台灣近年來歷經各類疫情的衝擊，公共衛生與傳染病防治日趨重要，因此，為能有效防範疫情及掌握傳染性疾病之監視系統更顯為重要。本論文運用在台灣地區登革熱疫情確定個案資料，經由全球定位系統（GPS）定位後，進一步利用地理資訊系統分析其地域之相關性，將蒐集之資料找出其各項特徵關係，歸納分析後，以本研究之定義指標來監測傳染病疫情發生，發掘資料中隱藏不同之特定訊息，以表現出疫情擴散速度、方向、群聚密度及速度等具體性所代表意義之呈現，亦可作為流行病學決策支援之用。
本研究運用地理資訊系統初步定義傳染病疫情發展監測指標，經專家效度完成本研究問卷後，並交由相關防疫工作人員進行普查以逐步建構出本研究之傳染病自動監測指標系統，並以密度式分群法，評估疫情資料之間密集度分群技術實際進行疫情監控。

The origin in recent years of Taiwan is through the impact of all kinds of epidemic situations, it is becoming more important that public health and infectious disease are prevented and cured, so, in order to take precautions against the epidemic situation and know effectively the monitoring system of the infective disease is more apparent it is important.

This thesis uses and confirms the case materials in Taiwan dengue fever epidemic situation, via the global positioning system (GPS) After making a reservation, utilize dependence of its region of network analysis of geographical information further, find out every characteristic relation their materials that collect, is it after analysing, is it monitor with definition indicator of research this epidemic situation of infectious disease take place to come to sum up, explore materials hide different specific information, in order to demonstrate epidemic situation rate of diffusion, direction, clustering density and speed,etc. getting concrete to appear the meaning represented, can also serve the purpose of decision support of epidemiology.

Use the geographical preliminary definition infectious disease epidemic situation development of information system to monitor the indicator via this research, after expert result degree finishes this research questionnaire, transfer to relevant epidemic prevention staff member carry on general survey in order to is it is it happen infectious disease of research this monitor the indicator system automatically to construct to build progressively, hive off law with the density type, assess between the epidemic situation materials the intensive degree of technology of hiving off controls the epidemic situation actually.

誌 謝 IV
目 錄 V
表目錄 VIII
圖目錄 IX
中文摘要 XII
ABSTRACT XIV
第一章、緒論 1
1.1 研究動機 2
1.2 研究目的 3
第二章、文獻探討 6
2.1 地理資訊系統 6
2.1.1 地理資訊系統在公共衛生之應用 7
2.1.2 地理資訊系統在傳染病之重要性 9
2.1.3 地理資訊系統運用在國內之分析研究 10
2.2 資料探勘 12
2.2.1 資料探勘的演進 12
2.2.2 資料庫系統 15
2.2.3 群集分析 16
2.3 當前傳染性疾病及監測系統 18
2.3.1 傳染病 18
2.3.2 病媒蚊疾病 22
2.3.3 疾病監測系統 25
2.3.4 人工智慧技術與疾病運用 29
第三章、研究方法 32
3.1 研究流程 32
3.2 研究材料與方法 33
3.2.1 疫情地理管理資訊系統 34
3.2.2 專家效度 36
3.2.3 問卷設計 36
3.2.4 疫情資料 37
3.2.5 分析工具 39
第四章、研究結果 42
4.1 初步定義指標 42
4.2 建構指標過程 43
4.2.1 專家效度呈現 44
4.2.2 問卷結果 47
4.3 疫情指標評估 56
4.3.1 疫情指標實證分析 56
4.3.2 自動分群演算法 63
4.3.3 自動分群成效分析 71
第五章、結論與建議 76
參考文獻 78
中文文獻 78
英文文獻 80
電子文獻 82

中文文獻

賴進貴(2005)。地理資訊系統應用於登革熱疫情防治之檢討與建議。環境與世界，11，65-81。
溫在弘等(2002)，地理資訊系統應用於傳染流行病的疫情偵測、數據分析與速效控制，台灣衛誌21，6，449-456。
王秋原主編(2003)：高中地理第三冊，台北：東華書局
梁定澎(2006)。決策支援系統與企業智慧。台北，智勝。P224-225
陳建仁 (1999)。流行病學：原理與方法。台北，聯經。
蔡耀明（2000）。電腦與人腦。臺北，台灣商務
李紹綸(2006)。資料庫系統理論與實務：使用SQL Server 2005。台北:金禾
周天穎(2003)。地理資訊系統理論與實務。台北:儒林
石計生(2001)。地理資訊系統社會學。台北:儒林
曾新穆，李建億(2004)。資料探勘。台北:東華




施義雄，1999,「台灣地區癌症發生率與環境之相關分析及其地理資訊系統的建構」，中國醫藥學院/環境醫學研究所，碩士論文。

廖勇柏，2000，「癌症地圖的繪製: 趨勢面分析法的改變與其在時空特性探討之應用」，國立臺灣大學/流行病學研究所，博士論文。
張春蘭（2005）高雄市登革熱擴散的地圖分析，國科會研究報告(NSC 93-2415-H-017-002)。
杜智弘(Yu, Jyh-Horng)國立臺灣師範大學地理研究報告1982年第 08 期台灣地區死亡人口之季節性及區域性研究
Study On Mortality In Taiwan Based On Seasonality And Regionality。
苙世駿(2003)。以GIS為基礎之災情資訊彙整系統設計-以SARS疫情新聞為例。碩士論文。國立交通大學。
周貝盈(2000)。開發與評估台灣登革熱爆發流行監測系統。國立陽明大學公共衛生研究所碩士。
張念台,蘇明道(1995),利用地理資訊系統進行病媒蚊監測之研究, 國立屏東技術學院學報 (4):45-54
賴進貴 (1994),地理資訊系統之準確性探討與測試，第四屆 ESRI &ERDAS User Conference 論文集，台北市劍潭青年活動中心，663-672頁

