Skip to main content

Über dieses Buch

Nature-inspired algorithms such as cuckoo search and firefly algorithm have become popular and widely used in recent years in many applications. These algorithms are flexible, efficient and easy to implement. New progress has been made in the last few years, and it is timely to summarize the latest developments of cuckoo search and firefly algorithm and their diverse applications. This book will review both theoretical studies and applications with detailed algorithm analysis, implementation and case studies so that readers can benefit most from this book. Application topics are contributed by many leading experts in the field. Topics include cuckoo search, firefly algorithm, algorithm analysis, feature selection, image processing, travelling salesman problem, neural network, GPU optimization, scheduling, queuing, multi-objective manufacturing optimization, semantic web service, shape optimization, and others.

This book can serve as an ideal reference for both graduates and researchers in computer science, evolutionary computing, machine learning, computational intelligence, and optimization, as well as engineers in business intelligence, knowledge management and information technology.



Cuckoo Search and Firefly Algorithm: Overview and Analysis

Firefly algorithm (FA) was developed by Xin-She Yang in 2008, while cuckoo search (CS) was developed by Xin-She Yang and Suash Deb in 2009. Both algorithms have been found to be very efficient in solving global optimization problems. This chapter provides an overview of both cuckoo search and firefly algorithm as well as their latest developments and applications. We analyze these algorithms and gain insight into their search mechanisms and find out why they are efficient. We also discuss the essence of algorithms and its link to self-organizing systems. In addition, we also discuss important issues such as parameter tuning and parameter control, and provide some topics for further research.
Xin-She Yang

On the Randomized Firefly Algorithm

The firefly algorithm is a stochastic meta-heuristic that incorporates randomness into a search process. Essentially, the randomness is useful when determining the next point in the search space and therefore has a crucial impact when exploring the new solution. In this chapter, an extensive comparison is made between various probability distributions that can be used for randomizing the firefly algorithm, e.g., Uniform, Gaussian, Lévi flights, Chaotic maps, and the Random sampling in turbulent fractal cloud. In line with this, variously randomized firefly algorithms were developed and extensive experiments conducted on a well-known suite of functions. The results of these experiments show that the efficiency of a distributions largely depends on the type of a problem to be solved.
Iztok Fister, Xin-She Yang, Janez Brest, Iztok Fister

Cuckoo Search: A Brief Literature Review

Cuckoo search (CS) was introduced by Xin-She Yang and Suash Deb in 2009, and it has attracted great attention due to its promising efficiency in solving many optimization problems and real-world applications. In the last few years, many papers have been published regarding cuckoo search, and the relevant literature has expanded significantly. This chapter summarizes briefly the majority of the literature about cuckoo search in peer-reviewed journals and conferences found so far. These references can be systematically classified into appropriate categories, which can be used as a basis for further research.
Iztok Fister, Xin-She Yang, Dušan Fister, Iztok Fister

Improved and Discrete Cuckoo Search for Solving the Travelling Salesman Problem

Improved and Discrete Cuckoo Search (DCS) algorithm for solving the famous travelling salesman problem (TSP), an NP-hard combinatorial optimization problem, is recently developed by Ouaarab, Ahiod, and Yang in 2013, based on the cuckoo search (CS), developed by Yang and Deb in 2009. DCS first reconstructs the population of CS by introducing a new category of cuckoos in order to improve its search efficiency, and adapts it to TSP based on the terminology used either in inspiration source of CS or in its continuous search space. The performance of the proposed DCS is tested against a set of benchmarks of symmetric TSP from the well-known TSPLIB library. The results of the tests show that DCS is superior to some other metaheuristics.
Aziz Ouaarab, Belaïd Ahiod, Xin-She Yang

Comparative Analysis of the Cuckoo Search Algorithm

Cuckoo Search Algorithm (CS) is a population based, elitist evolutionary search algorithm proposed for the solution of numerical optimization problems. Despite its wide use, the algorithmic process of CS has been scarcely studied in detail. In this chapter, the algorithmic structure of CS and its effective problem solving success have been studied. Fifty benchmark problems were used in the numerical tests performed in order to study the algorithmic behavior of CS. The success of CS in solving benchmark problems was compared with three widely used optimization algorithms (i.e., PSO, DE, and ABC) by means of Kruskal–Wallis statistical test. The search strategy of CS, which utilizes the Lèvy distribution, enables it to analyze the search space in a very successful manner. The statistical results have verified that CS has the superior problem-solving ability as a search strategy.
Pinar Civicioglu, Erkan Besdok

