臺灣博碩士論文加值系統

隨著醫療水準漸漸提高與生活環境改善，臺灣人口結構逐漸邁向高齡化社會甚至超高齡化，導致慢性疾病逐漸滲入。膽結石和腎結石兩者皆是近代常見的公共健康問題，現代人為了工作生活忙碌，導致平時生活作息不正常、缺乏運動，以及三餐不正常加上飲食型態日益西餐化，高熱量、高脂肪、高醣類的東西常常攝取過多，使的膽結石的罹患率逐漸升高。而膽結石與腎結石同為結石類疾病，兩者間也有共同的危險因子，但探討兩者之間關聯性的研究並不多。
　　本研究以某醫療機構資料庫中膽結石病患為研究對象，透過文獻探討與醫師訪談，篩選出會增加腎結石疾病風險之重要因子，運用人工智慧中的粒子群最佳化演算法、基因邏輯斯迴歸演算法、交叉熵演算法計算因子權重值，並分別結合倒傳遞類神經網路與支援向量機，以建構六種預測模型與三種案例式推理系統評估，來評估膽結石患者後續是否產生腎結石的風險。
　　研究結果顯示六種預測模型，經由傅利曼統計檢定，並無顯著差異，皆適合作為本研究之預測模型，其平均測試準確率皆達89%以上ROC曲線下面積也在0.85以上；而三種案例式推理系統模型，雖然以粒子群演算法之模型準確率89.01%與ROC曲線下面積0.894較佳，但檢定結果三種模型亦無顯著差異，皆適合做為案例式推理評估系統之權重計算。

　　With the gradual improvement of medical standards and the improved living environment, Taiwan’s population structure has gradually headed towards the aging society or even ultra-aging, leading to the gradual infiltration of chronic diseases. Gallstones and kidney stones are both today’s common public health problems. Modern people lead a busy lifestyle, resulting in disrupted daily routine, lack of exercise, and failure to take meals regularly. In addition, the increasingly westernized diet pattern and excessive intake of high-calorie, high-fat, and high-sugar foods have resulted in a gradual rise in gallstone incidence rates. Gallstones and kidney stones both fall under the stone disease category and share common risk factors. However, researches exploring the connection between the two remain scarce.
　　In this study, patients with gallstones from the database of an anonymous medical institution were adopted as research participants. Through literature reviews and interviews with physicians, the important factors contributing to increased risk of gallstone disease were screened. Through the use of algorithm in artificial intelligence such as particle swarm optimization algorithm, genetic logistic regression algorithm, and cross entropy algorithm, the factor weights were calculated. The back propagation neural network and support vector machine were conjunctively employed to construct six prediction models and three case-based reasoning systems in order to evaluate whether patients with gallstones are at risk of future gallstones in the future.
　　Research results show that after the Friedman’s test, the six predictive models showed no significant differences and are all suitable as predictive models for research. The models all reached 89% average test accuracy, and the area under the ROC curve was above 0.85. For the three case-based reasoning system models, although the model of particle swarm optimization algorithm with 89.01% accuracy and 0.894 area under the ROC curve was better, the test results of the three models show no significant differences, making them suitable for calculating the weight of the case-based reasoning assessment system.

