论文部分内容阅读
以往的土壤分类与等级综合评价多是建立在模糊数学 (Fuzzy)基础上的模糊聚类分析与模糊综合评判 ,因此不可避免的涉及权重矩阵人为干扰 ,导致分类与评价结果的人为倾向。本文将高维降维技术——投影寻踪评价模型 (PPE)应用到土壤学科领域 ,利用改进的加速遗传算法 (RAGA)优化投影方向 ,将多维数据指标转换到低维子空间 ,通过寻求最优投影方向及投影函数值来实现对土壤的分类与等级评价 ,避免了主观赋权的人为干扰 ,取得了较好效果 ,可为土壤分类与等级评价研究提供一条新思路
In the past, soil classification and grade comprehensive evaluation mostly based on fuzzy mathematics (Fuzzy) clustering analysis and fuzzy comprehensive evaluation, therefore inevitably involves the weight matrix interference, leading to classification and evaluation results of the artificial tendency. In this paper, PPE is applied to the field of soil science. The improved accelerating genetic algorithm (RAGA) is used to optimize the projection direction, and the multidimensional data is transformed into low dimensional subspace. Excellent projection direction and projection function to realize soil classification and grade evaluation, avoiding the subjective empowerment of man-made interference, and achieved good results, which can provide a new idea for soil classification and grading evaluation