CAJ | 학술논문

针对传统的Adaboost算法可能出现在应对较大训练数据集训练时间过长的问题，提出了一种改进的Adaboost 算法———PCAdaboost。改进算法利用PCA方法的降维技术，对训练样本特征提取主要成分，去除输入样本特征间的相关性，提高分类精度。同时，从样本阈值搜索角度考虑了特征值等分和特征值空间维数，给出了阈值快速搜索方法。实验结果表明，该算法在UCI数据集上取得较好的效果。
침대전통적Adaboost산법가능출현재응대교대훈련수거집훈련시간과장적문제，제출료일충개진적Adaboost 산법———PCAdaboost。개진산법이용PCA방법적강유기술，대훈련양본특정제취주요성분，거제수입양본특정간적상관성，제고분류정도。동시，종양본역치수색각도고필료특정치등분화특정치공간유수，급출료역치쾌속수색방법。실험결과표명，해산법재UCI수거집상취득교호적효과。
In view of the problem of the long training time in dealing with large training dataset in the training process of the traditional Adaboost algorithm , an improved methods was introduced to these problem .Improved al-gorithm using PCA dimension reduction technique , extracts main ingredients for the training sample feature , re-moves the correlation between the input sample characteristics , and improves the classification accuracy .At the same time , from the angle of sample threshold search takes into consideration the divisions and eigenvalue space di -mension, threshold fast search method is presented .Experimental results show that the algorithm to achieve better results on UCI datasets .