- 學位論文
實作領域本體應用在糖尿病藥物查詢系統
The Implementation of Domain Ontology Applying to Diabetes Drugs Query System
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
隨著資訊科技的進步與網際網路的蓬勃發展加速了知識的傳播，相對的也產生了過多知識的問題。此外，在知識多元化的時代有很多相關領域知識由於可能來自不同國家、專家、系統、部門組織…等，導致目前還是有許多相關知識無法有效的來做整合(Integration)，以至於知識無法達到一個完整性。由於目前在特定領域(例如：醫療、企業…等)之知識來源來自不同的文件、企業…等，因此在知識的呈現與架構的表示會因人而異，所以知識整合就必須要解決溝通的障礙、彼此互動的限制、彼此之間能分享的困難以及彼此相關聯之關係。本研究將以糖尿病用藥為例，將依據美國糖尿病學會(ADA)、美國臨床內分泌科學會(AACE)、中華民國糖尿病學會和英國國家衛生事業局(NHS)，四個糖尿病學會的用藥之知識建立出領域本體知識，並且先做前置處理將這些本體知識做初步相似性之測量，找出彼此之間關聯性並且評估出推薦之藥物。此外，將本體知識做一個整合的動作以及將格式做一個轉換並且轉存到Joseki，然後使用者可以透過SPARQL的平台寫指令來查詢所需要的資料。為了讓使用者可以更方便的使用這套系統，本文將建置一個圖形使用者介面(GUI)來讓使用者方便查詢。另外，在本論文將對使用到的技術及方法做概述(例如：本體論、OWL、本體整合、SPARQL…等)。除此之外，將本研究的架構做一個簡介以及將各個糖尿病學會的用藥知識做一個分類，因為在不同的情況下所能服用的藥物在不同糖尿病學會之間並不完全相同。本論文完成之後，將提供給使用者更便利的取得不同學會之間相關的用藥知識，如此一來也能提高配藥之準確度。
並列摘要
The rise and development of information technologies with internet has accelerated the spread of knowledge, but is coupled with too much knowledge problems. Even in the same topic, experts from different backgrounds may have different opinions about domain knowledge. Therefore, it is hard to integrate effectively when the knowledge is acquired from various sources in a particular area such as medicine, business and so on. Moreover, the knowledge-presentation will vary from one to another. All these limit the interaction with each other, and make the share and association with others difficult. In order to overcome the barries of communication, the issue of knowledge integration must be addressed. This research will use guidelines of oral diabetes drugs for type 2 diabetes mellitus as examples to do the knowledge integration and make an application. There are 4 versions of guidelines cited, including American Diabetes Association (ADA), American Association of Clinical Endocrinology Society (AACE), the Republic of China Diabetes Association and the British National Health Service Bureau (NHS). This project will integrate the four guidelines of oral diabetes drugs to establish knowledge ontologies. Our system consists of three parts: (1) the ontologies will be pre-processed and we will calculate the similarity between the ontologies and then find out the correlation between ontologies, (2) the system transfers the ontologies format into Joseki, and (3) the user through a graphical user interface to obtain information. In addition, this paper will present an overview of techniques and methods, such as ontology, ontology integration, OWL, SPARQL, and so on. And then the structure of this paper we make an introduction and the Diabetes Association of each medication will be a classification of knowledge, because in different situations use the drugs are not the same between the different diabetes associations.
參考文獻
[3] Chandrasekaran, B., Josephson, J. R., and Benjamins, V. R.(1999), “What Are Ontologies, and Why Do. We Need Them?,” IEEE Intelligent Systems, Vol. 14, No. 1, pp. 20-26.
[5] Chassin, L., Wilinska, M., and Hovorka, R.(2004), “Evaluation of Glucose Controllers in Virtual Environment: Methodology and Sample Application,” Artificial Intelligence in Medicine, Vol. 32, No. 3, pp. 171-181.
[7] Campos-Delgado, D. U., Hernadez-Ordonez, M., Femat, R., and Gordillo-Moscoso, A.(2006), “Fuzzy-Based Controller for Glucose Regulation in Type-1 Diabetic Patients by Subcutaneous Route,” IEEE Transactions on Biomedical Engineering, Vol. 53, No. 11, pp. 2201-2210.
[8] De Boer, M., Bosch, F. A. J., and Volberda, H. W.(1999) “Managing Organizational Knowledge Integration in the Emerging Multimedia Complex,” Journal of Management Studies, Vol. 36, No. 3, pp. 379-398.
[9] Gruber, T. R.(1993), ”A Translation Approach to Portable Ontology Specifications,” Knowledge Acquisition, Vol.5, No. 2, pp. 199-220.