Resample-Based Ensemble Framework for Drifting Imbalanced Data Streams
- Submitting institution
-
Birmingham City University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11Z_OP_D2015
- Type
- D - Journal article
- DOI
-
10.1109/access.2019.2914725
- Title of journal
- IEEE Access
- Article number
- -
- First page
- 65103
- Volume
- 7
- Issue
- -
- ISSN
- 2169-3536
- Open access status
- Compliant
- Month of publication
- May
- Year of publication
- 2019
- URL
-
https://ieeexplore.ieee.org/document/8706959
- 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
- 2
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Typically real-world data streams suffer from class imbalance and concept drift. The proposed method in this paper combines both block-based and online classification of data streams to overcome the shortcomings of previously proposed methods. Mainly, the proposed hybrid method overcomes the initial low performance of online methods, and the poor handling of sudden concept drifts by block-based methods. Such advantages make the method the first choice dealing with critical applications like cyber-attack detection, and continuous patient monitoring in intensive care units.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -