摘要
資料挖掘目前在企業界的應用已經愈來愈普遍，許多使用者也認為此技術是一項增加各企業競爭力的重要指標，為企業重要利基所在。傳統的資料挖掘技術大都應用在企業內部之決策支援系統和主管資訊系統，現在已經開始應用於無遠弗界之網際網路上，發揮更大的效能及層面。資料挖掘除了在企業的應用以外，近年來在醫學及藥物領域的應用也受到愈來愈多的關注。由於在用藥的過程當中，有可能會有交互作用而產生嚴重的問題，所以藥物間的交互作用是藥師在調配處方時要特別注意的事項之一。基於這個理由，我們發展了一個Web-based之資料挖掘雛型系統，提供藥師或使用者線上查詢藥物交互作用相關知識庫的資料。
本研究使用某醫院的部份藥物交互作用資料作為樣本，經過分析模組建立其文件型別定義（DTD），再撰寫程式建構其物件模型，剔除有問題之資料後，成功的將資料建立於XML文件檔。分析的過程中，並建立一藥物作用現象的知識庫，將挖掘關聯法則之Apriori演算法實作於Web上的伺服器中，再透過XML中DOM、XSL及XML查詢引擎等相關技術，架構出完整的一套雛型系統。
傳統的資料庫系統已無法滿足電子商務的所有需求，因為它們在處理自己的資料內容時是各自獨立的，而XML技術將網際網路的發展帶入一個新紀元，同一份XML文件不但可以做跨平台﹙WAP， PDA，WEB﹚的呈現，還能提高文件運用的彈性，增進搜尋的品質。由我們的實作中，由單一的XML來源，即可達到各種不同的運用，展現其強大的延伸性功能。本研究所提出的系統架構，實作的結果能夠結合XML與資料挖掘技術而且有效的完成知識庫建置，提供使用者一個重要的參考依據。我們也希望本研究在藥物交互作用領域所提供的完整解決方案，也能推廣至其他領域，發揮其最大的功效。

The using of data mining for enterprise is more popular today. Many researchers recognize the fact that this technique is one of the most important index about how to increase competitions and make profits. The traditional using of data mining is to support the internal decision support system（DSS）and executive information system（EIS）. If we can use the technique for Internet, it must bring the performance and scope into full play. The policymaker can quickly make decision after discussion with the customer in the other country or get a good way in the middle of home. Beside enterprise application, the researchers focus of using data mining in the medical science and medicine fields. There could be the interaction of many medicines and result in a serious problem, so it is the particular concern for either doctor writes out a prescription or pharmacist fill a prescription. For this reason, we develop a web-based data mining system providing pharmacists and users on-line to query the knowledge information about medicine interactions.
In this study, we use some hospital’s medicine interaction data for our sample data, as the result of analysis process and to construct object model, finally we transfer our source data to XML file. During this process, we also create knowledge base of effects field. With the knowledge-base table, we implement the Apriori algorithm into the web server, combine the associate techniques of XML DOM, XSLT and XML query engine, complete to implement them to our system.
The traditional databases do not meet the all of the requirements of the Electronic Commerce, because they processing independently the records of the database. The XML bring a new way to science and technology industry, the XML documents can access in any platform including WAP, PDA, WEB, and improve the flexibility of using of the paper and speed up the searching quality. In our implementation, the single XML source file can used in any applications and has the strongly extension capability. We provide a system structure to combine the XML technique and data mining technique to successfully building the knowledge base, and give the users a good reference when they make the decision. We hopefully this study providing the total solution about medicine interactions can use in another fields.