摘要...i
Abstract...ii
誌謝...iv
目錄...v
表目錄...ix
圖目錄...xi
第一章　緒論...1
1.1 研究背景...1
1.2 研究動機...1
1.3 研究目的...2
1.4 研究範圍與限制...2
1.5 研究流程...2
第二章　文獻探討...4
2.1 膽結石疾病...4
2.1.1 膽結石簡介...4
2.1.2 膽結石危險因子...4
2.1.3膽結石症狀與診斷...5
2.1.4 膽結石預防與治療...5
2.2 腎結石...6
2.2.1 腎結石簡介...6
2.2.2 腎結石症狀...6
2.2.3 腎結石危險因子...7
2.2.4 腎結石預防與治療...7
2.2.5 腎結石風險文獻...8
2.3 粒子群最佳化演算法...9
2.3.1 粒子群最佳化演算法簡介...9
2.3.2 粒子群最佳化演算法流程...9
2.3.3 粒子群最佳化演算法相關文獻...12
2.4 基因邏輯斯迴歸演算法...12
2.4.1 基因演算法簡介...12
2.4.2 邏輯斯回歸分析...13
2.4.3 基因演算法流程...13
2.4.4 基因演算法相關文獻...14
2.5 交叉熵演算法...15
2.5.1 交叉熵演算法簡介...15
2.5.2 交叉熵理論...15
2.5.3 交叉熵演算法相關文獻...16
2.6 倒傳遞類神經網路...16
2.6.1 倒傳遞類神經網路簡介...16
2.6.2 倒傳遞類神經模型...17
2.6.3 倒傳遞類神經網路相關文獻...18
2.7 支援向量機...18
2.7.1 支援向量機簡介...18
2.7.2 非線性支援向量機...19
2.7.3 支援向量機相關文獻...19
2.8 案例式推理系統...20
2.8.1 案例式推理系統簡介...20
2.8.2 案例式推理系統之架構...20
2.8.3 案例式推理系統相關文獻...21
第三章　研究方法...22
3.1 研究架構...22
3.2 研究資料與對象...24
3.3 研究變數定義...25
3.4 變數編碼...25
3.5 模型與系統架構...26
3.6 演算法參數設定...27
3.6.1 粒子群最佳化演算法...27
3.6.2 基因邏輯斯迴歸演算法...27
3.6.3 交叉熵演算法...28
3.6.4 倒傳遞類神經網路...28
3.6.5 支援向量機...28
3.6.6 案例式推理系統...29
3.7 模型驗證與績效評估...30
3.7.1 K疊交叉驗證法...30
3.7.2 ROC曲線...30
3.7.3 模型差異檢定...31
第四章　研究結果...32
4.1 案例敘述統計...32
4.2 粒子群最佳化演算法實驗分析...33
4.2.1 粒子群最佳化演算法參數設定...33
4.2.2 粒子群最佳化演算法之權重分析...33
4.3 粒子群最佳化演算法結合倒傳遞類神經網路實驗分析...34
4.3.1 參數設定...34
4.3.2 十疊交互驗證...36
4.3.3 ROC曲線下面積...36
4.4 粒子群最佳化演算法結合支援向量機實驗分析...38
4.4.1 參數設定...38
4.4.2 十疊交互驗證...39
4.4.3 ROC曲線下面積...39
4.5 基因邏輯斯迴歸演算法分析...40
4.5.1 基因邏輯斯迴歸演算法參數設定...40
4.5.2 基因邏輯斯迴歸演算法權重分析...40
4.6 基因邏輯斯迴歸演算法結合倒傳遞類神經網路實驗分析...41
4.6.1 參數設定...41
4.6.2 十疊交互驗證...43
4.6.3 ROC曲線下面積...43
4.7 基因邏輯斯迴歸演算法結合支援向量機實驗分析...44
4.7.1 參數設定...44
4.7.2 十疊交互驗證...45
4.7.3 ROC曲線下面積...46
4.8 交叉熵演算法實驗分析...47
4.8.1 交叉熵演算法參數設定...47
4.8.2 交叉熵演算法之權重分析...47
4.9 交叉熵演算法結合倒傳遞類神經網路實驗分析...48
4.9.1 參數設定...48
4.9.2 十疊交互驗證...50
4.9.3 ROC曲線下面積...50
4.10 交叉熵演算法結合支援向量機實驗分析...51
4.10.1 參數設定...51
4.10.2 十疊交互驗證...52
4.10.3 ROC曲線下面積...53
4.11 研究模型比較...54
4.11.1 研究模型分析結果比較...54
4.11.2 模型差異統計檢定...54
4.12 案例式推理評估系統...55
4.12.1 權重值設定...55
4.12.2 案例式推理系統操作...56
4.12.3 案例式推理評估系統驗證...59
第五章　結論與建議...61
5.1 研究結論...61
參考文獻...62
附錄A預測模型傅利曼檢定表...67
附錄B評估系統傅利曼檢定表...68
Extended Abstract...69
簡歷...75

1.王美齡、馮正一、張育瑄(2010)「基因演算法於邊坡穩定分析之初步應用」，水土保持學報，42卷，1期，頁65-82。
2.王濟川、郭志剛(2008)「Logistic 回歸模型—方法及應用」，五南圖書公司http://www.nhi.gov.tw/epaper/ItemDetail.aspx?DataID=3994&IsWebData=0&ItemTypeID=7&PapersID=355。
3.吳忠敏、周聖鈞(2013)，「應用分群技術與基因演算法建構以趨勢為基礎之股市投資策略」，臺北科技大學學報，45卷，2期，頁49-67。
