Skip to content

Research at St Andrews

SLearn: shared learning human activity labels across multiple datasets

Research output: ResearchConference contribution


School/Research organisations


The research of sensor-based human activity recognition has been attracting increasing attention over years as it is playing an important role in various human-beneficiary applications such as ambient assistive living, health monitoring, and behaviour changing. Nowadays, the advancement of sensing and communication technologies has led to the possibility of collecting a large amount of sensor data, however, to build a reliable computational model and accurately recognise human activities we still need the annotations on sensor data. Acquiring high-quality, detailed, continuous annotations is a challenging task. In this paper, we explore the solution space on sharing annotated activities across different datasets in order to enhance the recognition accuracies. We have designed and developed two approaches: sharing training data and sharing classifiers towards addressing this challenge. We have validated the approach on three datasets and demonstrated their effectiveness in recognising activities only with annotations from as little as 0.1% of each dataset.


Original languageEnglish
Title of host publicationIEEE International Conference on Pervasive Computing and Communications
PublisherIEEE Computer Society
Number of pages10
StatePublished - 19 Mar 2018
EventIEEE International Conference on Pervasive Computing and Communications (PerCom) - Divani Caravel Hotel, Athens, Greece
Duration: 19 Mar 201823 Mar 2018


ConferenceIEEE International Conference on Pervasive Computing and Communications (PerCom)
Abbreviated titlePerCom
Internet address

    Research areas

  • Human activity recognition, Smart home, Active learning, Transfer learning, Uncertainty reasoning

Discover related content
Find related publications, people, projects and more using interactive charts.

View graph of relations

Related by author

  1. Wearable assistive technologies for autism: opportunities and challenges

    Mansouri Benssassi, E., Gomez, J-C., Boyd, L. E., Hayes, G. R. & Ye, J. 1 Sep 2017 (Accepted/In press) In : IEEE Pervasive Computing.

    Research output: Research - peer-reviewReview article

  2. Spatial awareness in pervasive ecosystems

    Dobson, S. A., Viroli, M., Fernandez-Marquez, J-L., Zambonelli, F., Stevenson, G. T., di Marzo Serugendo, G., Montagna, S., Pianini, D., Ye, J., Castelli, G. & Rosi, A. 7 Dec 2016 In : The Knowledge Engineering Review. 31, 4, p. 343-366

    Research output: Research - peer-reviewArticle

  3. A robust reputation-based location-privacy recommender system using opportunistic networks

    Zhao, Y., Ye, J. & Henderson, T. 1 Dec 2016 Proceedings of The 8th EAI International Conference on Mobile Computing, Applications and Services. ACM

    Research output: ResearchConference contribution

  4. Detecting abnormal events on binary sensors in smart home environments

    Ye, J., Stevenson, G. & Dobson, S. Dec 2016 In : Pervasive and Mobile Computing. 33, p. 32-49 23 p.

    Research output: Research - peer-reviewArticle

  5. Capturing social cues with imaging glasses

    Murray, L., Hands, P., Goucher, R. & Ye, J. 12 Sep 2016 Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct. New York, NY: ACM, p. 968-972 5 p.

    Research output: ResearchConference contribution

ID: 251864837