Co-eye: a multi-resolution ensemble classifier for symbolically approximated time series
- Submitting institution
-
Birmingham City University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11Z_OP_D2002
- Type
- D - Journal article
- DOI
-
10.1007/s10994-020-05887-3
- Title of journal
- Machine Learning
- Article number
- -
- First page
- 2029
- Volume
- 109
- Issue
- 11
- ISSN
- 0885-6125
- Open access status
- Compliant
- Month of publication
- -
- Year of publication
- 2020
- 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
-
-
- Research group(s)
-
-
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The proposed time series classification method, co-eye, provides unique features, providing the community with a state-of-the-art algorithm which is open source (https://github.com/zabdallah/Co-eye). The method is evidently domain independent, having being tested on over 100 data sets from a wide range of applications. Since the method has shown special performance boost in the medical domain (e.g. ECG), an early exploration of the possibility of industrial engagement with medical device manufacturers is in discussion at the university.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -