可拓理論(Extension theory)是透過事物變化的可能性,用以解決矛盾問題的科學。目前已有許多研究將可拓理論應用於決策、控制、檢測、診斷、評判及識別等領域,但是僅有少數研究進行改善可拓理論的判斷準確度。所以本研究應用統計概念,發展一套新的關聯函數公式來提升可拓理論於分類問題之準確度,並且藉由九個UCI(University of California-Irvine)資料集合,來驗證其績效表現。實驗結果顯示,本研究所提出之修正式可拓理論可以顯著地改善可拓理論分類正確率。此外,與其他2個知名分類器(k-鄰近解法則、決策樹)相比,也達到令人滿意的分類表現。
The extension theory (ET) is one of the simplest and most attractive pattern classification methods. However, the traditional extended relational function used in extension theory does not provide very useful summaries of asymmetrical data. This study proposes a modified extension theory (MET) to overcome these shortcomings. Experimental results indicate that the MET consistently achieved better or comparable results than the traditional ET. The MET also produces a classifier with satisfactory classification accuracy compared with wellknown classifiers (e.g., decision trees and k-nearest neighbor).