臺灣博碩士論文加值系統

現今社會上有許多人罹患慢性病三高，但大多數的患者會先依據搜尋引擎找尋相關的飲食資訊，進而尋求營養專家的意見來做為自己飲食的規劃。但網路上之飲食資訊大多數是基於文字敘述，因此使用者必須尋找更多的飲食資訊結合，且網路上之資訊不是基於正式標準所定義的資訊的，因此在於知識的結構上較無規劃，由於上述兩點，對於使用者取得適當飲食資訊來說是比較不友善的。因此，本研究希望透過本體論的觀點，來建構一個具有專家知識之慢性病三高飲食推薦系統進而給予使用者更為完善且更為精確的飲食資訊。
本研究中使用Protege來輔助建立本體(ontology)結構知識庫。並使用模糊邏輯(fuzzy logic)做為系統之前導推論，依患者之身體資訊推論出適合使用者每日所需之總熱量值，並使用JENA做為我們的推論器建立我們的知識規則。最後整合類背包演算法將fuzzy logic與JENA推論之結果組合出適合使用者之三餐組合，實做出一個慢性病三高飲食推薦系統。並經由營養專家評估與驗證，本實驗之系統能提供營養專家推薦符合於人們現實生活的飲食結果。

Nowadays many people suffer from three high chronic diseases: just like diabetes, hypertension and high cholesterol, but people use search engine to find information related to diet and nutrition experts to give advice for diet recommendations. However, the dietary information on the network is mostly text-based narrative, so users must find more information about the diet combination. The diet information on the network is not based on ontology, so the knowledge is less friendly. The aims of this study are through the ontological of viewers to construct our diet recommendation system with the three high chronic diseases of expert’s knowledge. And we will give users more complete and more accurate information.
In this study, we used Protege to establish our ontology and used OWL DL to construct the structure of knowledge. The system uses fuzzy logic as a guide prior to inference. According to the patient''s health information, the system infers daily calories requirement, and then use JENA inference device and use JENA rule format to build our knowledge of the rules. Finally, the Knapsack-like algorithm will combine the results. The reasoning results will recommender suitable foods for users. The system was evaluated by nutritionist to proof that the system is useful for three high chronic diseases.

Table of Contents
中文摘要 IV
Abstract V
致謝 VII
Table of Contents IX
List of Tables XI
List of Figure XII
Chapter 1 Introduction 1
1.1 Background 1
1.2 Motivation and Objective 4
1.3 The Framework of Thesis 5
Chapter 2 Literature Review 6
2.1 Ontology 6
2.2 Fuzzy theory 7
2.3 JENA inference and inference rules 8
2.4 Body information and diet of the patient 10
2.5 Knapsack Problem 13
2.6 Recommender System 17
Chapter 3 System Architecture 19
3.1 Fuzzy Reasoning 21
3.2 JENA inference 22
3.3 Knapsack Algorithm 22
Chapter 4 The Operation of Recommender System 23
4.1 Fuzzy 23
4.2 Ontology 32
4.3 JENA rules 34
4.4 Like-Knapsack problem 38
Chapter 5 The Experiment and Evaluation 43
5.1 Preliminary Experiment 43
5.2 Experiment and Evaluation 45
5.3 Discussions 56
Chapter 6 Conclusions and Future Works 58
References 60
Appendix-1 65
Appendix-2 67


List of Tables
Table 1 The top ten causes of death in Taiwan in 2010 3
Table 2 The descriptions of three type of OWL 7
Table 3 Use activity levels and BMI to find requirement kilo calories per day for per kilogram of body weight 12
Table 4 Item list of 0/1 knapsack problem 14
Table 5 Item list of Branch-and-Bound Strategy knapsack problem 16
Table 6 The normalize of activity levels and BMI (kilo calories/ kilogram) 28
Table 7 The example of food items list 40
Table 8 The volunteers’ profiles 46
Table 9 The users select foods 47
Table 10 The Result of System recommended 49
Table 11 The evaluation result of System recommender 55


