通常在考慮決定一項事物時，會受到許多層面、因素的影響，所以推薦系統則是一項能夠在複雜的資訊中，幫助使用者做出分析需求、推薦的系統。而我們研究是將焦點放在醫療輔助上，依國內行政院衛生署的統計，2009年的主要死因死亡率，糖尿病名列十大死因之一，因此對於糖尿病發展一個有效的治療是非常重要的。由於糖尿病患者眾多，避免專科醫師不足或是患者無法給予專科醫師看診的情況下，希望藉由此推薦系統來幫助家庭醫師在選擇藥物上做出合適的輔助。此研究的實驗希望藉由患者知識本體的建構建立患者項目，接著再利用多準則決策的方法，其重要性的熵量度運算將其資料的用藥程度做出計算，接著與藥品知識本體做出結合排序並推薦出最適用的藥品類型，最後呈現醫師較適用的藥類推薦。

Generally speaking, we have to consider the effect of many factors when making a decision. The recommended system can help user to analyze needs and give suggestions with complex information. Our research focuses on the assistance of medical suggestion for doctors. According to the statistics of Department of Health, diabetes was one of the top ten causes of death in Taiwan in 2009. Therefore, developing an effective treatment for diabetes is very important. The fact is that the amount of diabetes specialists is not enough and not all diabetic patients can be treated by specialists. We present this recommender system to help treatment. The purpose is to develop a recommender system to assist the general practitioner (GP) to make more appropriate decision in selecting anti-diabetic medicines. First, we built up the ontology of diabetic knowledge, and then multiples criteria decision making method (MCDM) was applied to compute for medication. Entropy was used to compute data of patients’ profile. With medicine knowledge ontology, the results of calculation will list appropriate medications. Finally, the system will show the preference of medications to doctors.

Table of Contents
中文摘要 I
Abstract II
致謝 IV
Table of Contents VI
List of Tables VIII
List of Figure XI
Chapter 1 Introduction 1
1.1 Background 1
1.2 Motivation and Object 4
1.3 The Framework of Thesis 7
Chapter 2 Literature Review 8
2.1 Ontology 8
2.2 Web Ontology Language (OWL) 11
2.3 Multiple Criteria Decision Making (MCDM) 12
2.4 Recommender System 16
2.5 Anti-diabetic Medications 19
2.6 Relational Database 20
Chapter 3 System Architecture 22
3.1 System Flow 22
3.2 Knowledge Construction 24
3.3 MCDM - Entropy Measure of Importance 27
Chapter 4 The Operation of Recommender System 30
4.1 Factors and Weights Construction 30
4.2 The Entropy Weights 31
4.3 Instance Declaration 38
Chapter 5 Experiments 43
5.1 Experiment 1 43
5.2 Experiment 2 47
5.3 Experiment 3 63
5.4 Experiment 4 71
Chapter 6 Discussions 81
Chapter 7 Conclusions and Future Works 85
References 87
Appendix-1 95
Appendix-2 96
Appendix-3 97


List of Tables
Table 1 The top ten causes of death in Taiwan in 2009 3
Table 2 The advantages and disadvantages of MCDM methods 15
Table 3 The scope volume of benefit and risk factors weight 30
Table 4 The corresponding relationship between data and parameters 31
Table 5 The weights of variable factor given by doctors 32
Table 6 The weights scoring of variable factors. 32
Table 7 The corresponding probability of factors(a) 33
Table 8 The ith attribute contrast intensity 34
Table 9 The value of normalized weight of benefit and risk factors 34
Table 10 The combination of subjective and objective weights 34
Table 11 The final weight of benefit and risk factors(a) 35
Table 12 The result of medications sort of benefit and risk factors(a) 36
Table 13 The recommendation of anti-diabetic medications from AACE 37
Table 14 The report of a 59-year-old male patient 39
Table 15 The corresponding probability of factors(b) 41
Table 16 The final weight of benefit and risk factors(b) 41
Table 17 The result of medications sort of benefit and risk factors(b) 42
Table 18 Detection data 44
Table 19 The sort of calculation result 45
Table 20 Scores computation 46
Table 21 The 31 simulation data of diabetic patients 49
Table 22 Range of values table 55
Table 23 A male patient physical examination reports(a) 57
Table 24 The normalized values(a) 57
Table 25 The standardized weight values(a) 58
Table 26 The combination of subjective and objective weights(a) 58
Table 27 The corresponding probability of factors for benefit factors 59
