A Neural Network Evaluation Model for College Students’ Mental Health

Abstract

Due to the lack of reasonable evaluation in the analysis of college students’ mental health nowdays, this paper puts forward the strategy of combining neural network and genetic algorithm for the analysis and prediction of college students’ mental health. First, aiming at the shortcomings of traditional BP neural network, such as slow convergence speed and easy to fall into local minima, we use GA to optimize its weights and thresholds. Then, the structural characteristics of neural network and the artificial neural network toolbox of MATLAB are used for case analysis. The data sample is the total score of SCL-90 psychological scale test results as the output sample to establish a sample data set, which can predict the weight of each influencing factor of mental health. The experimental results show that the error between the predicted value and the measured value is only 1.03%, which achieves the expected effect and can reasonably evaluate the mental health of college student.