The particle swarm optimization based parameters determination for Gaussian mixture model

Gaussian mixture model (GMM) is one of the most popular methods to estimate the underlying density function. In this paper, a parameter determination method (PSOGMM) for GMM based on particle swarm optimization (PSO) is proposed. PSOGMM optimizes parameters in GMM based on a new error criterion which is derived based on the integrated square error between the true density function and the estimated density. In order to validate the feasibility and effectiveness of PSOGMM, we carry out some numerical experiments on four types of one-dimensional artificial datasets: Uniform dataset, Normal dataset, Exponential dataset and Rayleigh dataset. The finally comparative results show that our strategies are well-performed and PSOGMM can obtain the better estimation performance when the appropriate parameters are selected for PSO.

[1]  E. Parzen.  On Estimation of a Probability Density Function and Mode , 1962 .

[2]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[3]  William N. Venables,et al.  Modern Applied Statistics with S-Plus. , 1996 .

[4]  Marc G. Genton,et al.  Classes of Kernels for Machine Learning: A Statistics Perspective , 2002, J. Mach. Learn. Res..

[5]  Zhihua Zhang,et al.  EM algorithms for Gaussian mixtures with split-and-merge operation , 2003, Pattern Recognition.

[6]  Christophe Biernacki,et al.  Choosing starting values for the EM algorithm for getting the highest likelihood in multivariate Gaussian mixture models , 2003, Comput. Stat. Data Anal..

[7]  Haixian Wang,et al.  Estimation for the number of components in a mixture model using stepwise split-and-merge EM algorithm , 2004 .

[8]  Zhi-Qiang Liu,et al.  Hidden Markov models with factored Gaussian mixtures densities , 2005, Pattern Recognit..

[9]  Edward J. Delp,et al.  Decomposing parameters of mixture Gaussian model using genetic and maximum likelihood algorithms on dental images , 2006, Pattern Recognit. Lett..

[10]  Chao Feng,et al.  Dynamical Gaussian mixture model for tracking elliptical living objects , 2006, Pattern Recognit. Lett..

[11]  Jia Zeng,et al.  Type-2 fuzzy Gaussian mixture models , 2008, Pattern Recognit..

[12]  Jinwen Ma,et al.  A fast fixed-point BYY harmony learning algorithm on Gaussian mixture with automated model selection , 2008, Pattern Recognit. Lett..

[13]  Dan Schonfeld,et al.  Maximum-Entropy Expectation-Maximization Algorithm for Image Reconstruction and Sensor Field Estimation , 2008, IEEE Transactions on Image Processing.

[14]  Salvatore Ingrassia,et al.  Degeneracy of the EM algorithm for the MLE of multivariate Gaussian mixtures and dynamic constraints , 2011, Comput. Stat. Data Anal..