计算机科学与探索2016，Vol.10Issue(5)：709-721,13.DOI:10.3778/j.issn.1673-9418.1507068
基于改进置信规则库推理的分类方法
Classification Approach Based on Improved Belief Rule-Base Reasoning
摘要
Abstract
This paper proposes a new classification approach based on improved belief rule-base reasoning by intro-ducing linear combinational mode, setting the number of rules based on the classifications and improving the method of calculating individual matching degree. Compared with the traditional belief rule-base inference methodology, the number of rules in the proposed method does not depend on the number of antecedent attributes or its referential values, and it is only related to classification number. In this way, the new method can ensure the applicability for complex problems. In the experiments, the differential evolution algorithm is applied to train parameters, including rule weights, attribute weights, referential values of antecedent attributes and belief degrees. Three commonly public datasets have been employed to validate the proposed method. And the classification results are proved to be ideal, which shows that the proposed method is reasonable and effective.关键词
置信规则库/基于证据推理的置信规则库推理方法(RIMER)/参数学习/分类方法Key words
belief rule-base/belief rule-base inference methodology using evidence reasoning (RIMER)/parameter learning/classification method引用本文复制引用
叶青青,杨隆浩,傅仰耿,陈晓聪..基于改进置信规则库推理的分类方法[J].计算机科学与探索,2016,10(5):709-721,13.基金项目
The National Natural Science Foundation of China under Grant Nos.61300026,71371053,71501047(国家自然科学基金) （国家自然科学基金）
the Natural Sci-ence Foundation of Fujian Province under Grant No.2015J01248(福建省自然科学基金) （福建省自然科学基金）
the National Collegiate Innovation and Entrepreneurship Training Program of China under Grant No.201410386009(国家级大学生创新创业训练计划项目) （国家级大学生创新创业训练计划项目）
the Social Science Research Supported Foundation of Fuzhou University under Grant No.14SKF16(福州大学社科科研扶持基金) （福州大学社科科研扶持基金）
