Abstract
In evolutionary algorithm, one of the main issues is how to reduce the number of fitness evaluations required to obtain optimal solutions. Generally a large number of evaluations are needed to find optimal solutions, which leads to an increase of computational time. Expensive cost may have to be paid for fitness evaluation as well. Differential evolution (DE), which is widely used in many applications due to its simplicity and good performance, also cannot escape from this problem. In order to solve this problem a fitness approximation model has been proposed so far, replacing real fitness function for evaluation. In fitness approximation, an ability to estimate accurate value with compact structure is needed for good performance. Therefore in this paper we propose an efficient differential evolution using fitness estimator. We choose k-nearest neighbor (kNN) as fitness estimator because it does not need any training period or complex computation. However too many training samples in the estimator may cause computational complexity to be exponentially high. Accordingly, two schemes with regard to accuracy and efficiency are proposed to improve the estimator. Our proposed algorithm is tested with various benchmark functions and shown to find good optimal solutions with less fitness evaluation and more compact size, compared with DE and DE-kNN.
Similar content being viewed by others
References
Adra SF, Dodd TJ, Griffin IA, Fleming PJ (2009) Convergence acceleration operator for multiobjective optimization. IEEE Trans Evol Comput 13(4):825–847
Alba E, Tomassini M (2002) Parallelism and evolutionary algorithms. IEEE Trans Evol Comput 6(5):443–462
Alcalá-Fdez J, Sánchez L, García S, del Jesus MJ, Ventura S, Garrell JM, Otero J, Romero C, Bacardit J, Rivas VM, Fernández JC, Herrera F (2009) KEEL: a software tool to assess evolutionary algorithms for data mining problems. Soft Comput 13(3):307–318
Cabido R, Montemayor A, Pantrigo J (2012) High performance memetic algorithm particle filter for multiple object tracking on modern GPUs. Soft Comput 16(2):217–230
Chan TM, Leung KS, Lee KH (2012) Memetic algorithms for de novo motif discovery. IEEE Trans Evol Comput 16(5):730–748
Cruz-Ramírez M, Hervás-Martínez C, Gutiérrez P, Pérez-Ortiz M, Briceño J, de la Mata M (2013) Memetic pareto differential evolutionary neural network used to solve an unbalanced liver transplantation problem. Soft Comput 17(2):275–284
Hansen N, Ostermeier A (2001) Completely derandomized self-adaptation in evolution strategies. Evol Comput 9(2):159–195
Hu XM, Zhang J, Yu Y, Chung HH, Li YL, Shi YH, Luo XN (2010) Hybrid genetic algorithm using a forward encoding scheme for lifetime maximization of wireless sensor networks. IEEE Trans Evol Comput 14(5):766–781
Iacca G, Neri F, Mininno E, Ong YS, Lim MH (2012) Ockham’s razor in memetic computing: three stage optimal memetic exploration. Inf Sci 188:17–43
Jin S (2007) An efficient evolutionary optimization with fitness approximation using neural networks. Master’s thesis, Korea Advanced Institute of Science and Technology
Jin Y (2005) A comprehensive survey of fitness approximation in evolutionary computation. Soft Comput 9(1):3–12
Kennedy J, Eberhart R (1995) Particle swarm optimization. In: Proceedings of the IEEE International Conference on Neural Networks, pp 1942–1948
Kumar S (2004) Neural networks: a classroom approach. Tata McGraw-Hill, New Delhi
Kuncheva LI (2000) Fuzzy classifier design. Physica Verlag, New York
Larrañaga P (2002) Estimation of distribution algorithms: a new tool for evolutionary computation, chap. A review on estimation of distribution algorithm. Kluwer Academic Publishers, Boston, pp 57–100
Liu Y, Sun F (2011) A fast differential evolution algorithm using k-nearest neighbour predictor. Expert Syst Appl 38(4):4254–4258
