基于直觉模糊聚类的电子作业抄袭检测研究

Research on Electronic Homework Plagiarism Detection Based on Intuitionistic Fuzzy Set Cluster Analysis

对电子作业做分词处理,生成语义单元序列;用动态规划法计算序列最长公共子序列,引入序列空位度概念。将最长公共子序列长度和空位度诱导出的直觉模糊数作为作业相似度模型,自然、合理。基于直觉模糊传递闭包方法对电子作业进行聚类分析。讨论基于直觉模糊聚类的电子作业抄袭检测算法的复杂度,并给出该算法的一个应用实例,结果显示该算法合理、高效。

The word is processed for electronic homework to generate semantic unit sequences. The sequence＇ s longest common subsequenee is calculated by dynamic programming method. A new concept： vacancy degree of longest common subsequence is introduced. Building a similarity degree model based on an intuitionistic fuzzy number which is inducted by longest common sub- sequence＇ s length and vacancy degree, the model is natural and reasonable. Based on intuitionistic fuzzy transitive closure clus- tering analysis algorithm, the electronic homewors are clustered. By discussing the electronic homework plagiarism detection based on intuitionistic fuzzy set cluster analysis algorithm＇ s complexity, and then gives an application example of the algorithm, the results show that the algorithm is reasonable and efficient.