dc.contributor.author | Zeng, Ming | |
dc.contributor.author | Gao, Haoxiang | |
dc.contributor.author | Yu, Tong | |
dc.contributor.author | Mengshoel, Ole Jakob | |
dc.contributor.author | Langseth, Helge | |
dc.contributor.author | Lane, Ian | |
dc.contributor.author | Liu, Xiaobing | |
dc.date.accessioned | 2019-04-30T07:32:59Z | |
dc.date.available | 2019-04-30T07:32:59Z | |
dc.date.created | 2018-10-10T11:28:23Z | |
dc.date.issued | 2018 | |
dc.identifier.isbn | 978-1-4503-5967-2 | |
dc.identifier.uri | http://hdl.handle.net/11250/2596034 | |
dc.description.abstract | Deep neural networks, including recurrent networks, have been successfully applied to human activity recognition. Unfortunately, the final representation learned by recurrent networks might encode some noise (irrelevant signal components, unimportant sensor modalities, etc.). Besides, it is difficult to interpret the recurrent networks to gain insight into the models' behavior. To address these issues, we propose two attention models for human activity recognition: temporal attention and sensor attention. These two mechanisms adaptively focus on important signals and sensor modalities. To further improve the understandability and mean Fl score, we add continuity constraints, considering that continuous sensor signals are more robust than discrete ones. We evaluate the approaches on three datasets and obtain state-of-the-art results. Furthermore, qualitative analysis shows that the attention learned by the models agree well with human intuition. | nb_NO |
dc.language.iso | eng | nb_NO |
dc.publisher | Association for Computing Machinery (ACM) | nb_NO |
dc.relation.ispartof | Proceedings of the 2018 ACM International Symposium on Wearable Computers | |
dc.relation.uri | https://doi.org/10.1145/3267242.3267286 | |
dc.title | Understanding and Improving Recurrent Networks for Human Activity Recognition by Continuous Attention | nb_NO |
dc.title.alternative | Understanding and Improving Recurrent Networks for Human Activity Recognition by Continuous Attention | nb_NO |
dc.type | Chapter | nb_NO |
dc.description.version | acceptedVersion | nb_NO |
dc.source.pagenumber | 56-63 | nb_NO |
dc.identifier.doi | 10.1145/3267242.3267286 | |
dc.identifier.cristin | 1619300 | |
dc.description.localcode | © ACM, 2018. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published here, https://doi.org/10.1145/3267242.3267286 | nb_NO |
cristin.unitcode | 194,63,10,0 | |
cristin.unitname | Institutt for datateknologi og informatikk | |
cristin.ispublished | true | |
cristin.fulltext | original | |
cristin.qualitycode | 1 | |