Llorà X, Sastry K, Goldberg DE, Gupta A, Lakshmi L (2005) Combating user fatigue in iGAs: partial ordering, support vector machines, and synthetic fitness. In: Proceedings of the 2005 conference on Genetic and evolutionary computation, pp 1363–1370
Masters T, Land W (1997) New training algorithm for the general regression neural network. In: Proceedings of the IEEE international conference on systems, man, and cybernetics, vol 3. Springer, pp 1990–1994
Meuth R, Lim MH, Ong YS, Wunsch II DC (2009) A proposition on memes and meta-memes in computing for higher-order learning. Memetic Comput 1(2):85–100
Michalewicz Z (1996) Genetic algorithms + data structures = evolution programs. Springer, London
Moscato P (1989) On evolution, search, optimization, genetic algorithms and martial arts—towards memetic algorithms. Caltech concurrent computation program, C3P Report, 826, Pasadena
Navot A, Shpigelman L, Tishby N, Vaadia E (2006) Nearest neighbor based feature selection for regression and its application to neural activity. Advances in Neural Information Processing Systems, NIPS, pp 995–1002
Neri F, Cotta C (2012) Memetic algorithms and memetic computing optimization: a literature review. Swarm Evol Comput 2:1–14
Neri F, Cotta C, Moscato P (2012) Handbook of memetic algorithms. Springer, Berlin
Neri F, Tirronen V, Karkkainen T, Rossi T (2007) Fitness diversity based adaptation in multimeme algorithms: a comparative study. In: Proceedings of the IEEE congress on evolutionary computation, pp 2374–2381
Ong Y, Keane A (2004) Meta-Lamarckian learning in memetic algorithms. IEEE Trans Evol Comput 8(2):99–110
Ong YS, Lim M, Chen X (2010) Memetic computation—past, present & future. IEEE Comput Intell Mag 5(2):24–31
Price KV, Storn RM, Lampinen JA (2005) Differential evolution: a practical approach to global optimization. Springer, Berlin
Queipo NV, Haftka RT, Shyy W, Goel T, Vaidyanathan R, Tucker PK (2005) Surrogate-based analysis and optimization. Progress Aerospace Sci 41(1):1–28
Shi L, Rasheed K (2010) Computational intelligence in expensive optimization problems, chap. A survey of fitness approximation methods applied in evolutionary algorithms. Springer, Berlin, pp 3–28
Smith J (2007) Coevolving memetic algorithms: a review and progress report. IEEE Trans Systems Man Cybern Part B Cybern 37(1):6–17
Storn R, Price K (1997) Differential evolution—a simple and efficient heuristic for global optimization over continuous spaces. J Global Optim 11:341–359
Tenne Y, Armfield SW (2009) A framework for memetic optimization using variable global and local surrogate models. Soft Comput 13(8-9):781–793
Whitty S (2005) A memetic paradigm of project management. Int J Project Manag 23(8):575–583
Yao X, Liu Y, Lin G (1999) Evolutionary programming made faster. IEEE Trans Evol Comput 3(2):82–102
Zhang Q, Liu W, Tsang E, Virginas B (2010) Expensive multiobjective optimization by MOEA/D with Gaussian process model. IEEE Trans Evol Comput 14(3):456–474
Zhou Z, Ong YS, Lim MH, Lee BS (2007) Memetic algorithm using multi-surrogates for computationally expensive optimization problems. Soft Comput 11(10):957–971
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by G. Acampora.
Appendices
Appendix A: Benchmark functions
f 1: Sphere model
f 2: Schwefel’s problem 2.22
f 3: Schwefel’s problem 1.2
f 4: Schwefel’s problem 2.21
f 5: Generalized Rosenbrock’s function
f 6: Step function
f 7: Quartic function i.e. noise
f 8: Generalized Schwefel’s problem 2.26
f 9: Generalized Rastrigin’s function
f 10: Ackley’s function
f 11: Generalized Griewank function
f 12 , f 13: Generalized penalized functions
where
f 14: Six-hump camel-back function
f 15: Branin function
f 16: Goldstein-Price function
f 17: Bukin function
Appendix B
Rights and permissions
About this article
Cite this article
Park, SY., Lee, JJ. An efficient differential evolution using speeded-up k-nearest neighbor estimator. Soft Comput 18, 35–49 (2014). https://doi.org/10.1007/s00500-013-1030-x
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-013-1030-x