Abstract
In this study, a comprehensive methodology for overcoming the design problem of the Fuzzy ARTMAP neural network is proposed. The issues addressed are the sequence of training data for supervised learning and optimum parameter tuning for parameters such as baseline vigilance. A genetic algorithm search heuristic was chosen to solve this multi-objective optimization problem. To further augment the ARTMAP’s pattern classification ability, multiple ARTMAPs were optimized via genetic algorithm and assembled into a classifier ensemble. An optimal ensemble was realized by the inter-classifier diversity of its constituents. This was achieved by mitigating convergence in the genetic algorithms by employing a hierarchical parallel architecture. The best-performing classifiers were then combined in an ensemble, using probabilistic voting for decision combination. This study also integrated the disparate methods to operate within a single framework, which is the proposed novel method for creating an optimum classifier ensemble configuration with minimum user intervention. The methodology was benchmarked using popular data sets from UCI machine learning repository.
Similar content being viewed by others
References
Carpenter GA, Grossberg S, Marzukon N, Reynolds JH, Rosen DB (1992) Fuzzy ARTMAP: a neural network architecture for incremental supervised learning of analog multidimensional maps. IEEE Trans Neural Netw 3(5):698–713
Jin M, Li R, Xu Z, Zhao X (2014) Reliable fault diagnosis method using ensemble Fuzzy ARTMAP based on improved Bayesian belief method. Neurocomputing 133(10):309–316
Mokhtar M, Howe J (2013) Comparing the online learning capabilities of Gaussian ARTMAP and Fuzzy ARTMAP for building energy management systems. Expert Syst Appl 40(15):6007–6018
Tran VT, AlThobiani F, Ball A, Choi BK (2013) An application to transient current signal based induction motor fault diagnosis of Fourier–Bessel expansion and simplified fuzzy ARTMAP. Expert Syst Appl 40(13):5372–5384
Liang Z, Xu B, Chi Z, Feng D (2012) Intelligent characterization and evaluation of yarn surface appearance using saliency map analysis, wavelet transform and fuzzy ARTMAP neural network. Expert Syst Appl 39(4):4201–4212
Tan SC, Lim CP (2010) Evolutionary fuzzy artmap neural networks and their applications to fault detection and diagnosis. Neural Process Lett 31(3):219–242
Carpenter GA, Gaddam SC (2010) Biased ART: a neural architecture that shifts attention toward previously disregarded features following an incorrect prediction. Neural Netw 23(3):435–451
Dagher I, Georgiopoulos M, Heileman GL, Bebis G (1999) An ordering algorithm for pattern presentation in fuzzy ARTMAP that tends to improve generalization performance. IEEE Trans Neural Netw 10(4):768–778
Al-Daraiseh A, Georgiopoulos M, Anagnostopoulos G, Wu AS, Mollaghasemi M (2006) GFAM: a genetic algorithm optimization of fuzzy ARTMAP. In: Proceedings of the 2006 IEEE International Conference on Fuzzy Systems, pp 315–322
Granger E, Henniges P, Oliveira L, Sabourin R (2006) Particle swarm optimization of fuzzy ARTMAP parameters. In: Proceedings of the 2006 International Joint Conference on Neural Networks, pp 2060–2067
Palaniappan R, Eswaran C (2009) Using genetic algorithm to select the presentation order of training patterns that improves simplified fuzzy ARTMAP classification performance. Appl Soft Comput 9(1):100–106
Cervantes L, Lee J, Lee J (2007) Agent-based approach to distributed ensemble learning of Fuzzy ARTMAP classifiers. In: Jo GS et al (eds) Agent and multi-agent systems: technologies and applications. Springer, Berlin, pp 805–814
de Medeiros Santos A, de Paula Canuto AM (2008) Using ARTMAP-based ensemble systems designed by three variants of boosting. In: Kurkova-Pohlova V et al (eds) Artificial neural networks—ICANN 2008. Springer, Berlin, pp 562–571
Williamson JR (1996) Gaussian ARTMAP: a neural network for fast incremental learning of noisy multidimensional maps. Neural Netw 9(5):881–897
Gómez-Sánchez E, Dimitriadis YA, Cano-Izquierdo JM, López-Coronado J (2002) \(\mu\)ARTMAP: use of mutual information for category reduction in fuzzy ARTMAP. IEEE Trans Neural Netw 13(1):58–69
Kaylani A, Georgiopoulos M, Mollaghasemi M, Anagnostopoulos GC (2008) MO-GART: multiobjective genetic ART architectures. In: Proceedings of the 2008 IEEE Congress on Evolutionary Computation, pp 1425–1432
Zhang Y, Ji H, Zhang W (2014) TPPFAM: use of threshold and posterior probability for category reduction in fuzzy ARTMAP. Neurocomputing 124:63–71
Fernández C, Valle C, Saravia F, Allende H (2012) Behavior analysis of neural network ensemble algorithm on a virtual machine cluster. Neural Comput Appl 21(3):535–542
Seera M, Lim CP, Nahavandi S, Loo CK (2014) Condition monitoring of induction motors: a review and an application of an ensemble of hybrid intelligent models. Expert Syst Appl 41(10):4891–4903
