distribution of activity classes, DynaLAP learns a dynamic prior that updates for each window. DynaLAP thereby learns protocol-specific dynamics when trained on data from subjects abiding by a fixed protocol. Two datasets from previously published literature were used to evaluate DynaLAP: the fully labeled MotionSense dataset of 24 subjects and a weakly labeled dataset of 17 subjects collected at the Georgia Institute of Technology. For each dataset, we varied the number of training labels used from a single subject's data to the entire dataset. DynaLAP outperformed previous supervised and semi-supervised HAR approaches by 6-42 percentage points, with F1 scores that remained above 80%. These results suggest that DynaLAP can achieve state-of-the-art HAR performance in fixed protocols by learning protocol-specific dynamics, especially in weakly and scarcely labeled settings. DynaLAP could ultimately reduce the necessity for labor-intensive annotation efforts in HAR applications involving routine activities (e.g., military training). | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | DynaLAP: Human Activity Recognition in Fixed Protocols via Semi-Supervised Variational Recurrent Neural Networks With Dynamic Priors | - |
dc.type | Article | - |
dc.identifier.wosid | 000880106500070 | - |
dc.identifier.scopusid | 2-s2.0-85135762329 | - |
dc.type.rims | ART | - |
dc.citation.volume | 22 | - |
dc.citation.issue | 18 | - |
dc.citation.beginningpage | 17963 | - |
dc.citation.endingpage | 17976 | - |
dc.citation.publicationname | IEEE SENSORS JOURNAL | - |
dc.identifier.doi | 10.1109/JSEN.2022.3194677 | - |
dc.contributor.localauthor | An, Sungtae | - |
dc.contributor.nonIdAuthor | Gazi, Asim H. | - |
dc.contributor.nonIdAuthor | Inan, Omer T. | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Activity recognition | - |
dc.subject.keywordAuthor | deep learning | - |
dc.subject.keywordAuthor | semi-supervised learning | - |
dc.subject.keywordAuthor | variational recurrent neural networks (VRNNs) | - |
dc.subject.keywordPlus | ACCELEROMETER | - |
dc.subject.keywordPlus | SENSORS | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.