Towards deep clustering of human activities from wearables

Alireza Abedin, Farbod Motlagh, Qinfeng Shi, Hamid Rezatofighi, Damith Ranasinghe

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

3 Citations (Scopus)

Abstract

Our ability to exploit low-cost wearable sensing modalities for critical human behaviour and activity monitoring applications in health and wellness is reliant on supervised learning regimes; here, deep learning paradigms have proven extremely successful in learning activity representations from annotated data. However, the costly work of gathering and annotating sensory activity datasets is labor intensive, time consuming and not scalable to large volumes of data. While existing unsupervised remedies of deep clustering leverage network architectures and optimization objectives that are tailored for static image datasets, deep architectures to uncover cluster structures from raw sequence data captured by on-body sensors remains largely unexplored. In this paper, we develop an unsupervised end-to-end learning strategy for the fundamental problem of human activity recognition (HAR) from wearables. Through extensive experiments, including comparisons with existing methods, we show the effectiveness of our approach to jointly learn unsupervised representations for sensory data and generate cluster assignments with strong semantic correspondence to distinct human activities.

Original languageEnglish
Title of host publicationProceedings of the 2020 ACM International Symposium on Wearable Computers
EditorsJennifer Healey, Thomas Ploetz
Place of PublicationNew York NY USA
PublisherAssociation for Computing Machinery (ACM)
Pages1-6
Number of pages6
ISBN (Electronic)9781450380775, 978145038077
DOIs
Publication statusPublished - 2020
Externally publishedYes
EventACM International Joint Conference on Pervasive and Ubiquitous Computing and ACM International Symposium on Wearable Computers, UbiComp/ISWC 2020 - Virtual Event, Mexico
Duration: 12 Sep 202017 Sep 2020
https://iswc.hosting2.acm.org/iswc20/ (Website)
https://dl.acm.org/doi/proceedings/10.1145/3410531 (Proceedings)

Publication series

NameProceedings - International Symposium on Wearable Computers, ISWC
PublisherThe Association for Computing Machinery
ISSN (Print)1550-4816

Conference

ConferenceACM International Joint Conference on Pervasive and Ubiquitous Computing and ACM International Symposium on Wearable Computers, UbiComp/ISWC 2020
Abbreviated titleUbiComp/ISWC’20
CountryMexico
Period12/09/2017/09/20
Internet address

Keywords

  • activity recognition
  • clustering
  • deep learning
  • wearable sensors

Cite this