Steamed Palm Classification by Decision trees and Neural Network

カテゴリ: 全国大会

論文No: 3-040

グループ名: 【全国大会】平成14年電気学会全国大会論文集

発行日: 2002/03/26

タイトル(英語): Steamed Palm Classification by Decision trees and Neural Network

著者名: Prasetijo Dwi Wiratno (早稲田大学),内田 健康(早稲田大学)

著者名(英語): Prasetijo Dwi Wiratno (Waseda University),Kenkou Uchida(Waseda University)

要約(日本語): In the palm oil production process, when applied to imperfectly steamed palm, will influence the quality and increase the production cost. Accordingly, we need a classification of steamed palm to best select well-steamed palm. Decision trees and neural network are data classification methods that are used. Decisions tree is a flow chart like tree structure, each branch represents an outcome of the test, and leaf nodes represent classes. Neural network is a set of connected input/output units where each connection has a weight associated with it. This paper reports results of applying both methods. While both approaches substantially give predictive accuracy, neural network shows better result.

原稿種別: 日本語

PDFファイルサイズ: 114 Kバイト