查詢結果分析
來源資料
頁籤選單縮合
題 名 | 基於γ完全測度之Choquet積分迴歸模式=The Choquet Integral Regression Model Based on γ-complete Measure |
---|---|
作 者 | 劉湘川; | 書刊名 | 教育研究與發展期刊 |
卷 期 | 2:4 民95.12 |
頁 次 | 頁87-107 |
分類號 | 521.3 |
關鍵詞 | λ測度; P測度; v測度; γ完全測度; Choquet積分迴歸模式; λ-measure; P-measure; V-measure; γ-complete measure; Choquet integral regression model; |
語 文 | 中文(Chinese) |
中文摘要 | 當綜合測驗中之分測驗間具潛在重疊交互作用或互補交互作用時,傳統可加性整合計分方法,常功效不彰,此時應考慮採用非可加性之模糊測度與模糊積分。常用之Sugeno(1974)λ測度、Zadeh(1978)ρ測度與劉湘川(2006a,b,c,d,e)先後提出改進之m測度、ρ測度、ρ*測度、廣義m測度及ν測度等,均一致假設基本事件測度為已知,只考慮聯合事件測度之決定,當基本事件測度為未知時,上述模糊測度均不適用,本文特提出基本事件之測度為未知,須與聯合事件之測度同時決定,基於複相關係數之γ完全測度,進而提出基於γ完全測度之Choquet積分迴歸模式。 |
英文摘要 | When the sub-tests of a composite test contain interactions, the performance of the traditional additive scale method is poor. Non-additive fuzzy measures and fuzzy integral can be applied to improve this situation. Theλ-measure (Sugeno, 1974), P-measure (Zadeh, 1978), m-measure, ρ-measure, ρ*-measure, polyvalent m-measure, and ν-measure proposed by Liu (2006a, b, c, d, e) assume that the measure of basic events is known to estimate the measure of joint events. But these fuzzy measures are not suitable for the situation when the measure of the basic event is unknown. In this paper, the γ- complete measure based on the multiple correlation coefficients is proposed to estimate the measures of basic events and joint events simultaneously and a new Choquet integral regression model with this γ- complete measure is also proposed. |
本系統中英文摘要資訊取自各篇刊載內容。