英文文獻

Anwar, T. M., Beck. H. W. & Navathe., “Knowledge Mining by Imprecise
Querying: A Classification-Based Approach, IEEE 8th International Conference
on Data Engineering”, Phoenix, Arizona, 1992, pp.622-630.
Agrawal, R. and R. Srikant, “Mining Generalized Association Rules, The 21th International Conference Proceedings on Very Large Databases, 1995.
Brief Report: Outbreak of Marburg Virus Hemorrhagic Fever --- Angola, October 1, 2004--March 29, 2005(Morbidity and Mortality Weekly Report Morbidity and Mortality Weekly Report Centers for Disease Control and Prevention enters for Disease Control and Prevention)
Blaz, Z., Janez, D. W., Kattan, J. and Robert, B. I., “Machine Learning for Survival Analysis: A Case Study on Recurrence of Prostate Cancer,” Artificial Intelligence in Medicine, Vol. 20, pp.59-75, 2000.
Frawley , W. J., G. Piatetsky-Shapiro and C. J. Matheus, Knowledge Discovery in Database: An Overview, AAAI/MIT Press, 1991.
Gore, A. 1999 The Digital Earth Vision, The Second Interagency Digital Earth Workshop, http://www.digitalearth.gov
Han, J., Kamber, M. (2000).Data mining: Concepts and Techniques.Morgan Kaufmann.Retrieved from http://mylibrary.e-lib.ncyu.edu.tw/
Haydon, G. H., Jalan, R., Ala-Korpela, M., Hiltunen, Y., Hanley, J., Jarvis, L. M., Ludlum, C. A. and Hayes, P. C., “Prediction of Cirrhosis in Patients with Chronic Hepatitis C Infection by Artificial Neural Network Analysis of Virus and Clinical Factors,” Journal of Viral Hepatitis, Vol.5, No.4, pp.255-64, Jul 1998.
Heffernan, R., et al., Syndromes surveillance in public health practice, New York City. Emerge Infect Dis, 2004. 10（5）: p. 858-64.
John, H., Dennis, R. and Flaura, K., “The Learning Classifier System: an Evolutionary Computation Approach to Knowledge Discovery in Epidemiologic Surveillance,” Artificial Intelligence in Medicine, Vol.19, pp.53-74, 2000.
Keith C. Clarke, Sara L. McLafferty, and Barbara J. Tempalski(1996).On Epidemiology and Geographic Information Systems: A Review and Discussion of Future Directions, Emerging Infectious Diseases ,2(2)
Kononenko, I., “Machine Learning for Medical Diagnosis: History, State of the Art and Perspective,” Artificial Intelligence in Medicine, Vol. 23, Issue: 1, pp. 89-109, August 2001.
Lang L. GIS for Health Organization. Caledonia: ESRI Press 2000: 20-35
Lewis MD, Pavlin JA, Mansfield JL, O''Brien S, Boomsma LG, Elbert Y, Kelley PW. Disease outbreak detection system using syndromes data in the greater Washington DC area. Am.J.Prev.Med. 2002; 23(3):180-186.
Longley, P., Goodchild, M., Maguire, D. and Rhind, D. (2001) Geographic Information Systems and Science, Chichester: John Wiley & Sons.
Nakano, H., Okamoto, Y., Nakabayashi, H., Takamatsu, S. and Tsujii, H., “Application of Neural Network to the Interpretation of Laboratory Data for the Diagnosis of Two Forms of Chronic Active Hepatitis,” International Herpetology Communications, Vol. 5, and Issue: 3, pp. 160-165, July 1996.
Openshaw, S., Charlton, M., &Craft, A. (1988).Searching for Leukemia Clusters Using a Geographic Analysis Machine. Papers of the Regional Science Association.64:95-106.
Rigau-Perez JG, Millard PS, Walker DR, Deseda CC, and Casta-Velez A.A deviation bar chart for detecting dengue outbreaks in Puerto Rico. Am. J. Public Health, 1999; 89:374-378.
Rushton, Gerry, Elmes, Greg, and Robert McMaster (2000), Considerations for Improving Geographic Information System Research in Public Health “The URISA Journal, Vol. 12, No. 2, pp. 31-50.
Steven, k., Dennis, W. and Matthew, K., “Artificial Neural Networks for Early Detection and Diagnosis of Cancer,” Cancer Letters, Vol.77, pp.79-83, 1994.
Snow J. Interview. John Snow interviewed by Kenneth J. Rothman. Epidemiology.2004 Sep; 15(5):641-4.
Theophilides,C.N.,Ahearn ,S.C.,Grady,S.,Merlino,M.(2003).Identifying West Nile Virus Risk Areas: The Dynamic Continuous-Area Space-Time System. Am. J.Epidemiol.157:843-854
Tom Koch, Ken，GIS approaches to the problem of disease clusters :a brief commentary ，Social Science & Medicine Volume 52, Issue 11 , June 2001, Pages 1751-1754
Tsui, F.C., et al., Technical description of RODS: a real-time public health surveillance system. J Am Med Inform Assoc, 2003. 10（5）: p. 399-408.
Weiss, S. M. and Indurkhya, N. (1998) Predictive Data Mining-A Practical Guide, New York: Morgan Kaufmann.

電子文獻
.
衛生署統計資料網http://www.doh.gov.tw/statistic/index.htm
http://www.cdc.gov.tw/index_info_info.asp?data_id=2996