Pruning belief decision tree methods in averaging and conjunctive approaches

Trabelsi, Salsabil; Elouedi, Zied; Mellouli, Khaled

doi:10.1016/j.ijar.2007.02.004

Cited by 24 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To learn from data with soft labels, nonparametric techniques such as the evidential k-nearest neighbor rule [11] and decision trees [16,20,46] have first been proposed. A general mechanism for parametric inference in the presence of uncertain data (of which soft labels are a special case) was later introduced in [12].…”

Section: Introductionmentioning

confidence: 99%

Parametric classification with soft labels using the evidential EM algorithm: linear discriminant analysis versus logistic regression

Quost

Denœux

2017

Adv Data Anal Classif

View full text Add to dashboard Cite

classification with soft labels using the Evidential EM algorithm : linear discriminant analysis versus logistic regression.Abstract Partially supervised learning extends both supervised and unsupervised learning, by considering situations in which only partial information about the response variable is available. In this paper, we consider partially supervised classification and we assume the learning instances to be labeled by Dempster-Shafer mass functions, called soft labels. Linear discriminant analysis and logistic regression are considered as special cases of generative and discriminative parametric models. We show that the evidential EM algorithm can be particularized to fit the parameters in each of these models. We describe experimental results with simulated data sets as well as with two real applications: K-complex detection in sleep EEGs signals and facial expression recognition. These results confirm the interest of using soft labels for classification as compared to potentially erroneous crisp labels, when the true class membership is partially unknown or ill-defined.

show abstract

Section: Introductionmentioning

confidence: 99%

Parametric classification with soft labels using the evidential EM algorithm: linear discriminant analysis versus logistic regression

Quost

Denœux

2017

Adv Data Anal Classif

View full text Add to dashboard Cite

show abstract

“…This rule was applied to regression problems with uncertain dependent variable in [36]. Methods for building decision trees from partially supervised data were proposed in [37], [38], [39]. An extension of the k-mode clustering algorithm to data with uncertain attributes was introduced in [40].…”

Section: Introductionmentioning

confidence: 99%

Maximum Likelihood Estimation from Uncertain Data in the Belief Function Framework

Denœux

2013

IEEE Trans. Knowl. Data Eng.

216

171

View full text Add to dashboard Cite

We consider the problem of parameter estimation in statistical models in the case where data are uncertain and represented as belief functions. The proposed method is based on the maximization of a generalized likelihood criterion, which can be interpreted as a degree of agreement between the statistical model and the uncertain observations. We propose a variant of the EM algorithm that iteratively maximizes this criterion. As an illustration, the method is applied to uncertain data clustering using finite mixture models, in the cases of categorical and continuous attributes.

show abstract

“…Thus, previous problems are special cases of this general formulation. Other studies have already proposed solutions in which class labels are expressed by possibility distributions or belief functions [21,22,23,24]. These labels are interesting when they are supplied by one or several experts and when crisp assignments are hard to obtain.…”

Section: Introductionmentioning

confidence: 99%

Learning from partially supervised data using mixture models and belief functions

Côme

Oukhellou

Denux

et al. 2009

Pattern Recognition

108

110

View full text Add to dashboard Cite

This paper addresses classification problems in which the class membership of training data is only partially known. Each learning sample is assumed to consist in a feature vector xi ∈ X and an imprecise and/or uncertain "soft" label mi defined as a Dempster-Shafer basic belief assignment over the set of classes. This framework thus generalizes many kinds of learning problems including supervised, unsupervised and semi-supervised learning. Here, it is assumed that the feature vectors are generated from a mixture model. Using the Generalized Bayesian Theorem, an extension of Bayes' theorem in the belief function framework, we derive a criterion generalizing the likelihood function. A variant of the EM algorithm dedicated to the optimization of this criterion is proposed, allowing us to compute estimates of model parameters. Experimental results demonstrate the ability of this approach to exploit partial information about class labels.

show abstract

Pruning belief decision tree methods in averaging and conjunctive approaches

Cited by 24 publications

References 13 publications

Parametric classification with soft labels using the evidential EM algorithm: linear discriminant analysis versus logistic regression

Parametric classification with soft labels using the evidential EM algorithm: linear discriminant analysis versus logistic regression

Maximum Likelihood Estimation from Uncertain Data in the Belief Function Framework

Learning from partially supervised data using mixture models and belief functions

Contact Info

Product

Resources

About