Direct Rule Extraction and Classification with Incremental Neural Network
Proceeding: Second International Conference on Artificial Intelligence and Pattern Recognition (AIPR2015)Publication Date: 2015-04-16
Authors : John Tsiligaridis;
Page : 18-23
Keywords : Data Mining; Neural Networks; Rule Extraction; Incremental Neural Network; Backpropagation;
Abstract
The purpose of this project is to present a direct method for rules extraction and he use of Neural Network for classification. A direct method with simplification (DMS) to extract rules from data using a hash table is also developed. Apart from the rules DMS, can also produce the corresponding decision tree for each subset with predefined class value. The merge of the paths of all the call values can produce the decision tree of the data. Therefore, DMS works as both direct and indirect method. The advantages of DMS are the ability to produce rules with a maximum number of conditions and prevention of subtree overlapping. Moreover an incremental Backpropagation Neural Network (IBNN) is created using the instances of data grouping according to their predefined class. Comparisons show that IBNN outperforms the DMS. Simulation results are provided.
Other Latest Articles
- A Novel Coarse-to-fine Level Set Framework for Ultrasound Image Segmentation
- A Summary of Research on Model Identification and Target Tracking of Non-cooperative Target
- Detection and Categorization of Errors by Novice Programmers in a First Year Java Programming Class: A Comparative Analysis
- A Novel Segmentation Approach for Brain Tumor in MRI
- The Role of Electronic Leadership in Crisis Management Practices of National Companies: A Research into Virtual, E-Commerce, Industrial Businesses and Public Sector
Last modified: 2015-04-18 14:15:07