Time Series Prediction Based on Gene Expression
Programming
J. Zuo, C. Tang, C. Li, C. an Yuan, and A. long Chen. Advances in Web-Age Information Management: 5th
International Conference, WAIM 2004, volume 3129 of Lecture Notes in Computer Science, page 55--64. Dalian, China, Springer, (15-17 July 2004)
Abstract
Two novel methods for Time Series Prediction based on
GEP (Gene Expression Programming). The main
contributions include: (1) GEP-Sliding Window
Prediction Method (GEP-SWPM) to mine the relationship
between future and historical data directly. (2)
GEP-Differential Equation Prediction Method (GEP-DEPM)
to mine ordinary differential equations from training
data, and predict future trends based on specified
initial conditions. (3) A brand new equation mining
method, called Differential by Microscope Interpolation
(DMI) that boosts the efficiency of our methods. (4) A
new, simple and effective GEP-constants generation
method called Meta-Constants (MC) is proposed. (5) It
is proved that a minimum expression discovered by
GEP-MC method with error not exceeding delta/2 uses at
most log3(2L/delta) operators and the problem to find
delta-accurate expression with fewer operators is
NP-hard. Extensive experiments on real data sets for
sun spot prediction show that the performance of the
new method is 20-900 times higher than existing
algorithms.
%0 Conference Paper
%1 DBLP:conf/waim/ZuoTLYC04
%A Zuo, Jie
%A Tang, Changjie
%A Li, Chuan
%A an Yuan, Chang
%A long Chen, An
%B Advances in Web-Age Information Management: 5th
International Conference, WAIM 2004
%C Dalian, China
%D 2004
%E Li, Qing
%E Wang, Guoren
%E Feng, Ling
%I Springer
%K Data Processing Series Time algorithms, expression gene genetic programming,
%P 55--64
%T Time Series Prediction Based on Gene Expression
Programming
%U http://springerlink.metapress.com/openurl.asp?genre=article&issn=0302-9743&volume=3129&spage=55
%V 3129
%X Two novel methods for Time Series Prediction based on
GEP (Gene Expression Programming). The main
contributions include: (1) GEP-Sliding Window
Prediction Method (GEP-SWPM) to mine the relationship
between future and historical data directly. (2)
GEP-Differential Equation Prediction Method (GEP-DEPM)
to mine ordinary differential equations from training
data, and predict future trends based on specified
initial conditions. (3) A brand new equation mining
method, called Differential by Microscope Interpolation
(DMI) that boosts the efficiency of our methods. (4) A
new, simple and effective GEP-constants generation
method called Meta-Constants (MC) is proposed. (5) It
is proved that a minimum expression discovered by
GEP-MC method with error not exceeding delta/2 uses at
most log3(2L/delta) operators and the problem to find
delta-accurate expression with fewer operators is
NP-hard. Extensive experiments on real data sets for
sun spot prediction show that the performance of the
new method is 20-900 times higher than existing
algorithms.
%@ 3-540-22418-1
@inproceedings{DBLP:conf/waim/ZuoTLYC04,
abstract = {Two novel methods for Time Series Prediction based on
GEP (Gene Expression Programming). The main
contributions include: (1) GEP-Sliding Window
Prediction Method (GEP-SWPM) to mine the relationship
between future and historical data directly. (2)
GEP-Differential Equation Prediction Method (GEP-DEPM)
to mine ordinary differential equations from training
data, and predict future trends based on specified
initial conditions. (3) A brand new equation mining
method, called Differential by Microscope Interpolation
(DMI) that boosts the efficiency of our methods. (4) A
new, simple and effective GEP-constants generation
method called Meta-Constants (MC) is proposed. (5) It
is proved that a minimum expression discovered by
GEP-MC method with error not exceeding delta/2 uses at
most log3(2L/delta) operators and the problem to find
delta-accurate expression with fewer operators is
NP-hard. Extensive experiments on real data sets for
sun spot prediction show that the performance of the
new method is 20-900 times higher than existing
algorithms.},
added-at = {2008-06-19T17:35:00.000+0200},
address = {Dalian, China},
author = {Zuo, Jie and Tang, Changjie and Li, Chuan and an Yuan, Chang and long Chen, An},
bibsource = {DBLP, http://dblp.uni-trier.de},
biburl = {https://www.bibsonomy.org/bibtex/272530b9ae63d5ff27088b5ecf81fc618/brazovayeye},
booktitle = {Advances in Web-Age Information Management: 5th
International Conference, WAIM 2004},
editor = {Li, Qing and Wang, Guoren and Feng, Ling},
interhash = {15daab01ddc2968821fd1e265ed52029},
intrahash = {72530b9ae63d5ff27088b5ecf81fc618},
isbn = {3-540-22418-1},
keywords = {Data Processing Series Time algorithms, expression gene genetic programming,},
month = {15-17 July},
notes = {Computer Science Department, Sichuan University,
Chengdu, Sichuan, China, 610065},
pages = {55--64},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
timestamp = {2008-06-19T17:56:01.000+0200},
title = {Time Series Prediction Based on Gene Expression
Programming},
url = {http://springerlink.metapress.com/openurl.asp?genre=article&issn=0302-9743&volume=3129&spage=55},
volume = 3129,
year = 2004
}