Showing papers in "International Journal of Bio-inspired Computation in 2011"
TL;DR: In this paper, a multi-objective bat algorithm (MOBA) is proposed to solve multiobjective design problems such as welded beam design, and validated against a subset of test functions.
Abstract: Engineering optimisation is typically multi-objective and multidisciplinary with complex constraints, and the solution of such complex problems requires efficient optimisation algorithms. Recently, Xin-She Yang proposed a bat-inspired algorithm for solving non-linear, global optimisation problems. In this paper, we extend this algorithm to solve multi-objective optimisation problems. The proposed multi-objective bat algorithm (MOBA) is first validated against a subset of test functions, and then applied to solve multi-objective design problems such as welded beam design. Simulation results suggest that the proposed algorithm works efficiently.
767 citations
TL;DR: This tutorial highlights the most recent nature-based inspirations as metaphors for swarm intelligence meta-heuristics and describes the biological behaviours from which a number of computational algorithms were developed.
Abstract: The growing complexity of real-world problems has motivated computer scientists to search for efficient problem-solving methods. Evolutionary computation and swarm intelligence meta-heuristics are outstanding examples that nature has been an unending source of inspiration. The behaviour of bees, bacteria, glow-worms, fireflies, slime moulds, cockroaches, mosquitoes and other organisms have inspired swarm intelligence researchers to devise new optimisation algorithms. This tutorial highlights the most recent nature-based inspirations as metaphors for swarm intelligence meta-heuristics. We describe the biological behaviours from which a number of computational algorithms were developed. Also, the most recent and important applications and the main features of such meta-heuristics are reported.
368 citations
TL;DR: A comprehensive overview of nature-inspired meta-heuristics can be found in this article, where the authors propose a generalised evolutionary walk algorithm (GEWA) to solve global optimisation problems.
Abstract: Meta-heuristic algorithms are often nature-inspired, and they are becoming very powerful in solving global optimisation problems. More than a dozen major meta-heuristic algorithms have been developed over the last three decades, and there exist even more variants and hybrids of meta-heuristics. This paper intends to provide an overview of nature-inspired meta-heuristic algorithms, from a brief history to their applications. We try to analyse the main components of these algorithms and how and why they work. Then, we intend to provide a unified view of meta-heuristics by proposing a generalised evolutionary walk algorithm (GEWA). Finally, we discuss some of the important open questions.
174 citations
TL;DR: The contribution consists in defining an appropriate representation scheme in the cuckoo search algorithm that allows applying successfully on combinatorial optimisation problems some quantum computing principles like qubit representation, superposition of states, measurement, and interference.
Abstract: This paper presents a new inspired algorithm called quantum inspired cuckoo search algorithm (QICSA) This one is a new framework relying on quantum computing principles and cuckoo search algorithm The contribution consists in defining an appropriate representation scheme in the cuckoo search algorithm that allows applying successfully on combinatorial optimisation problems some quantum computing principles like qubit representation, superposition of states, measurement, and interference This hybridisation between quantum inspired computing and bioinspired computing has led to an efficient hybrid framework which achieves better balance between exploration and exploitation capabilities of the search process Experiments on knapsack problems show the effectiveness of the proposed framework and its ability to achieve good quality solutions
171 citations
TL;DR: The definitions of the most important concepts such as emergence and self-organisation from an engineer's perspective are reviewed, and different types of nature-inspired technology are analyzed.
Abstract: Complexity science has seen increasing interest in the recent years. Many engineers have discovered that traditional methods come to their limits when coping with complex adaptive systems or autonomous agents. To find alternatives, complexity science can be applied to engineering, resulting in a quickly growing field, referred to as complexity engineering. Most current efforts come either from scientists who are interested in bio-inspired methods and working in computer science or mobile robots, or they come from the area of systems engineering. This article reviews the definitions of the most important concepts such as emergence and self-organisation from an engineer's perspective, and analyses different types of nature-inspired technology. This is the first part of a set of two-articles on this topic; the second one provides a survey of currently existing approaches to complexity engineering, identifies challenges and gives directions for further research.
