Abstract
This paper proposes a framework to obtain ensembles of classifiers from a Multi-objective Evolutionary Algorithm (MOEA), improving the restrictions imposed by two non-cooperative performance measures for multiclass problems: (1) the Correct Classification Rate or Accuracy (CCR) and, (2) the Minimum Sensitivity (MS) of all classes, i.e., the lowest percentage of examples correctly predicted as belonging to each class with respect to the total number of examples in the corresponding class. The proposed framework is based on collecting Pareto fronts of Artificial Neural Networks models for multiclass problems by the Memetic Pareto Evolutionary NSGA2 (MPENSGA2) algorithm, and it builds a new Pareto front (ensemble) from stored fronts. The ensemble built significantly improves the closeness to the optimum solutions and the diversity of the Pareto front. For verifying it, the performance of the new front obtained has been measured with the habitual use of weighting methodologies, such as Majority Voting, Simple Averaging and Winner Takes All. In addition to CCR and MS measures, three trade-off measures have been used to obtain the goodness of a Pareto front as a whole: Hyperarea, Laumanns’s Hyperarea (LAUMANNS) and Zitzler’s Spread (M3). The proposed framework can be adapted for any MOEA that aims to improve the compaction and diversity of its Pareto front, and whose fitness functions impose severe restrictions for multiclass problems.
Similar content being viewed by others
References
Duda RO, Hart PE, Stork DG (2000) Pattern classification, 2nd edn. Wiley, New York
Bishop CM (2006) Pattern recognition and machine learning. Springer, New York
Kuncheva LI (2004) Combining patterns classifiers, methods and algorithms. Wiley, London
Rokach L (2010) Pattern classification using Ensemble Methods. Series in machine perception artificial intelligence. World Scientific Publishing Company, Singapore
Zhou ZH (2012) Ensemble methods, foundations and algorithms. CRC Press, Boca Raton
Mohapatra S, Patra D, Satpathy S (2014) An ensemble classifier system for early diagnosis of acute lymphoblastic leukemia in blood microscopic images. Neural Comput Appl 24(7–8):1887–1904
Vieira DAG, Vasconcelos JA, Caminhas WM (2007) Controlling the parallel layer perceptron complexity using a multiobjective learning algorithm. Neural Comput Appl 16(4–5):317–325
Ahmad F, Mat-Isa NA, Hussain Z, Sulaiman SN (2013) A genetic algorithm-based multi-objective optimization of an artificial neural network classifier for breast cancer diagnosis. Neural Comput Appl 23(5):1427–1435
Deb K (2004) Multi-objective optimization using evolutionary algorithms. Wiley-interscience series in systems and optimization. John Wiley & Sons, London
Loghmanian SMR, Jamaluddin H, Ahmad R, Yusof R, Khalid M (2012) Structure optimization of neural network for dynamic system modeling using multi-objective genetic algorithm. Neural Comput Appl 21(6):1281–1295
Albuquerque R, Pádua A, Takahashi RHC, Saldanha RR (2000) Improving generalization of MLPs with multi-objective optimization. Neurocomputing 35:189–194
Knowles J, Watson R, Corne D (2001) Reducing local optima in single-objective problems by multi-objectivization. In: Proceedings of the 1st international conference on evolutionary multi-criterion optimization, vol 1993. Springer, pp 269–283
Abbass HA (2003) Speeding up backpropagation using multiobjective evolutionary algorithms. Neural Comput 15:2705–2726
Tan KC, Khor EF, Lee TH (2006) Multiobjective evolutionary algorithms and applications. Advanced information and knowledge processing. Springer, London
Ghanem AS, Venkatesh S, West G (2010) Multi-class pattern classification in imbalanced data. In: Proceedings of the 20th international conference on pattern recognition (ICPR 2010), IEEE Press, pp 2881–2884
Wang S, Yao X (2012) Multiclass imbalance problems: analysis and potential solutions. IEEE Trans Syst Man Cybern B Cybern 42(4):1119–1130
Provost F, Fawcett T (1997) Analysis and visualization of the classifier performance: comparison under imprecise class and cost distribution. In: Proceedings of the third international conference on knowledge discovery (KDD97) and Data Mining, California, USA, August 1997, pp 43–48
Provost F, Fawcett T (1998) Robust classification system for imprecise environments. In: Proccedings of the fithteenth national conference on artificial intelligence, Chicago, USA, July 1998, pp 706–713
Yao X, Islam MM (2008) Evolving artificial neural network ensembles. IEEE Comput Intell Mag 3(1):31–42
