Skip to Main content Skip to Navigation
Theses

Une approche probabiliste pour le classement d'objets incomplètement connus dans un arbre de décision

Lamis Hawarah 1
1 OSIRIS
TIMC [2011-2015] - Techniques de l'Ingénierie Médicale et de la Complexité - Informatique, Mathématiques et Applications, Grenoble - UMR 5525 [2011-2015]
Abstract : We describe in this thesis an approach to fill missing values in decision trees during the classification phase. This approach is derived from the it ordered attribute trees (OAT) method, proposed by Lobo and Numao in 2000, which builds a decision tree for each attribute and uses these trees to fill the missing attribute values. It is based on the Mutual Information between the attributes and the class. Our approach extends this method by taking the dependence between the attributes into account when constructing the attributes trees, and provides a probability distribution as a result when classifying an incomplete object (instead of the most probable class). We present our approach and we test it on some real databases. We also compare our results with those given by the C4.5 method and OAT.

We also propose a k-nearest neighbours algorithm which calculates for each object from the test data its frequency in the learning data. We compare these frequencies with the classification results given by our approach, C4.5 and OAT. Finally, we calculate the complexity of constructing the attribute trees and the complexity of classifying a new instance with missing values using our classification algorithm, C4.5 and OAT.
Document type :
Theses
Complete list of metadatas

Cited literature [73 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-00335313
Contributor : Lamis Hawarah <>
Submitted on : Thursday, October 30, 2008 - 9:06:27 AM
Last modification on : Friday, July 17, 2020 - 2:06:14 PM
Long-term archiving on: : Wednesday, September 22, 2010 - 10:27:51 AM

Identifiers

  • HAL Id : tel-00335313, version 2

Collections

Citation

Lamis Hawarah. Une approche probabiliste pour le classement d'objets incomplètement connus dans un arbre de décision. Informatique [cs]. Université Joseph-Fourier - Grenoble I, 2008. Français. ⟨tel-00335313v2⟩

Share

Metrics

Record views

482

Files downloads

3053