Research on the classification of mental health of officers and soldiers based on support vector machine algorithm
ZHANG Lili
HUI Duoduo
DANG Weitao
Abstract：Objective To train the sample features by using support vector machine(SVM)algorithm,and to use machine learning for mental health status,so as to realize automatic classification and recognition.Methods Firstly,undersampling method was used to solve the problem of sample imbalance,then normalization method was used to control the scores of all indicators in an interval,and samples were trained by selecting different kernel functions of SVM.Finally,hyperparameters were tuned by grid search to obtain the best parameter combination,and the samples were tested again to obtain the evaluation report of the model.Results The results showed that the accuracy,recall and F1-Score of the algorithm based on Sigmoid and RBF kernel functions were improved after grid search parameter tuning.Conclusion This paper provides an idea for the intelligent assessment of psychological risk,which can be applied to other scenarios with a little modification.
Keywords：support vector machinenormalizationgrid searchpsychological test
Publication Date：2025-05-31
Online Publishing Date：2026-08-26(First online date of this platform, not the publication date of the document)
Pages：4( 630-632,638 )