Pool and Accuracy Based Stream Classification: A New Ensemble Algorithm on Data Stream Classification Using Recurring Concepts Detection

One of the main challenges of data streams is the occurrence of concept drift. Concept drift is the change of target (or feature) distribution, and can occur in different types: sudden, gradual, incremental or recurring. Because of the forgetting mechanism existing in the data stream learning process, recurring concepts has received much attention recently, and became a challenging problem. This paper tries to exploit the existence of recurring concepts in the learning process and improve the classification of data streams. It uses a pool of concepts to detect the reoccurrence of a concept using two methods: a Bayesian, and a heuristic method. Two approaches are used in the classification process: active classifier and weighted classifier. Experimental results show the effectiveness of the proposed method with respect to the Conceptual Clustering and Prediction (CCP) framework.