On Discrete Data Clustering

Bouguila, Nizar; ElGuebaly, Walid

doi:10.1007/978-3-540-68125-0_44

Cited by 18 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An important problem is the categorization of this multimedia content which is typically noisy and generally described in the form of high-dimensional feature vectors [46]. In this first application, we focus on the problem of image categorization which has several potential applications and can be used for image databases browsing, content-based image categorization, retrieval and suggestion [47], [48], [49], [50], [51], [52]. We follow the same categorization methodology previously proposed in [13] by using adopting the bag of visual words formalism which has been widely used recently for this task.…”

Section: A Visual Scenes Categorizationmentioning

confidence: 99%

Count Data Clustering Using Unsupervised Localized Feature Selection and Outliers Rejection

Bouguila

2011

2011 IEEE 23rd International Conference on Tools With Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

This paper presents an unsupervised statistical model for simultaneous clustering, feature selection and outlier rejection in the case of count data. The proposed model is based on a finite discrete mixture to which a uniform component is added to ensure robustness to outliers and noise. The consideration of a finite mixture model is justified by its flexibility, its solid grounding in the theory of statistics and its competitive results. We derive a complete maximum a posteriori learning approach that does not require a priori knowledge about the number of outliers and the number of clusters. A rigorous expectation maximization (EM) algorithm, based on the formulation of a maximum a posteriori (MAP) estimation, is also provided. We report experimental results of applying our model to the challenging problems of visual scenes categorization and texture discrimination.

show abstract

Section: A Visual Scenes Categorizationmentioning

confidence: 99%

Count Data Clustering Using Unsupervised Localized Feature Selection and Outliers Rejection

Bouguila

2011

2011 IEEE 23rd International Conference on Tools With Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

show abstract

“…I Zi=j is the number of vector in cluster j. It is common to consider a Dirichlet distribution as a prior for P which is justified by the fact that the Dirichlet is conjugate to the multinomial [7]:…”

Section: Infinite Modelmentioning

confidence: 99%

An Infinite Mixture Model of Generalized Inverted Dirichlet Distributions for High-Dimensional Positive Data Modeling

Bouguila¹,

Mashrgy²

2014

Information and Communication Technology

Self Cite

View full text Add to dashboard Cite

Part 1: Information & Communication Technology-EurAsia Conference 2014, ICT-EurAsia 2014International audienceWe propose an infinite mixture model for the clustering of positive data. The proposed model is based on the generalized inverted Dirichlet distribution which has a more general covariance structure than the inverted Dirichlet that has been widely used recently in several machine learning and data mining applications. The proposed mixture is developed in an elegant way that allows simultaneous clustering and feature selection, and is learned using a fully Bayesian approach via Gibbs sampling. The merits of the proposed approach are demonstrated using a challenging application namely images categorization

show abstract

“…First, in spite of its flexibility and the fact that it is conjugate to the multinomial, the Dirichlet has a very restrictive negative covariance matrix which violates generally experimental observations [33]. Another restriction of the Dirichlet is that the variables with the same mean must have the same variance as shown in [34,35]. Third, generally the hyperparameters are taken independently from the sample according to a certain expert's knowledge.…”

Section: Introductionmentioning

confidence: 99%

On the smoothing of multinomial estimates using Liouville mixture models and applications

Bouguila

2011

Pattern Anal Applic

Self Cite

View full text Add to dashboard Cite

There has been major progress in recent years in statistical model-based pattern recognition, data mining and knowledge discovery. In particular, generative models are widely used and are very reliable in terms of overall performance. Success of these models hinges on their ability to construct a representation which captures the underlying statistical distribution of data. In this article we focus on count data modeling. Indeed, this kind of data is naturally generated in many contexts and in different application domains. Usually, models based on the multinomial assumption are used in this case which may have several shortcomings especially in the case of high-dimensional sparse data. We propose then a principled approach to smooth multinomials using a mixture of Beta-Liouville distributions which is learned to reflect and model prior beliefs about multinomial parameters. Via both theoretical interpretations and experimental validations, we argue that the proposed smoothing model is general and flexible enough to allow accurate representation of count data.

show abstract

On Discrete Data Clustering

Cited by 18 publications

References 9 publications

Count Data Clustering Using Unsupervised Localized Feature Selection and Outliers Rejection

Count Data Clustering Using Unsupervised Localized Feature Selection and Outliers Rejection

An Infinite Mixture Model of Generalized Inverted Dirichlet Distributions for High-Dimensional Positive Data Modeling

On the smoothing of multinomial estimates using Liouville mixture models and applications

Contact Info

Product

Resources

About