臺灣博碩士論文加值系統

在台灣，由於醫療水平的進步，使得國民平均壽命增加，但現代人生
活型態的轉變，礙於工作或其他因素導致生活作息與飲食的不正常，容易
導致糖尿病、高血壓等慢性病的發生。而這些慢性病通常需要定期的醫院
去做追蹤檢查外，對於日常的飲食管理也有助於減緩病情與併發症的發生
率。也因此飲食管理也變成近年來非常重要且熱門的議題。良好的飲食控
制除了能維持身體健康外，針對有糖尿病，高血壓等慢性病患者更可以有
效的控制住病情。本研究結合飲食本體、Jena 推論與決策樹提出一個針對
糖尿病或高血壓等慢性病患的飲食推薦系統，透過本體與Jena 推論來根據
患者的飲食偏好來推薦食物，並結合決策樹來計算出每日用戶所需的營養
素控制，達成每日均衡飲食的目標。

Due to the improvement level of medical technology, the person's average
age has increased in Taiwan. Lifestyle changes such as unhealthy diet, work
pressure and other factor will result chronic disease like diabetic, hypertension and so on. These chronic diseases usually need to spend a lot of time for examinations in hospital; the daily diet management also can help reducing the incidence of the disease and complications. Therefore, the dietary management has become very popular and important topic in recent years. The healthy diet not only to maintain good health, but also assist to reduce this chronic disease and the complication happening. Based on these reasoning, we design a new diet recommendation system based on food Ontology, Jena reasoning and decision tree for patients with diabetes or hypertension and other chronic diseases. Using Ontology and Jena reasoning to recommends suitable food according to user diet preferences, and combine with decision tree to calculate user’s daily nutrients to reach a balanced diet management.

Table of Contents
中文摘要 I
Abstract II
致謝 III
Table of Contents V
List of Table VII
List of Figure VIII
Chapter 1 Introduction 1
1.1 Background 1
1.2 Motivation 2
1.3 Purpose 3
1.4 The Framework of Thesis 4
Chapter 2 Related Work 5
2.1 Literature Review 5
2.2 Ontology 7
2.3 Decision Tree 8
2.4 Jena Inference 13
2.5 User Dietary Recommendations Information 14
Chapter 3 Research Methodology 20
3.1 System Architecture 20
3.2 Ontology Architecture 22
3.3 Decision Tree Architecture 25
3.4 Jena Inference Rule 29
Chapter 4 ExperImemts 31
4.1 Experimental Design 31
4.2 Experimental Result 31
Chapter 5 Conclusion and Future Works 39
5.1 Conclusions 49
5.2 Future Works 50
Reference 51
Appendix 1 57
Appendix 2 59

List of Table
Table 1-1 The top 10 causes of death in 2014 2
Table 2-1 The example of weather assessment 11
Table 2-2 The man daily required Kcal per kilogram 17
Table 3-1 The Jena reasoning rule 30
Table 4-1 The users information 31
Table 4-2 The classification of decision tree 38
Table 4-3 The volunteer’s dietary records 39
Table 4-4 The volunteer’s dietary record nutrients values 44

List of Figure
Figure 3-1 The system architecture 20
Figure 3-2 The food Ontology 24
Figure 3-3 The personal Ontology 25
Figure 3-4 The diet nutrients classification of decision tree 28
Figure 4-1 The system website interface 32
Figure 4-2 The adjusted of user diet preference 33
Figure 4-3 The result of Jena reasoning 34
Figure 4-4 The dietary record 35
Figure 4-5 The chart of Kcal diet situation 36
Figure 4-6 The chart of lipid diet situation 36
Figure 4-7 The chart of protein diet situation 37
Figure 4-8 The chart of carbohydrate diet situation 37

