Design of a Homogeneous Ensemble for Splice-Site Identification in Human Sequences
|
 |
|
Post a Comment
|
 |
|
|
|
CONTRIBUTORS:
|
|
|
PROCEEDINGS TITLE:
|
|
|
YEAR:
|
2008
|
|
PUB TYPE:
|
Conference Paper in Proceedings
|
|
PAGES:
|
n/a -
n/a
|
|
SUBJECT(S):
|
plice-site recognition; neural network; ensemble
|
|
DISCIPLINE:
|
No discipline assigned
|
|
HTTP:
|
http://www.ics.uplb.edu.ph/node/266
|
|
LANGUAGE:
|
None
|
|
PUB ID:
|
103-444-117
(Last edited on
2008/10/20 06:11:51 GMT-6)
|
|
SPONSOR(S):
|
|
|
ABSTRACT:
This paper outlines a methodology for designing and implementing two novel combination methods for an ensemble of neural network models that classify donor and acceptor sites in human genome sequences. Using a data set of 3,190 sequences, the majority-vote ensemble reduced the false sites recognized by the best stand-alone neural network model by more than 1% while the weighted-vote ensemble reduced it further by more than 3%.
|
|
|
|
STATISTICS
|
|
Click on # to view
|
|
Citations
|
|
0
|
|
References
|
|
0
|
|
Comments
|
|
0
|
|
Quality
|
|
0/0.00
|
|
Interest
|
|
0/0.00
|
|
View(er)s
|
|
1/89
|
|
|
|
|
|
|
| Prev |
Next |
|