人工神经网络在含氧有机化合物定量结构-保留关系中的应用

Study on QSRR of Oxygen-containing Organic Compounds Based on ANN

采用人工神经网络(ANN)对一系列含氧有机化合物的气相色谱保留指数建立定量结构-保留关系(QSRR)的模型,和多元线性回归(MLR)预测结果进行比较。在OV-1固定相上,相关系数R分别为0.989 1,0.991 1;在SE-54上,相关系数R分别为0.989 2,0.991 7。结果表明:MLR建立的模型优于ANN,具有良好的拟合度和预测精度。

Artificial neural network（ANN） was used to establish model of quantitative structure-retention relationship（QSRR） for a series of oxygen-containing organic compounds GC retention index,and it was compared with predictive results by multiple linear regression（MLR）.The correlation coefficient on OV-1 is 0.989 1 and 0.991 1 respectively;that on SE-54 is 0.989 2,0.991 7.The results show that the MLR predicted results have better degree of fitting and forecast accuracy than those of ANN.