基于K-means聚类的大学生综合素质评定方法  

K-Means Cluster Based Ability Evaluation Method for University Students

作　　者：冯小芹[1] 何宏[1] 胡晓辉[1] 孙晨旭[1] 向朝参[1] 喻赛萱 

机构地区：[1]中国人民解放军后勤工程学院,重庆401331 [2]四川文轩职业学院,成都611330

出　　处：《重庆理工大学学报（自然科学）》2017年第5期125-132,共8页Journal of Chongqing University of Technology：Natural Science

基　　金：国家自然科学基金资助项目(61502520)

摘　　要：随着教育改革呼声的提高,科学评定高等院校学生的综合能力素质成为各大高校的焦点。民主测评常常被作为大学生综合素质能力的评定方法,然而由于民主测评的不确定性和不可控性以及学生实际综合能力的复杂性,如何基于民主测评来客观、可靠、准确地评定学生综合素质能力是一大难题。针对该问题,提出了基于K-均值聚类的大学生综合素质评定方法。首先将民主测评数据处理成数据矩阵,然后通过K-均值聚类进行数据矩阵的预处理,剔除不准确、不可靠的民主测评数据,最后根据保留数据进行学员综合能力素质评定。基于重庆某高校12个专业278名学生的实际民主测评数据的实验结果表明:所提方法能够较为客观、准确地评定学生综合素质。同时,理论分析表明算法复杂度较小。It is critical for the university to accurately evaluate the ability of students with the development of education reform. However, it is very difficult to evaluate the students＇ ability reliably and objectively due to the extremely complex ability of students. As a result, this paper proposed a K- means cluster based ability evaluation method for university students. Firstly, we pre-process the dataof democratic appraisal, followed by eliminating the inaccurate data using K-means cluster. At last, according to the remaining accurate data, we rate the students＇ ability. The real experiments show that, our method can accurately evaluate the students＇ ability based on the real democratic assessment data of 278 students of 12 majors in a university at Chongqing. Moreover, the theoretical analysis illustrates that the time complexity is low.

关 键 词：民主测评 K-均值聚类 学员综合素质能力 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]