Data classification with a generalized Gaussian components based density estimation algorithm

Chih Hung Hsieh, Darby Tien Hao Chang, Yen Jen Oyang

研究成果: Conference contribution

6 引文 斯高帕斯(Scopus)

摘要

Data classification is an intensively studied machine learning problem and there are two major categories of data classification algorithms, namely the logic based and the kernel based. The logic based classifiers, such as the decision tree and the rule-based classifier, feature the advantage of presenting a good summary about the distinctive characteristics of different classes of data. On the other hand, the kernel based classifiers, such as the neural network and the support vector machine (SVM), typically can deliver higher prediction accuracy than the logic based classifiers. However, the user of a kernel based classifier normally cannot get an overall picture about the distribution of the data set. For some applications, the overall picture of the distribution of the data set can provide valuable insights about the distinctive characteristics of different classes of data and therefore is highly desirable. In this article, aiming to close the gap between the logic based classifiers and the kernel based classifiers, we propose a novel approach to carry out density estimation based on a mixture model composed of a limited number of generalized Gaussian components. One favorite feature of the classifier constructed with the proposed approach is that a user can easily obtain an overall picture of the distributions of the data set by examining the eigenvectors and eigenvalues of the covariance matrices associated with the generalized Gaussian components. Experimental results show that the classifier constructed with the proposed approach is capable of delivering superior prediction accuracy in comparison with the conventional logic based classifiers and the EM (Expectation Maximization) based classifier. On the other hand, though it cannot match the prediction accuracy delivered by the SVM, the proposed classifier enjoys one major advantage due to providing the user with an overall picture of the underlying distributions.

原文English
主出版物標題2009 International Joint Conference on Neural Networks, IJCNN 2009
頁面1259-1266
頁數8
DOIs
出版狀態Published - 2009 十一月 18
事件2009 International Joint Conference on Neural Networks, IJCNN 2009 - Atlanta, GA, United States
持續時間: 2009 六月 142009 六月 19

出版系列

名字Proceedings of the International Joint Conference on Neural Networks

Other

Other2009 International Joint Conference on Neural Networks, IJCNN 2009
國家/地區United States
城市Atlanta, GA
期間09-06-1409-06-19

All Science Journal Classification (ASJC) codes

  • 軟體
  • 人工智慧

指紋

深入研究「Data classification with a generalized Gaussian components based density estimation algorithm」主題。共同形成了獨特的指紋。

引用此