Language:
繁體中文
English
日文
說明(常見問題)
南開科技大學
圖書館首頁
編目中圖書申請
登入
回首頁
切換:
標籤
|
MARC模式
|
ISBD
Automating recognition of regions of...
~
Dalhousie University (Canada).
Automating recognition of regions of intrinsically poor multiple alignment using machine learning.
紀錄類型:
書目-電子資源 : 單行本
正題名/作者:
Automating recognition of regions of intrinsically poor multiple alignment using machine learning./
作者:
Shan, Yunfeng (Henry).
面頁冊數:
105 p.
附註:
Source: Masters Abstracts International, Volume: 42-03, page: 0974.
Contained By:
Masters Abstracts International42-03.
標題:
Computer Science. -
電子資源:
Download fulltext (下載全文)
ISBN:
0612836886
Automating recognition of regions of intrinsically poor multiple alignment using machine learning.
Shan, Yunfeng (Henry).
Automating recognition of regions of intrinsically poor multiple alignment using machine learning.
- 105 p.
Source: Masters Abstracts International, Volume: 42-03, page: 0974.
Thesis (M.C.Sc.)--Dalhousie University (Canada), 2003.
Phylogenetic analysis requires alignment of gene sequences. Automatic alignment programs produce regions of intrinsically poor alignment that are currently detected and deleted manually. We present the results of a machine learning approach to the detection of these regions of an alignment. We compare three approaches: naive Bayes (NB), standard decision trees (C4.5), and support vector machine (SVM).
ISBN: 0612836886Subjects--Topical Terms:
1000005419
Computer Science.
Automating recognition of regions of intrinsically poor multiple alignment using machine learning.
LDR
:02775nmm 2200301 4500
001
1000004335
005
20051102155247.5
008
141201s2003 eng d
020
$a
0612836886
035
$a
(UnM)AAIMQ83688
035
$a
AAIMQ83688
040
$a
UnM
$c
UnM{me_controlnum}
100
1
$a
Shan, Yunfeng (Henry).
$3
1000005687
245
1 0
$a
Automating recognition of regions of intrinsically poor multiple alignment using machine learning.
300
$a
105 p.
500
$a
Source: Masters Abstracts International, Volume: 42-03, page: 0974.
500
$a
Advisers: E. Milios; A. Roger.
502
$a
Thesis (M.C.Sc.)--Dalhousie University (Canada), 2003.
520
$a
Phylogenetic analysis requires alignment of gene sequences. Automatic alignment programs produce regions of intrinsically poor alignment that are currently detected and deleted manually. We present the results of a machine learning approach to the detection of these regions of an alignment. We compare three approaches: naive Bayes (NB), standard decision trees (C4.5), and support vector machine (SVM).
520
$a
The results show that all three algorithms can accurately identify the bad sites of multiple sequence alignment based on three attributes which include the gap ratio, the normalized site log likelihood ratio and the degree of homoplasy (consistency index). The F-measure (product of precision and recall) reaches 0.970. Of the three algorithms, SVM provides the best performance for prediction of bad sites or ambiguous sites, but C4.5 provides the best performance for prediction of good sites. Of the three site classes, it is the most difficult to distinguish the ambiguous sites, but easiest to distinguish the bad sites. The F-measure is only 0.776 for prediction of ambiguous sites and 0.888 for prediction of good sites. No significant difference among three parsimony scores of gaps as attributes for reducing classification error was observed. The best performance for prediction of bad sites occurred when three kinds of the classifiers were trained on a balanced class distribution. The classifiers of C4.5 and NB trained on a balanced class distribution generally had the best performance for prediction of ambiguous sites. However, the random subset was better for SVM for prediction of ambiguous sites or good sites than the balanced subset. The classifiers of C4.5 and NB trained on the whole dataset had the best performance for the prediction of good sites.
590
$a
School code: 0328.
650
4
$a
Computer Science.
$3
1000005419
650
4
$a
Artificial Intelligence.
$3
165300
690
$a
0984
690
$a
0800
710
2 0
$a
Dalhousie University (Canada).
$3
1000005688
773
0
$t
Masters Abstracts International
$g
42-03.
790
1 0
$a
Milios, E.,
$e
advisor
790
1 0
$a
Roger, A.,
$e
advisor
790
$a
0328
791
$a
M.C.Sc.
792
$a
2003
856
4 0
$u
http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=MQ83688
$z
Download fulltext (下載全文)
0 筆讀者評論
館藏地:
全部
線上資料庫
出版年:
卷號:
館藏
1 筆 • 頁數 1 •
1
條碼號
典藏地名稱
館藏流通類別
資料類型
索書號
使用類型
借閱狀態
預約人數
備註欄
附件
OE0000635
線上資料庫
線上資源
線上電子書
OE c.2
一般(Normal)
在架
0
1 筆 • 頁數 1 •
1
多媒體
評論
新增評論
分享你的心得
建立或儲存個人書籤
書目轉出
取書館別
處理中
...
變更密碼
登入