Data Discretization using Statistical Maximum Likelihood Approach
Data clustering technique has been applied in many research areas. An efficient data clustering mechanism not only discriminates patterns from an information system but also increases the visibilities of the recognized patterns. In general, a decision table in an information system is the kernel of the decision-making processes that generate decision rules. Considering an information system, the object and the attribute are two essences that construct a decision table. The attribute values also called features, which describe object behaviors, have various domain types. In practice, a typical attribute domain could contain either a set of continuous numbers or a set of nominal codes. The variety in attribute domains increases computational complexity and difficulty. In some research areas, such as data mining and knowledge discovery from database(KDD), a meaningful and easy-to-interpret information model is required. Thus, an effective data transformation method or an efficient data clustering mechanism for those information models are highly in demand. In this paper, we proposed an effective data transformation approach that precisely partitions continuous numbers into optimized discrete intervals. The proposed technique has been applied to different sets of data for comparison. The result of our experiments is encouraging.
원문복사신청을 하시면, 일부 해외 인쇄학술지의 경우 외국학술지지원센터(FRIC)에서
무료 원문복사 서비스를 제공합니다.
NDSL에서는 해당 원문을 복사서비스하고 있습니다. 위의 원문복사신청 또는 장바구니 담기를 통하여 원문복사서비스 이용이 가능합니다.
- 이 논문과 함께 출판된 논문 + 더보기