CAJ | 학술논문

针对标准的 C-SVM(C-support vector machine)算法在处理很多实际分类问题时，对识别错误代价损失差异很大的极端情况表现出的局限性，提出一种通用的广义支持向量机算法。根据识别错误后所付出的代价，可以把最优分类面向代价损失低的一方进行推移，留给代价损失高的一方更大的空间，提高其识别率，从而减小识别错误后带来的代价损失。该方法进一步提高了标准 C-SVM 的适用性以及样本的正确识别率，将新算法应用到高分辨雷达距离像的识别中，实验证明，广义 C-SVM 能取得比传统 C-SVM 更好的识别效果。
침대표준적 C-SVM(C-support vector machine)산법재처리흔다실제분류문제시，대식별착오대개손실차이흔대적겁단정황표현출적국한성，제출일충통용적엄의지지향량궤산법。근거식별착오후소부출적대개，가이파최우분류면향대개손실저적일방진행추이，류급대개손실고적일방경대적공간，제고기식별솔，종이감소식별착오후대래적대개손실。해방법진일보제고료표준 C-SVM 적괄용성이급양본적정학식별솔，장신산법응용도고분변뢰체거리상적식별중，실험증명，엄의 C-SVM 능취득비전통 C-SVM 경호적식별효과。
Standard C-support vector machine (C-SVM)algorithm has certain limitation when dealing with many factual pattern classification problems,especially in the extreme case such as the recognition error cost loss in great difference.A kind of generalized C-SVM algorithm is introduced.By estimating the cost of the recognition error,optimal separating hyperplane can be translated into the low cost pas-sage,and leaves more space for the high lost cost to increase recognition rate,thus reducing the damage of recognition error.The new method improves the applicability of C-SVM and sample recognition correct rate.When applied to radar high resolution range profile′s recognition,experimental results show that the proposed method can achieve better recognition effect than the traditional method.