Hsiuping University of Science and Technology Institutional Repository : Item 310993100/2249

English | 正體中文 | 简体中文 | Items with full text/Total items : 4334/7631
Visitors : 3189350 Online Users : 143

RC Version 3.2 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.

Scope Adv. Search

Login ‧ Upload ‧ Help ‧ About ‧ Administer

HUSTIR > College of Engineering > Department of Electrical Engineering & Graduate Institute > Theses and Dissertations > Item 310993100/2249

Please use this identifier to cite or link to this item: http://ir.hust.edu.tw/dspace/handle/310993100/2249

Title:	利用 SVM 對 RNA 結構做自動分類 A Study of RNA Structure Automatic Classification byusing Support Vector Machine
Authors:	張家傑
Contributors:	電機工程研究所
Keywords:	支持向量機(SVM) SCOR 分類編碼特徵選擇生物資訊學
Date:	2009-07
Issue Date:	2011-05-23T05:55:55Z
Abstract:	本論文是以支持向量機 (Support Vector Machine; SVM)預測分析的方式，嘗試找出RNA 的型態。我們選擇SCOR（Structural Classification of RNA）資料庫裡的數據作為訓練和性能測試，本研究對於 SCOR 中的 RNA 做特徵值的攫取以及編碼的程序，透過 SVM 以驗證本項研究的可行性。RNA 是一類極重要的生物大分子，它不僅種類繁多，而且其結構也比 DNA 要複雜得多。不同種類的 RNA 其結構雖有共同之處，但也有著顯著的差異。由於 RNA 種類和結構的多樣性這就決定了 RNA 具有多種生物學功能。本研究將透過智慧學習系統的協助，提供更多的生物資訊。 In this study the RNA structures is predicted by support vector machine (SVM). The source of RNAs comes from SCOR (Structural Classification of RNA), which was used to feed into SVM for training and testing. In our study, the features of RNAs are extracted and coded to demonstrate the feasibility of prediction by using SVM. RNAs play very important roles in the biological macromolecules. Compared with DNA, the kinds of RNA are more and the structures are much complex than DNA also. Though different kinds of RNAs have some common structures but significant differences are also exist. And the differences make wide range of biological functions. In this study, the intelligent learning system is introduced to provide the help of bioinformatics.
Description:	指導教授：黃淳德
Appears in Collections:	[Department of Electrical Engineering & Graduate Institute] Theses and Dissertations

Files in This Item:

File	Size	Format
index.html	0Kb	HTML	317	View/Open

Loading...