Associative classification using naive Bayes theorem

Other Title(s)

التصنيف المبني على الروابط باستخدام نظرية بايز

Dissertant

Abu Jabir, Fawzi Ali

Thesis advisor

al-Zubaydi, Rashid A.

University

Philadelphia University

Faculty

Faculty of Information Technology

Department

Department of Computer Science

University Country

Jordan

Degree

Master

Degree Date

2014

English Abstract

-Associative classification usually generates a large set of rules.

Therefore, it is inevitable that an instance matches several rules which classes are conflicted, several associative classification based their prediction on one rule and ignore all other rules, even high confident ones, In this research, a new approach called Associative Classification using naïve Bayes (AC-NB) is proposed, which uses an improved naïve Bayes theorem to address these issues.

Our experiments on five UCI datasets show that AC-NB outperforms both RIPPER and NB on accuracy, also compared with new associative classification approaches; our proposed approach was highly competitive.

Main Subjects

Mathematics

Topics

• Data mining
• Decision trees

No. of Pages

55

Table of Contents

• APA
• MLA
• AMA

Language

English

Data Type

Arab Theses

Record ID

BIM-546116