4.吳建達、宋狄恩(2013)，「以類神經技術為基礎之柴油車輛油耗預估研究」，車輛工程學刊，10期，頁75-88。
5.宋裕祺、王俊穎(2015)，「結合粒子群演算法與遺傳演算法於斜張橋鋼索預力之最佳化設計」，中國土木水利工程學刊，21卷，1期，頁1-10。
6.李建邦、俞星辰(2014)，「以粒子群最佳化演算法結合分類器預測疾病急搜尋變數之研究」數據分析，9卷1期，頁57－74。
7.李維平 王雅賢 江正文(2008)，「粒子群最佳化演算法改良之研究」，科學與工程技術期刊，第4卷，第2期，頁51-62。
8.周跃孝(2016)，「基於粒子群演算法的路面施工養護維修作業最佳化研究」，公路工程，41卷，3期，頁43-48。
9.林軒宇，劉說安(2015)，「以支援向量機為基礎於有限氣象資料進行蒸發量補遺」，農業工程學報，61卷，4期，頁1-10。
10.林建輝(2015)，「致命的舍利子」，嘉義長庚排尿障礙中心專刊，36卷，12期
https://www.cgmh.org.tw/cgmn/category s.asp?id seq=1511079。
11.放心醫苑網(2016)「預防膽結石 膽結石的九大預防方法」
http://www.fx120.net/disease1/201606/1042567.html。
12.科技部高瞻自然科學教學資訊平台(2011)「腎結石的分類及形成原因」http://highscope.ch.ntu.edu.tw/wordpress/?p=23037。
13.孫瑛霙，王明庸，藍天雄(2015)，「應用倒傳遞神經網路於負載啟斷開關接觸電阻預測之研究」，管理資訊計算，4卷，1期，頁142-149。
14.徐怡,陳瑋嘉(2013)，「以類神經網路探討影響台灣年輕族群運動商品購買意願之因素研究」，數據分析學報，8卷，1期，頁139-166。
15.徐賢斌(2017)，「用混合式粒子群演算法進行離散型船席及變動式橋式起重機指派」，運輸學刊，9卷，1期，頁1-34
16.張嘉玲、陳永燊、魏逸葳等人(2013)，「以倒傳遞類神經網路探討水庫水質與集水區降雨之相關性」，農業工程學報，43卷，4期，頁56-66。
17.張新明、黨留群、鄭延斌、孫印傑、李雙(2010)，「一種改進的二維最小交叉熵圖像分割方法」，光電工程，37卷，11期，頁103-109。
18.莊凱智、黃士滔(2011)，「應用改良式粒子群演算法於旅行銷售員問題」，工程科技與教育學刊，8卷，3期，頁533-546。
19.陳正美、徐建業等人(2011)，「以類神經網路及分類迴歸樹輔助肝癌病患預測存活情形」，臺灣公共衛生雜誌，5卷，30期，頁481-493。
20.游凈惠，黃鈞源等人(2015)，「台灣民眾血脂肪濃度與罹患膽結石症之相關性研究」，台灣家醫誌，25卷，2期，頁129-137。
21.甯方璽、陳佳菱(2014)，「應用粒子群演算法改善傳統二次曲面擬合區域性大地起伏－以台中地區為例」，台灣土地研究，17卷，1期，頁23-35。
22.黃承龍、陳穆臻、王界人(2004)，「支援向量機於信用評等之應用」，計量管理期刊，1卷，2期，頁155-172。
23.楊逸仁、林子建、何正得(2010)，「模具設計之案例式推理系統建構」，工程科技與教育學刊，第7卷，第4期，頁560-578。
24.萬絢、張士勛、陳銘賢(2013)，「以螞蟻演算法與支援向量機判釋在霧社水庫影像崩塌第之判釋」，水保技術，8卷，4期，頁180-186。
25.萬絢、雷祖強、陳達祺(2010)，「以樹狀倒傳遞類神經網路於田埂判釋研究」，航測及遙測學刊，15卷，3期，頁205-214。
26.葉美均、周宗南(2015)，「應用基因演算法整合五大購面選股策略」，全球商業經營管理學報，8期，頁113-123。
27.廖麗滿 黃敬仁 林志諭(2011)，「穩健多目標基因演算法應用於流程型工廠之排程研究」，技術學刊，26卷，1期，頁65-71。
28.劉晏孜、陳琬青、林益卿(2012)，「腎結石之治療與預防」，家庭醫學與基層醫療，27卷、11期、頁384-390。
29.劉正達(2011)，「人工智慧方法應用於聖火傳遞路經最佳化」，大專體育學刊，13卷，4期，368-378頁。
30.劉朝華(2014)，「混合免疫智能算法理論及應用」，電子工業出版社，頁1-55。
31.劉蓓麗、李宜致等人(2007)，「肥胖病人膽結石生成之預測因子研究」，澄清醫護管理雜誌，3卷，3期，頁29-36。
32.衛生福利部台中醫院(2016)，「認識膽結石及膽結石的治療」http://www.taic.mohw.gov.tw/?aid=509&pid=88&page_name=detail&type=1143&iid=1723。
33.衛生福利部彰化醫院(2014)，「輕忽不得的腎結石」http://www.chhw.mohw.gov.tw/?aid=302&page_name=detail&iid=110&pid=96。
34.賴春生、呂佩穎、陳自諒(2016)，「外科的臨床推理教學」，台灣醫學，20卷，3期，頁290-296。
35.鄭中浩、鄭鴻鈞、邱泓文(2013)，「應用類神經網路預測鼻咽癌病人之五年存活狀態」，放射治療與腫瘤學，20卷，3期，191-197頁。
36.Abbassi M, Ashrafi M, Tashniz E.S(2014). “Selecting balanced portfolios of R&D projects with interdependencies: A Cross-Entropy based methodology” ,Technovation, vol.34, no.1, pp.54-63.
