Name
Abstract | ||
|---|---|---|
•A novel concept drift detector for data streams is proposed.•The drift detector can be combined with an arbitrary classification algorithm.•The drift detector uses model explanation to detect concept drift.•The approach features good drift detection, accuracy, robustness and sensitivity.•Interpretable macro- and micro- visualization of concept drift is proposed. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1016/j.eswa.2017.10.003 | Expert Systems with Applications |
Keywords | Field | DocType |
Data stream,Concept drift,Explanation,Visualization | Data mining,Interpretability,Data stream mining,Visualization,Data stream,Computer science,Concept drift,Robustness (computer science),Artificial intelligence,Macro,Detector,Machine learning | Journal |
Volume | ISSN | Citations |
92 | 0957-4174 | 5 |
PageRank | References | Authors |
0.41 | 41 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jaka Demsar | 1 | 7 | 0.77 |
| Zoran Bosnic | 2 | 220 | 18.74 |
| DemarJaka | 3 | 5 | 0.41 |
| BosniZoran | 4 | 5 | 0.41 |