支持向量机与哈夫曼树实现多分类的研究

提出了基于哈夫曼树的支持向量机多分类方法，该方法首先将1个多分类问题分解为多个2分类问题，针对每个2分类问题使用支持向量机2分类方法解决；然后根据相异度来决策分类的优先顺序，构建基于哈夫曼树的支持向量机多分类模型；最后使用勒卡斯开源数据集进行验证，并将它与传统的支持向量机多分类方法进行实验比较。实验结果表明:新的方法在分类速度和分类精度上较传统的支持向量机多分类方法优越。

The Research of Multi-Classification Based on SVM and Huffnan Tree

A new multi-classification method which conducts a multi-classification model based on Huffman tree and SVM is proposed. It divides a multi-classification problem into multiple binary classification problems and gives classification priority depending on the dissimilarity. At last,an experiment with Lecast open source data sets verifies the effectiveness. The experimental results show that the new method has a superior effect than the traditional multi-classification method in classification speed and classification accuracy.