Table 28 Combining form of the normalized values and the combination weight values(a) 59
Table 29 The final weight of benefit factors(a) 60
Table 30 The 31 medications recommended result of diabetic patients with benefit factors 61
Table 31 A male patient physical examination reports(b) 64
Table 32 The normalized values(b) 66
Table 33 The standardized weight values(b) 66
Table 34 The combination of subjective and objective weights(b) 66
Table 35 Combining form of the normalized values and the combination weight values(b) 67
Table 36 The corresponding probability of factors for risk factors 67
Table 37 The final weight of risk factors(b) 67
Table 38 The 31 medications recommended result of diabetic patients with risk factors(b) 70
Table 39 A male patient physical examination reports(c) 72
Table 40 The normalized values(c) 73
Table 41 The standardized weight values(c) 74
Table 42 The combination of subjective and objective weights(c) 74
Table 43 Combining form of the normalized values and the combination weight values(c) 75
Table 44 The corresponding probability of factors for benefit and risk factors 75
Table 45 The final weight of benefit and risk factors(c) 75
Table 46 The sort of calculation final result 76
Table 47 The 31 medications recommended result of diabetic patients with benefit and risk factors(c) 79
Table 48 Average score results of doctors 84

List of Figure
Figure 1 The recommended flow of diabetic medicines 24
Figure 2 Patient knowledge, medicine knowledge and weight ontology 25
Figure 3 Instances of ontology 26
Figure 4 The broken line graph of medications sorting 36
Figure 5 The calculation flow chart 39
Figure 6 Enter interface of benefit factors 58
Figure 7 Enter interface of risk fastors 65
Figure 8 Enter interface of benefit and risk factors 73

[1]A. Bhattacherjee(2001), “An Empirical Analysis of The Antecedents of Electronic Commerce Service Continuance”, Decision Support Systems, Vol. 32, No. 2, pp. 201-214.
[2]A. Valls, K. Gibert, D. Sánchez, and M. Batet(2010), “Using Ontologies for Structuring Organizational Knowledge in Home Care Assistance,” International Journal of Medical Informatics, Vol. 79, No. 5, pp. 370-387.
[3]A.S. Niaraki and K. Kim(2009), “Ontology Based Personalized Route Planning System using A Multi-criteria Decision Making Approach,” Expert Systems with Applications, Vol. 36, No. 2, pp. 2250-2259.
[4]B.H. Chu, C.E. Lee, and C.S. Ho(2008), “An Ontology-Supported Database Refurbishing Technique and Its Application in Mining Actionable Troubleshooting Rules from Real-Life Databases,” Engineering Applications of Artificial Intelligence, Vol. 21, No. 8, pp. 1430-1442.
[5]C.S. Lee, M.H. Wang, and H. Hagras(2010), “A Type-2 Fuzzy Ontology and Its Application to Personal Diabetic-Diet Recommendation,” IEEE Transactions on Fuzzy Systems, Vol. 18, No. 2, pp. 374-395.
[6]C.S. Lee, M.H. Wang, and J.J. Chen(2008), “Ontology-Based Intelligent Decision Support Agent for CMMI Project Monitoring and Control,” International Journal of Approximate Reasoning, Vol. 48, No. 1, pp. 62-76.
[7]D. Mun and K. Ramani(2011), “Knowledge-Based Part Similarity Measurement utilizing Ontology and Multi-Criteria Decision Making Technique,” Advanced Engineering Informatics, Vol. 25, No 2, pp. 119-130.
[8]D. Yang, R. Miao, H. Wu,and Y. Zhou(2009), “Product Configuration Knowledge Modeling using Ontology Web Language,” Expert Systems with Applications, Vol. 36, No. 3, pp. 4399-4411.
[9]E.F. Codd(1970), “A Relational Model of Data for Large Shared Data Banks,” Communications of the ACM, Vol. 13, No. 6, pp. 377–387.
[10]F. Bobillo, M. Delgado, J. Gómez-Romero, and E. López(2009), “A Semantic Fuzzy Expert System for A Fuzzy Balanced Scorecard,” Expert Systems with Applications, Vol. 36, No. 1, pp. 423-43.
[11]H.Y. Kao, S.H. Lin, J.M. Ho, and M.S. Chen(2004), “Mining Web Informative Structures and Contents Based on Entropy Analysis,” Knowledge and Data Engineering, Vol. 16, No. 1, pp. 41-55.
