Transfer Learning and Data Fusion Approach to Recognize Activities of Daily Life

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Activity recognition is a core domain within intelligent systems that utilizes the sensing devices available in an environment to identify human activity. Conventional solutions rely on machine-learning approaches and the assumption that the target scenario will Rit the algorithm training conditions, which raises the cost and effort of labelling data, as daily living environments are dynamic, unpredictable, and exposed to new activities. Hence, we take advantage of the ubiquitous presence of personal gadgets such as smart-watches combined with data fusion approaches to dynamically transfer learned knowledge across devices in a natural environment while performing daily living activities. In this paper, we focus on recognizing walking as an activity, which might enable carers or medical practitioners to monitor the risk of falling or suffering from a chronic disease whose progression is linked to a reduction in movement and mobility. Preliminary results show a 2% increase in activity recognition accuracy on the wearable approach, and a 10% improvement in accuracy when combining features from both wearable and environmental domains.
Original languageEnglish
Title of host publicationProceedings of the 12th EAI International Conference on Pervasive Computing Technologies for Healthcare
Place of PublicationNew York, USA
PublisherAssociation for Computing Machinery
Pages227-231
Number of pages5
ISBN (Print)978-1-4503-6450-8
Publication statusPublished - 17 Sep 2018
Event12th EAI International Conference on Pervasive Computing Technologies for Healthcare: PervasiveHealth '18 - New York, United States
Duration: 21 May 201824 May 2018
http://pervasivehealth.org/

Publication series

NameACM International Conference Proceeding Series
PublisherPublished by ACM

Conference

Conference12th EAI International Conference on Pervasive Computing Technologies for Healthcare
CountryUnited States
CityNew York
Period21/05/1824/05/18
Internet address

Keywords

  • Transfer learning
  • Activity recognition
  • Data fusion
  • Wearable devices

Fingerprint Dive into the research topics of 'Transfer Learning and Data Fusion Approach to Recognize Activities of Daily Life'. Together they form a unique fingerprint.

  • Cite this

    Hernandez-Cruz, N., Razzaq, M. A., Nugent, CD., McChesney, I., & Zhang, S. (2018). Transfer Learning and Data Fusion Approach to Recognize Activities of Daily Life. In Proceedings of the 12th EAI International Conference on Pervasive Computing Technologies for Healthcare (pp. 227-231). (ACM International Conference Proceeding Series). Association for Computing Machinery.