KCAR : a knowledge-driven approach for concurrent activity recognition
- Submitting institution
-
University of St Andrews
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 252030203
- Type
- D - Journal article
- DOI
-
10.1016/j.pmcj.2014.02.003
- Title of journal
- Pervasive and Mobile Computing
- Article number
- -
- First page
- 47
- Volume
- 19
- Issue
- -
- ISSN
- 1574-1192
- Open access status
- Out of scope for open access requirements
- Month of publication
- February
- Year of publication
- 2014
- 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
-
2
- Research group(s)
-
A - Artificial Intelligence
- Citation count
- 44
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Can we recognise individual human activities when we are observing several people independently performing different activities? This paper develops a qualified "yes" to this question, combining machine learning with semantic descriptions of the activities to allow them to be disambiguated as long as they are semantically distinct. It was the first paper to use a semantic model to segment a sensor data stream automatically, and demonstrates a large improvement in recognition performance.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
