Abstract
This paper presents a novel ensemble classifier system designed to process data streams featuring occasional changes in their characteristics (concept drift). The ensemble is especially effective when the concepts reappear (recurring context). The system collects information on emerging contexts in a pool of elementary classifiers trained on subsequent data chunks. The pool is updated only when concept drift is detected. In contrast to other ensemble solutions, classifiers are not removed from the pool, and therefore, knowledge of past contexts is preserved for future use. To ensure high classification performance, the number of classifiers contributing to decision-making is fixed and limited. Only selected elements from the pool can join the decision-making ensemble. The process of selecting classifiers and adjusting their weights is realized by an evolutionary-based optimization algorithm that aims to minimize the system misclassification rate. Performance of the system is evaluated through a series of experiments presenting some key features of the system.
Similar content being viewed by others
References
Bifet A (2009) Adaptive learning and mining for data streams and frequent patterns. PhD thesis, Universitat Politecnica de Catalunya
Widmer G, Kubat M (1996) Learning in the presence of concept drift and hidden contexts. Mach Learn 23(1): 69–101
Zliobait˙e I (2010) Adaptive training set formation. PhD thesis, Vilnius University, Lithuania
Hilas C (2009) Designing an expert system for fraud detection in private telecommunications networks. Expert Syst Appl 36(9):11559–11569
Black M, Hickey R (2002) Classification of customer call data in the presence of concept drift and noise, In: Soft-Ware 2002, Proceedings of the 1st International Conference on Computing in an Imperfect World, Springer, Berlin, pp 74–87
Delany SJ, Cunningham P, Tsymbal A (2005) A comparison of ensemble and case-based maintenance techniques for handling concept drift in spam filtering. Technical Report TCD-CS-2005-19, Trinity College Dublin
Cunningham P, Nowlan N (2003) A case-based approach to spam filtering that can track concept drift. In: ICCBR-2003 Workshop on Long-Lived CBR Systems. Springer, London, pp 3–16
Kelly MG, Hand DJ, Adams NM (1999) The impact of changing populations on classifier performance. In: Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining-KDD′99, ACM Press, New York, USA, pp 367–371
Markou M, Singh S (2003) Novelty detection: a review—part 1: statistical approaches. Signal Process 83:2481–2497
Widmer G, Kubat M (1993) Effective learning in dynamic environments by explicit context tracking. Proceedings of the 6th European Conference on Machine Learning ECML-1993, Springer. Lecture Notes Comput Sci 667:227–243
Kuncheva LI (2008) Classifier ensembles for detecting concept change in streaming data: overview and perspectives. In: Proceedings of the 2nd Workshop SUEMA, ECAI 2008, Patras, Greece, pp 5–9
Mak L-O, Krause P (2006) Detection and management of concept drift, machine learning and cybernetics. In: International Conference on, 2006, pp 3486–3491
Ouyang Z, Zhou M, Wang T, Wu Q (2009) Mining concept-drifting and noisy data streams using ensemble classifiers, artificial intelligence and computational intelligence, 2009. AICI’09. International Conference, vol 4, pp 360–364
Tsymbal A (2004) The problem of concept drift: definitions and related work, Technical Report TCD-CS-2004-15. Department of Computer Science, Trinity College Dublin, Ireland
Klinkenberg R, Renz I (1998) Adaptive information filtering: Learning in the presence of concept drifts. In: Learning for text categorization. AAAI Press, Marina del Rey, pp 33–40
Klinkenberg R (2004) Learning drifting concepts: example selection vs. example weighting. Intell data anal 8:281–300