37.Ahmed M H., Barakat S, Almobarak A O(2014). “The association between renal stone disease and cholesterol gallstones: the easy to believe and not hard to retrieve theory of the metabolic syndrome”, Ren Fail, vol.36, no.6, pp.957-962.
38.Alptekin G I, Büyüközkan G(2011). “An integrated case-based reasoning and MCDM system for Web based tourism destination planning”,Expert Systems with Applications, vol.38, no.3, pp.2125-2132.
39.Amailef K, Lu J(2013). “Ontology-supported case-based reasoning approach for intelligent m-Government emergency response services” , Decision Support Systems, vol.55, no.1, pp.79-97.
40.de Moura Meneses A A, Schirru R(2015). “A cross-entropy method applied to the In-core fuel management optimization of a Pressurized Water Reactor”, progress in Nuclear Energy, Vol.83, pp.326-335.
41.Chen Y C, Su Y C, Li C Y, Hung S K(2015). “13-year nationwide cohort study of chronic kidney disease risk among treatment-naïve patients with chronic hepatitis B in Taiwan Epidemiology and Health Outcomes ” , BMC Nephrology, vol.15, no.1, pp.110.
42.Chen Y C, Su Y C, Lee C C, Huang Y S, Hwang S J(2012). “Chronic Kidney Disease Itself Is a Causal Risk Factor for Stroke beyond Traditional Cardiovascular Risk Factors: A Nationwide Cohort Study in Taiwan” , PLoS ONE, vol.7, no.4, pp.e36332.
43.Dai M, Zhao A, Liu A, You L, Wang P.(2013). “Dietary factors and risk of kidney stone: A case–control study in Southern China”, Journal of Renal Nutrition, vol.23, no.2, pp.e21-e28.
44.Fan C Y, Chang P C, Lin J J, Hsiwh J C(2011). “A hybrid model combining case-based reasoning and fuzzy decision tree for medical data classification” , Applied Soft Computing, vol.11, no.1, pp.632-644.
45.Guessoum S, Laskri M T, Lieber J(2014). “RespiDiag: A Case-Based Reasoning System for the Diagnosis of Chronic Obstructive Pulmonary Disease” , Expert Systems with Applications, vol.41, no.2, pp.267-273.
46.Kuo R J, Lin L M(2010). “Application of a hybrid of genetic algorithm and particle swarm optimization algorithm for order clusterin , Decision Support Systems, vol.49, no.4, pp.451-462
47.Kuo R J, Han YS (2011). “A hybrid of genetic algorithm and particle swarm optimization for solving bi-level linear programming problem – A case study on supply chain model” , Applied Mathematical Modelling, vol.35, no.8, pp.3905-3917.
48.Li C H, Sung F C, Wang Y C, Lin D, Kao C H(2014). “Gallstones increase the risk of developing renal stones: a nationwide population-based retrospective cohort study” ,Q J Med; vol.107, no.6, pp.451-457.
49.Liao J N, Chao T F, Liu CJ, et al(2015). “Incidence and risk factors for new-onset atrial fibrillation among patients with end-stage renal disease undergoing renal replacement therapy”, Kidney International, vol.87, no.6, pp.1209-1215.
50.Lin S Y, Lin C L, Chang Y J, et al(2016). “Association Between Kidney Stones and Risk of Stroke A Nationwide Population-Based Cohort Study”, Medicine, Vol.95, no8.
