Self organizing mixture network in mixture discriminant analysis: An experimental study

Autor: Çalis, N., Erişoǧlu, M., Erol, H., TAYFUN SERVI
Přispěvatelé: Çukurova Üniversitesi
Předmět:
Zdroj: Scopus-Elsevier
Popis: In the recent works related with mixture discriminant analysis (MDA), expectation and maximization (EM) algorithm is used to estimate parameters of Gaussian mixtures. But, initial values of EM algorithm affect the final parameters- estimates. Also, when EM algorithm is applied two times, for the same data set, it can be give different results for the estimate of parameters and this affect the classification accuracy of MDA. Forthcoming this problem, we use Self Organizing Mixture Network (SOMN) algorithm to estimate parameters of Gaussians mixtures in MDA that SOMN is more robust when random the initial values of the parameters are used [5]. We show effectiveness of this method on popular simulated waveform datasets and real glass data set.
{"references":["Hastie T. and Tibshirani R. (1996), Discriminant Analysis by Gaussian\nMixtures, Journal of the Royal Statistical Society. Series B\n(Methodological), Vol. 58, No. 1, pp. 155-176","Zohar Halbe, Mayer Aladjem(2005),Model-based mixture discriminant\nanalysisÔÇöan experimentalstudy, Pattern Recognition, 38, 437-440","Bashir S. and Carter E. M. (2005),Robust Reduced Rank Mixture\nDiscriminant Analysis, Communications in Statistics Theory and\nMethods, 34, 135-145","Bashir S. and Carter E.M. (2005),High breakdown mixture discriminant\nanalysis, Journal of Multivariate Analysis, 93, 102-11","Yin H. and Allinson N. M. (2001),Self-Organizing Mixture Networks\nfor Probability Density Estimation, IEEE Transactions on Neural\nNetworks, Vol. 12, No. 2, pp. 405-411","P. Dempster, N. M. Laird, and D. B. Rubin, \"Maximum likelihood from\nincomplete date via the EM algorithm,\" J. Roy. Statist. Soc. B, vol.39,\npp. 1-38, 1977.","S. Kullback and R. A. Leibler, \"On information and sufficiency,\" Ann.\nMath. Statist., vol. 22, pp. 79-86, 1951.","H. Robbins and S. Monro, \"A stochastic approximation method,\" Ann.\nMath. Statist., vol. 22, pp. 400-407, 1951.","Murphy, P. M., Aha, D. W. (1995). UCI Repository of Machine\nLearning Databases. Irvine, CA: University of California, Dept. of\nInformation and Computer Science.\n[10] Breiman, L., Friedman, J., Olshen, R. and Stone, C. (1984),\nClassification and Regression Trees Belmont; Wadsworth\n[11] Xu, L. and Jordan, M. I. (1993). Unsupervised learning by EM\nalgorithm based on finite mixture of Gaussians. In Proc. World\nCongress Neural Networks, vol. 2, pp. 431-434, Portland, OR, USA.\n[12] McLachlan, G.J., Peel, D., Basford, K.E., and Adams, P. (1999). The\nEMMIX software for the fitting of mixtures of normal and tcomponents.\nJournal of Statistical Software 4, No. 2.\n[13] Yin, H. and Allinson, N. M. (1997). Comparison of a Bayesian SOM\nwith the EM algorithm for Gaussian mixtures. Proc. Workshop on Self-\nOrganising Maps (WSOM'97), pp. 118-123."]}
Databáze: OpenAIRE
Externí odkaz: