用改进的主成分分析法对东湖的水质污染进行评价

Principal Component Analysis of the Water Quality Evaluation in East Lake

从对逆指标进行线性变换、用对数化法对指标进行无量纲化及评价指标的选择等三个方面对传统主成分分析方法进行改进,并应用于东湖的水质污染质量评价中。与传统方法相比,本文方法更为合理地保留了原始指标矩阵中的信息,且第一主成分的贡献率有了显著的提高。评价过程全部用计算机实现,并将评价结果生成东湖水质污染专题图。

The traditional principal component analysis was improved from the three aspects such as lineal transform of negative index, logarithmic treatment of original index and choosing the evaluation index. Then it was applied to the water pbllution evaluation in East Lake. Comparing with the traditional methods, it could hold more information of the original index matrix and had much higher contributing rate of the first principal component. The whole process was accomplished hy the computer and created a water pollution map.