一种基于小生境的模糊支持向量机新算法

A new algorithm of fuzzy support vector machine based on niche

提出了一种基于小生境的模糊支持向量机新算法,该算法主要是通过对样本小生境与类小生境之间对比,并利用类小生境中样本最小半径来度量样本与类之间的关系,改变传统支持向量机简单使用样本欧氏距离来度量样本与类之间的关系的方法,克服了传统支持向量机算法对噪声和异常点过于敏感以及有效样本区分度差等缺点.实验数据表明,与只使用基于样本与类中心之间距离的传统模糊支持向量机算法相比,该算法提高了算法的收敛速度,且大大增强了包含噪声样本与有效样本的区分度.

A new algorithm of fuzzy support vector machine based on niche is presented in this paper. In this algorithm, through comparing samples niche with class niche, the method of simply using Euclidean distance to measure the relationship of samples and class in the traditional support vector machine is changed by using the minimum radius in class niche, and the disadvantages of traditional support vector machine, which are sensitive to noise and outliers, and poor performance of differentiation of valid samples are overcome. Experimental data show that compared with the traditional support vector machine which only uses the distance between the sample and the center of class, this new algorithm can improve the convergence speed, and thus greatly enhance the discrimination between valid samples and noise samples.