针对现有特征选择方法计算量大、速度慢的缺点,提出了一种基于SVM的快速特征选择算法。该算法使用SVM作为分类器,并利用粒子群优化算法进行搜索。通过利用SVM线性核与多项式核函数的特性,减少了在特征选择中训练分类器的次数,降低了计算复杂度。实验结果表明在不损失分类精度的情况下,能显著提高特征选择的速度。 Aiming at the shortcomings of high computational complexity and slow speed of existing feature selection methods, a fast feature selection algorithm based on SVM is proposed. The algorithm uses SVM as a classifier, and uses PSO to search. By using the characteristics of SVM linear kernel and polynomial kernel function, the number of training classifiers in feature selection is reduced and the computational complexity is reduced. The experimental results show that the speed of feature selection can be significantly improved without losing the classification accuracy.