A Method for Partitioning Continuous Attribute Values Based on Interval Similarity
MAO Mingyang
Abstract：A new Region Analogy-based continuous attributes partition approach called RA-PA is proposed in this paper.In RA-PA,a new region analogy function which can realizes fair and quantifying the real value attributions exactly and reasonably is used.A new partition algorithm to finding the best partition results is also described in detail for inductive learning in data mining.A series of experiments to evaluate the utility of RA-PA method on Irvine repository dataset at the University of California has been done.The simulation results show that RA-PA significantly can improve the mean accuracy of inductive learning algorithms than other known quantization methods such as Modify Chi2,MDLP,Extended Chi2.
Keywords：region analogydiscretizationcontinuous attributes partitiondata mininginductive learning algorithm
Publication Date：2025-06-20
Online Publishing Date：2025-09-23(First online date of this platform, not the publication date of the document)
Pages：4( 1539-1541,1563 )