Chen S, Wang H, Zhou S, Yu P (2008) Stop chasing trends: Discovering high order models in evolving data. In: Proceedings of the 24th International Conference on Data Engineering, 2008, pp 923–932
Kuncheva LI (2004) Classifier ensembles for changing environments. In: 5th International Workshop on Multiple Classifier Systems, MCS 04, LNCS, vol. 3077, Springer, Berlin, pp 1–15
Kuncheva LI (2004) Combining pattern classifiers. Methods and algorithms. Wiley, New York
Littlestone N, Warmuth MK (1994) The weighted majority algorithm. Inf Comput 108:212–261
Schlimmer J, Granger R (1986) Incremental learning from noisy data. Mach Learn 1(3):317–354
Aha DW, Kibler D, Albert MK (1991) Instance-based learning algorithms. Mach Learn 6(1):37–66
Ouyang Z, Gao Y, Zhao Z, Wang T (2011) Study on the classification of data streams with concept drift. In: 2011 Eighth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD), pp 1673–1677
Domingos P, Hulten G (2003) A general framework for mining massive data streams. J Comput Graph Stat 12:945–949
Polikar R, Udpa L, Udpa SS, Honavar V (2001) Learn++: An incremental learning algorithm for supervised neural networks. IEEE Trans Syst Man Cybern Part C Appl Rev 31(4): 497–508
Hulten G, Spencer L, Domingos P (2001) Mining time-changing data streams. In 7th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM Press, San Francisco, pp 97–106
Bifet A, Holmes G, Pfahringer B, Read J, Kranen P, Kremer Hardy, Jansen H, Seidl T (2011) MOA: a real-time analytics open source framework. ECML/PKDD 3:617–620
Bifet A, Holmes G, Pfahringer B, Kirkby R, Gavalda R (2009) New ensemble methods for evolving data streams. In: KDD’09 Proceedings of the 15th ACM SIGKDD international conference on knowledge discovery and data mining, ACM, pp 139–148
Chu F, Zaniolo C (20074) Fast and light boosting for adaptive mining of data streams. In: Dai H, Srikant R, Zhang C (eds) PAKDD. Springer, Berlin,*** pp 282–292
Bifet A, Gavalda R (2006) Learning from time-changing data with adaptive windowing. Technical report, Universitat Politecnica de Catalunya, 2006. (http://www.lsi.upc.edu/~abifet)
Lazarescu M, Venkatesh S, Bui H (2003) Using multiple windows to track concept drift. Technical report. Faculty of Computer Science, Curtin University
Kurlej B, Woźniak M (2011) Learning Curve in Concept Drift While Using Active Learning Paradigm. In: Bouchachia A (ed) Adaptive and Intelligent Systems. Springer Berlin Heidelberg, pp 98–106
Koychev I (2000) Gradual forgetting for adaptation to concept drift. In: Proceedings of ECAI 2000 Workshop Current Issues in Spatio-Temporal Reasoning, pp 101–106
Stanley K (2003) Learning concept drift with a committee of decision trees. Technical Report UT-AI-TR-03-302, Computer Sciences Department, University of Texas
Tsymbal A, Pechenizkiy M, Cunningham P, Puuronen S (2008) Dynamic integration of classifiers for handling concept drift. Inf Fusion 1:56–68
Shipp CA, Kuncheva LI (2002) Relationships between combination methods and measures of diversity in combining classifiers. Inf Fusion 3(2):135–148
Littlestone N, Warmuth M (1994) The weighted majority algorithm. Inf Comput 108(2):212–261
Jacobs RA, Jordan MI, Nowlan SJ, Hinton GE (1991) Adaptive mixtures of local experts. Neural Comput 3:79–87
Nikunj CO (2000) Online ensemble learning. In: AAAI/IAAI. AAAI Press/The MIT Press, USA
Rodriguez J, Kuncheva L (2008) Combining online classification approaches for changing environments. In: SSPR/SPR, vol 5342 of LNCS, Springer, Berlin, pp 520–529
Street N, Kim Y (2001) A streaming ensemble algorithm (sea) for large scale classification. In: KDD’01 Proceedings of the 7th ACM SIGKDD international conference on knowledge discovery and data mining, ACM, pp 377–382
Wang H, Fan W, Yu PS, Han J (2003) Mining concept-drifting data streams using ensemble classifiers. In: Getoor L, Senator TE, Domingos P, Faloutsos C (eds) KDD, ACM, pp 226–235