第1章 導論 1
1.1 研究背景 1
1.2 研究動機 3
1.3 研究目的 4
1.4 研究範圍與限制 5
1.5 論文架構 5
第2章 相關研究 7
2.1 藥物交互作用概論 7
2.1.1 藥物交互作用簡介 9
2.1.2 藥物交互作用原因 9
2.1.3 藥物交互作用等級 10
2.1.4 藥物交互作用實例探討 10
2.2 資料挖掘的技術 12
2.2.1 關聯式法則（Association Rule） 14
2.2.2 時間序列分析（Time Sequence Analysis） 17
2.2.3 分類式法則（Classification Rule） 18
2.2.4 組群式法則（Clustering Rule） 20
2.2.5 序列型樣（Sequential Pattern） 22
2.3 可延伸標示語言（XML）相關技術 22
2.3.1 XML指標語言（XML Pointer）─Xpointer 24
2.3.2 XML連結語言（XML Link）─ Xlink 25
2.3.3 文件型別定義（Document Type Definition；DTD） 25
2.3.4 文件物件模型（Document Object Model；DOM） 26
2.3.5 Simple API for XML（SAX） 27
2.3.6 XSL（Extensible Stylesheet Language） 28
2.3.7 XML查詢語言 33
2.4 JAVA技術 34
2.4.1 JSP的基本概念 35
2.4.2 JAVA RMI 37
第3章 系統架構 40
3.1 資料前處理 40
3.1.1 資料分析 41
3.1.2 模組建立 45
3.1.3 檔案架構 50
3.2 WEB系統建置 52
3.2.1 Data Collection Module 52
3.2.2 Data Query Module 54
3.2.3 Data Mining Module 54
3.2.4 Download Module 55
第4章 實作結果與討論 56
4.1 實作環境 56
4.1.1 N-Converter 57
4.1.2 XML Query Engine 58
4.1.3 Data mining實作 61
4.1.4 Transformer 63
4.1.5 XSL-FO（XSL Formatting Objects） 67
4.2 系統展示 69
4.3 系統評估 74
4.3.1 演算法 74
4.3.2 使用工具 75
4.3.3 系統功能 77
第5章 結論與未來發展 83
參考文獻 86

[1] R. Agrawal, T. Imilienski, and A. Swami, “Mining Association Rules between Sets of Items in Large Databases,” Proceedings of the ACM SIGMOD Int''''l Conf. on Management of Data, pp. 207-216, May 1993.
[2] R. Agrawal and R. Srikant, “ Fast Algorithms for Mining Association Rules,” Proceedings of the 20th International Conference on Very Large Databases, September 1994.
[3] R. Agraeal, and R. Srikant, “Mining sequential patterns,” Proc. of Eleventh International Conf. on Data Engineering, IEEE Computer Society Press, pp. 3-4, 1995.
[4] K. Alsabti, S. Ranka, and V. Singh, “An Efficient K-Means Clustering Algorithm,” PPS/SPDP Workshop on High performance Data Mining, 1997.
[5] Alex Berson and Stephen J. Smith, “Data Warehousing, Data Mining, and OLAP,” MaGraw-Hill, 1997.
[6] R. Brause, T. Langsdort, and M. Hepp, “Neural Data Mining for Credit Card Fraud Detection,” Proceedings of the 11th IEEE International Conference on Tools with Artificial Intelligence, 1999.
[7] L. Breiman, J. Friedman, R. Olshen, and C. Stone, “Classification of Regression Trees,” Wadsworth, 1984.
[8] S. Brin, R. Motwani, J.D. Ullman, and S. Tsur, “Dynamic Itemset Counting and Implication Rules for Market Basket Data”, 1997 ACM SIGMOD Conference on Management of Data, pp. 255-264, 1997.
[9] Paolo Ciancarini, Fabio Vitali, and Cecilia Mascolo, “Managing Complex Documents Over The WWW: A Case Study For XML,” IEEE Transactions on Knowledge and Data Engineering, Vol. 11, No. 4, July/August 1999.
[10] Mark W. Craven and Jude W. Shavlik, “Using Neural Networks for Data Mining,” Future Generation Computer Systems special issue on Data Mining, 1998.
