数据挖掘中分类方法的研究

分类是数据挖掘中的最重要的技术之一。目前实现分类的方法有统计方法、机器学习方法和人工智能方法等，常用的技术有决策树分类、贝叶斯分类、神经网络分类等。通过对当前具有代表性的分类算法原理进行分析、比较，总结出每种算法的性能特征，既便于使用者了解掌握各种分类算法、更好地选择合适的算法，又便于研究者对算法进行研究改进，提出性能更好的分类算法。

Research of Classification for Data Mining

Classification is one of the most important tec hn iques in data mining. At present there are many methods to achieve classificatio n, such as statistics, machine learning, artificial intelligence, etc. And the t echniques such as decision tree, Bayes, neural network are often used in various classified application. In this paper, we summarize the main features of every algorithm by analyzing and comparing a variety of typical classified algorithms. This summary can be used to learn these classified algorithms better and select an appropriate algorithm for the application. It can also be used to provide a basis for improving old algorithms or developing new effective ones.