In this paper a hybrid adaptive particle swarm optimization aided learnable Bayesian classifier is proposed. The objective of the classifier is to solve some of the fundamental problems associated with the pure naive Bayesian classifier and its variants with a larger view towards maximization of the classifier accuracy. Further, the proposed algorithm can exhibits an improved capability to elim...

Citizen science and human computation involves working with multiple, untrusted decision makers. We demonstrate how Bayesian Classifier Combination outperforms a naive Bayes method when classifying documents using unreliable crowdsourced labels. We also present methods for screening workers and selecting informative documents to label. Finally, we explain how the Bayesian Classifier Combination...

We introduce a Bayesian network classifier less restrictive than Naive Bayes (NB) and Tree Augmented Naive Bayes (TAN) classifiers. Considering that learning an unrestricted network is unfeasible the proposed classifier is confined to be consistent with the breadth-first search order of an optimal TAN. We propose an efficient algorithm to learn such classifiers for any score that decompose over...

Bayesian classifiers such as Naive Bayes or Tree Augmented Naive Bayes (TAN) have shown excellent performance given their simplicity and heavy underlying independence assumptions. In this paper we introduce a classifier taking as basis the TAN models and taking into account uncertainty in model selection. To do this we introduce decomposable distributions over TANs and show that the expression ...

We compare the performance of several machine learning algorithms in the problem of prognostics of the femoral neck fracture recovery: the K-nearest neighbours algorithm, the semi-naive Bayesian classifier, backpropagation with weight elimination learning of the multilayered neural networks, the LFC (lookahead feature construction) algorithm, and the Assistant-I and Assistant-R algorithms for t...

Bayesian classifiers such as Naive Bayes or Tree Augmented Naive Bayes (TAN) have shown excellent performance given their simplicity and heavy underlying independence assumptions. In this paper we introduce a classifier taking as basis the TAN model and taking into account uncertainty in model selection. To do this we introduce decomposable distributions over TANs and show that they allow the e...

In this paper, we propose a Dynamic Naive Bayesian (DNB) network model for classifying data sets with hierarchical labels. The DNB model is built upon a Naive Bayesian (NB) network, a successful classifier for data with flattened (nonhierarchical) class labels. The problems using flattened class labels for hierarchical classification are addressed in this paper. The DNB has a top-down structure...

This paper addresses personal E-mail filtering by casting it in the framework of text classification. Modeled as semi-structured documents, Email messages consist of a set of fields with predefined semantics and a number of variable length free-text fields. While most work on classification either concentrates on structured data or free text, the work in this paper deals with both of them. To p...

In multidimensional classification the goal is to assign an instance to a set of different classes. This task is normally addressed either by defining a compound class variable with all the possible combinations of classes (label power-set methods, LPMs) or by building independent classifiers for each class (binary-relevance methods, BRMs). However, LPMs do not scale well and BRMs ignore the de...

In multi-label classification the goal is to assign an instance to a set of different classes. This task is normally addressed either by defining a compound class variable with all the possible combinations of labels (label power-set methods) or by building independent classifiers for each class (binary relevance methods). The first approach suffers from high computationally complexity, while t...