雖然台灣實施全民健保已多年，但在家庭醫師制度尚未普及化之前，病患大多習慣以憑自身的症狀感覺直接至醫院就診或以電話和網路掛號，但因民眾普遍醫療知識不足而經常掛錯科別，造成醫療資源的浪費或延誤病情。本研究針對此問題，採用類神經網路中的支援向量機 (Support Vector Machine, SVM)來建立一個就診科別預測分類專家系統，將具有共同病徵之疾病正確分類。此系統可輔助病患能選更好。

Taiwan implements all the people health insurance already many years. Before family doctor system not yet universalization, sickness mostly custom by depends on own symptom feeling directly to the hospital seeing a doctor or by the telephone and the network registration. Insufficient hangs the wrong branch because of the populace universal medical service knowledge to leave frequently, creates the medical resources waste or the delay condition. This research in view of this question to adopt Support Vector Machine(SVM) of Artificial Neural Network to establishes a forecast classifies expert system to search doctor branch . It will correct distribution disease of the common symptom. This system may assist sickness to be able to choose the suitable branch seeing a doctor. Avoids hanging the wrong branch to cause of repeatedly to go see a doctor either the error diagnostic causes life and the health and the medical resources waste or the harm sickness. In order to appraise result of this diagnosis system. We also respectively use Back-propagation Network(BPN) regarded as compares to the standard. The experimental result showed that Support Vector Machine(SVM) is better than
Back-propagation Network(BPN).

摘要........................................................................................................................... I
Abstract .................................................................................................................II
致謝..................................................................................................... .................... III
表目錄..................................................................................................................... VI
圖目錄....................................................................................................................VII
1.緒論...........................................................................................................................1
2.文獻探討...................................................................................................................6
3.研究方法....................................................................................................................7
3.1倒傳遞式類神經網路(Back-propagation Network, BPN) ...............................10
3.2支援向量機(Support Vector Machine, SVM) ................................................. 13.
4.研究資料的處理及系統架構..................................................................................13
4.1資料、變數及函數............................................................................................13
4.1.1、資料來源與樣本處理....................................................................................13
4.1.2變數定義.........................................................................................................15
4.1.3類神經激勵函數及指令.................................................................................16
4.2交插驗證法........................................................................................................17
4.3倒傳遞網路(Back-propagation Network, BPN)模式建立及分析....................19
4.4支援向量機(Support Vector Machine, SVM)模式建立及分析........................21
5.實驗結果..................................................................................................................24
5.1.實驗結果-倒傳遞網路(BPN) ..........................................................................27
5.2.實驗結果-支援向量機(SVM) .........................................................................27
6.結論與建議.............................................................................................................28
6.1結論....................................................................................................................28
6.2研究貢獻............................................................................................................28
6.3研究限制...........................................................................................................29
6.3.1資料蒐集方面.................................................................................................29
6.3.2對特別樣本之因素.........................................................................................29
6.3.4未來研究之建議.............................................................................................29
參考文獻.................................................................................................................... 30
附錄A: 問卷調查表................................................................................................31.

1.袁本治。(2003)”眩暈預測模式之研究”。義守大學管理科學研究所碩士論文。
2.Baloh R.W. (1998). Vertigo. Lancet, 352, 1841-1846.
3.Oghalai J.S., Manolidis S., Barth J.L., Stewart M.G., Jenkins H.A. (2000). Unrecognized benign paroxysmal positional vertigo in elderly patients. Otolaryngol Head Neck Surg, 122, 630-634.
4.Saadah H.A. (1999). Vertigo. Lancet, 353,591.
