A Parallel Approximate Rule Extracting Algorithm Based on the Improved Discernibility Matrix

A parallel rule-extracting algorithm based on the improved discernibility matrix [2] is proposed, by this way, a large amount of raw data can be divided into some small portions to be processed in parallel. The confidence factor is also introduced to the rule sets to obtain the uncertainty rules. The most important advantage of this algorithm is that it does not need to calculate the discernibility matrix corresponding to these overall data.

• Type: Conference
• Year: 2004
• Where: RSCTC
• Authors: Yong Liu, Congfu Xu, Yunhe Pan
• Keywords: Artificial Intelligence, Discernibility Matrix, Parallel Rule-extracting Algorithm, Raw Data, RSCTC 2004