47 citations
TL;DR: The paper describes a novel algorithm, inspired by the phenomenon of wisdom of crowds, for solving instances of NP-hard problems that achieves superior performance compared to the genetic algorithm-based approach and requires modest computational resources.
Abstract: The paper describes a novel algorithm, inspired by the phenomenon of wisdom of crowds, for solving instances of NP-hard problems. The proposed approach achieves superior performance compared to the genetic algorithm-based approach and requires modest computational resources. On average, a 6%-9% improvement in quality of solutions has been observed.
45 citations
TL;DR: A survey of the currently existing approaches to complexity engineering is provided and challenges ahead are indicated.
Abstract: Complexity science has seen increasing interest in the recent years. Many engineers have discovered that traditional methods come to their limits when coping with complex adaptive systems or autonomous agents. To find alternatives, complexity science can be applied to engineering, resulting in a quickly growing field, referred to as complexity engineering. Most current efforts come either from scientists who are interested in bio-inspired methods and working in computer science or mobile robots, or they come from the area of systems engineering. This article is the second part of a set of two articles on this topic; the first one reviewed the definitions of the most important concepts such as emergence and self-organisation from an engineer's perspective, and analysed different types of nature-inspired technology. This article provides a survey of the currently existing approaches to complexity engineering. In the end, challenges ahead are indicated.
42 citations
TL;DR: This work develops confinement strategies through simple biological models, drawing inspiration from the foraging techniques used by bottlenose dolphins to catch fish, to provide an algorithm for one group of agents to perpetually confine the other group.
Abstract: Confinement of a group of mobile robots is of significant interest to the multi-agent robotics community. We develop confinement strategies through simple biological models; in particular, we draw inspiration from the foraging techniques used by bottlenose dolphins to catch fish. For a multi-agent system, we achieve the following goals: 1) provide an algorithm for one group of agents to perpetually confine the other group; 2) characterise the regions from which the herded agents are guaranteed to be captured. The simplicity of the model allows easy implementation in engineered devices (e.g., exploiting the collision avoidance modules already embedded in unmanned air and ground vehicles) and the richness of the model allows replication of a complex biological phenomenon, such as capturing of prey.
40 citations
TL;DR: The application of modified version of a recently developed metaheuristic algorithm, known as the invasive weed optimisation (IWO), to optimise the spacing between the elements of the linear array to produce a radiation pattern with minimum side lobe level and null placement control.
Abstract: Linear antenna array design is one of the most important electromagnetic optimisation problems of current interest This article describes the application of modified version of a recently developed metaheuristic algorithm, known as the invasive weed optimisation (IWO), to optimise the spacing between the elements of the linear array to produce a radiation pattern with minimum side lobe level and null placement control IWO is a novel ecologically inspired algorithm that mimics the process of weeds colonisation and distribution and is capable of solving general multi-dimensional, linear and non-linear optimisation problems with appreciable efficiency For this application, we modified the classical IWO by introducing a more explorative routine of changing the mutation step-size with iterations Three design examples are presented that illustrate the use of the IWO algorithm, and the optimisation goal in each example is easily achieved The results of the modified IWO algorithm have been shown to meet or beat the results obtained using other state-of-the-art metaheuristics like the classical IWO, genetic algorithm (GA), particle swarm optimisation (PSO), memetic algorithms (MA), and tabu search (TS) in a statistically meaningful way
20 citations
TL;DR: To show the capability of MBBO to solve the problems of continuous type, MBBO and other optimisation algorithms are applied as soft computing tool to calculate the resonant frequency of rectangular microstrip patch antennas of different dimensions having various substrate thicknesses.
