Learning imbalanced classes in the presence of concept growth

Many practical scenarios see a concept growth problem rather than the well-known concept drift problem. Applications with imbalanced classes are also common, but the problem is seldom considered. This paper proposes a cognitively inspired classification system to handle the difficulties that arise, and shows marked improvements in the classification results.

[1]  Edwin Lughofer.  A dynamic split-and-merge approach for evolving cluster models , 2012, Evol. Syst..

[2]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[3]  R. Polikar,et al.  Incremental learning from unbalanced data , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[4]  Haibo He,et al.  Towards incremental learning of nonstationary imbalanced data stream: a multiple selectively recursive approach , 2011, Evol. Syst..

[5]  J. Kruschke,et al.  ALCOVE: an exemplar-based connectionist model of category learning. , 1992, Psychological review.

[6]  Pedro M. Domingos.  MetaCost: a general method for making classifiers cost-sensitive , 1999, KDD '99.

[7]  Marcus A. Maloof,et al.  Dynamic weighted majority: a new ensemble method for tracking concept drift , 2003, Third IEEE International Conference on Data Mining.

[8]  Ralf Klinkenberg,et al.  Learning drifting concepts: Example selection vs. example weighting , 2004, Intell. Data Anal..

[9]  L. Rips.  Similarity, typicality, and categorization , 1989 .

[10]  B. Matthews.  Comparison of the predicted and observed secondary structure of T4 phage lysozyme. , 1975, Biochimica et biophysica acta.

[11]  Marcus A. Maloof,et al.  Dynamic Weighted Majority: An Ensemble Method for Drifting Concepts , 2007, J. Mach. Learn. Res..

[12]  Nathalie Japkowicz,et al.  The class imbalance problem: A systematic study , 2002, Intell. Data Anal..

[13]  Avrim Blum,et al.  Empirical Support for Winnow and Weighted-Majority Algorithms: Results on a Calendar Scheduling Domain , 2004, Machine Learning.

[14]  A. Vandierendonck,et al.  A parallel rule activation and rule synthesis model for generalization in category learning , 1995, Psychonomic bulletin & review.

[15]  Pierre Baldi,et al.  Assessing the accuracy of prediction algorithms for classification: an overview , 2000, Bioinform..

[16]  Philip S. Yu,et al.  A General Framework for Mining Concept-Drifting Data Streams with Skewed Distributions , 2007, SDM.

[17]  Shai Ben-David,et al.  Detecting Change in Data Streams , 2004, VLDB.

[18]  Plamen P. Angelov,et al.  Handling drifts and shifts in on-line data streams with evolving fuzzy systems , 2011, Appl. Soft Comput..

[19]  Stan Matwin,et al.  Addressing the Curse of Imbalanced Training Sets: One-Sided Selection , 1997, ICML.

[20]  Kezhi Mao,et al.  Cognitively inspired classification for adapting to data distribution changes , 2012, 2012 IEEE Conference on Evolving and Adaptive Intelligent Systems.

[21]  JapkowiczNathalie,et al.  The class imbalance problem: A systematic study , 2002 .

[22]  Haibo He,et al.  SERA: Selectively recursive approach towards nonstationary imbalanced stream data mining , 2009, 2009 International Joint Conference on Neural Networks.

[23]  Anton Dries,et al.  Adaptive concept drift detection , 2009, SDM.

[24]  Nitesh V. Chawla,et al.  An Incremental Learning Algorithm for Non-Stationary Environments and Class Imbalance , 2010 .

[25]  R. Nosofsky,et al.  Rule-plus-exception model of classification learning. , 1994, Psychological review.

[26]  J. Kruschke,et al.  Rule-based extrapolation in perceptual categorization , 2002, Psychonomic bulletin & review.

[27]  Marcos Salganicoff,et al.  Tolerating Concept and Sampling Shift in Lazy Learning Using Prediction Error Context Switching , 1997, Artificial Intelligence Review.