5.田昀宗。(2004)”類神經網路於中醫哮喘診斷之應用”。長庚大學資訊管理研究所碩士論文。
6.Eun-Jung Song , Min-Jea Tahk , “ Three-dimensional midcourse guidance using neural networks for interception of ballistic targets ” , IEEE Trans. Aerospace and Electronic Systems , Vol. 38 , No. 2 , April , 2002
7.Xicai Yue , Datian Ye , Chongxun Zheng , and Xiaoyu Wu , “ Neural networks for improved text-independent speaker identification ,” IEEE Engineering in Medicine and Biology , March/April , 2002
8.Paul Sajda , Clay Spence , and John Pearson , “ Learning contextual relationships in mammograms using a hierarchical pyramid neural network ,” IEEE Trans. Medical Imaging , Vol. 21 , No. 3 , March , 2002
9.侯幸雨。(2003)”應用模擬技術探討台灣醫院門診預約掛號系統”。國立中正大學企業管理研究所碩士論文。
10.邱海雲。(2003)”利用類神經網路的理論來預測麻醉深度BIS(Bispectral Index)數值”。元智大學機械工程學系碩士論文。
11.J. W. Johansen, Peter S. Sebel, J. C. Sigl: Clinical Impact of Hypnotic Titration Guidelines Based on EEG Bispectral Index (BIS) Monitoring During Routine Anesthetic Care. Journal of Clinical Anesthesia 2000; 12: 433-443.
12.G. N. C. Kenny, H. Mantzaridis, “Closed-loop Control of Propofol Anesthesia,” British Journal of Anaesthesia, 83 (2), pp. 223-238, 1999.
13.J. W. Huang, Y. Y. Lu, A. Nayak, R. J. Roy, “Depth of Anesthesia Estimation and Control,” IEEE Transacitons on Biomedical Engineering, Vol. 46, No. 1, Jan., pp. 71-81, 1999.
14.李文瑞。(2003)”運用基因演算法建構疾病早期診斷模型之研究-以糖尿病前期之診斷為例”。輔仁大學資訊管理學系碩士論文。
15.ADA, "Standards of Medical Care for Patients with Diabetes Mellitus, " Diabetes Care, 25: S1, 2002/01, pp. S33-S49

16.Adriaanse M.C., Snoek F.J., Dekker J.M., van der Ploeg H.M, Heine R.J., "Screening for Type 2 diabetes: an exploration of subjects’ perceptions regarding diagnosis and procedure," Diabetes UK. Diabetic Medicine, 19,2002, pp.406-411
17.Bahman P.T., Willam H.H., "A Multivariate Logistic Regression Equation to Screen for Diabetes," Diabetes Care, 25:11, 2002/11，pp.1999-2003
18.簡詠霖。(2003)”條件邏輯斯迴歸模式於二元分類法的應用探討”。 國立陽明大學公共衛生研究所碩士論文。
19.StataCorp. 2001. Stata Reference Software: Release 7.0. College Station, TX: Stata Corporation: 1 A-G.
20.Neuhuser, M. and Becher, H. (1997). Improved odds ratio estimation by post hoc stratification of case-control data. Statistic in Medicine 16, 993-1004.
21.Hosmer, D. W. and Lemeshow, S. (2000). Applied Logistic Regression. New York:John Wiley & Sons, Inc. 2nd.
22.萬義泰。(2004)”利用邏輯斯迴歸來改善糖尿病病患之醫學診斷”。 淡江大學數學學系碩士論文。
23.John H. Wasson, Harold C. Sox, Raymond K. Neff, and Lee Goldman（1985）,“Clinical Prediction Rules. Applications and Methodological Standards”,N Engl J Med ,1985,313,p.793-p.799
24.Chih-Hsiu Wu, May Meei-Shyuan Lee, Kuo-Chin Huang, Jenq-Yuh Ko, Tzung-Shiahn Sheen, Fon-Jou Hsieh（2000）,“A probability prediction rule for malignant cervical lymphadenopathy using sonography”, Head & Neck, 22, p.223-p.228
25.孫漢屏。(2002)”類神經網路為基礎之智慧型醫院網路掛號系統”。中國醫藥學院醫務管理研究所碩士論文。
26.江宏志（2003）” 運用基因演算法建構疾病預測模型之研究-以尿路結石疾病預測為例 ”。 國立臺灣大學商學研究所博士論文。
27.Chiang, David, Chiang H.C., Chen W.C. and Tsai F.J.(2003). Prediction of stone disease by using discriminate analysis and artificial neural networks in genetic polymorphisms- A new modality. British Journal of Urology. (In Press)
28.Chen, W.C., Chiang D., Yang S. J. and Chiang H.C.(2003). Use of genetic algorithms and artificial neural network to the prediction of stone disease from clinical parameters and genetic polymorphisms. Urology. (In Press)
29.Negnevitsky, M.(2002). Artificial Intelligence- A Guide to Intelligent System, Addison Wesley.