Abstract: Modified biogeography-based optimisation (MBBO) technique is modified version of BBO which is a bio-inspired and population-based optimisation technique. Biogeography is the study of distribution of species in nature. In this paper, BBO is modified by applying the concept of mutation as extended migration in phenomenon of mutation and prevention of similar habitats. Mutation as concept of extended migration is based on sharing of the information from best solution which controls the diversity among the population limited to the near feasible solution. These make the fine-tuning of the algorithm from one generation to next and converge fast. Fourteen standard benchmark functions are used to demonstrate the performance of MBBO. The results are compared with eight other population-based optimisation algorithms with discrete version of population. The experimental results are analysed using statistical two paired t-test. MBBO performance is also compared with other modified BBO algorithms. To show the capability of MBBO to solve the problems of continuous type, MBBO and other optimisation algorithms are applied as soft computing tool to calculate the resonant frequency of rectangular microstrip patch antennas of different dimensions having various substrate thicknesses.
20 citations
TL;DR: A possible explanation of the phenomenon of diffusion in terms of a network of interacting agents whose decisions are determined by the action of their neighbours according to a probabilistic model is presented.
Abstract: Diffusion is the process by which new products and practices are invented and successfully introduced into a society This paper presents a possible explanation of this phenomenon in terms of a network of interacting agents whose decisions are determined by the action of their neighbours according to a probabilistic model It is known that the maximum eigenvalue of the network decides a tipping point of a diffusion process by probabilistic model The network with large maximum eigenvalue is susceptible to a diffusion process Evolutionary optimisation is used to make the network in which the diffusion process will start more early than in other networks Two properties are identified in which the network is suitable for fast diffusion These are a power law of degree distribution and the phenomena in which hub nodes are connected very densely, it is called a rich-club phenomena Finally, the results of numerical diffusion simulation are compared with other network topology to verify the performance of evolutionary optimised networks
TL;DR: A modified variant of DE algorithm called improved differential evolution (IDE) is proposed, which works in three phases: decentralisation, evolution and centralisation of the population.
Abstract: Differential evolution (DE) is a reliable and versatile function optimiser especially suited for continuous optimisation problems. Practical experience, however, shows that DE easily looses diversity and is susceptible to premature and/or slow convergence. This paper proposes a modified variant of DE algorithm called improved differential evolution (IDE). It works in three phases: decentralisation, evolution and centralisation of the population. Initially, the individuals of the population are partitioned into several groups of subpopulations (decentralisation phase) through a process of shuffling. Each subpopulation is allowed to evolve independently from each other with the help of DE (evolution phase). Periodically, the subpopulations are merged together (centralisation phase) and again new subpopulations are reassigned to different groups. These three phases helps in searching all the potential regions of the search domain effectively, thereby, maintaining the diversity. The promising nature of IDE is demonstrated on a testbed of 16 benchmark problems having box constraints. Comparison of numerical results shows that IDE is either better or at par with other contemporary algorithms.
TL;DR: A wet lab algorithm is proposed for applicable form of fuzzy reasoning by DNA computing with an aim to add a new dimension to the existing similarity-based fuzzy reasoning method by bringing it down to nanoscale computing.
Abstract: In this paper, we propose a wet lab algorithm for applicable form of fuzzy reasoning by DNA computing with an aim to add a new dimension to the existing similarity-based fuzzy reasoning method by bringing it down to nanoscale computing. We replace the logical aspect of fuzzy reasoning by DNA chemistry. To achieve this goal, we first fuzzify the synthetic DNA sequence which is called fuzzy DNA and which handles the vague concept of human reasoning. We adopt the basic notion of DNA computing based on standard DNA operations. In the present model, we consider double stranded DNA sequences with a specific aim of measuring similarity between two DNA sequences. The present wet lab procedure can exploit massive parallelism of DNA computing. The end result of the wet lab algorithm produces multivalued status which can be linguistically interpreted to match the perception of human expert.