Cuckoo Search and Firefly Algorithm Applied to Multilevel Image Thresholding

Multilevel image thresholding is a technique widely used in image processing, most often for segmentation. Exhaustive search is computationally prohibitively expensive since the number of possible thresholds to be examined grows exponentially with the number of desirable thresholds. Swarm intelligence metaheuristics have been used successfully for such hard optimization problems. In this chapter we investigate performance of two relatively new swarm intelligence algorithms, cuckoo search and firefly algorithm, applied to multilevel image thresholding. Particle swarm optimization and differential evolution algorithms have also been implemented for comparison. Two different objective functions, Kapur’s maximum entropy thresholding function and multi Otsu between-class variance, were used on standard benchmark images with known optima from exhaustive search (up to five threshold points). Results show that both, cuckoo search and firefly algorithm, exhibit superior performance and robustness.
Ivona Brajevic, Milan Tuba

A Binary Cuckoo Search and Its Application for Feature Selection

In classification problems, it is common to find datasets with a large amount of features, some of theses features may be considered as noisy. In this context, one of the most used strategies to deal with this problem is to perform a feature selection process in order to build a subset of features that can better represents the dataset. As feature selection can be modeled as an optimization problem, several studies have to attempted to use nature-inspired optimization techniques due to their large generalization capabilities. In this chapter, we use the Cuckoo Search (CS) algorithm in the context of feature selection tasks. For this purpose, we present a binary version of the Cuckoo Search, namely BCS, as well as we evaluate it with different transfer functions that map continuous solutions to binary ones. Additionally, the Optimum-Path Forest classifier accuracy is used as the fitness function. We conducted simulations comparing BCS with binary versions of the Bat Algorithm, Firefly Algorithm and Particle Swarm Optimization. BCS has obtained reasonable results when we consider the compared techniques for feature selection purposes.
L. A. M. Pereira, D. Rodrigues, T. N. S. Almeida, C. C. O. Ramos, A. N. Souza, X.-S. Yang, J. P. Papa

How to Generate the Input Current for Exciting a Spiking Neural Model Using the Cuckoo Search Algorithm

Spiking neurons are neural models that try to simulate the behavior of biological neurons. This model generates a response (spikes or spike train) only when the model reaches a specific threshold. This response could be coded into a firing rate and perform a pattern classification task according to the firing rate generated with the input current. However, the input current must be carefully computed to obtain the desired behavior. In this paper, we describe how the Cuckoo Search algorithm can be used to train a spiking neuron and determine the best way to compute the input current for solving a pattern classification task. The accuracy of the methodology is tested using several pattern recognition problems.
Roberto A. Vazquez, Guillermo Sandoval, Jose Ambrosio

Multi-Objective Optimization of a Real-World Manufacturing Process Using Cuckoo Search

This chapter describes the application of Cuckoo Search in simulation-based optimization of a real-world manufacturing process. The optimization problem is a combinatorial problem of setting 56 unique decision variables in a way that maximizes utilization of machines and at the same time minimizes tied-up capital. As in most real-world problems, the two optimization objectives are conflicting and improving performance on one of them deteriorates performance of the other. To handle the conflicting objectives, the original Cuckoo Search algorithm is extended based on the concepts of multi-objective Pareto-optimization.
Anna Syberfeldt

Solving Reliability Optimization Problems by Cuckoo Search

A powerful approach to solve engineering optimization problems is the cuckoo search algorithm. It is a developed by Yang and Deb [1, 2]. In this chapter uses CS algorithm, to solve the reliability optimization problem. The reliability optimization problem involves setting reliability objectives for components or subsystems in order to meet the resource consumption constraint, e.g. the total cost. The difficulties facing reliability optimization problem are to maintain feasibility with respect to three nonlinear constraints, namely, cost, weight and volume related constraints. The reliability optimization problems have been studied in the literature for decades, usually using mathematical programming or metaheuristic optimization algorithms. The performance of CS algorithm is tested on five well-known reliability problems and two complex systems. Finally, the results are compared with those given by several well-known methods. Simulation results demonstrate that the optimal solutions obtained by CS, are better than the best solutions obtained by other methods.
Ehsan Valian

Hybridization of Cuckoo Search and Firefly Algorithms for Selecting the Optimal Solution in Semantic Web Service Composition

This chapter investigates how the Cuckoo Search and Firefly Algorithm can be hybridized for performance improvement in the context of selecting the optimal or near-optimal solution in semantic Web service composition. Cuckoo Search and Firefly Algorithm are hybridized with genetic, reinforcement learning and tabu principles to achieve a proper exploration and exploitation of the search process. The hybrid algorithms are applied on an enhanced planning graph which models the service composition search space for a given user request. The problem of finding the optimal solution encoded in the enhanced planning graph can be reduced to identifying a configuration of semantic Web services, out of a very large set of possible configurations, which maximizes a fitness function which considers semantics and QoS attributes as selection criteria. To analyze the benefits of hybridization we have comparatively evaluated the classical Cuckoo Search and Firefly Algorithms versus the proposed hybridized algorithms.
Ioan Salomie, Viorica Rozina Chifu, Cristina Bianca Pop

