基于FCA与CBR的设计模式检测  

Design patterns detection based on FCA and CBR

作　　者：肖卓宇[1] 何锫[2] 余波[1] 黎妍 胡振涛[1] 

机构地区：[1]中南林业科技大学涉外学院,湖南长沙410200 [2]广州大学计算机科学与教育软件学院,广东广州510006 [3]湖南高速公路管理局,湖南长沙410209

出　　处：《山东大学学报（工学版）》2016年第2期22-28,共7页Journal of Shandong University（Engineering Science）

基　　金：国家自然科学基金资助项目(61170199);湖南省教育厅重点基金资助项目(11A004);湖南省大学生研究性学习和创新性实验计划资助项目(湘教通[2015]84号197);广东省自然科学基金资助项目(2015A030313501);中南林业科技大学教学改革资助项目(201509;201611)

摘　　要：以一个精确可靠的设计模式检测模型为目标,结合形式概念分析(formal concept analysis,FCA)与实例推理(case based reasoning,CBR)技术,提出一种基于更完整问题描述的改进技术模型,通过FCA与余弦理论思想计算特征指标与相近案例的相似性值Score,对其结果进行优先级排序,并取得最优选择之后,将其匹配的特征结果存储到学习模型的保存过程阶段。最后,给出一种基于平均精度MAP的性能评估方法模型。试验结果表明。Aiming to obtain the accurate and reliable detecting model of design patterns that fusion formal concept analy-sis (FCA)techniques and case cased reasoning (CBR),a novel refinement technique based on more complete software problem description was proposed.Indexes and cases similarity score value was calculated by FCA and Cosine theory. The results of the priority achieved optimal choices,the new knowledge for the retention process phase of the learning model was provided.An approach based on mean average precision (MAP)to assess the performance was proposed. Finally,the experimental results showed that the presented model had more detecting ability in term of MAP comparing to the traditional models.

关 键 词：设计模式检测 形式概念分析 典型特征值 概念格 平均精度 实例推理 

分 类 号：TP311.5[自动化与计算机技术—计算机软件与理论]