Data classification with a generalized Gaussian components based density estimation algorithm

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publication2009 International Joint Conference on Neural Networks, IJCNN 2009
Pages1259-1266
Number of pages8
DOIs
Publication statusPublished - 2009 Nov 18
Event2009 International Joint Conference on Neural Networks, IJCNN 2009 - Atlanta, GA, United States
Duration: 2009 Jun 142009 Jun 19

Publication series

NameProceedings of the International Joint Conference on Neural Networks

Other

Other2009 International Joint Conference on Neural Networks, IJCNN 2009
CountryUnited States
CityAtlanta, GA
Period09-06-1409-06-19

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Data classification with a generalized Gaussian components based density estimation algorithm'. Together they form a unique fingerprint.

  • Cite this

    Hsieh, C. H., Chang, D. T. H., & Oyang, Y. J. (2009). Data classification with a generalized Gaussian components based density estimation algorithm. In 2009 International Joint Conference on Neural Networks, IJCNN 2009 (pp. 1259-1266). [5179000] (Proceedings of the International Joint Conference on Neural Networks). https://doi.org/10.1109/IJCNN.2009.5179000