Iguchi Yukihiro    Department   Undergraduate School  , School of Science and Technology    Position   Professor
Date	2023/01/07
Presentation Theme	Feature Reduction in Classfication Functions Using Decision Trees
Promoters	IEICE
Conference Type	Workshop/Symposium
Presentation Type	Speech (General)
Contribution Type	Collaborative
Country	Japan
Holding period	2023/01/07～2023/01/08
Publisher and common publisher	Ryo TAKAHASHI, Tsutomu SASAO, and Yukihiro IGUCHI
Details	We developed a method to reduce the number of features in classification functions that maintains a high classification performance. The proposed method is a modified version of C4.5 algorithm. Experiments were conducted using the UCI dataset, and the results were compared with those of J48 algorithm in the WEKA system. Compared with the J48 algorithm, our method produced the number of features, but the classification performance such as accuracy was decreased.