TL;DR: A heuristic-based approach, called GP-TBM, based on a hybrid of the genetic algorithm (GA) and particle swarm optimisation (PSO) algorithm by introducing the balance modulating (BM) mechanism to solving the mathematical model to find the optimal supply chain network pattern.
Abstract: In this study, an optimisation mathematical model is developed for presenting the supply chain design problem which is based on a single-product and multi-echelon unbalanced system, and considering four criteria, including cost, quality, delivery time and partner relationship management (PRM), as well as decision factors such as quantity discount and capacity limits. To extract critical factors of PRM evaluation and estimate relative weight among the criteria, the analytic network process (ANP) is utilised. In addition, we propose a heuristic-based approach, called GP-TBM, based on a hybrid of the genetic algorithm (GA) and particle swarm optimisation (PSO) algorithm by introducing the balance modulating (BM) mechanism to solving the mathematical model to find the optimal supply chain network pattern. In the GP-TBM, the parameters are designed by the Taguchi method. Finally, a case of a {4-3-3-3} supply chain network structure is used to demonstrate the effectiveness of the proposed approach, and GP-TBM compared with standard PSO and GA. The empirical analysis results demonstrate GP-TBM is superior to standard PSO and GA in the proposed supply chain planning problems.
TL;DR: A comparison between BeesCol and some best-known algorithms for the GCP shows that the use of taboo search as worker in BeesCol reached most of best known results.
Abstract: Marriage in honey bees optimisation (MBO) is a recent evolutionary metaheuristic inspired by the bees reproduction process. Contrary to most of swarm intelligence algorithms such as ant colony optimisation (ACO), MBO uses self-organisation to mix different heuristics. In this paper, we present an MBO approach for the graph colouring problem (GCP). We propose, as worker, in our algorithm (BeesCol) one of the following methods: local search, taboo search or a proposed-based ant colony system algorithm (IACSCol). The worker intervenes at two levels; it improves initial and crossed solutions. Moreover, in BeesCol, one or several queens are generated randomly or by a specific constructive method, namely, recursive largest first or DSATUR. Experimental results on some well studied Dimacs graphs are reported. A comparison between BeesCol and some best-known algorithms for the GCP (hybrid colouring algorithm HCA, ant system and ant colony system) shows that the use of taboo search as worker in BeesCol reached most of best known results.
TL;DR: Improved forms of PSO algorithm applied to PID controller and Smith predictor design for a class of time delay systems with improved convergence than original PSO are introduced.
Abstract: Particle swarm optimisation (PSO), a population-based nature inspired algorithm has mostly been used for solving continuous optimisation problems, discrete variants also exist. It finds application in most of the engineering design problems. This paper introduces two improved forms of PSO algorithm applied to PID controller and Smith predictor design for a class of time delay systems. In this paper, derivative free optimisation methods, namely simplex derivative pattern search and implicit filtering are used to hybridise PSO algorithm with improved convergence than original PSO. The effectiveness of the proposed algorithms namely SDPS-PSO, IMF-PSO are demonstrated using unit step set point response for a class of dead-time systems using PID controller and Smith predictor designed using the proposed hybrid PSO algorithms. The results are compared with earlier controller tunings proposed by Kookos, Syrcos, Chidambaram, Kanthaswamy and Luyben.
TL;DR: The experimental evaluation on a two-way and four-way graph partitioning with 1% and 5% imbalance confirms that with respect to the sequential version, the DMACA obtains statistically, equally good solutions at a 99% confidence level within a reduced overall computation time.