[12]H.W. Rodbard, P.S. Jellinger, J.A. Davidson, D. Einhorn, A.J. Garber, G. Grunberger, Y. Handelsman, E. S. Horton, H. Lebovitz, P. Levy, E. S. Moghissi, S. S. Schwartz(2009), “Statement by an American Association of Clinical Endocrinologists/American College of Endocrinology Consensus Panel on Type 2 Diabetes Mellitus: An Algorithm for Glycemic Control,” Endocrine Practice, Vol. 15, No. 6, pp. 540-559.
[13]L. Qin and V. Atluri(2009), “Evaluating the Validity of Data Instances Against Ontology Evolution over the Semantic Web,” Information and Software Technology, Vol. 51, No. 1, pp. 83-97.
[14]L.Y. Shue, C.W. Chen, and W. Shiue(2009), “The Developent of An Ontology-Based Expert System for Corporate Financial Rating,” Expert Systems with Applications, Vol. 36, No. 2, pp. 2130-2142.
[15]M.H. Wang, C.S. Lee, H.C. Li, and W.M. Ko(2007), “Ontology-Based Fuzzy Inference Agent for Diabetes Classification,” Fuzzy Information Processing Society, pp.79-83.
[16]M.K. Chen and S.C. Wang(2010), “The Critical Factors of Success for Information Service Industry in Developing International Market: Using Analytic Hierarchy Process Approach,” Expert Systems with Applications, Vol. 37, No. 1, pp. 694-704.
[17]P. Resnick and H.R. Varian(1997), “Recommendation Systems,” Communication of ACM, Vol. 40, No. 3, pp. 56-58.
[18]R.C. Chen, J.Y. Liang, and R.H. Pan(2008), “Using Recursive ART Network to Construction Domain Ontology Based on Term Frequency and Inverse Document Frequency,” Expert Systems with Applications, Vol. 34, No. 1, pp. 488-501.
[19]R.M. Gardner, Ph D(1985), “Computerized Data Management and Decision Making in Critical Care,” Surgical Clinics of North America, Vol. 65, No. 4, pp.1041-1052.
[20]R.N. Cardozo(1965), “An Experimental Study of Consumer Effort, Expectation and Satisfaction,” Journal of Marketing Research, Vol. 11, pp.244-249.
[21]S. Kaza and H. Chen(2008), “Evaluating Ontology Mapping Techniques: An Experiment in Public Safety Information Sharing,” Decision Support Systems, Vol. 45, No. 4, pp. 714-728.
[22]S.S. Weng and H.L. Chang(2008), “Using Ontology Network Analysis for Research Document Recommendation,” Expert Systems with Applications, Vol. 34, No. 3, pp. 1857-1869.
[23]T. Andreasen and H. Bulskov(2009), “Conceptual querying through ontologies,” Fuzzy Sets and Systems, Vol. 160, No. 15, pp. 2159-2172.
[24]T. Mabotuwana and J. Warren(2009), “An Ontology-Based Approach to Enhance Querying Capabilities of General Practice Medicine for Better Management of Hypertension,” Artificial Intelligence in Medicine, Vol. 47, No. 2, pp. 87-103.
[25]T.R. Gruber(1993), “A Translation Approach to Portable Ontology Specifications,” Knowledge Acquisition, Vol. 5, pp.199-220.
[26]W. Hu, Y. Qu and G. Cheng(2008), “Matching Large Ontologies: A Divide-and-Conquer Approach,” Data & Knowledge Engineering, Vol. 67, No.1, pp. 140-160.
[27]X. Chang and J. Terpenny(2009), “Ontology-Based Data Integration and Decision Support for Product e-Design,” Robotics and Computer-Integrated Manufacturing, Vol. 25, No. 6, pp. 863-870.
[28]Y.L. Chi(2009), “Ontology-Based Curriculum Content Sequencing System with Semantic Rules,” Expert Systems with Applications, Vol. 36, No. 4, pp. 7837-7847.
[29]Y.T. İÇ and M. Yurdakul(2010), “Development of A Quick Credibility Scoring Decision Support System using Fuzzy TOPSIS,” Expert Systems with Applications, Vol. 37, No. 1, pp. 567-574.
[30]H.F. Wang(2004), Multicriteria Decision Analysis- From Certainty to Uncertainty, Tsang Hi Book Publishing Co., pp.108.
