Files in this item
Discovery and recognition of emerging human activities using a hierarchical mixture of directional statistical models
Item metadata
dc.contributor.author | Fang, Lei | |
dc.contributor.author | Ye, Juan | |
dc.contributor.author | Dobson, Simon Andrew | |
dc.date.accessioned | 2019-03-14T11:30:09Z | |
dc.date.available | 2019-03-14T11:30:09Z | |
dc.date.issued | 2020-07-01 | |
dc.identifier | 258157119 | |
dc.identifier | 29f365f1-7133-4211-9588-7217227a270b | |
dc.identifier | 85086429531 | |
dc.identifier | 000543006000006 | |
dc.identifier.citation | Fang , L , Ye , J & Dobson , S A 2020 , ' Discovery and recognition of emerging human activities using a hierarchical mixture of directional statistical models ' , IEEE Transactions on Knowledge and Data Engineering , vol. 32 , no. 7 , pp. 1304 - 1316 . https://doi.org/10.1109/TKDE.2019.2905207 | en |
dc.identifier.issn | 1041-4347 | |
dc.identifier.other | ORCID: /0000-0002-2838-6836/work/68280955 | |
dc.identifier.other | ORCID: /0000-0001-9633-2103/work/70234151 | |
dc.identifier.uri | https://hdl.handle.net/10023/17284 | |
dc.description | Funding: UK EPSRC under grant number EP/N007565/1, “Science of Sensor Systems Software”. | en |
dc.description.abstract | Human activity recognition plays a significant role in enabling pervasive applications as it abstracts low-level noisy sensor data into high-level human activities, which applications can respond to. With more and more activity-aware applications deployed in real-world environments, a research challenge emerges - discovering and learning new activities that have not been pre-defined or observed in the training phase. This paper tackles this challenge by proposing a hierarchical mixture of directional statistical models. The model supports incrementally, continuously updating the activity model over time with the reduced annotation effort and without the need for storing historical sensor data. We have validated this solution on four publicly available, third-party smart home datasets, and have demonstrated up to 91.5 % accuracies of detecting and recognising new activities. | |
dc.format.extent | 13 | |
dc.format.extent | 1514378 | |
dc.language.iso | eng | |
dc.relation.ispartof | IEEE Transactions on Knowledge and Data Engineering | en |
dc.subject | Activity recogntiion | en |
dc.subject | Online learning | en |
dc.subject | Incremental learning | en |
dc.subject | Active learning | en |
dc.subject | Semi-supervised learding | en |
dc.subject | Mixture model | en |
dc.subject | von Mises-Fisher distribution | en |
dc.subject | Hierarchical mixture | en |
dc.subject | Pervasive computing | en |
dc.subject | Smart home | en |
dc.subject | QA75 Electronic computers. Computer science | en |
dc.subject | T Technology | en |
dc.subject | 3rd-DAS | en |
dc.subject | BDC | en |
dc.subject | R2C | en |
dc.subject | ~DC~ | en |
dc.subject.lcc | QA75 | en |
dc.subject.lcc | T | en |
dc.title | Discovery and recognition of emerging human activities using a hierarchical mixture of directional statistical models | en |
dc.type | Journal article | en |
dc.contributor.sponsor | EPSRC | en |
dc.contributor.institution | University of St Andrews. School of Computer Science | en |
dc.identifier.doi | 10.1109/TKDE.2019.2905207 | |
dc.description.status | Peer reviewed | en |
dc.identifier.grantnumber | EP/N007565/1 | en |
This item appears in the following Collection(s)
Items in the St Andrews Research Repository are protected by copyright, with all rights reserved, unless otherwise indicated.