一种改进的模糊认知诊断模型

发布时间：2018-03-16 11:21

本文选题：认知诊断　切入点：连接型　出处：《数据采集与处理》2017年05期 　论文类型：期刊论文

【摘要】：认知诊断模型利用学生做题的得分情况和测试题-知识点的关系来挖掘学生的潜在特质,以得到学生对知识点的掌握情况,进而可以预测学生对测试题的得分情况。但已有的认知诊断模型一般都忽视了主观题中学生对知识点的掌握数量和掌握程度及知识点的重要性对认知诊断的影响。本研究提出一种改进的模糊认知诊断模型(Revised fuzzy cognitive diagnosis framework,R-FuzzyCDF),在主观题的诊断中假设随着学生掌握知识点的个数增多,学生正确作答的概率增高,并考虑了知识点的重要性对认知诊断的影响,实验结果表明这种改进的FuzzyCDF模型进一步提高了认知诊断的准确性。
[Abstract]:The cognitive diagnostic model uses the relationship between the students' scores and the test questions-knowledge points to excavate the students' potential characteristics, so as to obtain the students' mastery of the knowledge points. However, the existing cognitive diagnostic models generally ignore the influence of the number and degree of students' mastery of knowledge points and the importance of knowledge points on cognitive diagnosis. In this study, an improved fuzzy cognitive diagnosis model, revised fuzzy cognitive diagnosis framework, R-FuzzyCDFs, is proposed. In the diagnosis of subjective questions, it is assumed that with the increase of the number of knowledge points grasped by students, The probability of students' correct answer is increased, and the influence of the importance of knowledge points on cognitive diagnosis is considered. The experimental results show that the improved FuzzyCDF model can further improve the accuracy of cognitive diagnosis.
【作者单位】：桂林电子科技大学计算机与信息安全学院;桂林电子科技大学广西可信软件重点实验室;
【基金】：国家自然科学基金(61363029,61662014)资助项目广西区科学研究与技术开发项目(桂科攻14124005-2-1)资助项目教育部在线教育研究基金(全通教育)课题(2016YB155)资助项目广西高校图像图形智能处理重点实验室课题(GIIP201505)资助项目
【分类号】：G420;O211

【相似文献】