[11] Hichem Frigui and Raghu Krishnapuram, “A Robust Clustering Algorithm Based on Competitive Agglomeration and Soft Rejection of Outliers”, IEEE on Computer Vision and Pattern Recognition, pp.550-555, 1996.
[12] A. Levy, M. Fernandez, D. Suciu, D. Florescu, and A. Deutsch, “XML-QL : A Query Language for XML,” World Wide Web Consortium Technical Report, Number NOTE-xml-ql- 19980819, 1998.
[13] Heikki Mannila and Pirio Ronkainen, “Similarity of Event Sequences (Revised version),” Proceedings of the Fourth International Workshop on Temporal Representation and Reasoning (TIME’97), Daytona Breach, Florida, USA, pp. 136-139, May 1997.
[14] Chuang-Hue Moh, Ee-Peng Lim, and Wee-Keong Ng, “DTD-Miner: A Tool for Mining DTD from XML Documents,” Advanced issues of E-Commerce and Web-Based Information Systems, pp. 144-151, 2000.
[15] H. Ouahid and A. Karniouch, “Converting Web Pages into Well-formed XML Documents,” ICC’99, pp. 676-680, 1999.
[16] Jong Soo Park, Ming Syan Chen, and Philip S. Yu, “Using a Hash-Based Method with Transaction Trimming for Mining Association Rules,” IEEE Transactions on Knowledge and Data Engineering, Vol. 9, No. 5, September/ October 1997.
[17] C. Petrou, S. Hadjiefthymiades, and D. Martakos, “An XML-based, 3-tier Scheme for Integrating Heterogeneous Information Sources to the WWW,” Proceedings of the Tenth International Workshop on Database and Expert Systems Applications, pp. 706-710, 1999.
[18] Jonathan Robie, Joe Lapp, and David Schach, “XML Query Language (XQL),” World Wide Web Consortium Query Languages Workshop, Boston, MA, December 1998.
[19] W3C, “Document Object Model Level 1 specification,” http://www.w3.org/TR/REC-DOM -Level-1/, Oct. 1998.
[20] W3C, “Extensible Markup Language (XML) 1.0 Recommendation,” http://www.w3.org/TR/1998/ REC-XML-19980210.html, Feb. 1998.
[21] W3C, “Extensible Stylesheet Language (XSL) Version 1.0,” http://www.w3.org/TR/2001/REC-xsl-20011015/, Oct. 2001.
[22] W3C, “XML Schema Part 0: Primer ,” http://www.w3.org/TR/2001/REC-xmlschema-0-20010502/, May 2001
[23] W3C, “XQuery 1.0: An XML Query Language,” http://www.w3.org/TR/2001/WD-xquery-20010607/, June 2001.
[24] http://business.fortunecity.com/gap/1851ppa.chitosan.htm
[25] http://ec.icareasia.com.tw/druginfo/medcon_hol.asp
[26] http://www.ccpc.com.tw/mdcencyc/870709.htm
[27] http://www.ehato.com.tw/pharm_info/pharm_inter/index.asp
[28] http://www.medicalvillage.org.tw/lifemed/chn- 20.htm
[29] http://www.renderx.com/FO2PDF.html
[30] http://www.sanofi-synthelabo.com.tw/products/product_s.asp
[31] http://www.webhospital.org.tw/medicine/index.html
[32] http://www.zx.gov.tw/H-edu/hedu301.htm
[33] http://xml.apache.org/fop/index.html
[34] http://xml.darmstadt.gmd.de/xql
[35] 施威銘, “HTML Home Page設計實務,” 旗標出版有限公司, 1996年7月.
[36] 陳會安, “XML網頁製作徹底研究,” 旗標出版有限公司, 2000.
[37] 連麗真,吳采菽,陳雪美, “電子交易技術實務篇,” 翔威國際有限公司, 1997.
[38] 蔡靖彥, “常用藥品手冊,” 杏欣出版社, 1990