30.李博智(2002)” 資料探勘在慢性病預測模式之建構”。 元智大學資訊管理學系碩士論文。
31.Guidelines Subcommittee. 1999 World Health Organization-International Society of Hypertension Guidelines for the Management of Hypertension. J Hyertension, Vol.17,pp.151-83, 1999.
33.iang, H., Paul, K. and Whelton, P. K., “Epidemiology and Prevent of Hypertension,” Medical Clinics of North America, Vol.81, pp.1077-97, 1997.
34.Armengol, E., Palaudaries, A. and Plaza, E., “Individual Prognosis of Diabetes Long-term Risks: A CBR Approach,“ Method Inform Med, Vol.40, pp.46-51, 2001.
35.Dazzi, D., Taddei, F., Gavarini, A., Uggeri, E. and Negro, R., “The Control of Blood Glucose in the Critical Diabetic Patient: a Neuro-Fuzzy Method,” Journal of Diabetes and Its Complications, Vol.15, pp.80-87, 2001.
36.陳章友(2000)” 類神經網路在醫學檢驗的應用──以肝病為例”。 國立交通大學工業工程與管理系碩士論文。
37.Fikret, G., 1999, "Neural-Network-Based Decision Making in Diagnostic Applications," IEEE Engineering In Medicine And Biology, Vol. 18, No. 4, pp. 89-93.
38.Elizabeth, G., Violante, A. and Francisco, C., 1998, "Using Neural Networks for Differential Diagnosis of Alzheimer Disease and Vascular Dementia," Expert Systems with Applications, Vol. 14, pp. 219-225.
39.黃勝崇(2001)” 資料探勘應用於醫療院所輔助病患看診指引之研究”。 南華大學資訊管理學系碩士論文。
40.Christian Borgelt，Apriori－Find Association Rules Hyperedges with Apriori Algorithm，2000，Gemany。
41.Po Shun Ngan、Man Leung Wong、Wai Lam、Kwong Sak Leung、Jack C. Y. Cheng，Medical data mining using evolutionary computation，1999，Artificial intelligence in medicine，Vol.16。
42.廖介銘(2003)” 決策樹應用於糖尿病之探勘”。 華梵大學資訊管理學系碩士論文。
43.Zorman, M., Gou Masuda, Kokol, P., Yamamoto, R., Stiglic, “Mining Diabetes Database With Decision Trees And Association Rules”, Proceedings Of The 15th IEEE Symposium On Computer-Based Medical Systems, 2002, pp. 134-139.
44.Jiwei, H., Micheline K., “Data Mining:Concepts Amd Techniques ”, Morgan Kaufmann Publishers, New York, 2001.
45.張傳育(2000)” 整合類神經網路及影像處理技術在鼻咽疾病診斷之應用”。 國立成功大學電機工程學系博士論文。
46.B. D Daly, “Thoracic metastases from nasopharyngeal carcinoma presenting as hypertrophic pulmonary osteoarthropathy: scintigraphic and CT findings,” Clinical Radiology, vol. 50, pp.545-547, 1995.
47.Takashi Togawa, Nobuharu Y., Fujimi K., Fumiyuki S., Ken O., and Sanzou T., “Visualization of nasopharyngeal carcinoma with Tl-201 chloride and a three-head rotating gamma camera SPECT system,” Annals of Nuclear Medicine, Vol. 7, pp.105-113, 1993.
49.Y. K. Cheung; Jonathan Sham; Y. L. Cheung; F. L. Chan, “Evaluation of skull base erosion in nasopharyngeal carcinoma: comparison of plain radiography and computed tomography,” Oncology, Vol. 51, pp. 42-46, 1994.
