摘要
针对学业分析预测模型簇中心模糊问题,采用k-means聚类算法对学生的表现数据进行分析,提出了一种学生学业表现的预测模型。在聚类分析中,结合欧式距离与距离度量公式,定义聚类优化目标函数,计算出每个元素与每个簇中心的距离。将计算出的数据元素与每个簇中心的距离进行比较,并将数据元素分配到最近的簇中心,将数据元素分配到各自的簇中心重新计算每个集群中分配的数据元素的簇中心。在明确簇中心的基础上,与学习者学习相关的数据实行聚类分析,获取学生学业表现分析预测模型。实验结果表明,该模型可准确计算出学习者对课程的忠诚度得分,提高用户在线学习的热度,精确率以及召回率均控制在90%以上,可以对教育机构提供决策帮助。
Aiming at the fuzzy problem of cluster center of academic analysis and prediction model,k-means clustering algorithm is used to analyze the performance data of students. This paper proposes a prediction model of academic performance of students. In cluster analysis,combined with Euclidean distance and distance measurement formulas,a cluster optimization objective function is defined,and the distance between each element and the center of each cluster is calculated. The calculated data elements are compared with the distance of each cluster center,and the data elements are allocated to the nearest cluster center,and the data elements are allocated to the respective cluster centers to recalculate the cluster centers of the data elements allocated in each cluster. On the basis of clarifying the cluster center,cluster analysis is performed on the data related to the learner’s learning,and the prediction model of the student’s academic performance analysis is obtained. The experimental results show that the model can accurately calculate the learner’s loyalty score to the course,improve the user’s online learning enthusiasm,and the accuracy rate and recall rate are controlled above90%,which can provide decision-making assistance to educational institutions.
作者
陈来
张华
CHEN Lai;ZHANG Hua(Fujian Police College,Fujian Fuzhou 350007)
出处
《山西警察学院学报》
2020年第2期114-118,共5页
Journal of Shanxi Police College
关键词
聚类分析
数据挖掘
学生学业表现
预测
cluster analysis
data mining
student academic performance
prediction