论文部分内容阅读
在模式识别中,特征选择是其中非常重要的步骤,特征集的选择直接影响分类器的精度.该文提出了一种基于遗传算法的特征权重确定方法,首先使用传统遗传算法进行特征的初步选择,得到一个粗选的特征集;然后使用实数编码的遗传算法在第一步的基础上进一步精选特征,并确定每个入选特征的权重.通过实验和一些传统特征选择方法进行对比,结果显示,该文提出的算法取得了较好的效果.
In pattern recognition, feature selection is one of the most important steps. The selection of feature sets directly affects the accuracy of the classifier. In this paper, a method of feature weight determination based on genetic algorithm is proposed. Firstly, the traditional genetic algorithm , Then get a rough feature set, and then use the real-coded genetic algorithm based on the first step to further select features and determine the weight of each of the selected features.Experiments and some traditional feature selection methods for comparison, the results show , The algorithm proposed in this paper has achieved good results.