基于免疫关联挖掘的教学信息评价  

Teaching Quality Evaluation Based on Immune Association Rule Mining

作　　者：徐雪松[1] 王四春[1] 

机构地区：[1]湖南商学院信息学院管理工程研究所,长沙410205

出　　处：《情报学报》2011年第5期508-513,共6页Journal of the China Society for Scientific and Technical Information

基　　金：国家自然科学基金项目（60425310）; 湖南省自然科学基金项目（No.05JJ40103）; 湖南省社会科学基金项目（No.09ZDB080）

摘　　要：针对数据挖掘中的关联规则挖掘广度及效率问题,提出了一种基于免疫优化的关联规则挖掘算法。将数据原始记录和候选模式分别作为抗原和识别抗体,通过免疫聚类竞争加速克隆扩增,提高抗体成熟力及亲和性,增强候选模式支持度。在算法执行过程中,支持度大于阈值的优秀个体都将被作为记忆细胞保存下来。这样,记忆细胞所代表的模式满足最小支持度要求,可以很容易提取出也同时满足最小置信度要求的关联规则。试验表明,该算法加快了关联规则挖掘的收敛速度,具有更强的全局与局部搜索能力,提高了所得关联规则的准确率。在高校教学质量评估及规则挖掘中体现出应用价值。Aiming at the problem of the efficiency and large scales of association rules mining,a novel association rule mining algorithm based immune clonal was proposed.Raw data are regarded as antigen and candidate patterns are regarded as antibody,through the antibody clustering and competing,enhancing the antibody＇ s affinity maturation rate and improving the support of candidate patterns.In the process of algorithm implementation,those who excellent individuals more than support threshold will be preserved as memory cells,which represents the model satisfied the requirement minimum support,it can be easily extracted the association rules,also have the minimum confidence.The simulation illustrates that this algorithm can increase the convergence velocity and advance veracity of the association rule,and has the remarkable quality of the global and local research reliability.Applying it in university teaching quality evaluation and rules mining shows its application value.

关 键 词：关联规则 质量评估 克隆选择 数据挖掘 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]