Simultaneous feature selection and Gaussian mixture model estimation for supervised classification problems

A new expectation maximization (EM) algorithm for time-critical supervised classification tasks in remote sensing is proposed. Compared to standard EM and other approaches, it has the following advantages: (1) No knowledge about the class distributions is needed. (2) The number of components is estimated. (3) It does not require careful initialization. (4) Singular estimates are avoided due to the ability of pruning components. (5) The best discriminating features are identified simultaneously. (6) The features are identified by incorporating Mahalanobis distances.     

A new feature selection method for Gaussian mixture clustering

With the wide applications of Gaussian mixture clustering, e.g., in semantic video classification [H. Luo, J. Fan, J. Xiao, X. Zhu, Semantic principal video shot classification via mixture Gaussian, in: Proceedings of the 2003 International Conference on Multimedia and Expo, vol. 2, 2003, pp. 189-192], it is a nontrivial task to select the useful features in Gaussian mixture clustering without class labels. This paper, therefore, proposes a new feature selection method, through which not only the most relevant features are identified, but the redundant features are also eliminated so that the smallest relevant feature subset can be found. We integrate this method with our recently proposed Gaussian mixture clustering approach, namely rival penalized expectation-maximization (RPEM) algorithm [Y.M. Cheung, A rival penalized EM algorithm towards maximizing weighted likelihood for density mixture clustering with automatic model selection, in: Proceedings of the 17th International Conference on Pattern Recognition, 2004, pp. 633-636; Y.M. Cheung, Maximum weighted likelihood via rival penalized EM for density mixture clustering with automatic model selection, IEEE Trans. Knowl. Data Eng. 17(6) (2005) 750-761], which is able to determine the number of components (i.e., the model order selection) in a Gaussian mixture automatically. Subsequently, the data clustering, model selection, and the feature selection are all performed in a single learning process. Experimental results have shown the efficacy of the proposed approach.     

Simultaneous feature selection and clustering using mixture models

Clustering is a common unsupervised learning technique used to discover group structure in a set of data. While there exist many algorithms for clustering, the important issue of feature selection, that is, what attributes of the data should be used by the clustering algorithms, is rarely touched upon. Feature selection for clustering is difficult because, unlike in supervised learning, there are no class labels for the data and, thus, no obvious criteria to guide the search. Another important problem in clustering is the determination of the number of clusters, which clearly impacts and is influenced by the feature selection issue. In this paper, we propose the concept of feature saliency and introduce an expectation-maximization (EM) algorithm to estimate it, in the context of mixture-based clustering. Due to the introduction of a minimum message length model selection criterion, the saliency of irrelevant features is driven toward zero, which corresponds to performing feature selection. The criterion and algorithm are then extended to simultaneously estimate the feature saliencies and the number of clusters.     

Bayesian estimation of the Gaussian mixture GARCH model

Bayesian inference and prediction for a generalized autoregressive conditional heteroskedastic (GARCH) model where the innovations are assumed to follow a mixture of two Gaussian distributions is performed. The mixture GARCH model can capture the patterns usually exhibited by many financial time series such as volatility clustering, large kurtosis and extreme observations. A Griddy-Gibbs sampler implementation is proposed for parameter estimation and volatility prediction. Bayesian prediction of the Value at Risk is also addressed providing point estimates and predictive intervals. The method is illustrated using the Swiss Market Index.     

A countably infinite mixture model for clustering and feature selection

Mixture modeling is one of the most useful tools in machine learning and data mining applications. An important challenge when applying finite mixture models is the selection of the number of clusters which best describes the data. Recent developments have shown that this problem can be handled by the application of non-parametric Bayesian techniques to mixture modeling. Another important crucial preprocessing step to mixture learning is the selection of the most relevant features. The main approach in this paper, to tackle these problems, consists on storing the knowledge in a generalized Dirichlet mixture model by applying non-parametric Bayesian estimation and inference techniques. Specifically, we extend finite generalized Dirichlet mixture models to the infinite case in which the number of components and relevant features do not need to be known a priori. This extension provides a natural representation of uncertainty regarding the challenging problem of model selection. We propose a Markov Chain Monte Carlo algorithm to learn the resulted infinite mixture. Through applications involving text and image categorization, we show that infinite mixture models offer a more powerful and robust performance than classic finite mixtures for both clustering and feature selection.     

