基于K最近邻样本平均距离的代价敏感算法的集成

Integration of cost-sensitive algorithms based on average distance of K-nearest neighbor samples

为了解决不均衡数据集的分类问题和一般的代价敏感学习算法无法扩展到多分类情况的问题,提出了一种基于 K 最近邻( K NN)样本平均距离的代价敏感算法的集成方法。首先,根据最大化最小间隔的思想提出一种降低决策边界样本密度的重采样方法;接着,采用每类样本的平均距离作为分类结果的判断依据,并提出一种符合贝叶斯决策理论的学习算法,使得改进后的算法具备代价敏感性;最后,对改进后的代价敏感算法按 K 值进行集成,以代价最小为原则,调整各基学习器的权重,得到一个以总体误分代价最低为目标的代价敏感AdaBoost算法。实验结果表明,与传统的 K NN算法相比,改进后的算法在平均误分代价上下降了31.4个百分点,并且代价敏感性能更好。

To solve the problem of classification of unbalanced data sets and the problem that the general cost-sensitive learning algorithm can not be applied to multi-classification condition,an integration method of cost-sensitive algorithm based on average distance of K -Nearest Neighbor ( K NN) samples was proposed. Firstly,according to the idea of maximizing the minimum interval,a resampling method for reducing the density of decision boundary samples was proposed. Then,the average distance of each type of samples was used as the basis of judgment of classification results,and a learning algorithm based on Bayesian decision-making theory was proposed,which made the improved algorithm cost sensitive. Finally,the improved cost-sensitive algorithm was integrated according to the K value. The weight of each base learner was adjusted according to the principle of minimum cost,obtaining the cost-sensitive AdaBoost algorithm aiming at the minimum total misclassification cost. The experimental results show that compared with traditional K NN algorithm,the improved algorithm reduces the average misclassification cost by 31.4 percentage points and has better cost sensitivity.