Abstract | ||
---|---|---|
•Efficient implementation of computationally expensive Fisher’s Exact Test.•Three new concept drift detection methods based on Fisher’s Exact Test.•Tested against DDM, ECDD, SEED, FHDDM, and STEPD using two base classifiers.•Proposed methods are significantly superior to most other Detectors in accuracy.•Proposed methods have better Precision, Recall and F-Measure than the other methods. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1016/j.ins.2018.02.054 | Information Sciences |
Keywords | Field | DocType |
Concept drift,Data streams,Drift detection,Online learning,Statistical tests | Online learning,Data stream mining,Algorithm,Exact test,Concept drift,Software,Artificial intelligence,Detector,Statistical hypothesis testing,Machine learning,Mathematics,Sample size determination | Journal |
Volume | Issue | ISSN |
442 | C | 0020-0255 |
Citations | PageRank | References |
5 | 0.43 | 24 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Danilo Rafael de Lima Cabral | 1 | 16 | 0.93 |
Roberto S. M. Barros | 2 | 72 | 8.68 |