摘要
案例检索是基于案例推理(CBR)系统的中心环节,检索速度和精度关系着整个系统的质量.文章系统地提出了一套案例检索及其权重优化方法(FRAWO),重点研究了用基于梯形的模糊集和改进的欧氏距离检索算法分别解决案例中模糊概念属性、区间特征属性的相似度计算问题以及采用PULL&PUSH调整策略进行案例权重的调整.在实验系统上基于案例库对FRAWO法的有效性、准确度、效率等进行了实验.实验结果表明,FRAWO法适用于CBR系统,检索速度较快、准确性高.
Case retrieval is the focal stage of case-based reasoning systems whose quality is determined by the speed and accuracy of retrieval. In this paper, a new case retrieval method called FRAWO is proposed in a systematical way, in which emphasis is put on the problems of similarity calculation of fuzzy and interval attributes of cases using trapezia-based fuzzy set and an improved Eulerian-Lagrangian distance algorithm, and the dynamic weight of a case is adjusted by adopting PULL&PUSH strategy. Meanwhile, based on the and efficiency of the method are tested by using experimental system, the effectiveness, accuracy, original case base. And the results indicate that FRAWO is suitable for CBR system due to its efficiency and accuracy
出处
《系统工程学报》
CSCD
北大核心
2009年第6期764-768,共5页
Journal of Systems Engineering
基金
国家自然科学基金重点资助项目(70631003)
国家自然科学基金资助项目(70741046)
教育部博士点资助项目(20050359006)
合肥工业大学科学研究发展基金资助项目(2009HGXJ0039)
合肥工业大学博士专项基金资助项目(2007GDBJ039)
关键词
案例推理
案例检索
权重优化
病历生成
cased-based reasoning
case retrieval
weight optimizing
medical record generation