List of Figure
Figure 1 The tree of Branch-and Bound Strategy knapsack problem 17
Figure 2 The architecture of recommender system 20
Figure 3 The membership functions of BMI on Mathlab system 25
Figure 4 The membership functions of WORK on Mathlab system 27
Figure 5 The membership functions of Calorie Demand on Mathlab system 30
Figure 6 Fuzzy rules on Mathlab system 31
Figure 7 The food ontology 33
Figure 8 The diet knowledge ontology 34
Figure 9 The data workflow of JENA 37
Figure 10 The system’s rules 38
Figure 11 Decision diagrams of like-knapsack problem 41
Figure 12 The Fuzzy result of Experiment 1 44
Figure 13 The experimental results 44

[1]Ontology, http://en.wikipedia.org/wiki/Ontology.
[2]Guo, Q.L. and Zhang, M., "Semantic Information Integration and Question Answering based on Pervasive Agent Ontology," Expert Systems with Applications, Vol. 36, No. 6, pp. 10068-10077, 2009.
[3]Jepsen, T.C., “Just What Is an Ontology, Anyway?,” IEEE Computer Society, Vol. 11, No. 5, pp. 22-27, 2009.
[4]Labrou, Y. and Finin, T., “Yahoo! as an Ontology: using Yahoo! Categories to Describe Documents,” Conference on Information and Knowledge Management, pp.180-187, 1999.
[5]Wang, M.H., Lee, C.S., Hsieh, K.L., Hsu, C.Y., Acampora, G., and Chang, C.C., "Ontology-Based Multi-Agents for Intelligent Healthcare Applications," Journal of Ambient Intelligence and Humanized Computing, Vol. 1, No. 2, pp. 111-131, 2011.
[6]Meditskos, G. and Bassiliades, N., “A Rule-Based Object-Oriented OWL Reasoner,” IEEE Transactions on Knowledge and Data Engineering, Vol. 20, No. 3, pp. 397-410, 2008.
[7]Sanchez, D., Batet, M., and Isern, D., “Ontology-Based Information Content Computation,” Knowledge-Based Systems, Vol. 24, No. 2, pp. 297-303, 2011.
[8]OWL Web Ontology Language, http://www.w3.org/TR/owl-features/
[9]Li, H.C. and Ko, W.M., “Automated Food Ontology Construction Mechanism for Diabetes Diet Care,” Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, Hong Kong, pp.2953-2958, 2007.
[10]Zadeh, L.A., "Fuzzy sets," Information and Control, Vol. 8, No. 3, pp. 338-353, 1965.
[11]Hajek, P., "What is Mathematical Fuzzy Logic," Fuzzy Sets and Systems, Vol. 157, No. 5, pp.597-603, 2006.
[12]Lee, C.S. and Wang, M.H., "A Fuzzy Expert System for Diabetes Decision Support Application," IEEE Transactions on Systems, Vol.41, No. 1, pp. 139-153, 2011.
[13]Ma, J., Chen, S. and Xu, Y., "Fuzzy Logic from the Viewpoint of Machine Intelligence," Fuzzy Sets and Systems, Vol. 157, No. 5, pp. 628-634, 2006.
[14]Novak, V., "Which Logic is the Real Fuzzy Logic?," Fuzzy Sets and Systems, Vol. 157, No. 5, pp. 635-641, 2006.
[15]Zadeh, L.A., "Toward Extended Fuzzy Logic a Frst Step," Fuzzy Sets and Systems, Vol. 16, No. 21, pp. 3175-3181, 2009.
[16]Lee, C.S., Wang, M.H., and Hagras, H., “A Type-2 Fuzzy Ontology and Its Application to Personal Diabetic-Diet Recommendation,” IEEE Transactions on Fuzzy Systems, Vol. 18, No. 2, pp. 374 – 385, 2010.