Variational approximations in Bayesian model selection for finite mixture distributions

Variational methods, which have become popular in the neural computing/machine learning literature, are applied to the Bayesian analysis of mixtures of Gaussian distributions. It is also shown how the deviance information criterion, (DIC), can be extended to these types of model by exploiting the use of variational approximations. The use of variational methods for model selection and the calculation of a DIC are illustrated with real and simulated data. The variational approach allows the simultaneous estimation of the component parameters and the model complexity. It is found that initial selection of a large number of components results in superfluous components being eliminated as the method converges to a solution. This corresponds to an automatic choice of model complexity. The appropriateness of this is reflected in the DIC values.     

Bayesian change detection based on spatial sampling and Gaussian mixture model

A Gaussian mixture model (GMM) and Bayesian inferencing based unsupervised change detection algorithm is proposed to achieve change detection on the difference image computed from satellite images of the same scene acquired at different time instances. Each pixel of the difference image is represented by a feature vector constructed from the difference image values of the neighbouring pixels to consider the contextual information. The feature vectors of the difference image are modelled as a GMM. The conditional posterior probabilities of changed and unchanged pixel classes are automatically estimated by partitioning GMM into two distributions by minimizing an objective function. Bayesian inferencing is then employed to segment the difference image into changed and unchanged classes by using the conditional posterior probability of each class. Change detection results are shown on real datasets.     

于混合高斯莫型与联合特征的行人检测方法

针对视频环境下行人检测多数采用窗口滑动方法识别慢、不能快速找到行人窗口的缺点,提出了一种基于组合算法的行人目标识别方法,利用高斯混合模型方法提取视频中的运动前景,划定一个泛目标窗口,再使用HOG-l bp联合特征训练的分类器对泛目标窗口进行分类,得到分类结果,对行人目标进行标记.经实验验证:该方法相对于当前行人检测方法,检测速度和正确率都取得了很好的效果.     

Bayesian approaches to Gaussian mixture modeling

A Bayesian-based methodology is presented which automatically penalizes overcomplex models being fitted to unknown data. We show that, with a Gaussian mixture model, the approach is able to select an “optimal” number of components in the model and so partition data sets. The performance of the Bayesian method is compared to other methods of optimal model selection and found to give good results. The methods are tested on synthetic and real data sets     

The BYY annealing learning algorithm for Gaussian mixture with automated model selection

Bayesian Ying-Yang (BYY) learning has provided a new mechanism that makes parameter learning with automated model selection via maximizing a harmony function on a backward architecture of the BYY system for the Gaussian mixture. However, since there are a large number of local maxima for the harmony function, any local searching algorithm, such as the hard-cut EM algorithm, does not work well. In order to overcome this difficulty, we propose a simulated annealing learning algorithm to search the global maximum of the harmony function, being expressed as a kind of deterministic annealing EM procedure. It is demonstrated by the simulation experiments that this BYY annealing learning algorithm can efficiently and automatically determine the number of clusters or Gaussians during the learning process. Moreover, the BYY annealing learning algorithm is successfully applied to two real-life data sets, including Iris data classification and unsupervised color image segmentation.     

Variational learning for Gaussian mixture models.

This paper proposes a joint maximum likelihood and Bayesian methodology for estimating Gaussian mixture models. In Bayesian inference, the distributions of parameters are modeled, characterized by hyperparameters. In the case of Gaussian mixtures, the distributions of parameters are considered as Gaussian for the mean, Wishart for the covariance, and Dirichlet for the mixing probability. The learning task consists of estimating the hyperparameters characterizing these distributions. The integration in the parameter space is decoupled using an unsupervised variational methodology entitled variational expectation-maximization (VEM). This paper introduces a hyperparameter initialization procedure for the training algorithm. In the first stage, distributions of parameters resulting from successive runs of the expectation-maximization algorithm are formed. Afterward, maximum-likelihood estimators are applied to find appropriate initial values for the hyperparameters. The proposed initialization provides faster convergence, more accurate hyperparameter estimates, and better generalization for the VEM training algorithm. The proposed methodology is applied in blind signal detection and in color image segmentation.     

Bayesian mixture of autoregressive models

An infinite mixture of autoregressive models is developed. The unknown parameters in the mixture autoregressive model follow a mixture distribution, which is governed by a Dirichlet process prior. One main feature of our approach is the generalization of a finite mixture model by having the number of components unspecified. A Bayesian sampling scheme based on a weighted Chinese restaurant process is proposed to generate partitions of observations. Using the partitions, Bayesian prediction, while accounting for possible model uncertainty, determining the most probable number of mixture components, clustering of time series and outlier detection in time series, can be done. Numerical results from simulated and real data are presented to illustrate the methodology.     

