Name
Title | ||
|---|---|---|
A differential evolution based method for tuning concept drift detectors in data streams. |
Abstract | ||
|---|---|---|
•Empirical method to guide users on how to choose a concept drift detector.•The method uses a differential evolution to tune the parameters of the detectors.•It is based on 11 well-known concept drift detection methods.•It was tested using two base classifiers: Naive Bayes and Hoeffding Tree.•It allowed for significant improvement in the performance of the tuned detectors. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1016/j.ins.2019.02.031 | Information Sciences |
Keywords | Field | DocType |
Concept drift detectors,Tuning,Differential evolution,Data stream,Online learning | Data stream mining,Parametrization,Naive Bayes classifier,Data stream,Algorithm,Concept drift,Differential evolution,Artificial intelligence,Detector,Mathematics,Machine learning,Bayes' theorem | Journal |
Volume | ISSN | Citations |
485 | 0020-0255 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Silas Garrido Teixeira de Carvalho Santos | 1 | 54 | 5.01 |
| Roberto S. M. Barros | 2 | 72 | 8.68 |
| Paulo Mauricio Goncalves | 3 | 32 | 3.33 |