Abstract: The graph-partitioning problem arises as a fundamental problem in many important scientific and engineering applications. A variety of optimisation methods are used for solving this problem and among them the meta-heuristics outstand for its efficiency and robustness. Here, we address the performance of the distributed multilevel ant-colony algorithm (DMACA), a meta-heuristic approach for solving the multi-way graph partitioning problem, which is based on the ant-colony optimisation paradigm and is integrated with a multilevel procedure. The basic idea of the DMACA consists of parallel, independent runs enhanced with cooperation in the form of a solution exchange among the concurrent searches. The objective of the DMACA is to reduce the overall computation time, while preserving the quality of the solutions obtained by the sequential version. The experimental evaluation on a two-way and four-way partitioning with 1% and 5% imbalance confirms that with respect to the sequential version, the DMACA obtains statistically, equally good solutions at a 99% confidence level within a reduced overall computation time.
TL;DR: The results clearly show that the proposed improved IWD algorithm has better performance than those of original IWD, and MIWD-TSP algorithm and very competitive results to others meta-heuristics.
Abstract: Intelligent water drops (IWD) algorithm is a new meta-heuristic approach belonging to a class of swarm intelligence-based algorithms. It is inspired from observing processes of natural water swarm that happen in the natural river systems. This paper presents an improved IWD algorithm based on developing an adaptive schema to prevent the IWD algorithm from premature convergence. The performance of the adaptive IWD is compared with original IWD and other meta-heuristic algorithms in solving travelling salesman problem (TSP). The results clearly show that the proposed algorithm has better performance than those of original IWD, and MIWD-TSP algorithm and very competitive results to others meta-heuristics.
TL;DR: A framework for developing robust explanations using linked sets of models is proposed, and a programme of research incorporating both robotics and chemical experiments which is designed to investigate robustness in systems is described.
Abstract: Finding robust explanations of behaviours in Alife and related fields is made difficult by the lack of any formalised definition of robustness. A concerted effort to develop a framework which allows for robust explanations of those behaviours to be developed is needed, as well as a discussion of what constitutes a potentially useful definition for behavioural robustness. To this end, we describe two senses of robustness: robustness in systems; and robustness in explanation. We then propose a framework for developing robust explanations using linked sets of models, and describe a programme of research incorporating both robotics and chemical experiments which is designed to investigate robustness in systems.
TL;DR: The results obtained by the SOA are compared to those published in the recent literatures to establish its superiority and both the near optimality of the solution and the convergence speed of the algorithm are promising.
Abstract: Seeker optimisation algorithm (SOA), a novel heuristic population-based search algorithm, is utilised in this paper to solve different economic load dispatch (ELD) problems of thermal power units. In the SOA, the act of human searching capability and understanding are exploited for the purpose of optimisation. In this algorithm, the search direction is based on empirical gradient by evaluating the response to the position changes and the step length is based on uncertainty reasoning by using a simple fuzzy rule. The effectiveness of the algorithm has been tested on four different small, as well as, large-scale test power systems to solve the ELD problems. The outcome of the present work is to establish the SOA as a promising alternative approach to solve the ELD problems in practical power systems. Both the near optimality of the solution and the convergence speed of the algorithm are promising. The results obtained by the SOA are compared to those published in the recent literatures to establish its superiority.
TL;DR: It is argued that many elements for a general theory of complexity now exist and the universal nature of network model of complexity provides a suitable foundation for this general theory.
Abstract: The need to understand and manage complex systems is increasing in importance, but complexity theory is still hampered by being highly fragmented in nature. This article argues that many elements for a general theory of complexity now exist and briefly reviews the main features. First, the universal nature of network model of complexity provides a suitable foundation for a general theory. A brief summary of the network model is followed by a discussion of related issues, including simulation, dynamics and self-organisation. Gaps identified include the need for formal methods to describe complexity and to identify structural equivalence. Finally, some important lessons from biology are summarised.
TL;DR: It is demonstrated that, at least in the case of EC population size setting, the dynamic population, which is inspired by the natural population dynamics, indeed outperforms the traditional fixed-size population in the genetic algorithms (GA).
