Egipsys: An enhanced gene expression programming approach for symbolic regression problems

Heitor Lopes; Wagner Weinert

International Journal of Applied Mathematics and Computer Science (2004)

  • Volume: 14, Issue: 3, page 375-384
  • ISSN: 1641-876X

Abstract

top
This paper reports a system based on the recently proposed evolutionary paradigm of gene expression programming (GEP). This enhanced system, called EGIPSYS, has features specially suited to deal with symbolic regression problems. Amongst the new features implemented in EGIPSYS are: new selection methods, chromosomes of variable length, a new approach to manipulating constants, new genetic operators and an adaptable fitness function. All the proposed improvements were tested separately, and proved to be advantageous over the basic GEP@. EGIPSYS was also applied to four difficult identification problems and its performance was compared with a traditional implementation of genetic programming (LilGP). Overall, EGIPSYS was able to obtain consistently better results than the system using genetic programming, finding less complex solutions with less computational effort. The success obtained suggests the adaptation and extension of the system to other classes of problems.

How to cite

top

Lopes, Heitor, and Weinert, Wagner. "Egipsys: An enhanced gene expression programming approach for symbolic regression problems." International Journal of Applied Mathematics and Computer Science 14.3 (2004): 375-384. <http://eudml.org/doc/207704>.

@article{Lopes2004,
abstract = {This paper reports a system based on the recently proposed evolutionary paradigm of gene expression programming (GEP). This enhanced system, called EGIPSYS, has features specially suited to deal with symbolic regression problems. Amongst the new features implemented in EGIPSYS are: new selection methods, chromosomes of variable length, a new approach to manipulating constants, new genetic operators and an adaptable fitness function. All the proposed improvements were tested separately, and proved to be advantageous over the basic GEP@. EGIPSYS was also applied to four difficult identification problems and its performance was compared with a traditional implementation of genetic programming (LilGP). Overall, EGIPSYS was able to obtain consistently better results than the system using genetic programming, finding less complex solutions with less computational effort. The success obtained suggests the adaptation and extension of the system to other classes of problems.},
author = {Lopes, Heitor, Weinert, Wagner},
journal = {International Journal of Applied Mathematics and Computer Science},
keywords = {mathematical modeling; systems identification; symbolic regression; evolutionary computation},
language = {eng},
number = {3},
pages = {375-384},
title = {Egipsys: An enhanced gene expression programming approach for symbolic regression problems},
url = {http://eudml.org/doc/207704},
volume = {14},
year = {2004},
}

TY - JOUR
AU - Lopes, Heitor
AU - Weinert, Wagner
TI - Egipsys: An enhanced gene expression programming approach for symbolic regression problems
JO - International Journal of Applied Mathematics and Computer Science
PY - 2004
VL - 14
IS - 3
SP - 375
EP - 384
AB - This paper reports a system based on the recently proposed evolutionary paradigm of gene expression programming (GEP). This enhanced system, called EGIPSYS, has features specially suited to deal with symbolic regression problems. Amongst the new features implemented in EGIPSYS are: new selection methods, chromosomes of variable length, a new approach to manipulating constants, new genetic operators and an adaptable fitness function. All the proposed improvements were tested separately, and proved to be advantageous over the basic GEP@. EGIPSYS was also applied to four difficult identification problems and its performance was compared with a traditional implementation of genetic programming (LilGP). Overall, EGIPSYS was able to obtain consistently better results than the system using genetic programming, finding less complex solutions with less computational effort. The success obtained suggests the adaptation and extension of the system to other classes of problems.
LA - eng
KW - mathematical modeling; systems identification; symbolic regression; evolutionary computation
UR - http://eudml.org/doc/207704
ER -