51.Liu C M, Hsu C T, Liu T L, et al(2014). “The Correlation between Cholecystectomy and Seasonal Impact in Taiwan” , Chinese Journal of Physiology, vol.57, no.1, pp.48-56.
52.Leaf D E, Korets R, Taylor E N, et al(2012). “Effect of vitamin D repletion on urinary calcium excretion among kidney stone formers” , Clinical Journal of the American Society of Nephrology, vol.7, no.5, pp.829-834.＝
53.Olivares-Mendez M A, Mejias L, Campoy P et al(2013). “Cross-Entropy Optimization for Scaling Factors of a Fuzzy Controller: A See-and-Avoid Approach for Unmanned Aerial Systems” , Journal of Intelligent & Robotic Systems, vol.69, no.1, pp.189-205.
54.Mitra R, Basak J(2005). “Methods of Case Adaptation: A Survey” ,International Journal of Intelligent Systems, vol.20,no.5,pp.627-645.
55.Naka S, Genji T, Yura T, Fukuyama Y (2003). “A hybrid particle swarm optimization for distribution state estimation” , IEEE Transaction on Power Systems, vol.18, no.1, pp.60-68.
56.Pradhan B (2013). “A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS” ,Computers & Geosciences, vol.51, no.1, pp.350-365.
57.Qodmanan H R, Nasiri M, Minaei-Bidgoli B(2011). ”Multi objective association rule mining with genetic algorithm without specifying minimum support and minimum confidence” ,Expert Systems with applications, vol.38, no.1, pp. 288-298.
58.Caballeroa R, Hernandez-Diazb A G, Lagunac M, et al(2015). “Cross entropy for multiobjective combinatorial optimization problems with linear relaxations”, European Journal of Operational Research, vol.243, no.2, pp.362-368.
59.Rubinstein R Y(1997). “Optimization of computer simulation models with rare events” , Eur J Oper Res, vol.99, no.1, pp.89-112.
60.Rule A D, Roger V L, Melton L J, et al(2010). “Kidney stones associate with increased risk for myocardial infarction” , Journal of the American Society of Nephrology, vol.21, no.10, pp.1641-1644.
61.Salman A, Ahmad I, Al-Madani S(2002). “Particle swarm optimization for task assignment problem”, Microprocessors and Microsystems, vol.26,no.9,pp.363-71.
62.Sarkar S, Das S, Chaudhuri S S(2015). “A multilevel color image thresholding scheme based on minimum cross entropy and differential evolution”, Pattern Recognition Letters, vol.54, no.1, pp.27-35.
63.Shen A L, Lin H L, Tseng Y F,et al(2015). “Topiramate may not increase risk of urolithiasis: A nationwide population-based cohort study” ,Seizure, vol. 29, no.4, pp. 86-89.
64.Shih M T, Tang S H, Cha T L et al (2016). “The Risk of Nephrolithiasis Among Patients With Ankylosing Spondylitis: A Population-Based Cohort Study”, Arch Rheumatol, vol.31, no.4, pp.346-352.
65.Tandon V, El-Mounayri H, Kishawy H(2002). “NC end milling optimization using evolutionary computation” , International Journal of Machine Tools & Manufacture, vol.42, no.5, pp. 595-605.
66.Tian Z P, Zhang H Y, Wang J Q, Chen X H(2016). “Multi-criteria decision-making method based on a cross-entropy with interval neutrosophic sets”, International Journal of Systems Science, vol.47, no.15, pp.3598-3608.
67.Wang K J, Yang J W(2014). “Sunlight concentrator design using a revised genetic algorithm” , Renewable Energy, vol.72, pp.322-335.
68.Wen X, Si J, He Z et al(2012). “Support-Vector-Machine-Based Models for Modeling Daily Reference Evapotranspiration With Limited Climatic Data in Extreme Arid Regions” ,Water Resources Management, Vol.29,no.9, pp.3195-3209.
69.Zhang X, Ermolieva T, Balkovic J (2015). “Recursive cross-entropy downscaling model for spatially explicit future land uses: A case study of the Heihe River Basin” , Physics and Chemistry of the Earth, Parts A/B/C, vol.89, no.90, pp.56-64.
70.Zheng B, Yoon S W, Lam S S(2014). “Breast cancer diagnosis based on feature extraction using a hybrid of K-means and support vector machine algorithms” , Expert Systems with Applications, vol.41, no.4, pp.1476-1482.
71.Zukhri Z, Paputungan I V(2013). “Ahybrid Optimtzation Algorithm Based on Genetic Algorithm and Ant Colony Optimtzation” , International Journal of Artificial Intelligence & Applications, vol4, no5, pp.63.