透過您的圖書館登入
IP:3.23.101.60
  • 學位論文

以FCM為基礎之混合式演算法於中醫疾病經脈資料之分類

Using a Hybrid Computational Approach Based on FCM for Classification of Diseases in Traditional Chinese Medicine Meridian Data

指導教授 : 陳大正
若您是本文的作者,可授權文章由華藝線上圖書館中協助推廣。

摘要


模糊認知圖乃是一種描述因果關聯之模型,其可以分析變因間是否存在隱含的因果關連,而使得決策者能更深入洞悉問題本質而獲得更佳的解決方案。過去文獻中鮮少探討在缺乏專家意見的參與下如何建構最佳之模糊認知圖以探討分類之相關研究,故本研究應用混合式演算法建構模糊認知圖,透過基因演算法隨機產生初始的認知概念變因的數目和對應的變因,並應用粒子群演算法來決定對應該認知概念變因子集最佳的變因關聯矩陣,再經由模糊認知圖的矩陣運算推論分類之結果。 本研究在無任何專家意見的參與下,應用混和式進化演算法來建構一個最佳之模糊認知圖,將中醫師對於十二經脈的主觀認知客觀化,藉由十二經脈提取脈象之間的關連作為疾病判別之依據。 本研究和文獻中各種方法及商業軟體比較結果,實驗數據顯示本研究所提出之關連矩陣有較好的疾病分類準確度優於其它分類的方法,且所提取經脈集合也較小於其它分類的方法。

並列摘要


A fuzzy cognitive map is the model for description of causation in an event. It has been applied to find the implicit relationship between variables. The more advanced in nature of questions, the best solution decision-makers will do. Previous literature shows that the construction of well defined FCM without experts’ attendance is impossible. In this study, we proposed a hybrid computation approach to construct the fuzzy cognitive maps. The proposed approach is composed of two evolutionary computation methods which genetic algorithm(GA) and particle swarm optimization(PSO). The purpose of GA is to decide the significant variables. Based on those variables selected by GA. PSO will construct the most appropriate FCM, i.e., the relationship matrix for the set of variables. The proposed computational approach is then applied to construct the most appropriate fuzzy cognitive map without any experts’ advice. In this study, the diagnosis of traditional Chinese medicines’ has been investigation of base on twelve-meridian data obtained by meridian energy analysis device (MEAD). The computational results show the proposed approach can provide higher classification accuracy than those of the approaches in literature or commercial software.

參考文獻


【28】林文建、吳明珠,“經脈研究的進展”中國中醫臨床雜,10,338-344,2004.
【31】王佩、謝啟文,“中醫經典文獻探討經脈”,中西整合醫學雜誌,2,41-47,2000.
【2】Demetrio Lagana, P.L., and Ornella Pisacane, F.V.,“Solving simulation optimization problems on grid computing systems”, Parallel Computing, 32, pp. 688-700, 2006.
【4】Cortes, P., Larraneta, J., and Onieva, L., “Genetic algorithms for controllers in elevator groups: Analysis and simulation during lunchpeak traffic”, Appl. Soft. Comput., vol. 2, pp. 159–174, May 2004.
【7】Axelrod, R., “Structure of decision: the cognitive maps of political elites”, New York: Princeton, USA, 1976.

延伸閱讀