基于投影寻踪回归的电离辐射污染程度预测方法研究

Prediction Method of Ionizing Radiation Pollution Degree Based on Projection Pursuit Regression

为了有效保证市民的健康以及保护生态环境,设计并提出一种新型电离辐射污染程度预测方法。首先选用投影寻踪回归新技术,结合计算技术,将高维数据利用线性组合的方式转变为低维数据,从而组建电离辐射污染程度预测模型,根据详细的分析结果给出具体的辐射安全监管措施,研究重点选用“审视数据——模拟——预测”等操作过程为数据分析提供全新的途径,从而实现电离辐射污染的非线性、非正态问题的有效解决。相关研究结果表明,所设计模型的样本拟合率高达99.5%。

In order to effectively ensure the health of citizens and protect the ecological environment,a new method for predicting the degree of ionizing radiation pollution is designed and proposed.The study used new projection pursuit regression technology and combined with computing technology to convert high-dimensional data into low-dimensional data by linear combination,so as to build a prediction model of ionizing radiation pollution degree,and give specific radiation safety supervision measures based on detailed analysis results.The research focuses on selecting“review data-simulation-prediction”and other operating processes to provide a new way for data analysis,so as to achieve effective solutions to the nonlinear and non-normal problems of ionizing radiation pollution.Related research results show that the sample fitting rate of the designed model is as high as 99.5%.