Rahman MM, Islam MM, Murase K, Yao X (2016) Layered ensemble architecture for time series forecasting. IEEE Trans Cybern 46(1):270–283
Wang S, Minku LL, Yao X (2015) Resampling-based ensemble methods for online class imbalance learning. IEEE Trans Knownl Data Eng 27(5):1356–1368
Hsu CW, Lin CJ (2002) A comparison of methods for multi-class support vector machines. IEEE Trans Neural Netw 13(2):415–425
Sokolova M, Lapalme G (2009) A systematic analysis of performance measures for classification tasks. Inf Process Manag 45:427–437
Fernández JC, Martínez FJ, Hervás C, Gutiérrez PA (2010) Sensitivity versus accuracy in multi-class problems using memetic pareto evolutionary neural networks. IEEE Trans Neural Netw 21(5):750–770
Huband S, Hingston P, Barone L, While L (2006) A review of multiobjective test problems and a scalable test problem toolkit. IEEE Trans Evolut Comput 10(5):477–506
Paliwal M, Kumar UA (2009) Neural networks and statistical techniques: a review of applications. Expert Syst Appl 36:2–17
Rokach L (2009) Taxonomy for characterizing ensemble methods in classification tasks: a review and annotated bibliography. Comput Stat Data Anal 53:4046–4072
Brown G, Wyatt J, Harris R, Yao X (2005) Diversity creation methods: a survey and categorisation. Inf Fusion 6(1):5–20
Kuncheva LI, Whitaker CJ (2003) Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy. Mach Learn 51:181–207
Zhenan H, Gary GY (2011) An ensemble method for performance metrics in multiobjective evolutionary algorithms . In: Proccedings of the 2011 IEEE congress on evolutionary computation (CEC), pp 1724–1729
Woźniak M, Graña M, Corchado E (2014) A survey of multiple classifier systems as hybrid systems. Inf Fusion 16:3–17
Theodoridis S, Koutroumbas K (2006) Pattern recognition, 3rd edn. Elsevier, Academic Press, San Diego, USA
Jin Y, Sendhoff B (2008) Pareto-based multiobjective machine learning: an overview and case studies. IEEE Trans Syst Man Cybern C Appl Rev 38(3):397–415
Chandra A, Yao X (2004) DIVACE: Diverse and accurate ensemble learning algorithm. In: Proceedings of the fifth international conference on intelligent data engineering and automated learning, vol 3177 of Lectures Notes and Computer Science. Springer, Berlin, pp 619–625
Abbass HA (2003) Pareto neuro-evolution: constructive ensemble of neural networks using multi-objective optimization. In: IEEE congress on evolutionary computation CEC2003, IEEE press, vol 3. Canberra, Australia, pp 2074–2080
Hansen L, Salamon P (1990) Neural network emsembles. IEEE Trans Pattern Anal Mach Intell 12(10):993–1001
Liu Y, Yao X (1999) Ensemble learning via negative correlation. Neural Netw 12(10):1399–1404
Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140
Schapire RE (1999) A brief introduction to boosting. In: Proceedings of the 16th international joint conference on artificial intelligence, vol 2, pp 1401–1406
Liu Y, Yao X (1999) Simultaneous training of negatively correlated neural networks in an ensemble. IEEE Trans Syst Man Cybern B Cybern 29(6):716–725
Liu Y, Yao X (2000) Evolutionary ensembles with negative correlation learning. Trans Evolut Comput 4(4):380–387
Chen H, Yao X (2009) Multi-objective neural network ensembles based on regularized negative correlation learning. IEEE Trans Knowl Data Eng 22(12):1738–1751
Chen H, Yao X (2009) Regularized negative correlation learning for neural network ensembles. IEEE Trans Neural Netw 20(12):1962–1979
Abbass HA (2006) Pareto-optimal approaches to neuro-ensemble learning. In: Proceeding on studies in computational intelligence (SCI), vol 16. Springer, pp 407–427
Chandra A, Yao X (2006) Ensemble learning using multi-objective evolutionary algorithms. J Math Model Algorithms 5(4):417–445
Jin Y, Okabe T, Sendhoff B (2004) Evolutionary multi-objective approach to constructing neural network ensembles for regression, volume 1 of advances in natural computation. World Scientific, pp 653–672
Garcia-Pedrajas N, Hervas-Martinez C, Ortiz-Boyer D (2005) Cooperative coevolution of artificial neural network ensembles for pattern classification. IEEE Trans Evolut Comput 9(3):271–302
Minku FL, Ludemir TB (2008) Clustering and co-evolution to construct neural network ensembles: an experimental study. Neural Netw 21:1363–1379
Islam MM, Yao X (2003) A constructive algorithm for training cooperative neural networks ensembles. IEEE Trans Neural Netw 14(4):820–834
Jin Y, Okabe T, Sendhoff B (2004) Neural network regularization and ensembling using multi-objective evolutinary algorithms. In: Proceedings of the congress on evolutionary and ensembling using multi-objective evolutionary algorithms, vol 1. Portland, pp 1–8
