Advertisement

A Markov Chain Tabu Search Approach to the Evolutionary Allocation Problem

  • Hussein A. Abbass
  • Michael Towsey
  • Erhan Kozan
  • Julius Van der Werf
Chapter
Part of the International Series in Operations Research & Management Science book series (ISOR, volume 43)

Abstract

Mate-selection is the problem of deciding which animal should be culled and which should be mated in a breeding program. In addition, if the animal is to be mated, which animal from the other sex should it be mated with? With a linear objective function, integer linear programming was successfully used to solve the problem. Also, when the relation between the animals’ traits is additive, a strategy based on the classical index theory for selection with random allocation, results in the optimal solution. Today, non-linear and non-additive objectives are introduced and the problem is becoming increasingly complex. In this paper, we formulate the problem as a multi-stage quadratic transportation model. We then introduce a new version of Tabu Search that we call Markov Chain Tabu Search (MCTS) for solving the mate-selection problem. We then compare MCTS against five conventional heuristic techniques; these are, random search, hill climbing, simulated annealing, sequential genetic algorithms, and simultaneous genetic algorithms. MCTS is found statistically significantly better than the other heuristics for handling this large scale mate-selection problem.

Keywords

Tabu search mate-selection dairy industry 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Abbass, H. Computational intelligence techniques for decision making: with applications to the dairy industry. PhD thesis, School of Computing, Queensland University of Technology, 2000.Google Scholar
  2. Abbass, H., Towsey, M., der Werf, J. V., and Finn, G. Modelling evolution: the evolutionary allocation problem. In (Abbass, H. and Towsey, M.), The Application of Artificial Intelligence, Optimisation, and Bayesian Methods in Agriculture, QUT-Publication, 1999, pages 117–134.Google Scholar
  3. Abbass, H., Towsey, M., Kozan, E., and der Werf, J. V. The performance of genetic algorithms on the one-generation mate-selection problem. Proceedings of the 2nd Joint International Workshop on Operations Research, Sapporo, Japan, 2000.Google Scholar
  4. Glover, F. Tabu search: part 1. ORSA Journal on Computing, 1989, 1(3): 190–206.CrossRefGoogle Scholar
  5. Glover, F. Tabu search: part 2. ORSA Journal on Computing, 1999, 2(l):4–32.Google Scholar
  6. Glover, F. and Laguna, M. Tabu search. Kluwer Academic Publisher, Boston, 1997.CrossRefGoogle Scholar
  7. Henderson, C. Use of all relatives in intraherd prediction of breeding values and producing abilities. Dairy Science, 1975, 58:1910–1916.CrossRefGoogle Scholar
  8. Michalewicz, Z. and Fogel, D. How to solve it: modem heuristic. Springer verlag, 2000.Google Scholar
  9. Mrode, R. Linear models for the prediction of animal breeding values. CAB International, 1996.Google Scholar
  10. Paulli, J. A computational comparison of simulated annealing and Tabu search applied to the quadratic assignment problem. In (Vidal, R.), Applied simulated annealing. Springer-Verlag, 1993.Google Scholar

Copyright information

© Springer Science+Business Media New York 2002

Authors and Affiliations

  • Hussein A. Abbass
    • 1
  • Michael Towsey
    • 2
  • Erhan Kozan
    • 2
  • Julius Van der Werf
    • 3
  1. 1.School of Computer ScienceUniversity of New South WalesCanberraAustralia
  2. 2.School of Computing ScienceQueensland University of TechnologyBrisbaneAustralia
  3. 3.Division of Animal Science, School of Natural Resources and Rural ScienceUniversity of New EnglandArmidaleAustralia

Personalised recommendations