[1]Chuan-Jun Su, Chia-Wen Chih and Yin-An Chen (2012), “Ontology-based Personalized Diet Plan Web Service Using HL7 Health Screening Data,”Proceedings of the Asia Pacific Industrial Engineering &Management Systems Conference, pp. 1164-1176.
[2]Chi-Chun Lo, Chi-Hua Chen, Chih-Chien Lu, and Ding-Yuan Cheng(2012), “The Design and Implementation of a Curative Food Recommendation Mechanism Using Chinese Food Therapy as a Case Study,” Journal of e-Business, Vol. 14, No. 3, pp. 513-548.
[3]Chang-Shing Lee, Mei-Hui Wang, and Hani Hagras(2010), “A type-2 fuzzy ontology and its application to personal diabetic-diet recommendation,” (SCI) IEEE Transactions on Fuzzy Systems, Vol. 18, no. 2, pp. 374-395.
[4]Chun-Nan Hsu(2005), Decision tree learning,http://sjchen.im.nuu.edu.tw/MachineLearning/final/CLS_DT.pdf.
[5]C4.5 algorithm, https://en.wikipedia.org/wiki/C4.5_algorithm#cite_ref-1
[6]Craig Trim (2013), “A Semantic Web Framework,”http://trimc-nlp.blogspot.jp/2013/06/introduction-to-jena.html.
[7]D. Sánchez, M. Batet, and D. Isern (2011), “Ontology-Based Information Content Computation,” Knowledge-Based Systems, Vol. 24, No. 2, pp.297-303.
[8]Entropy(information theory),https://en.wikipedia.org/wiki/Entropy_(information_theory)
[9]G. Meditskos and N. Bassiliades (2008), “A Rule-Based Object-Oriented OWL Reasoner, ”IEEE Transactions on Knowledge and Data Engineering, Vol. 20, no. 3, pp. 397-410.
[10]Gijs Geleijnse, Peggy Nachtigall, Pim van Kaam, and Lucienne Wijgergangs (2011), “A personalized recipe advice system to promote healthful choices,” IUI '11 Proceedings of the 16th international conference on Intelligent user interfaces, pp. 437-438.
[11]Huan-Chung Li, Wei-Min Ko (2007), “Automated Food Ontology Construction Mechanism for Diabetes Diet Care, ”Machine Learning and Cybernetics, Vol. 5 , pp.2953-2958
[12]J. R. Quinlan (1993), C4.5: Programs for Machine Learning.
[13]J. R. Quinlan (1996), “Improved Use of Continuous Attributes in C4.5,”Journal of Artificial Intelligence Research,” Vol.4, pp.77-90.
[14]Jena (framework), http://en.wikipedia.org/wiki/Jena_(framework)
[15]Jena inference support, http://jena.apache.org/documentation/inference/#api
[16]Jena Official website, https://jena.apache.org/getting_started/index.html
[17]Jing Wu and Yong xin Huang (2009), “Reasoning with Ontology Model Based on Jena,” Intelligent Information Management, pp. 25-31.
[18]Mackay Memorial Hospital (three high dietary treatment),http://www.dryahoo.org.tw/次網頁/衛教走廊/內科/三高飲食.html
[19]Martin Svensson, Kristina Höök, and Rickard Cöster (2005), “Designing and evaluating kalas: A social navigation system for food recipes,” ACM Transactions on Computer-Human Interaction (TOCHI), Vol. 12, No. 3, pp.374-400.
[20]Maiyaporn Phanich, Phathrajarin Pholkul, and Suphakant Phimoltares (2010), “Food Recommendation System Using Clustering Analysis for Diabetic Patients”, International Conference on Information Science and Applications (ICISA), pp.1-8.
