應用模糊推論機制於知識本體管理之研究

Apply Fuzzy Inference Mechanism for Ontologies Management

謝東成(Tung-Cheng Hsieh)

指導教授 ： 李健興

共同指導教授 ： 陳祈男(Chyi-Nan Chen)

長榮大學/資訊暨工程學院/資訊管理研究所/碩士(2006年)

https://doi.org/10.6833/CJCU.2006.00095

摘要

近年來由於全球的人口逐年老化，呼吸重症病患也逐年遞增，因此必須依賴呼吸器的病患便日漸劇增，病患必須經常停留在加護病房，以致於加護病房床位不足，使得急診病患無法即時就醫，呼吸照護機制之研究在臨床上便扮演更重要的角色。因此，醫療照護人員必須要透過網際網路提供病患相關資訊，以及整合病患資訊以利照護程序。本論文應用知識本體(Ontology)表達健康照護領域知識，透過本研究所開發的一套知識本體編輯瀏覽器(Ontology Editor Viewer)提供領域專家編輯健康照護知識本體(Healthcare Ontology)，再利用先前學者所提出的相似度衡量方法，針對健康照護知識本體與統一醫學語言系統知識本體的知識，經由概念關聯值生成、概念相似度生成、機率向量生成以及機率分佈生成等處理程序計算出兩個知識本體之間Concept的相似性，最後透過模糊推論機制推論兩個知識本體整體的相似性。經由實驗數據驗證結果，本論文所提出之推論方法能夠有效的對知識本體之間相似性進行評估，並且作為未來知識本體整合上的參考依據。

關鍵字

知識本體 ； 知識本體整合 ； 統一醫學語言系統 ； 相似度衡量 ； 健康照護 ； 模糊推論機制

並列摘要

Recently, owning to the fact that the number of patients who suffer from the respiratory diseases are increasing progressively. It is important to take respiratory and critical care medicine seriously. Additionally, patients who are long-term mechanical ventilators are also rising increasingly around the world so that the resources of the intensive care unit (ICU) are keeping in shortage. The emergency case could not take medical treatment immediately. Therefore the respiratory healthcare plays an important role in clinical care medician. In addition, healthcare providers need to offer patient information by Internet, then they integrate those information. Therefore, healthcare providers will address healthcare procedure according to the information. In this thesis, we apply the characteristic of the ontology to describe the domain-specific knowledge of healthcare. We develop an Ontology Editor Viewer to offer domain expert editing the healthcare ontology. We adopts similarity measure that included Associated Concept Value Generator, Concept Similarity Generator, Probability Mass Value Generator and Probability Distribution Generator to compute concept similarity between healthcare ontology and UMLS ontology. Finally, the Fuzzy Inference Mechanism will infer the similarity between healthcare ontology and UMLS ontology. Experimental results show that our approach can work effectively for evaluating similarity of those two ontologies. Therefore, the proposed method can be used a referred decision on merging ontologies in the future.

並列關鍵字

Ontology ； Ontology Integration ； UMLS ； Healthcare ； Similarity Measure ； Fuzzy Inference Mechanism

參考文獻

[3]H. Alani, S. Kim, D. E. Millard, M. J. Weal, W. Hall, P. H. Lewis, and N. R. Shadbolt, “Automatic ontology-based knowledge extraction from web documents,” IEEE Intelligent Systems, vol. 18, no. 1, pp. 14-21, Jan.-Feb. 2003.

[4]C. Brewster, and K. O'Hara, “Knowledge representation with ontologies: the present and future,” IEEE Intelligent Systems, vol. 19, no. 1, pp. 72-81, Jan.-Feb. 2004.

[5]B. Chandrasekaran, J. R. Josephson, and V. R Benjamins, “What are ontologies, and why do we need them?,” IEEE Intelligent Systems, vol. 14, no. 1, pp. 20-26, Jan.-Feb, 1999.

[6]S. Dessena, A. R. Mori, and E. Galeazzi, “Development of a cross-thesaurus with Internet-based refinement supported by UMLS,” International Journal of Medical Informatics, vol. 53, no. 1, pp. 29-41, Jan. 1999.

[7]R. O. D’Aquila, C. Crespo, J. L. Mate, and J. Pazos, “An inference engine based on fuzzy logic for uncertain and imprecise expert reasoning,” Fuzzy Sets and Systems, vol. 129, no. 2, pp. 187-202, July 2002.