Seera M, Lim CP (2014) A hybrid intelligent system for medical data classification. Expert Syst Appl 41(5):2239–2249
Sesmero MP, Alonso-Weber JM, Gutiérrez G, Ledezma A, Sanchis A (2012) A new artificial neural network ensemble based on feature selection and class recoding. Neural Comput Appl 21(4):771–783
Hu JJ, Goodman ED (2002) The hierarchical fair-competition (HFC) model for parallel evolutionary algorithms. In: Proceedings of the 2002 IEEE Congress on Evolutionary Computation, pp 49–54
Zenobi G, Cunningham P (2001) Using diversity in preparing ensembles of classifiers based on different feature subsets to minimize generalization error. In: de Raedt L et al. (eds) Machine learning: ECML 2001, pp 576–587
Yang J, Honavar V (1998) Feature subset selection using a genetic algorithm. In: Liu H et al. (eds) Feature extraction, construction and selection, pp 117–136
Opitz DW (1999) Feature selection for ensembles. In: Proceedings of the 16th National Conference on Artificial Intelligence (AAAI-99), pp 379–384
Cunningham P (2000) Overfitting and diversity in classification ensembles based on feature selection. In: Computer Science Technical Report TCD-CS-2000-07, Trinity College Dublin, pp 1–8
Oliveira LS, Morita M, Sabourin R (2006) Feature selection for ensembles using the multi-objective optimization approach. In: Jin Y (ed) Multi-objective machine learning. Springer, Berlin, pp 49–74
Canuto AMP, Vale KMO, Feitosa A (2011) A reinforcement-based mechanism to select features for classifiers in ensemble systems. Int J Comput Inf Syst Ind Manag Appl 3:324–335
Lin X, Yacoub S, Burns J, Simske S (2003) Performance analysis of pattern classifier combination by plurality voting. Pattern Recognit Lett 24(12):1959–1969
Loo CK, Rao M (2005) Accurate and reliable diagnosis and classification using probabilistic ensemble simplified fuzzy ARTMAP. IEEE Trans Knowl Data Eng 17(11):1589–1593
Radtke PV, Sabourin R, Wong T, et al. (2006) Classification system optimization with multi-objective genetic algorithms. In: Tenth International Workshop on Frontiers in Handwriting Recognition
Ishibuchi H, Yamamoto T (2003) Evolutionary multiobjective optimization for generating an ensemble of fuzzy rule-based classifiers. In: Cantu-Paz E et al (eds) Genetic and evolutionary computation GECCO 2003. Springer, Berlin, pp 1077–1088
Mohamed MA, Hegazy AEF, Badr AA (2011) Evolutionary fuzzy ARTMAP approach for breast cancer diagnosis. Int J Comput Sci Netw Secur 11(4):77–84
Qasem SN, Shamsuddin SM, Zain AM (2012) Multi-objective hybrid evolutionary algorithms for radial basis function neural network design. Knowledge-Based Syst 27:475–497
Wu CH, Tzeng GH, Lin RH (2009) A Novel hybrid genetic algorithm for kernel function and parameter optimization in support vector regression. Expert Syst Appl 36:4725–4735
Frank A, Asuncion A (2011) UCI machine learning repository. http://archive.ics.uci.edu/ml
Dzeroski S, Zenko B (2002) Is combining classifiers better than selecting the best one? In: International Workshop and Conference on Machine Learning, pp 123–130
Partalas I, Tsoumakas G, Katakis I, Vlahavas I (2006) Ensemble pruning using reinforcement learning. In: Advances in artificial intelligence, Springer, pp 301–310
Zhang Y, Burer S, Street WN (2006) Ensemble pruning via semi-definite programming. J Mach Learn Res 7:1315–1338
Ordonez FJ, Ledezma A, Sanchis A (2008) Genetic approach for optimizing ensembles of classifiers. In: Proceedings of the Twenty-First International Florida Artificial Intelligence Research Society Conference (FLAIRS) Conference, pp 89–94
Wang SJ, Mathew A, Chen Y, Xi LF, Ma L, Lee J (2009) Empirical analysis of support vector machine ensemble classifiers. Expert Syst Appl 36(3):6466–6476
Wilcoxon F (1945) Individual comparisons by ranking methods. Biometrics 1(6):80–83
Dos Santos EM, Sabourin R, Maupin P (2009) Overfitting cautious selection of classifier ensembles with genetic algorithms. Inf Fus 10(2):150–162
Lofstrom T, Johansson U, Bostrom H (2009) Ensemble member selection using multi-objective optimization. In: IEEE 2009 Symposium on Computational Intelligence and Data Mining, IEEE, pp 245–251
Connolly JF, Granger E, Sabourin R (2012) Evolution of heterogeneous ensembles through dynamic particle swarm optimization for video-based face recognition. Pattern Recognit 45(7):2460–2477
Liu Y, Yao X, Higuchi T (2000) Evolutionary ensembles with negative correlation learning. IEEE Trans Evol Comput 4(4):380–387
Acknowledgments
This study was supported by University of Malaya Research Grant CG008-2013 and (UMRG) Project RG059-11ICT.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Loo, C.K., Liew, W.S., Seera, M. et al. Probabilistic ensemble Fuzzy ARTMAP optimization using hierarchical parallel genetic algorithms. Neural Comput & Applic 26, 263–276 (2015). https://doi.org/10.1007/s00521-014-1632-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-014-1632-y