References

top
  1. Ferreira C. (2001): Gene Expression Programming: A new adaptive algorithm for solving problems. - Complex Systems, Vol. 13, No. 2, pp. 87-129. Zbl1167.92329
  2. Ferreira C. (2003): Function finding and a creation of numerical constants in gene expression programming, In: Advances in Soft Computing, Engineering Design and Manufacturing (J.M. Benitez, O. Cordon, F. Hoffmann and R. Roy, Eds.). - Springer-Verlag: Berlin, pp. 257-266. 
  3. Fogel L.J., Owens A.J. and Walsh M.J. (1966): Artificial Intelligence Through Simulated Evolution. - New York: Wiley Zbl0148.40701
  4. Goldberg D.E. (1989): Genetic Algorithms in Search, Optimization and Machine Learning. - Reading: Addison-Wesley. Zbl0721.68056
  5. Guidorzi R.P. and Rossi P. (1974): Identification of a power plant from normal operating records. - Automat. Contr. Theory Applic., Vol. 2, No. 1, pp. 63-67. 
  6. Guidorzi R.P., Losito M.P. and Muratori T. (1980): On the last eigenvalue test in the structural identification of linear multivariable systems. - Proc. 5th Europ. Meeting Cybernetics and Systems Research, Vienna, pp. 217-228. Zbl0484.93070
  7. Hoai N.X., McKay R.I., Essam D. and Chau R. (2002): Solving the symbolic regression problem with tree-adjunct grammar guided genetic programming: The comparative results. - Proc. 2002 Congress on Evolutionary Computation, Honolulu, USA, Vol. 2, pp. 1326-1331. 
  8. Holland J.H. (1995): Adaptation in Natural and Artificial Systems. - Ann Arbor: The University of Michigan Press. 
  9. Koza J.R. (1992): Genetic Programming: On the Programming of Computers by Means of Natural Selection. - Cambridge: MIT Press. Zbl0850.68161
  10. Koza J.R. (1994): Genetic Programming II: Automatic Discovery of Reusable Programs. - Cambridge: MIT Press, 1994. Zbl0850.68160
  11. McAvoy T.J., Hsu E. and Lowenthal S. (1972): Dynamics of pH in controlled stirred tank reactor. - Ind. Eng. Chem. Process Des. Develop., Vol. 11, No. 1, pp. 71-78. 
  12. Moonen M., De Moor B., Vandenberghe L. and Vandewalle J. (1989): On- and off-line identification of linear state-space models. -Int. J. Contr., Vol. 49, No. 2, pp. 219-0232. Zbl0661.93072
  13. Rechenberg I. (1973): Evolutions strategie: Optimierung Technischer Systemen nach Prinzipien der Biologischen Evolution. - Stuttgart: Frommann-Holzboog Verlag. 
  14. Salhi A., Glaser H. and DeRoure D. (1998): Parallel implementation of a genetic-programming based tool for symbolic regression. - Inf. Process. Lett., Vol. 66, pp. 299-307. Zbl06590713
  15. Schwefel H-P. (1977): Numerische Optimierung von Computer-Modellen mittels der Evolutionsstrategie. - Basel: Birkhauser. Zbl0347.65035
  16. Shengwu X., Weinu W. and Feng L. (2003): A new genetic programming approach in symbolic regression. - Proc. 15th IEEE Int. Conf. Tools with Artificial Intelligence, Sacramento, USA, pp. 161-165. 
  17. Weigend A.S., Huberman B.A. and Rumelhart D.E. (1992): Predicting sunspots and exchange rates with connectionist networks, In: Nonlinear Modeling and Forecasting (S. Eubank and M. Casdagli, Eds.). - Redwood City: Addison-Wesley, pp. 395-432. 
  18. Zongker D., Punch B. and Rand B. (1998): Lilgp 1.1User's Manual. - Lansing: Michigan State University. 

NotesEmbed ?

top

You must be logged in to post comments.

To embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.

Only the controls for the widget will be shown in your chosen language. Notes will be shown in their authored language.

Tells the widget how many notes to show per page. You can cycle through additional notes using the next and previous controls.

    
                

                
Note: Best practice suggests putting the JavaScript code just before the closing </body> tag.