dc.contributor.authorAbu Alsheikh, Mohammad
dc.contributor.authorSelim, Ahmed
dc.contributor.authorNiyato, Dusit
dc.contributor.authorDoyle, Linda
dc.contributor.authorLin, Shaowei
dc.contributor.authorTan, Hwee-Pink
dc.date.accessioned2017-03-24T08:07:35Z
dc.date.available2017-03-24T08:07:35Z
dc.date.issued2016
dc.identifier.citationAbu Alsheikh, M., Selim, A., Niyato, D., Doyle, L., Lin, S., & Tan, H.-P. (2016). Deep activity recognition models with triaxial accelerometers. The Workshops of the Thirtieth AAAI Conference on Artificial Intelligence, 8-13.en_US
dc.identifier.urihttp://hdl.handle.net/10220/42197
dc.description.abstractDespite the widespread installation of accelerometers in almost all mobile phones and wearable devices, activity recognition using accelerometers is still immature due to the poor recognition accuracy of existing recognition methods and the scarcity of labeled training data. We consider the problem of human activity recognition using triaxial accelerometers and deep learning paradigms. This paper shows that deep activity recognition models (a) provide better recognition accuracy of human activities, (b) avoid the expensive design of handcrafted features in existing systems, and (c) utilize the massive unlabeled acceleration samples for unsupervised feature extraction. Moreover, a hybrid approach of deep learning and hidden Markov models (DL-HMM) is presented for sequential activity recognition. This hybrid approach integrates the hierarchical representations of deep activity recognition models with the stochastic modeling of temporal sequences in the hidden Markov models. We show substantial recognition improvement on real world datasets over state-of-the-art methods of human activity recognition using triaxial accelerometers.en_US
dc.format.extent7 p.en_US
dc.language.isoenen_US
dc.rights© 2016 Association for the Advancement of Artificial Intelligence (AAAI). This is the author created version of a work that has been peer reviewed and accepted for publication by The Workshops of the Thirtieth AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence (AAAI). It incorporates referee’s comments but changes resulting from the publishing process, such as copyediting, structural formatting, may not be reflected in this document. The published version is available at: [https://arxiv.org/abs/1511.04664].en_US
dc.subjectLearningen_US
dc.subjectHuman-Computer Interactionen_US
dc.titleDeep Activity Recognition Models with Triaxial Accelerometersen_US
dc.typeConference Paper
dc.contributor.conferenceThe Workshops of the Thirtieth AAAI Conference on Artificial Intelligenceen_US
dc.contributor.schoolSchool of Computer Science and Engineeringen_US
dc.description.versionAccepted versionen_US
dc.identifier.urlhttps://arxiv.org/abs/1511.04664


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record