Issue No. 10 - Oct. (2016 vol. 28)
Tahseen Al-Khateeb , Department of Computer Science, University of Texas at Dallas, TX 75080
Mohammad M. Masud , College of Information Technology, United Arab Emirates University, Al Ain, UAE
Khaled M. Al-Naami , Department of Computer Science, University of Texas at Dallas, TX 75080
Sadi Evren Seker , Department of Business, Istanbul Medeniyet University, Istanbul, Turkey
Ahmad M. Mustafa , Department of Computer Science, University of Texas at Dallas, TX 75080
Latifur Khan , Department of Computer Science, University of Texas at Dallas, TX 75080
Zouheir Trabelsi , College of Information Technology, United Arab Emirates University, Al Ain, UAE
Charu Aggarwal , IBM T.J. Watson Research Center, Yorktown Heights, New YorkNY 10598
Jiawei Han , Department of Computer Science, University of Illinois at Urbana-Champaign, IL 61801
Streaming data is one of the attention receiving sources for concept-evolution studies. When a new class occurs in the data stream it can be considered as a new concept and so the concept-evolution. One attractive problem occurring in the concept-evolution studies is the recurring classes from our previous study. In data streams, a class can disappear and reappear after a while. Existing studies on data stream classification techniques either misclassify the recurring class or falsely identify the recurring classes as novel classes. Because of the misclassification or false novel classification, the error rates increases on those studies. In this paper we address the problem by defining a novel ensemble technique “class-based” ensemble which replaces the traditional “chunk-based” approach in order to detect the recurring classes. We discuss the details of two different approaches in class-based ensemble and explain and compare them in detail. Different than the previous studies in the field, we also prove the superiority of both “class-based” ensemble method over state-of-art techniques via empirical approach on a number of benchmark data sets including web comments as text mining challenge.
Data models, Electronic mail, Benchmark testing, Twitter, Market research, Decision trees, Error analysis
T. Al-Khateeb et al., "Recurring and Novel Class Detection Using Class-Based Ensemble for Evolving Data Stream," in IEEE Transactions on Knowledge & Data Engineering, vol. 28, no. 10, pp. 2752-2764, 2016.