Fieldsend JE, Singh S (2005) Pareto evolutionary neural networks. IEEE Trans Neural Netw 16(2):338–354
Jin Y, Sendholf B, Körner E (2006) Simultaneous generation of accurate and interpretable neural network classifiers. Stud Comput Intell 16:291–312
Yen GG (2006) Multiobjective evolutionary algorithm for radial basis function neural network design. Multi-objective machine learning. Studies in computational intelligence, vol 162. Springer, Berlin, Heidelberg, pp 221–239
Dong JR, Zheng CY, Kan GY, Zhao M, Wen J, Yu J (2015) Applying the ensemble artificial neural network-based hybrid data-driven model to daily total load forecasting. Neural Comput Appl 26(3):603–611
Escalante HJ, Montes y Gómez M, González JA, Gómez-Gil P, Altamirano L, Reta CA, Rosales A (2012) Acute leukemia classification by ensemble particle swarm model selection. Artif Intell Med 55:163–175
Escalante HJ, Montes M, Sucar E (2010) Ensemble particle swarm model selection. In: Proceedings of the international joint conference on neural networks (IJCNN 2010), pp 1814–1824, July 2010
Acosta-Mendoza N, Morales-Reyes A, Escalante HJ, Gago-Alonso A (2014) Learning to assemble classifiers via genetic programming. Int J Pattern Recognit Artif Intell 28(7):1460005
Wang P, Weise T, Chiong R (2011) Novel evolutionary algorithms for supervised classification problems: an experimental study. Evolut Intell 4:3–16
Wang X, Wang H (2006) Classification by evolutionary ensembles. Pattern Recognit 39(4):595–607
Everson RM, Fieldsend JE (2006) Multi-class ROC analysis from a multi-objetive optimisation perspective. Pattern Recognit Lett 27:918–927
Deb K, Pratab A, Agarwal S, Meyarivan T (2002) A fast and elitist multiobjective genetic algorithm: NSGA2. IEEE Trans Evolut Comput 6(2):182–197
Chen MR, Lu YZ, Yang G (2008) Multiobjective optimization using population-based extremal optimization. Neural Comput Appl 17(2):101–109
Basseur M, Zeng RQ, Hao JK (2012) Hypervolume-based multi-objective local search. Neural Comput Appl 21(8):1917–1929
Igel C, Hüsken M (2003) Empirical evaluation of the improved Rprop learning algorithms. Neurocomputing 50(6):105–123
Angeline PJ, Sauders GM, Pollack JB (1994) An evolutionary algorithm that constructs recurren neural networks. IEEE Trans Neural Netw 5:54–65
Lichman M (2013) UCI Machine learning repository. University of california, school of information and computer science, CA. Available online at http://archive.ics.uci.edu/ml.Irvine
Fernandez-Navarro F, Hervás-Martínez C, García-Alonso C, Torres-Jiménez M (2011) Determination of relative agrarian technical efficiency by a dynamic over-sampling procedure guided by minimum sensitivity. Expert Syst Appl 38(10):12483–12490
McGillivray M (2003) Commitment to development index: a critical appraisal. Technical report, AusAid
Sianes A, Dorado-Moreno M, Hervás-Martínez C (2014) Rating the rich: an ordinal classification to determine which rich countries are helping poorer ones the most. Soc Indic Res 116(1):47–65
Gutiérrez PA, Segovia-Vargas MJ, Salcedo-Sanz S, Hervás-Martínez C, Sanchis A, Portilla-Figueras JA, Fernandez-Navarro F (2010) Hybridizing logistic regression with product unit and RBF networks for accurate detection and prediction of banking crises. Omega 38(5):333–344
Yen GG, Zhenan H (2014) Performance metrics ensemble for multiobjective evolutionary algorithms. IEEE Trans Evolut Comput 18(1):131–144
Zitzler E, Thiele L (1999) Multiobjective evolutionary algorithms: a comparative case study and the strenght Pareto approach. IEEE Trans Neural Netw 3(4):414–417
Laumanns M, Zitzler E, Thiele L (2000) A unified model for multiobjective evolutionary algorithms with Elitism. In: 2000 congress on evolutionary computation, vol 1, pp 46–53
Demsar J (2006) Statistical comparisons of clasiffiers over multiple data sets. J Mach Learn Res 7:1–30
Acknowledgements
This work has been partially subsidized by the TIN2014-54583-C2-1-R project of the Spanish Ministry of Economy and Competitiveness (MINECO), FEDER funds and the P11-TIC-7508 project of the “Junta de Andalucía” (Spain).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Fernández, J.C., Cruz-Ramírez, M. & Hervás-Martínez, C. Sensitivity versus accuracy in ensemble models of Artificial Neural Networks from Multi-objective Evolutionary Algorithms. Neural Comput & Applic 30, 289–305 (2018). https://doi.org/10.1007/s00521-016-2781-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-016-2781-y