Shuffled Frog Leaping Algorithm with Adaptive Exploration
Shuffled frog leaping algorithm is a nature inspired memetic stochastic search method which is gaining the focus of researchers since it was introduced. SFLA has the limitation that its convergence speed decreases towards the later stage of execution and
- PDF / 1,296,561 Bytes
- 9 Pages / 439.37 x 666.142 pts Page_size
- 6 Downloads / 176 Views
Abstract Shuffled frog leaping algorithm is a nature inspired memetic stochastic search method which is gaining the focus of researchers since it was introduced. SFLA has the limitation that its convergence speed decreases towards the later stage of execution and it also tends to stuck into local extremes. To overcome such limitations, this paper first proposes a variant in which a few new random frogs are generated and the worst performing frogs population are replaced by them. Experimental results show that a high number of replaced frogs does not always provide better results. As the execution progresses the optimized number of replaced frogs decreases. Based on the experimental observations, the paper then proposes another variant in which the number of replaced frogs adapts to the stage of the execution and hence provides the best results regardless of the stage of execution. Experiments are carried out on five benchmark test functions. Keywords Shuffled frog leaping algorithm Stochastic search
Nature inspired computing
1 Introduction Nature inspired computing algorithms (NICA) have been gaining popularity for a few decades now. More and more problems are now being solved using algorithms that are in some way inspired by some natural phenomenon. Most NICAs are stochastic search methods. A number of NICAs have been introduced. Genetic J. Rajpurohit (&) T.K. Sharma Amity University Rajasthan, Jaipur, India e-mail: [email protected] T.K. Sharma e-mail: [email protected] A.K. Nagar Liverpool Hope University, Liverpool, UK e-mail: [email protected] © Springer Science+Business Media Singapore 2016 M. Pant et al. (eds.), Proceedings of Fifth International Conference on Soft Computing for Problem Solving, Advances in Intelligent Systems and Computing 436, DOI 10.1007/978-981-10-0448-3_49
595
596
J. Rajpurohit et al.
algorithms [1] are based on natural reproduction system. Differential evolution [2] uses difference vector(s) of the participant solutions to increase diversity of the population. Particle swarm optimization [3] utilizes the way a flock of birds uses to maintain velocity and distance of each of its members. Similarly, artificial bee colony [4] and ant colony optimization [5] exploit the optimization methods used by honey bees and ants, respectively, in search for food. One of the latest such algorithms is shuffled frog leaping algorithm (SFLA) [6] which mimics the behavior of a group of frogs in a pond searching for the place with maximum food. The remainder of this paper is structured as follows: Sect. 2 explains the working process of the basic SFLA and a brief survey of modifications found in the literature. Section 3 explains the proposed variants of the algorithm which includes adaptive exploration. Experimental setup and results are discussed in Sect. 4. Finally Sect. 5 concludes the paper.
2 Working of SFLA SFLA combines the benefits of PSO and shuffled complex evolution (SCE). Its local search is inspired by PSO while global search process is inspired by SCE. Members of popul
Data Loading...
