A Decision-Based Dynamic Ensemble Selection Method for Concept Drift
This work addresses concept drift detection for data stream classification problems, offering an incremental improvement over existing dynamic ensemble selection approaches.
The paper tackles concept drift detection in data streams by proposing an online dynamic ensemble selection method that focuses on the decision space rather than local knowledge, achieving the highest detection precision and lowest false alarms in artificial datasets, along with competitive classification accuracy in real-world datasets.
We propose an online method for concept driftdetection based on dynamic classifier ensemble selection. Theproposed method generates a pool of ensembles by promotingdiversity among classifier members and chooses expert ensemblesaccording to global prequential accuracy values. Unlike currentdynamic ensemble selection approaches that use only local knowl-edge to select the most competent ensemble for each instance,our method focuses on selection taking into account the decisionspace. Consequently, it is well adapted to the context of driftdetection in data stream problems. The results of the experimentsshow that the proposed method attained the highest detection pre-cision and the lowest number of false alarms, besides competitiveclassification accuracy rates, in artificial datasets representingdifferent types of drifts. Moreover, it outperformed baselines indifferent real-problem datasets in terms of classification accuracy.