Abstract: In a classic monograph titled Ecological Theatre and Evolutionary Play, Hutchinson (1966) tried to 'break' the genetics dominance over the study of evolution and emphasised that natural selection happens in the context of environment. His vision clearly indicated the inseparability between evolution and ecology. In other words, without ecological 'theatre', natural selection has no place to act and evolution cannot happen. Perhaps following a similar development trajectory of evolutionary study in biology, much of the evolutionary computing (EC) has been inspired by genetics-centred evolutionary theory. The major objective of this paper is to suggest and review some inspirations from several fields of population ecology and evolutionary ecology to evolutionary computing (EC). A minor one is to demonstrate that, at least in the case of EC population size setting, the dynamic population, which is inspired by the natural population dynamics, indeed outperforms the traditional fixed-size population in the genetic algorithms (GA).
TL;DR: The proposed approach provides very high quality solutions which are very competitive to other existing techniques to ELD considering the valve-point effect, and has proven to be effective in solving non-linear constrained optimisation problems.
Abstract: A novel and effective method for solving economic load dispatch (ELD) problem is presented in this work by integrating the ? constrained method with differential evolution (DE) algorithm The ? constrained method sets us free from selecting the appropriate value for the penalty coefficient in the objective function, which is difficult and often chosen empirically Differential evolution with ? constrained method (?DE) has proven to be effective in solving non-linear constrained optimisation problems Here, the effectiveness of ?DE, in solving ELD problems is investigated by using three different ELD problems that take the valve-point loading effect into consideration The proposed approach provides very high quality solutions which are very competitive to other existing techniques to ELD considering the valve-point effect
TL;DR: This work showed that GA performs better than PSO and pattern search method and so is the preferable method in design of composite plate structures.
Abstract: Fibre reinforced composite materials are widely used in construction of components of aircraft, ships and marine structures that are subjected to high compression loads. One of the important problems in fibre reinforced composite markets is to find the optimal stacking sequence which tailors the properties of the composite structures. The motivation of the study is to apply the newly developed bio-inspired technique particle swarm optimisation (PSO) and compare its effectiveness with other optimisation techniques genetic algorithm (GA) and pattern search method in the design of composite structures. As a case study, a square and rectangular thick plate subjected to uniaxial or biaxial loading is considered and it is optimised to find the layer orientation which maximises the buckling load. This work showed that GA performs better than PSO and pattern search method and so is the preferable method in design of composite plate structures.
TL;DR: A new particle swarm optimisation (PSO) algorithm based on simulated annealing (SA) with adaptive jump strategy to alleviate some of the limitations of the standard PSO algorithm.
Abstract: This paper proposes a new particle swarm optimisation (PSO) algorithm based on simulated annealing (SA) with adaptive jump strategy to alleviate some of the limitations of the standard PSO algorithm. In this algorithm, swarm particles jump into the space to find new solutions. The jump radius is selected adaptively based on the particle velocity and its distance from the global best position. The designed algorithm has been tested on benchmark optimisation functions and on known autoregressive exogenous (ARX) model design problem. The results are superior as compared to the existing PSO methods. Finally, the designed algorithm has been applied for the analysis of the dynamic cerebral autoregulation mechanism.
TL;DR: It is demonstrated that a scale-free network does not always promote the evolution of cooperation and that there exists an appropriate structure at which the cooperation becomes stronger and the reason for the existence of such structure is considered using the fixation probability.
Abstract: In the present study, we investigate how the initial network structure affects the evolution of cooperation in the spatial prisoner's dilemma game. Previous studies have reported that a scale-free network promotes the evolution of cooperation. However, the dependency of the shape of the degree distribution on the evolution has not been investigated systematically. In the present paper, the evolution of cooperation on scale-free networks having different power-law exponents is investigated numerically. We demonstrate that a scale-free network does not always promote the evolution of cooperation and that there exists an appropriate structure at which the cooperation becomes stronger. In addition, we consider the reason for the existence of such structure using the fixation probability.
