Proposing a Features Preprocessing Method Based on Artificial Immune and Minimum Classification Errors Methods

 

M. Miralvand, S. Rasoolzadeh* and M. Majidi

 

Department of Computer Engineering Malayer Branch, Islamic Azad university Malayer, Iran. * Siam.rasoolzade@gmail.com

 

ABSTRACT

Artificial immune systems that have been inspired from organic immune systems, have drawn many attentions in recent years (and have been considered) as an evolutionary algorithm and have been applied in different papers. This algorithm can be used in two different areas of optimization and classification. In this paper, an artificial immune algorithm has been applied in optimization problem. In particular artificial immune systems have been used for computing the mapping matrices and improving features. Comparison of results of proposed method with other preprocessing methods shows the superiority of the proposed method so that in 90% of cases it has the best performance based on different measures. Evaluation measures are including classification rate, variance and compression measure.

Keywords: Artificial Immune Systems, Evolutionary Algorithm, Optimization Problem.

 

DESCARGAR ARTÍCULO EN FORMATO PDF

 

References

[1] Morasso, P. Spatial control arm movements. Exp. Brain Res., Vol. 42, pp. 223-227 (1981).         [ Links ]

[2] M. Ayara et al. "Negative Selection: How to Generate Detectors". In Proceedings of the 1st International Conference on Artificial Immune Systems (ICARIS). Canterbury, UK, 2002, pp. 89-98.         [ Links ]

[3] S.M. Garrett, "How Do We Evaluate Artificial Immune Systems?", Evolut. Comput. Vol. 13, No 2, 2005, pp.145-178.         [ Links ]

[4] A. Watkins and J. Timmis, "Artificial Immune Recognition System (AIRS): An Immuneinspired Supervised Learning Algorithm", Genet. Progr. Evol. Vol. 5, No 3,Mach. 2004, pp. 291-317.         [ Links ]

[5] M.S. Moin. "Optimized Linear Discriminant Analysis for Extracting Robust Speech Features", In Proceedings of the 3rd International Symposium on Communications Control and Signal Processing, 2008.         [ Links ]

[6] B Zamani et al. "Optimized Discriminative Transformations for Speech Features Based on Minimum Classification Error", Pattern Recognition Letters, Vol 32, No 7, 2011.         [ Links ]

[7] H. Moeinzadeh et al. "Improving Classification Accuracy Using Evolutionary Fuzzy Transformation", In Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation (GECCO), 2009, pp 2103-2108.         [ Links ]

[8] A. De La Torre et al. "An Application of Minimum Classification Error to Feature Space Transformation for Speech Recognition". Speech Communication, No. 20, 1996, pp. 273-290.         [ Links ]

[9] B Raahemi et al. "Exploiting Unlabeled Data to Improve Peer-to-Peer Traffic Classification Using Incremental Tri-training Method", Peer-to-Peer Networking and Applications, Vol. 2, No 2, 2009, pp 87-97.         [ Links ]

[10] M Mohammadi et al. "An Evolutionary Approach to Clustering Ensemble", In Proceedings of the Fourth International Conference on Natural Computation, 2008.         [ Links ]

[11] U Markowska-Kaczmar and B Kordas. "Multi-class Iteratively Refined Negative Selection Classifier", Applied Soft Computing, Vol 8, No 2, 2008, pp 972-984.         [ Links ]

[12] M Mohammadi et al. "Genetic-based Minimum Classification Error Mapping for Accurate Identifying Peer-to-Peer Applications in the Internet Traffic". Expert Syst. Appl. Vol 38, No 6, 2011, pp 6417-6423.         [ Links ]

[13] B. Raahemi et al. "Classification of Peer-to-Peer Traffic Using Neural Networks", In Proceedings of the Artificial Intelligence and Pattern Recognition, Orlando, USA, July 2007, pp.411-417.         [ Links ]

[14] B. Raahemi et al. "Peer-to-Peer IP Traffic Classification Using Decision Tree and IP Layer Attributes", Business Data Communications and Networks, Vol. 3, No 4, 2007, pp.60-74.         [ Links ]

[15] K. Dunn and J. Dunn "Well Separated Clusters and Optimal Fuzzy Partitions". Cybernetics , Vol 4, 1974, pp 95-104.         [ Links ]