[17]JENA, http://JENA.sourceforge.net/
[18]JENA-推論支援, http://JENA.sourceforge.net/inference/index.html
[19]McBride, B., “JENA: a Semantic Web Toolkit,” IEEE Computer Society, Vol. 6, No. 6, pp. 55-59, 2002.
[20]Gorsik, J., Paquete, L., and Pedrosa, F., "Greedy Algorithms for a Class of Knapsack Problems With Binary Weights," Computer & Operations Research, Vol. 39, No. 3, pp. 498-511, 2012.
[21]Kumar, R. and Singh, P.K., "Assessing Solution Quality of Biobjective 0-1 Knapsack Problem using Evolutionary and Heuristic Algorithms," Applied Soft Computing, Vol. 10, No.3, pp. 711-718, 2010.
[22]Ross, K.W. and Tsang, H.K., “The Stochastic Knapsack Problem,” IEEE Transactions on Communications, Vol. 37, No. 7, pp. 740-747, 1989.
[23]Lee, R.C.T., Tseng, S.S., Chang, R.C., and Tsai, Y.T., Introduction to the Design and Analysis of Algorithms A Strategic Approach, McGraw Hill, pp. 157-215, 2005.
[24]Chern, M.S. and Jan, R.H., “Reliability Optimization Problems with Multiple Constraints,” IEEE Transactions on Reliability, Vol. R-35, No. 4, pp. 431-436, 1986.
[25]Michel, S., Perrot, N., and vanderbeck, F., "Knapsack Problems with Setups," European Journal of Operational Research, Vol. 196, No. 3, pp. 909-918, 2009.
[26]Lee, R.C.T., Tseng, S.S., Chang, R.C., and Tsai, Y.T., Introduction to the Design and Analysis of Algorithms A Strategic Approach, McGraw Hill, pp. 2-15, 2005.
[27]Kellerer, H., Pferschy, U. and Pisinger, D., Knapsack problems, Springer, 2004.
[28]Lee, R.C.T., Tseng, S.S., Chang, R.C., and Tsai, Y.T., Introduction to the Design and Analysis of Algorithms A Strategic Approach, McGraw Hill, pp. 71-118, 2005.
[29]Weng, S.S. and Chang, H.L., "Using Ontology Network Analysis for Research Document Recommendation," Expert Systems with Applications, Vol. 34, No. 3, pp. 1857-1869, 2008.
[30]Barragans-Martinez, A.B.,Rey-Lopez, M., Costa Montenegro, E., Mikic-Fonte, F.A., Burguillo, J.C. and Peleteiro, A., "Exploiting Social Tagging in a Web 2.0 Recommender System," IEEE Computer Society, Vol. 14, No. 6, pp. 23-30, 2010.
[31]行政院衛生署-主要死因統計, http://www.doh.gov.tw/statistic/eBAS/生命統計/主要死因統計/主要死因統計.xls。
[32]許惠恒，臺灣小吃營養大解析北臺灣篇，中華民國糖尿病衛教學會，2009。
[33]許惠恒，臺灣小吃營養大解析中臺灣篇，中華民國糖尿病衛教學會，2010。
[34]許惠恒，臺灣小吃營養大解析南臺灣篇，中華民國糖尿病衛教學會，2011。
[35]行政院衛生署-食品成份表, http://www.doh.gov.tw/FoodAnalysis/ingredients.htm
[36]陳韻中，基於Web2.0架構旅遊規劃推薦系統，南台科技大學資訊工程系碩士論文，2008。
[37]李天祥，以模糊語意塑模法萃取決策知識之研究，國立高雄第一科技大學資訊管理系碩士論文，2002。
[38]李珍儀，運用模糊關聯法則於學生成績之分析，文化大學資訊管理系碩士論文，2002。
[39]簡志郎，模糊理論與TOPSIS法於失效模式與效應分析之應用，逢甲大學工業工程學系碩士論文，2003。
[40]行政院衛生署-跟著健康去旅行, http://healthmap2009.doh.gov.tw/get_it.asp
[41]臨床營養研究室, http://www2.cmu.edu.tw/~nmhls/nutritionclubibw.html
[42]體重控制, http://w2.csh.org.tw/web/22201010/wp-content/uploads/2009/02/e9ab94e9878de68ea7e588b6diy.pdf