EWMA model based shift-detection methods for detecting covariate shifts in non-stationary environments
- Submitting institution
-
The University of Essex
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1224
- Type
- D - Journal article
- DOI
-
10.1016/j.patcog.2014.07.028
- Title of journal
- Pattern Recognition
- Article number
- 3
- First page
- 659
- Volume
- 48
- Issue
- 3
- ISSN
- 0031-3203
- Open access status
- Out of scope for open access requirements
- Month of publication
- August
- 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)
-
B - Brain Computer Interfaces and Neural Engineering (BCI-NE)
- Citation count
- 31
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Well-cited and published in PatternRecongnition, a top Machine-Learning journal, our paper on challenging covariate shift detection, important in the change-detection literature, proposed an unsupervised method to detect covariate-shifts in both univariate and multivariate streaming data using EWMA statistics. Rigorously tested on various toy/real-world datasets; significantly, it impacted a range of other topics. I have implemented this method further at the Ulster University MEG Lab for monitoring brain waves in online MEG/EEG-based brain-computer-interfacing system and it is used by the R(CRAN) package "otsad" (online time-series anomaly detectors in open source), used for load demand forecasting, credit market, etc.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -