范例库中特征项权重的发现技术

Discovery Techniques on Attribute Weighting in Case Base

系统地探讨了在范例库中引入一系列可以使用的数据挖掘技术 ,以期提高范例推理系统中知识获取的自动化程度 .为了准确地表达范例比较间的本质特征 ,重点讨论了应用于范例库上特征项赋权的基本技术 ,并提出了一个自适应发现算法 ,然后进行了实验 。

Data mining approaches used in case base have been researched systematically. Data mining techniques may automate the acquisition of the knowledge and heighten the whole competence of the intelligent system. In order to represent characteristics comparison between cases, it is suggested that data mining techniques could be used in attribute weighting, and one adaptive algorithm is put forward. The experimental result shows that this method has good accuracy and better performance than other methods.