Data classification with a generalized Gaussian components based density estimation algorithm

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 characteristic s 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.

The discriminant power of RNA features for pre-miRNA recognition

“…SVMs were used in triplet-SVM, microPred and mirident, whereas RF was used in MiPred and HuntMi. Generalized Gaussian density estimator (G 2 DE) [ 24 ] is not a tool for pre-miRNA prediction in the sense that the features have to be computed by the user in his/her own pipeline. Nevertheless, we included G 2 DE because of its predictive performance and class distribution interpretability.…”

“…G 2 DE [ 24 ] was designed to predict an instance class based on the probability density functions (pdf) of both positive and negative classes. Each pdf is fitted as mixture of generalized Gaussian components, using a limited user-defined number of components.…”

“…Each pdf is fitted as mixture of generalized Gaussian components, using a limited user-defined number of components. One important feature of G 2 DE is to provide the coefficients and parameters associated with these generalized components [ 24 ].…”

Application of density estimation algorithms in analyzing co-morbidities of migraine

“…Density estimation is a classical problem in statistics aimed at constructing an approximate probability density function based on the samples randomly and independently taken from an underlined distribution. In the proposed approach, we have exploited the relaxed variable kernel density estimation (RVKDE) algorithm (Oyang et al 2005) and the generalized Gaussian component based density estimation (G 2 DE) algorithm (Hsieh et al 2009) that our research team has developed in recent years. The RVKDE algorithm has been exploited to identify those case samples that share some distinctive features in comparison with the control samples.…”

Gg DCT Coefficient Models

“…For example, it has been used for data classification algorithms in machine learning problems 18,19 ; for the detection of wheezing sounds, a continuous, coarse, whistling sound produced in the respiratory airways during breathing, commonly experienced by persons suffering from asthma, and for other speech processing systems 20,21 ; for classification of musical instruments 22 ; to model load duration curves [23][24][25][26] ; to model the human skin color 27 ; and, for blind source separation algorithms. 28 When modeling the DCT densities of a big image, the parameter β in (1.1) is likely to vary over different parts of the image and so one should consider β itself to be a random variable.…”