[21]Mayumi Ueda, Mari Takahata, and Shinsuke Nakajima (2011), “User's food preference extraction for personalized cooking recipe recommendation,” Proc. of the Second Workshop on Semantic Personalized Information Management: Retrieval and Recommendation, Vol. 781, No. 6,pp. 98-105.
[22]Ministry of Health and Welfare (Ten causes of death in 2012years),http://www.mohw.gov.tw/news/531349778.
[23]National Development Council (The elderly population aging trend),http://www.ndc.gov.tw/m1.aspx?sNo=0061369.
[24]Ontology (information science),https://en.wikipedia.org/wiki/Ontology_(information_science).
[25]OWL Web Ontology Language, http://www.w3.org/TR/owl-features/
[26]Peter Forbes and Mu Zhu (2011), “Content-boosted matrix factorization for recommender systems: Experiments with recipe recommendation,” Proceedings of the fifth ACM conference on Recommender systems, pp.261-264.
[27]Q.L. Guo and M. Zhang (2009), "Semantic Information Integration and Question Answering based on Pervasive Agent Ontology," Expert Systems with Applications, Vol. 36, No. 6, pp. 10068-10077.
[28]Rung-Ching Chen and Yung-Da Lin (2013), “The Recommendation of Diet for Chronic Diseases Based on Knapsack Problem and Domain Ontology,” International Journal of Advanced Information Technologies, Vol. 6, no.2, pp 155-167.
[29]T. C. Jepsen (2009), “Just What Is an Ontology, Anyway?,” IEEE Computer Society, Vol. 11, No. 5, pp. 22-27.
[30]Taiwan Dietary Reference Intake, http://www.hpa.gov.tw/BHPNet/Portal/File/ThemeDocFile/201308300213031785/國人營養素參考攝取量(DRIs)查詢.pdf
[31]Taiwan food nutrition database,https://consumer.fda.gov.tw/FoodAnalysis/ingredients.htm
[32]Tom Gruber (1992), "What is an Ontology,"http://www-ksl.stanford.edu/kst/what-is-an-ontology.html.
[33]Tom Gruber (1993), “A translation approach to portable ontology specifications,” Knowledge Acquisition, Vol. 5, No. 2, pp. 199-220.
[34]Wikipedia: body mass index, https://en.wikipedia.org/wiki/Body_mass_index
[35]Wikipedia: ID3 Algorithm, https://en.wikipedia.org/wiki/ID3_algorithm
[36]Wikipedia: Waist-Hip Ratio (WHR), https://en.wikipedia.org/wiki/Waist–hip_ratio
[37]Wikipedia: Weka, https://en.wikipedia.org/wiki/Weka_(machine_learning)
[38]李揚、田新平 (2008)，「痛風患者飲食保健療法新認識」，中華臨床免疫與變態反應雜誌，第二卷，第四期，第302-306 頁。
[39]游能俊、蘇秀悅、劉麗兒、彭慧鈺 (2012)，“台灣小吃營養大解析-北台灣篇”，中華民國糖尿病衛教學會。
[40]游能俊、蘇秀悅、劉麗兒、彭慧鈺 (2012)，“台灣小吃營養大解析-中台灣篇”，中華民國糖尿病衛教學會。
[41]游能俊、蘇秀悅、劉麗兒、彭慧鈺 (2012)，“台灣小吃營養大解析-南台灣篇”，中華民國糖尿病衛教學會。
[42]許惠恆 (2000)，「糖尿病的飲食保健療法建議」，中華民國內分泌暨糖尿病學會資訊，第十三卷，第二期，第 3-7 頁。
[43]張之一、梁斌 (2009)，「預防高血壓的營養食譜設計」，曲阜師範大學學報，第三十五卷，第一期，第95-98 頁。
[44]陳月卿 (2014)，「吃對全食物(上)(下)」，遠見天下文化出版股份有限公司。
[45]謝明哲、葉松鈴 (2002)，「膳食療養學實驗」，台北醫學大學保健營養學系。
[46]營養師走向預防醫學更前端http://careerweb.cjcu.edu.tw/news.php?type=1&article_id=26
[47]國民飲食指標手冊 - 衛生福利部國民健康署
http://www.hpa.gov.tw/BHPNet/Web/Books/Files/028/%E5%9C%8B%E6%B0%91%E9%A3%B2%E9%A3%9F%E6%8C%87%E6%A8%99%E6%89%8B%E5%86%8A.pdf