English  |  正體中文  |  简体中文  |  Items with full text/Total items : 2737/2828
Visitors : 342201      Online Users : 9
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search
LoginUploadHelpAboutAdminister

Please use this identifier to cite or link to this item: http://ir.lib.stu.edu.tw:80/ir/handle/310903100/2057

Title: 資料挖掘技術應用於醫療檢驗之研究 以唐氏症之預測為例
Divination of Down''s syndrome using Symbolic Regression
Authors: 駱獻仁
Xian-Ren Luo
Contributors: 吳志宏
Chih-Hung Wu
資訊管理研究所
Keywords: 唐氏症;符號式迴歸;基因演算法;運算函數
Dwon’s Syndrome;Symbolic Regression;Gentic Program
Date: 2004
Issue Date: 2011-05-26 11:09:39 (UTC+8)
Publisher: 高雄市:[樹德科技大學資訊管理研究所]
Abstract: 摘要
唐氏症是一種先天性的遺傳疾病,也是優生保健相當重要的一環。唐氏症可以透過某些生化檢驗指標計算後,而得孕婦懷有唐氏症胎兒的風險機率。以往,類似此種問題大部分皆使用統計技術及比較其他檢驗結果,往往需要大量的成本及人力。本論文透過分析各檢測指標的關係,試圖建立預測唐氏症發生風險機率的模型。使用的技術為Symbolic Regression,是屬於基因演算法的一種,對於非線性的問題可以提供不錯的計算模式。本論文介紹如何將預測唐氏症發生風險機率的問題轉換成Symbolic Regression的形式,並分析相關參數,並以數個實驗驗證此方法。由本研究獲得的預測模型可以獲得82%以上的預測正確性。
ABSTRACT
Down syndrome is one of the most common genetic birth defects, affecting approximately one in 800 to 1,000 babies. To predict the possibility of such birth defect, tests on blood of pregnant women and comparison on statistical model are performed. This research tries to build models that connect the possibility of Down syndrome with the indicators such as HCG and AFP from experiments. The technique of symbolic regression is employed in this thesis. The model found in by symbolic regression for predicting the possiblility of Down syndrome is of 82% correctness. We present in this these how and why the problem of detecting Down syndrome can be viewed as symbolic regression. The transformation of data and related parameters are discussed. Finally, several experiments are performed and presented.
Appears in Collections:[資訊管理系(所)] 博碩士論文

Files in This Item:

File Description SizeFormat
資料挖掘技術應用於醫療檢驗之研究 以唐氏症之預測為例__臺灣博碩士論文知識加值系統.htm國圖111KbHTML633View/Open


All items in STUAIR are protected by copyright, with all rights reserved.

 


無標題文件

著作權政策宣告:

1.

本網站之數位內容為樹德科技大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,惟仍請適度,合理使用本網站之內容,以尊重著作權人之權益。商業上之利用,則請先取得著作權人之授權。
 
2. 本網站之製作,已盡力防止侵害著作權人之權益,如仍發現本網站之數位內容有侵害著作權人權益情事者,請權利人通知本校護人員(clairhsu@stu.edu.tw),維護人員將立即採取移除該數位著作等補救措施。
 
DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback