A KIND OF INDUCTIVE LEARNING CLASSIFICATION ALGORITHM BASED ON STATISTICS RULE

摘要：

Induce learning is one of the most important research areas on application of artificial intelligence. The classification algorithm is the core of the machine learning. The article advanced a kind of decision classification algorithm that is in view of attribute value statistical regularity, on the characteristic and insufficient of ID3, C4.5 Algorithm. (In short of BS-CA) This algorithm takes the statistical regularity as foundation, and takes the multiplication as comprehensive tactics, simplifying the trimming and optimization processes of decision tree. The theory analysis and experiment shows that BS-CA possesses high accuracy, high classification speed,simple and high activity.

关键词： Induce learning Classificication algorithm Statistical rule Data mining BS-CA

作者: YAN LI FA-CHAO LI

作者单位: College of Sciences, Hebei University of Science and Technology, Shijiazhuang 050018, China College of Sciences, Hebei University of Science and Technology, Shijiazhuang 050018, China;College

会议类型: 国际会议

会议名称: 2006 International Conference on Machine Learning and Cybernetics(IEEE第五届机器学习与控制论坛)

会议地点: 大连

会议语种:英文

页码: 1308-1313

在线出版日期: 2006-08-13（万方平台首次上网日期，不代表论文的发表时间）