A New Supervised Learning Algorithm Using Naive Bayesian Classifier
Résumé
A new supervised learning algorithm using naïve Bayesian classifier is presented in this paper, which calculates the prior and conditional probabilities from a given training data and classifies the training examples using these probabilities. If any training example is misclassified then the algorithm calculates the information gain of attributes of the training data and chooses one attribute from training data with maximum information gain value. After the algorithm splits the training data into sub-datasets depending on the attribute values of the selected attribute, and again calculates the prior and conditional probabilities for each sub-dataset and classifies the examples of the each sub-dataset using their respective probabilities. The process will continue until all the training examples are correctly classified. Finally, the algorithm preserves the probabilities of each dataset for the future classification of unknown examples, whose attributes value are known but class value is unknown. The proposed algorithm addresses the problem of classifying the large dataset and it has been successfully tested on a number of benchmark problems, which achieved high classification rates using limited computational resources.
Fichier principal
Final_Version_IADIS_IS2010_Sub_Code_28_DMFarid.pdf (182.85 Ko)
Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)