A Study of Error-Correcting Output Codes for Structure Classification of Protein Sequence
碩士 === 國立中正大學 === 資訊工程所 === 93 === Structure classification and prediction of protein sequence has been an important research theme in structural bioinformatics. Most discriminative methods in machine learning suffers the well-known "False Positives" problem due to the larger amount of fol...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2005
|
Online Access: | http://ndltd.ncl.edu.tw/handle/77344414623169086094 |
id |
ndltd-TW-093CCU05392024 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-093CCU053920242015-10-13T10:45:04Z http://ndltd.ncl.edu.tw/handle/77344414623169086094 A Study of Error-Correcting Output Codes for Structure Classification of Protein Sequence 錯誤更正輸出碼在蛋白質序列之結構分類的研究 Che-Chi Wu 吳哲奇 碩士 國立中正大學 資訊工程所 93 Structure classification and prediction of protein sequence has been an important research theme in structural bioinformatics. Most discriminative methods in machine learning suffers the well-known "False Positives" problem due to the larger amount of folds available. In this thesis, we study new approach with multi-class classification methods to reduce the influence of the existing problem. We use the support vector machine (SVM) method as base classifiers and apply Error-Correcting Output Codes (ECOC) methods to achieve high-level multi-class classification. When scores of multiple parameter datasets are combined, majority voting reduces noise and increases recognition accuracy. The results show that our methods can obtain prediction accuracy 62.72% on a protein test dataset, where most of the proteins have below 25% sequence identity with the proteins used in training. Jyh-Jong Tasy 蔡志忠 2005 學位論文 ; thesis 24 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立中正大學 === 資訊工程所 === 93 === Structure classification and prediction of protein sequence has been
an important research theme in structural bioinformatics. Most
discriminative methods in machine learning suffers the well-known
"False Positives" problem due to the larger amount of folds
available. In this thesis, we study new approach with multi-class
classification methods to reduce the influence of the existing
problem. We use the support vector machine (SVM) method as base
classifiers and apply Error-Correcting Output Codes (ECOC) methods
to achieve high-level multi-class classification. When scores of
multiple parameter datasets are combined, majority voting reduces
noise and increases recognition accuracy. The results show that our
methods can obtain prediction accuracy 62.72% on a protein test
dataset, where most of the proteins have
below 25% sequence identity with the proteins used in training.
|
author2 |
Jyh-Jong Tasy |
author_facet |
Jyh-Jong Tasy Che-Chi Wu 吳哲奇 |
author |
Che-Chi Wu 吳哲奇 |
spellingShingle |
Che-Chi Wu 吳哲奇 A Study of Error-Correcting Output Codes for Structure Classification of Protein Sequence |
author_sort |
Che-Chi Wu |
title |
A Study of Error-Correcting Output Codes for Structure Classification of Protein Sequence |
title_short |
A Study of Error-Correcting Output Codes for Structure Classification of Protein Sequence |
title_full |
A Study of Error-Correcting Output Codes for Structure Classification of Protein Sequence |
title_fullStr |
A Study of Error-Correcting Output Codes for Structure Classification of Protein Sequence |
title_full_unstemmed |
A Study of Error-Correcting Output Codes for Structure Classification of Protein Sequence |
title_sort |
study of error-correcting output codes for structure classification of protein sequence |
publishDate |
2005 |
url |
http://ndltd.ncl.edu.tw/handle/77344414623169086094 |
work_keys_str_mv |
AT chechiwu astudyoferrorcorrectingoutputcodesforstructureclassificationofproteinsequence AT wúzhéqí astudyoferrorcorrectingoutputcodesforstructureclassificationofproteinsequence AT chechiwu cuòwùgèngzhèngshūchūmǎzàidànbáizhìxùlièzhījiégòufēnlèideyánjiū AT wúzhéqí cuòwùgèngzhèngshūchūmǎzàidànbáizhìxùlièzhījiégòufēnlèideyánjiū AT chechiwu studyoferrorcorrectingoutputcodesforstructureclassificationofproteinsequence AT wúzhéqí studyoferrorcorrectingoutputcodesforstructureclassificationofproteinsequence |
_version_ |
1716832020135411712 |