50.陳奕良(2000)” 一個建構於網路精神疾病診斷的個案庫決策支援系統”。 國防管理學院 資源管理研究所碩士論文。
51.Lynn Ling X Li [1999], “Knowledge-Based Problem Solving: An Approach to Health Assessment.” Expert Systems with Applications, 16, pp.33-42.
52.Liao, S. H. [2000], “Case-based Decision Support System: An Architecture for Simulating Military Command and Control.” The European Journal of Operational Research, Vol. 123, Issue: 3, pp. 558-567.
53.Althoff K. D. and Bergmann R. and Wess S. and Manago M. and Auriol E. and Larichev O. I. and Bolotov A. and Zhuravlev Y. I. and Gurov S. I. [1998], “Cased-Based Reasoning for Medical Decision Support Tasks: The Inreca Approach.” Artificial Intelligence in Medicine, 12, pp.25-41.
54.劉德笙(2003)” 中西醫診斷專家系統於冠狀動脈心臟病之應用”。中原大學醫學工程研究所碩士論文。
55.W. G. Baxt, “Use an artificial neural network for data analysis in clinical decision-making : the diagnosis for acute coronary occlusion ,” Neural Computation, 2, pp.480-489, 1990.
56.Y. Yoon et al., “A connectionist expert system for dermatology diagnosis,” Expert Systems, pp.23-31, 1990.
57.陳振亨(2004)” 應用類神經網路於心血管疾病分類與診斷”。 東海大學工業工程與經營資訊學系碩士論文。
58.Ichimura, Takumi, (2003) , “A classification capability of Reflective Neural Networks in medical database,” Lecture Notes in Artificial Intelligence, v 2774 PART 2, p 373-379
59.Shaout, Adnan, (2003) , “A fuzzy data mining system for medical records,” Proceedings of the International Conference on Artificial Intelligence IC-AI 2003, v 1, 2003, p 376-381
60.Guler, Inan, (2005) , “Improving medical diagnostic accuracy of ultrasound Doppler signals by combining neural network models,” ,Computers in Biology and Medicine, v 35, n 6, July, 2005, p 533-554
61.蔡孟潔(2005)” 應用邏輯斯迴歸於冠狀動脈心臟病之研究”。元智大學工業工程與管理學系碩士論文。
62.Gordon, T., Castelli, W. P., Hjortland, M. C., Kannel, W. B. and Dawber, T. R. (1997). ”High-density lipoprotein as a protective factor against coronary heart disease:
63.the Framingham Study,” American Journal of Medicine, Vol.62, pp.707-714.
64.Willett, W. C., Manson, J. E., Stampfer, M. J., Colditz, G. A., Rosner, B., Speizer, F. E. and Hennekens, C. H. (1995). ”Weight, weight change, and coronary heart disease in women,” Journal of the American Medical Association, Vol. 273, pp.461-465.
65.Drexel, H., Amann, F.W., Beran, J., Rentsch, K., Candinas, R., Muntwyler, J., Luethy, A., Gasser, T. and Follath, F. (1994). ”Plasma triglycerides and three lipoprotein cholesterol fractions are independent predictors of the extent of coronary atherosclerosis,” Circulation, Vol.90, pp.2230-2235
66.陳會安，2000[民89]，ASP網頁製作徹底研究，旗標。
67.位元文化，2000[民89]，ASP 3.0動態網頁實務入門，文魁資訊。
68.鍾錸，2000[民89]，ASP 3.0網際網路應用系統實作，科南出版松崗發行。
69.莫瑟、潘得龍、Mercer,Dave，2001[民90]， ASP 3.0程式設計入門手冊，麥格羅希爾。
70.小誌，2000[民89]，ASP入門與實作，文魁資訊。
71.蘿珊智慧型科技工作室，1999[民88]，MATLAB入門及應用(適用5.X版)，松崗。
72.2005,MATLAB程式設計應用實務，文魁資訊。
73.鄭錦聰，Matlab程式設計，全華。