Abstract: In order to solve the misclassification problem resulted from the imbalance of the number of training samples of different classes in the process of class-incremental learning for support vector machine，presents a weighted class-incremental learning algorithm.It uses one against rest training method to construct a new binary classifier takes all the samples from known classes as negative and that of the new class as positive，also introduces weight factors for classes according to the proportion of the training samples，which can effectively improve the classification accuracy of class that has fewer samples.The experiment shows that the result of this method is effective.

Key words: Support Vector Machines（SVM）, class-incremental learning, classification algorithm, weight

摘要： 针对支持向量机类增量学习过程中参与训练的两类样本数量不平衡而导致的错分问题，给出了一种加权类增量学习算法，将新增类作为正类，原有类作为负类，利用一对多方法训练子分类器，训练时根据训练样本所占的比例对类加权值，提高了小类别样本的分类精度。实验证明了该方法的有效性。

关键词: 支持向量机, 类增量学习, 分类算法, 加权