A deep learning approach to on-node sensor data analytics for mobile or wearable devices
- Submitting institution
-
Imperial College of Science, Technology and Medicine
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2138
- Type
- D - Journal article
- DOI
-
10.1109/JBHI.2016.2633287
- Title of journal
- IEEE Journal of Biomedical and Health Informatics
- Article number
- -
- First page
- 56
- Volume
- 21
- Issue
- 1
- ISSN
- 2168-2208
- Open access status
- Compliant
- Month of publication
- December
- Year of publication
- 2016
- URL
-
-
- Supplementary information
-
10.1109/JBHI.2016.2633287
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- 133
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This novel deep learning method for accurate and real-time activity classification outperforms conventional deep learning approaches in terms of computation power requirements, enabling it to operate on mobile or wearable devices. The paper is one of the 50 most popular articles in IEEE Journal of Biomedical Health Informatics (https://ieeexplore.ieee.org/xpl/topAccessedArticles.jsp?punumber=6221020). It led to invitations to give keynote lectures including the IEEE EMBC 2019 Mini-Symposium on Emerging Technologies (https://bit.ly/3gzNYuk), and to a Microsoft Azure for Research Award 2018 (CRM: 0740767).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
