摘要
为提高儿童心理健康分析的精度和效率,结合《中小学生心理健康诊断测验》量表,从8个维度分析儿童心理健康状态。针对FCM聚类结果易受其初始聚类中心选择的影响,将和声搜索算法应用于FCM初始聚类中心的选择,提出一种基于IHS-FCM的儿童心理健康分析方法。与HS-FCM和BPNN对比,IHS-FCM可以有效提高儿童心理健康聚类分析的精度,为儿童心理健康分析提供了新的方法。
In order to improve the accuracy and efficiency of children’s mental health analysis, the mental health status of children was analyzed from 8 dimensions by combining with the diagnostic test of mental health of primary and secondary school students. In view of the fact that FCM clustering results are easy to be affected by the selection of its initial clustering center, the harmony search algorithm is applied to the selection of FCM initial clustering center, and a children mental health analysis method based on IHS-FCM is proposed. Compared with HS-FCM and BPNN, IHS-FCM can effectively improve the accuracy of children’s mental health cluster analysis and provide a new method for children’s mental health analysis.
作者
闵金婵
MIN Jinchan(School of Physical Education,Shanxi Preschool Teachers College,Xi’an,Shanxi 710100,China)
出处
《微型电脑应用》
2020年第8期62-64,共3页
Microcomputer Applications
基金
2017年度陕西省教育厅科学研究计划项目(17JK0176)。
关键词
和声搜索算法
模糊C-均值聚类
心理健康分析
神经网络
反向学习
儿童
harmony search algorithm
fuzzy c-means clustering
mental health analysis
neural network
reverse learning
children