TL;DR: This approach is extended with the introduction of a genetic algorithm that explores the space of parameters these agents employ for making decisions about the interactions they are willing to embark upon and argues that this approximation lays the ground for coevolutionary change between agents in the system.
Abstract: In this paper, we describe an ecologically inspired technique for the development of interaction centred agent systems which facilitates the emergence of organisational patterns that are often found in ecological networks between mutualistic species. We then extend this approach with the introduction of a genetic algorithm that explores the space of parameters these agents employ for making decisions about the interactions they are willing to embark upon and argue that this approximation lays the ground for coevolutionary change between agents in the system, enhancing in this way their adaptive ability and the persistence of the society of agents as a whole.
TL;DR: An agent-based model of the evolutionary prisoner's dilemma on different combinations of interaction and replacement networks is constructed and shows that the larger scale of reproduction than the scale of interaction brought about higher level cooperation when the intensity of selection is high.
Abstract: There are various discussions on the evolution of cooperation on different combinations of interaction network for playing games and the replacement network for imitation of strategies. This paper aims at clarifying the topological relationship between these networks that facilitates the evolution of cooperation by focusing on the intensity of selection for imitation process of strategies. We construct an agent-based model of the evolutionary prisoner's dilemma on different combinations of interaction and replacement networks. The relationship between these networks can be adjusted by the scales of interaction and reproduction, and the intensity of selection can be adjusted from the almost deterministic selection of the best strategy to the extremely stochastic selection. The evolutionary experiments shows that the larger scale of reproduction than the scale of interaction brought about higher level cooperation when the intensity of selection is high, and the minimum scale of interaction and reproduction was the best for the evolution of cooperation when the intensity of selection is low.
TL;DR: It is shown that the convergence speed is faster in evolutionary optimised networks than previous networks which are known as better synchronisation networks, and the optimised network is created which is suitable to the property of the objective function by evolutionary algorithms.
Abstract: There is consensus problem as an important characteristic for coordinated control problem in collective behaviour, the interaction between agents and factors. Consensus problem is closely related to the complex networks. Recently, many studies are being considered in the complex network structure, the question what network is the most suitable to the property of the purpose has not been answered yet in many areas. In the previous study, network model has been created under the regular rules, and their characteristics have been investigated. But in this study, network is evolved to suit the characteristics of the objection by evolutionary algorithm and we create optimised network. As a function of the adaptive optimisation, we consider the objection that combine consensus, synchronisation index and the density of the link, and create the optimised network which is suitable to the property of the objective function by evolutionary algorithms. Optimal networks that we have designed have better synchronisation and consensus property in terms of the convergence speed and network eigenvalues. We show that the convergence speed is faster in evolutionary optimised networks than previous networks which are known as better synchronisation networks. As a result, we generate optimal consensus and synchronous network.
TL;DR: It is revealed that the proposed accuracy-based Pittsburgh-style LCS can find the waterbus routes that can cope with two different situations and employs NSGA-II to find the most effective and robust solutions among a lot of Pareto front solutions found in the multi-objective optimisation.
Abstract: This paper proposes an accuracy-based Pittsburgh-style learning classifier system (LCS) that can find effective and robust solutions against several different situations, and aims at investigating its effectiveness in the waterbus route optimisation problem. For this purpose, our accuracy-based Pittsburgh-style LCS: 1) introduces a new fitness calculation to remain robust classifiers (i.e., solutions) in different situations 2) employs NSGA-II to find the most effective and robust solutions among a lot of Pareto front solutions found in the multi-objective optimisation. Through intensive simulations on the waterbus route optimisation problem, we have revealed that our proposed LCS can find the waterbus routes that can cope with two different situations. In detail: 1) the relative fitness calculation can find the robust routes in comparison with the ordinary fitness calculation 2) the accuracy-based selection of the parents succeeds to find more effective and robust route in the different environments in comparison with the NSGA-II-based selection in the multi-objective optimisation.