[31]J.A. Hoffer, M.B. Prescott, and F.R. McFassen(2002), “Modern Database Management,” Pearson Education Inc.
[32]Y.L. Guo and H.J. Shen, Physical History, Fan Yi Publisher, pp. 109.
[33]H.C. Huang, W.S. Hou, and C.F. Liou(2009), “The Build of the Book Recommendation System,” The 2009 Conference on Computer Science and Information Engineering Applications.
[34]H.C. Li(2006), “The Patient-Oriented Portable Health Education of Personalized Remind Care Services,” The 2006 Conference on Object-Oriented Technology and Applications.
[35]H.C. Li, S.C. Jhong, S.D. Lin, S.L. Su, P.Y. Liao, S.D. Du, S.L. Lin, and S.M. Lin, “Decision-Making Knowledge Management of Self-Monitoring of Diabetes Blood Glucose,” The 2007 Conference on National Computer Symposium.
[36]K.L. Peng(2000), “Entropy in Application and Measurement of Growth of Enterprise System,” The 4th Conference on Asia Pacific Management, pp. 1E-1-1E-6.
[37]W.M. Ge and H.C. Li(2006), “The Health Care Education System Based on Ontology on Chronic Dietary Care,” The Symposium on Digital Life Technologies.
[38]F.D. Davis(1986), A Technology Acceptance Model for Testing New End-User Information Systems: Theory and Results, Massachusetts Institute of Technology: Doctoral dissertation, Sloan School of Management.
[39]C.H. Wu(2007), “A Document Recommendation System Based on Domain Ontology: System Development and Validation,” Master Thesis, Department of Management Information Systems of National Pingtung University of Science and Technology.
[40]C.L. Chien(2003), “Application of Fuzzy Set Theory and TOPSIS for Failure Mode and Effects Analysis,” Master Thesis, Department of Industrial Engineering and Systems Management of Feng Chia University.
[41]H.C. Chen(2000), “A Music Recommendation System Based on Music Data Grouping and User Interests,” Master Thesis, Department of Computer Science of National Tsing Hua University.
[42]J.G. Lin(2006), “Recommender System for Nutrient Meals in Early Childhood,” Master Thesis, Department of Electrical Engineering of Southern Taiwan University.
[43]J.Y. Huang(2009), “The Study on the Construction of Intelligence–Based Decision Support System for Diabetes Diagnosis and Risk Evaluation,” Master Thesis, Department of Information Management of Fu Jen Catholic University.
[44]M.Z. Yu(2002), “The Recommendation System of Personalized Library Collections,” Master Thesis, Department of Computer Science of National Chiao Tung University.
[45]T.Y. Chen(2005), “Personalized Itinerary Recommendation System Based on Travel Preferences,” Master Thesis, Department of Computer Science of National Tsing Hua University.
[46]Y.C. Huang(2008), “A Study on Ontology-based Intelligent Diet Planning,” Master Thesis, Department of Business and Management of National University of Tainan.
[47]Y.H. Lin(2004), “A Recommendation Scheme of Personalized Learning Activities Based on Learning Design Standard,” Master Thesis, Department of Computer Science of National Chiao Tung University.
[48]K.L. Peng(2005), “The Measurement of Decision Uncertainty By Shannon’s Entropy,” Ming Hsin Journal of Minghsin University of Science and Technology, Vol. 31, pp. 171-181.
[49]S.C. Jhang(1998), “Entropy in Application of Diversification Measure,” Journal of Business Administration of National Chung Hsing University, Vol. 42, pp. 1-26.
[50]National Health Research Institutes, June 2011, http://enews.nhri.org.tw/enews_list_new2_more.php?volume_indx=307&showx=showarticle&article_indx=7194
[51]OWL Web Ontology Language Overview, June 2011, http://www.w3.org/TR/owl-features/.
[52]S.G. Ju, MCDM Note, http://irw.ncut.edu.tw/peterju/mcdm.html#intro.
[53]The Cause of Death Statistics from Department of Health, Executive Yuan, R.O.C.(Taiwan), http://www.doh.gov.tw/CHT2006/DM/DM2_2_p02.aspx?class_no=440&now_fod_list_no=11397&level_no=4&doc_no=76512.
[54]The New Development of New Diabetes Treatment from Formosan Medical Association, http://www.fma.org.tw/2008/E-1-1.html.
[55]Wiki in Library and Information Science, Recommender Systems, http://morris.lis.ntu.edu.tw/wikimedia/index.php/推薦系統.