基于粒度熵的知识约简算法研究
首发时间:2010-09-21
摘要:针对现有知识约简算法中存在的不完备性问题,提出了一种基于粒度熵的启发式知识约简算法,该算法不需要求核,对无核的这种特殊信息系统计算约简更加有效。将该算法应用于电力变压器故障诊断决策表的约简,结果表明该约简算法可以从各约简集中选择最小最优的属性约简,避免了选择约简集的盲目性,同时也大大提高了故障诊断的效率。
For information in English, please click here
The Research of Knowledge Reduction Algorithm Based on Granularity Entropy
Abstract:In view of the incomplete questions which existed in existing knowledge reduction algorithms,we propose a new heuristic knowledge reduction algorithm based on granularity entropy.More,this algorithm is effective not only to the information system with core,and especially effective to the information system without core.Use the algorithm in transformer fault diagnosis decision table reduction.The results show that the minimalist and optimal reduction set can be selected from all reduction sets and the blindness of selecting reduction set is avoided.Moreover,the algorithm can greatly improves the efficiency of fault diagnosis.
Keywords: granularity entropy knowledge reduction fault diagnosis
论文图表:
引用
No.4385758518655128****
同行评议
共计0人参与
勘误表
基于粒度熵的知识约简算法研究
评论
全部评论0/1000