论文部分内容阅读
采用Boosting算法对多硝基芳香族化合物(PNACs)的密度进行预估。选用分子结构描述码作为输入特征参数。结果表明,PNACs的密度与其分子结构存在良好的相关性,与人工神经网络相比,Boosting算法对预测的准确性有显著提高,预测结果的相对误差都在8%以内。
The density of polynitroaromatics (PNACs) is estimated using the Boosting algorithm. Use molecular structure descriptors as input characteristic parameters. The results show that there is a good correlation between the density of PNACs and its molecular structure. Compared with artificial neural network, the accuracy of prediction of Boosting algorithm is significantly improved, and the relative error of prediction results is less than 8%.