Classifier using Extended Data Expression

C4.5 is a classification algorithm, an improved version of ID3. C4.5 is fast and deduces good result by constructing a decision tree on the problem of classification. Therefore C4.5 plays an important role in the field of classifier learning systems. This paper proposes two methods based on the decision tree for solving a classification problem. We construct the decision tree by using the measure of C4.5. First, an extended data expression of the existing C4.5 is described. Second, UChoo, a method of generating a rule from the previously made decision tree of C4.5 by using the extended data expression, is described. The rules expressed in the newly proposed method have almost the same information content as the original data set. This is quite an important result, as the size of the instance set will become usually large as the ubiquitous computation environment develops. It is not possible to keep all the individual instance data in memory. Instead, using the proposed method, large amount of data reduction can be done without losing information content.