摘要
面对当前大学生心理健康层出不穷的现状,为了全面了解大学生心理健康现状和需求,以提升大学生心理健康评估效果为目的,提出了基于数据驱动的大学生心理健康评估方法。这种方法采用改进模糊聚类算法,通过引入不确定隶属度,促使样本中的元素属于同一个聚类;利用不确定性隶属度的记忆存储功能,有效减少计算循环次数;合理准确的获取相关评估指标,建立评估指标体系;结合模糊综合评估模型,充分考虑模糊性的影响,根据各指标不同的重要性,采用归一化方法确定模糊权重,合成所有模糊权重得到综合评估模型,实现定性评估与定量评估的结合。实验结果表明,该评估方法聚类运行稳定,可实现大学生心理健康评估且评估误差低,具有良好的参考性和推广价值。
Facing on the current situation of college students’mental health,in order to fully understand the status and needs of college students’mental health,and to improve the effect of mental health assessment,this paper studies the method of college students’mental health assessment based on data-driven.Using the improved fuzzy clustering algorithm,by introducing the uncertain membership degree,the elements in the sample belong to the same cluster.The memory storage function of the uncertain membership degree is used to effectively reduce the number of calculation cycles,and reasonably and accurately obtain the relevant evaluation index.An evaluation index system is established by combining with the fuzzy comprehensive evaluation model.It fully considers the impact of fuzziness.The fuzzy synthetic weight model is used to determine the importance of different indicators.The experimental results show that the clustering operation of the evaluation method is stable,and it can realize the evaluation of college students’mental health with low error,which has good reference and promotion value.
作者
李刚
陈洁
LI Gang;CHEN Jie(Second Affiliated Hospital of Shaanxi University of Traditional Chinese Medicine,Xianyang 712000,China;Xi’an Big Data Service Center,Xi’an 710001,China)
出处
《微型电脑应用》
2022年第11期163-166,共4页
Microcomputer Applications
关键词
数据驱动
大学生
心理健康
评估研究
模糊聚类算法
评估模型
data driven
college students
mental health
evaluation research
fuzzy clustering algorithm
evaluation model