International Journal of Metaheuristics (7 papers in press)
Particle swarm optimization with population size and acceleration coefficients adaptation using hidden markov model state classification
by Oussama Aoun, Malek Sarhani, Abdellatif El Afia
Abstract: Particle swarm optimization (PSO) is a metaheuristic algorithm based on population, it succeeded in solving a large number of optimization problems. Several adaptive PSO algorithms have been proposed to enhance the performance of the original one. In particular, parameter adaptation has become a promising issue of PSO. In this article, we propose an adaptive control of two PSO parameters using HMM classification to enhance PSO performance, called HMM Adaptive Control of PSO (HMM-ACPSO). That is, we integrate Hidden Markov Model (HMM) to have a stochastic control of states at each iteration. Then, the classified state by HMM is used to adapt PSO both acceleration parameters and population size. Furthermore, several strategies varying the swarm are adopted according to the classified state. We performed evaluations on several benchmark functions to test the HMM-ACPSO algorithm. Experimental results reveal that our suggested scheme gives competitive results comparing to PSO variants regarding both solution accuracy and convergence speed.
Keywords: Particle swarm optimization; swarm Intelligence; hidden markov model; machine learning; adaptive population size; parameters adaptation; metaheuristics control.
Flying Elephants Method applied to the problem of covering solid bodies with spheres
by Daniela Cristina Lubke, Vinicius Layter Xavier, Helder Manoel Venceslau, Adilson Elias Xavier
Abstract: The use of the Flying Elephants Method engenders a simple one-level completely differentiable optimization problem and allows overcoming the main difficulties presented by the original one. Computational results obtained for the covering of some solid body test instances show the good performance of the proposed methodology.
Keywords: location problems; min-max-min problems; non-differentiable programming; smoothing.
Azeotropy in a refrigerant system: an useful scenario to test and compare metaheuristics
by Gustavo Platt, Lucas Lima
Abstract: The comparison between metaheuristics has been frequently addressed in the last decades and, in a certain way, there is some controversy regarding the techniques to be employed in such comparison. In a multimodal optimization
problem, the capability of the algorithm to identify more than one solution
(possibly using auxiliary techniques to the identification of multiple solutions)
must be considered. Computation time and/or the number of fitness function
evaluations are possible metrics to be compared. On the other hand, the robustness and the accuracy of the methodologies are also fundamental quantities. In this work, we present a scenario of several comparisons between two metaheuristics the Differential Evolution and the Symbiotic Organisms Search, arbitrarily chosen. This scenario consisted of a problem characterized by a nonlinear algebraic system (converted into an optimization problem) with two solutions (in a narrow range of temperatures): the double azeotrope problem in the refrigerant fluid formed by ammonia + R-125. The statistical analysis of the results indicates that Differential Evolution and Symbiotic Organisms Search exhibits similar performances in the search for the first minimum of the problem. Nevertheless, the Differential Evolution outperformed the Symbiotic Organisms Search with respect to the capability to identify both minima.
Keywords: Metaheuristics; Azeotropy; Refrigerant Systems; Thermodynamics.
Predicting nationwide road fatalities in the US: a neural network approach
by Gokhan Egilmez, Deborah McAvoy
Abstract: Road crashes are among the top five leading causes of deaths in the US although the national trend in fatal crashes has reached to the lowest level since 1949. Therefore, this paper introduces a non-parametric prediction models, artificial neural network (ANN), to assist policy-makers in minimising fatal crashes across the United States. Seven input variables from four safety performance input domains while fatal crash was utilised as the single output variable for the scope of the research. ANN was utilised and the best neural network model was developed out of 1,000 networks. The proposed neural network model predicted data with 84% coefficient of determination. In addition, developed ANN model was benchmarked with a multiple linear regression model and outperformed in all performance metrics including r, R-square and the standard error of estimate.
Keywords: artificial neural networks; highway safety; multivariate regression analysis; prediction; US road fatalities.
Is the Bee Colony Optimisation algorithm suitable for continuous numerical optimisation?
by Miloš Simić
Abstract: Bee colony optimisation (BCO) is a nature-inspired swarm metaheuristic for solving hard optimisation problems. It has successfully been applied to various areas of science, industry, and engineering. However, all those cases belong to the field of combinatorial optimisation. This paper is among the first to test BCO's capacities for solving continuous numerical optimisation problems. We found that the performance of the algorithm depended on the settings of its parameters and characteristics of the optimisation problems to which it was applied. We examined for which types of numerical functions our implementation of improvement-based BCO, known as BCOi, performed well and which classes it was not able to handle successfully. Also, following the design of experiments (DoE) approach, we analysed how the parameters of the algorithm affected its performance and provided some useful explanations that might hold for other applications of our version and other variants of BCO.
Keywords: bees foraging principles; nature-inspired metaheuristics; numerical optimisation; optimisation problems; swarm intelligence.
A quantum-inspired binary firefly algorithm for QoS multicast routing
by Yassine Meraihi, Dalila Acheli, Amar Ramdane-Cherif, Mohammed Mahseur
Abstract: The quality of service multicast routing problem (QoSMRP) is one of the main issues for transmission in wireless mesh networks. It is known to be an NP-hard problem, so many heuristic algorithms have been employed to solve this problem. This paper proposes a new quantum-inspired binary firefly algorithm (QIBFA) to solve the QoSMRP. QIBFA is based on the combination of the standard binary firefly algorithm (BFA) with the concept and principles of the quantum evolutionary algorithm (QEA). Its main idea is the introduction of the Q-bit and the quantum operator adopted in the quantum-inspired evolutionary algorithm (QEA) into the binary firefly algorithm to avoid the premature convergence, ensure the diversity of the solutions and enhance the performance of the BFA. The simulation results show the efficiency and the superiority of our proposed algorithm compared with other existing algorithms in the literature.
Keywords: firefly algorithm; multicast routing; QoS; quality of service; quantum evolutionary algorithm.
Parametric optimisation of abrasive water jet machining of glass fibre reinforced plastic composite using non-dominated sorting genetic algorithm-II
by Anil Yashvant Mali, Padmakar Jagannath Pawar
Abstract: Machining of glass fibre reinforced plastic (GFRP) possesses several challenges; it is completely different from metal machining. Abrasive water jet machining has proved to be an interesting manufacturing process to machine GFRP in environment friendly manner. In this paper, experimentation is conducted and mathematical model has been developed to establish the correlation between process variables: water jet pressure, traverse rate, abrasive mass flow rate and standoff distance with performance measures: surface roughness, kerf width and kerf taper angle using response surface methodology. A well-known multi-objective optimisation method, non-dominated sorting genetic algorithm-II, is applied to obtain the set of Pareto-optimal solutions, which can be used as a ready reference by the process engineers. Rarely if ever, multiple responses are considered but that too are attempted with priori approach considering finite solutions. Whereas in practice, the problem has to be dealt with infinite solutions with posteriori approach, which is attempted in the proposed method.
Keywords: AWJM; abrasive water jet machining; GFRP; glass fibre reinforced plastic; NSGA-II.