Bayesian skew selection for multivariate models

We develop a Bayesian approach for the selection of skew in multivariate skew t distributions constructed through hidden conditioning in the manners suggested by either Azzalini and Capitanio (2003) or Sahu et al. (2003). We show that the skew coefficients for each margin are the same for the standardized versions of both distributions. We introduce binary indicators to denote whether there is symmetry, or skew, in each dimension. We adopt a proper beta prior on each non-zero skew coefficient, and derive the corresponding prior on the skew parameters. In both distributions we show that as the degrees of freedom increases, the prior smoothly bounds the non-zero skew parameters away from zero and identifies the posterior. We estimate the model using Markov chain Monte Carlo (MCMC) methods by exploiting the conditionally Gaussian representation of the skew t distributions. This allows for the search through the posterior space of all possible combinations of skew and symmetry in each dimension. We show that the proposed method works well in a simulation setting, and employ it in two multivariate econometric examples. The first involves the modeling of foreign exchange rates and the second is a vector autoregression for intra-day electricity spot prices. The approach selects skew along the original coordinates of the data, which proves insightful in both examples.     

A nonparametric Bayesian learning model using accelerated variational inference and feature selection

Pattern Analysis and Applications - Developing effective machine learning methods for multimedia data modeling continues to challenge computer vision scientists. The capability of providing...     

Active curve axis Gaussian mixture models

Gaussian Mixture Models (GMM) have been broadly applied for the fitting of probability density function. However, due to the intrinsic linearity of GMM, usually many components are needed to appropriately fit the data distribution, when there are curve manifolds in the data cloud.

In order to solve this problem and represent data with curve manifolds better, in this paper we propose a new nonlinear probability model, called active curve axis Gaussian model. Intuitively, this model can be imagined as Gaussian model being bent at the first principal axis. For estimating parameters of mixtures of this model, the EM algorithm is employed.

Experiments on synthetic data and Chinese characters show that the proposed nonlinear mixture models can approximate distributions of data clouds with curve manifolds in a more concise and compact way than GMM does. The performance of the proposed nonlinear mixture models is promising.     

Imputation through finite Gaussian mixture models

Imputation is a widely used method for handling missing data. It consists in the replacement of missing values with plausible ones. Parametric and nonparametric techniques are generally adopted for modelling incomplete data. Both of them have advantages and drawbacks. Parametric techniques are parsimonious but depend on the model assumed, while nonparametric techniques are more flexible but require a high amount of observations. The use of finite mixture of multivariate Gaussian distributions for handling missing data is proposed. The main reason is that it allows to control the trade-off between parsimony and flexibility. An experimental comparison with the widely used imputation nearest neighbour donor is illustrated.     

Type-2 fuzzy Gaussian mixture models

This paper presents a new extension of Gaussian mixture models (GMMs) based on type-2 fuzzy sets (T2 FSs) referred to as T2 FGMMs. The estimated parameters of the GMM may not accurately reflect the underlying distributions of the observations because of insufficient and noisy data in real-world problems. By three-dimensional membership functions of T2 FSs, T2 FGMMs use footprint of uncertainty (FOU) as well as interval secondary membership functions to handle GMMs uncertain mean vector or uncertain covariance matrix, and thus GMMs parameters vary anywhere in an interval with uniform possibilities. As a result, the likelihood of the T2 FGMM becomes an interval rather than a precise real number to account for GMMs uncertainty. These interval likelihoods are then processed by the generalized linear model (GLM) for classification decision-making. In this paper we focus on the role of the FOU in pattern classification. Multi-category classification on different data sets from UCI repository shows that T2 FGMMs are consistently as good as or better than GMMs in case of insufficient training data, and are also insensitive to different areas of the FOU. Based on T2 FGMMs, we extend hidden Markov models (HMMs) to type-2 fuzzy HMMs (T2 FHMMs). Phoneme classification in the babble noise shows that T2 FHMMs outperform classical HMMs in terms of the robustness and classification rate. We also find that the larger area of the FOU in T2 FHMMs with uncertain mean vectors performs better in classification when the signal-to-noise ratio is lower.     

A finite mixture model for simultaneous high-dimensional clustering, localized feature selection and outlier rejection

Model-based approaches and in particular finite mixture models are widely used for data clustering which is a crucial step in several applications of practical importance. Indeed, many pattern recognition, computer vision and image processing applications can be approached as feature space clustering problems. For complex high-dimensional data, however, the use of these approaches presents several challenges such as the presence of many irrelevant features which may affect the speed and also compromise the accuracy of the used learning algorithm. Another problem is the presence of outliers which potentially influence the resulting model’s parameters. For this purpose, we propose and discuss an algorithm that partitions a given data set without a priori information about the number of clusters, the saliency of the features or the number of outliers. We illustrate the performance of our approach using different applications involving synthetic data, real data and objects shape clustering.