Kolter J, Maloof M (2003) Dynamic weighted majority: a new ensemble method for tracking concept drift. In: ICDM, IEEE, pp 123–130
Zliobaite I (2009) Learning under concept drift: an overview. Technical report, Vilnius University, Faculty of Mathematics and Informatics
Gaber MM, Yu PS (2006) Classification of changes in evolving data streams using online clustering result deviation. In: Third international workshop on knowledge discovery in data streams, Pittsburgh, PA, USA
Salganicoff M (1993) Density-adaptive learning and forgetting. In: Proceedings of the 10th International Conference on Machine Learning, pp 276–283
Klinkenberg R, Joachims T (2000) Detecting concept drift with support vector machines. In: Proceedings of the 17th international conference on machine learning (ICML), San Francisco, CA, USA, pp 487–494
Baena-Garcıa M, Campo-Avila J, Fidalgo R, Bifet A, Gavalda R, Morales-Bueno R (2006) Early drift detection method. In: 4th international workshop on knowledge discovery from data streams, pp 77–86
Kurlej B, Wozniak M (2012) Active learning approach to concept drift problem. Log J IGPL 20:550–559
Ramamurthy S, Bhatnagar R (2007) Tracking recurrent concept drift in streaming data using ensemble classifiers. In: Proceedings of the 6th international conference on machine learning and applications, pp 404–409
Sasthakumar R, Raj B (2007) Tracking recurrent concept drift in streaming data using ensemble classifiers. In: ICMLA’07 Proceedings of the 6th international conference on machine learning and applications, IEEE Computer Society, Washington, DC, pp 404–409
Turney P (1993) Exploiting context when learning to classify. In: Proceedings of the European conference on machine learning (ECML-93), pp 402–407
Widmer G (1997) Tracking context changes through meta-learning. Mach Learn 27(3):59–286
Gomes JB, Ruiz EM, Sousa PAC (2011) Learning recurring concepts from data streams with a context-aware ensemble. In: Proceedings of SAC, 2011, pp 994–999
Katakis I, Tsoumakas G, Vlahavas I (2010) Tracking recurring contexts using ensemble classifiers: an application to email filtering. Knowl Inf Syst 22(3):371–391
Hosseini MJ, Ahmadi Z, Beigy H (2011) Pool and accuracy based stream classification: a new ensemble algorithm on data stream classification using recurring concepts detection. In: 2011 IEEE 11th International Conference on Data Mining Workshops, pp 588–595
Bäck T, Fogel D, Michalewicz Z (1997) Handbook of evolutionary computation. Oxford University Press, Oxford
Jackowski K, Wozniak M (2010) Method of classifier selection using the genetic approach. Expert Syst 27(2):114–128
Alpaydin E (2004) Introduction to machine learning. The MIT Press, Cambridge
Duin RPW, Juszczak P, Paclik P, Pekalska E, de Ridder D, Tax DMJ (2004) PRTools4, a Matlab toolbox for pattern recognition, Delft University of Technology, The Netherlands
UCI Machine Learning Repository. http://www.archive.ics.uci.edu/ml/
Harries M (1999) Splice-2 comparative evaluation: electricity pricing, Technical report, The University of South Wales, Australia
Bifet A, Gavaldá R (2009) Adaptive learning from evolving data streams in IDA 2009
Dietterich TG (1998) Approximate statistical tests for comparing supervised classification learning algorithms. Neural Comput 10(7):1895–1924
Acknowledgments
This work was supported by The Polish National Science Centre under the grant N N519 576638 which is being realized in years 2010-2013.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Jackowski, K. Fixed-size ensemble classifier system evolutionarily adapted to a recurring context with an unlimited pool of classifiers. Pattern Anal Applic 17, 709–724 (2014). https://doi.org/10.1007/s10044-013-0318-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-013-0318-x