Geometric Firefly Algorithms on Graphical Processing Units

Geometric unification of Evolutionary Algorithms (EAs) has resulted in an expanding set of algorithms which are search space invariant. This is important since search spaces are not always parametric. Of particular interest are combinatorial spaces such as those of programs that are searchable by parametric optimisers, providing they have been specially adapted in this way. This typically involves redefining concepts of distance, crossover and mutation operators. We present an informally modified Geometric Firefly Algorithm for searching expression tree space, and accelerate the computation using Graphical Processing Units. We also evaluate algorithm efficiency against a geometric version of the Genetic Programming algorithm with tournament selection. We present some rendering techniques for visualising the program problem space and therefore to aid in characterising algorithm behaviour.
A. V. Husselmann, K. A. Hawick

A Discrete Firefly Algorithm for Scheduling Jobs on Computational Grid

Computational grid emerged as a large scale distributed system to offer dynamic coordinated resources sharing and high performance computing. Due to the heterogeneity of grid resources scheduling jobs on computational grids is identified as NP-hard problem. This chapter introduces a job scheduling mechanism based on Discrete Firefly Algorithm (DFA) to map the grid jobs to available resources in order to finish the submitted jobs within a minimum makespan time. The proposed scheduling mechanism uses population based candidate solutions rather than single path solution as in traditional scheduling mechanism such as tabu search and hill climbing, which help avoids trapping in local optimum. We used simulation and real workload traces to evaluate the proposed scheduling mechanism. The simulation results of the proposed DFA scheduling mechanism are compared with Genetic Algorithm and Tabu Search scheduling mechanisms. The obtained results demonstrated that, the proposed DFA can avoid trapping in local optimal solutions and it could be efficiently utilized for scheduling jobs on computational grids. Furthermore, the results have shown that DFA outperforms the other scheduling mechanisms in the case of typical and heavy loads.
Adil Yousif, Sulaiman Mohd Nor, Abdul Hanan Abdullah, Mohammed Bakri Bashir

A Parallelised Firefly Algorithm for Structural Size and Shape Optimisation with Multimodal Constraints

In structural mechanics, mass reduction conflicts with frequency constraints when they are lower bounded since vibration mode shapes may easily switch due to shape modifications. This may impose severe restrictions to gradient-based optimisation methods. Here, in this chapter, it is investigated the use of the Firefly Algorithm (FA) as an optimization engine of such problems. It is suggested some new implementations in the basic algorithm, such as the parallelisation of the code, based on literature reports in order to improve its performance. It is presented several optimization examples of simple and complex trusses that are widely reported in the literature as benchmark examples solved with several non-heuristic and heuristic algorithms. The results show that the algorithm outperforms the deterministic algorithms in accuracy, particularly using the Parallel Synchronous FA version.
Herbert Martins Gomes, Adelano Esposito

Intelligent Firefly Algorithm for Global Optimization

Intelligent firefly algorithm (IFA) is a novel global optimization algorithm that aims to improve the performance of the firefly algorithm (FA), which was inspired by the flashing communication signals among firefly swarms. This chapter introduces the IFA modification and evaluates its performance in comparison with the original algorithm in twenty multi-dimensional benchmark problems. The results of those numerical experiments show that IFA outperformed FA in terms of reliability and effectiveness in all tested benchmark problems. In some cases, the global minimum could not have been successfully identified via the firefly algorithm, except with the proposed modification for FA.
Seif-Eddeen K. Fateen, Adrián Bonilla-Petriciolet

Optimization of Queueing Structures by Firefly Algorithm

In the chapter we describe the application of firefly algorithm in discrete optimization of simple queueing structures such as queueing systems. The optimization of these systems is complicated and there is not any universal method to solve such problem. We briefly cover basic queueing systems. Hence, Markovian systems with exponential service times and a Poisson arrival process with losses, with finite capacity and impatient customers and closed queueing system with finite number of jobs are presented. We consider structural optimization, for example maximization of overall profits and minimizing costs controlled by the number of servers. We show the results of performed experiments.
Joanna Kwiecień, Bogusław Filipowicz

Firefly Algorithm: A Brief Review of the Expanding Literature

Firefly algorithm (FA) was developed by Xin-She Yang in 2008 and it has become an important tool for solving the hardest optimization problems in almost all areas of optimization as well as engineering practice. The literature has expanded significantly in the last few years. Various FA variants have been developed to suit different applications. This chapter provides a brief review of this expanding and state-of-the-art literature on this dynamic and rapidly evolving domain of swarm intelligence.
Iztok Fister, Xin-She Yang, Dušan Fister, Iztok Fister
Weitere Informationen

Premium Partner