Gaussian mixture model

Gaussian mixture models for training data predmix <- predict (resmix,newdata = dat [-train, ], type = "post") matrix with posterior... 

FIGURE 5.28 Comparison of the test errors for the glass data using different classification methods. One hundred replications of the evaluation procedure (described in the text) are performed for the optimal parameter choices (if the method depends on the choice of a parameter). The methods are LDA, LR, Gaussian mixture models (Mix), fc-NN classification, classification trees (Tree), ANN, and SVMs. 

Examples of nonhierarchical clustering [22] methods include Gaussian mixture models, means, and fuzzy C means. They can be subdivided into hard and soft clustering methods. Hard classification methods such as means assign pixels to membership of only one cluster whereas soft classifications such as fuzzy C means assign degrees of fractional membership in each cluster. 

Press, W.H. Gaussian Mixture Models and k-Means Clustering. Numerical Recipes The Art of Scientific Computing (3rd.). New York Cambridge University Press. 2007. 

Keywords Electronic vision Fruit sorting and grading Video image Maturity prediction Gaussian mixture model (GMM) Fuzzy logic... 

In the present work parameters of the individual classes are estimated from the above features using Gaussian Mixture Model. There are several techniques available for estimating the parameters of a GMM [21]. A brief theory of GMM is presented in next section, the details and the methods adopted in the present work for estimation of individual classes can be found in [22]. 

Maturity Prediction Using Gaussian Mixture Model... 

Wang W, Wang H, Hempel M, Peng D, Sharif H, Chen HH. Study of stochastic ECG signal security via Gaussian mixture model in wireless healthcare. IEEE Syst J December 2011 5(4) 564-73. 

In comparison with the problem considered in (Shental, Bar-Hillel, Hertz, Weinshall 2003), there is another main difference. The model is not a Gaussian mixture model and especially the degradation increments have different density distributions. The density distributions of all the degradation increments would be the same only in the case of homogeneous Gamma process, and of regularly sampled paths. 

Yonghong, H., glehart, K., Hudgins, B., Chan, A. (2005). A Gaussian mixture model based classification scheme for myoelectric control of powered upper limb prostheses. IEEE Tran, on Biomedical Engineering, 52 (11), 1801-1811. 

Keywords— Speaker Verification, Gaussian Mixture Model, Equal Error Rate. 

This paper applies GMM for SV. Three different experiments were set up with different number of Gaussian mixture model with 32, 64 and 256. In one of the experiments, where speaker performance was evaluated base on time variation, there was not much performance difference when the time variation was less than a month. There was a vast difference in performance when the system was trained with one type of microphone but tested with another microphone type. This result shows that there is a difference in performance measures for the EER. When the system trained under one type of microphone, it should be tested with the same type of microphone. The best overall performance of the SV system is based on the 256 Gaussian models for the imposter and 32 Gaussian models for the client with an EER of 3.01%. 

Douglas A.Reynolds, Thomas F. Quatieri and Robest B. Dunn (2000 January/April/July). Speaker Verification Using Adapted Gaussian Mixture Models. Pages 19-41. 

Reynolds, D. A., (September 1992). A Gaussian Mixture Modelling Approach to Text-Independent Speaker Identification. Ph.D. thesis, Georgia Institute of Technology. 

---