This package contains Matlab m-files for learning finite Gaussian mixtures from sample data and performing data classification with Mahalanobis distance or Bayesian classifiers. Each class in training set is learned individually with one of the three

对传统的支持向量机分类器的改进,利用了半监督学习的方法，可以极大的提高分类效率。-The traditional support vector machine classifiers is improved with a semi-supervised learning methods, can greatly improve classification efficiency.