Loading...

Pool and accuracy based stream classification: A new ensemble algorithm on data stream classification using recurring concepts detection

Hosseini, M. J ; Sharif University of Technology

762 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/ICDMW.2011.137
  3. Abstract:
  4. 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
  5. Keywords:
  6. Concept drift ; Classification of data ; Classification process ; Concept drifts ; Conceptual clustering ; Data stream ; Ensemble algorithms ; Ensemble learning ; Learning process ; Recurring concepts ; Stream classification ; Stream mining ; Data communication systems ; Heuristic methods ; Lakes ; Learning systems ; Data mining
  7. Source: Proceedings - IEEE International Conference on Data Mining, ICDM, 11 December 2011 through 11 December 2011, Vancouver, BC ; 2011 , Pages 588-595 ; 15504786 (ISSN) ; 9780769544090 (ISBN)
  8. URL: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6137433