微型电脑应用

心理障碍的建模与预测是当前研究的热点,为了获得理想的心理障碍预测效果,提出了改进神经网络的心理障碍预测模型。首先分析了当前心理障碍预测的研究进展,找到当前各种心理障碍预测模型的局限性,然后采集心理障碍的历史数据,并引入混沌算法对心理障碍历史数据进行预处理,以更好地挖掘心理障碍变化特点,然后采用神经网络对预处理后的心理障碍历史数据进行学习,并引入粒子群算法对神经网络存在的问题进行改进,建立最优的心理障碍预测模型,最后与其他心理障碍预测模型进行了对比测试,结果表明,改进神经网络的心理障碍预测精度超过95%,相对于对比模型,精度提高了5%以上,同时心理障碍建模时间更短,提高了心理障碍预测的效率,具有更高的实际应用价值。

The modeling and prediction of mental disorders are the focus of current research. In order to obtain the ideal prediction effect of mental disorders, an improved neural network model for mental disorders prediction is proposed. First, we analyze the current research progress of mental disorder prediction, find out the limitations of various mental disorder prediction models, then collect the historical data of mental disorders, and introduce chaos algorithm to preprocess the historical data of mental disorders, in order to better mine the characteristics of mental disorder changes. Then we use neural network to learn the historical data of mental disorders after preprocessing, introduce particle group algorithm to improve the existing problems of neural network, establish the optimal prediction model of mental disorders, and finally compare it with other prediction models of mental disorders. The results show that the prediction accuracy of mental disorders of the improved neural network is more than 95%, which is about 5% higher than that of the comparison model. At the same time, the modeling time of mental disorders is shorter, which improves the prediction of mental disorders the efficiency of measurement. It has higher practical value.