Efficient k-NN implementation for real-time detection of cough events in smartphones
- Submitting institution
-
University of the West of Scotland
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 13100130
- Type
- D - Journal article
- DOI
-
10.1109/JBHI.2017.2768162
- Title of journal
- IEEE Journal of Biomedical and Health Informatics
- Article number
- -
- First page
- 1672
- Volume
- 22
- Issue
- 5
- ISSN
- 2168-2194
- Open access status
- Compliant
- Month of publication
- November
- Year of publication
- 2017
- URL
-
-
- Supplementary information
-
-
- 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
-
4
- Research group(s)
-
-
- Citation count
- 8
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Proposed an efficient optimisation of the k-NN algorithm achieving 18x speed-up over classic vp-trees and 560x over standard machine-learning implementations. Implementations are incorporated to the Smartcough App (https://smartcough.wordpress.com/) to achieve real-time detection in low-end smartphones and to enable self-training. 1.5 billion revenue semiconductor company Cirrus Logic funded a validation study to explore the app commercialisation(£30k). Collaboration with Regional Health System in Castilla León(Spain) has also resulted to app deployment app in a real clinical environment. Contacts:
Corporate Business Development Manager (Cirrus Logic)
Admissions Manager, Castilla León Health System(SACYL)
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -