A wide range of predator evasion strategies have been reported for several real predator-prey systems in the wild. We investigate predator evasion in a system of many simulated animal agents. Our model is capable of simulating the emergent effects arising from around a million individual microscopic agents which make individual intelligent choices based on their local information. We find oscillatory and other system wide effects arising from enhanced abilities of prey to evade their predators. We compare some of these effects to real predator-prey observed patterns of behaviour. We find additional oscillatory effects arising when prey can evolve towards different levels of evasive behaviour.

For continuous multi-objective optimization problems there exists an infinite number of solutions on the Paretooptimal front. A multi-objective evolutionary algorithm attempts to find a representative set of the Pareto-optimal solutions. In the case of multi-objective multi-modal problems, there exist multiple decision vectors which map to identical objective vectors on Pareto front. Many multi-objective evolutionary algorithms fail to find and preserve all of the multi-modal solutions in the non-dominated solutions set. Finding more of the available multi-modal solutions would give the decision maker a greater selection when choosing between solutions. In this paper, we present an extended version of the Pareto estimation method, to increase the density of the multi-objective multi-modal solutions. The method uses clustering analysis to identify and separate different clusters in the decision variables space which correspond to the multi-modal Pareto optimal solutions. Then Pareto estimation procedure is employed for these individual clusters, there by increasing the density of available multi-modal solutions. The proposed method has been tested on experimental test functions and is shown to be successful.

Cancer is defined as a disease that involves changes or mutations in the cell genome. The underlying cause of mutations leading to cancer is DNA damage. Cancer genome sequencing includes cancer genome assembly and cancer genome alignment is through early detection improving survival opportunity of cancer patients. In this research, a bioinformatics approach is proposed to solve cancer genome sequencing by constructing De Bruijn Graphs along with using the Euler Path for finding an optimal cancer genome reassembly and the Smith–Waterman scoring matrix for cancer genome alignment optimization.

This paper examines an interesting combinatorial optimisation problem that generalises both the graph colouring and k-partition problems. The problem has an interesting practical application in the construction of wedding seating plans, where we seek to assign equal numbers of guests to tables such that they are sat near friends and, perhaps more importantly, kept away from their ene mies. We describe an effective two-stage metaheuristic-based approach for this problem which is currently used with the online tool on the commercial web- site www.weddingseatplanner.com. We also present results on the performance of this algorithm, indicating what factors can influence run time and solution quality.

This paper discusses the results of applying Reinforced Ant Colony Optimization algorithm to solve the Traveling Salesman Problem (TSP), an NP Complete problem. To evaluate the performance of Ant Colony Optimization algorithm, comparative studies were done between research which introduced Hybrid Genetic algorithm [3] to solve the Traveling Salesman Problem and the original Ant Colony Optimization algorithm proposed by Dorigo[1]. After comparing the Hybrid and Genetic algorithms as well as the Nearest Neighbor (NN) algorithm and the original ACO against the reinforced ACO algorithm, it was found that the reinforced ACO algorithm performs the best with the tour length being the shortest. However, the convergence time for the reinforced ACO algorithm increases when the number of cities increases. Thus, although tour length was shorter for the reinforced ACO, for a large number of cities, the reinforced ACO algorithm took a relatively long time to find a tour.

This paper presents a method based on the particle swarm optimization algorithm applied to estimate harmonic components in radial distribution feeders. It is important to mention that this method is not applied as harmonic state estimator, neither to estimate the total harmonic distortion at the substation. So, the proposed method can be employed to estimate the harmonic components in specific points of common coupling between the harmonic source and the feeder. In this sense, some case studies were prepared in order to validate the method. The point of common coupling where the harmonic source is located were obtained by means of expert knowledge. Nevertheless, the specialist/engineer should be induced to err the exact position of the harmonic source due to the presence of other harmonic sources with lower levels of distortion. Thus, the precision rate of this method was evaluated in accordance with the uncertainty that can be generated by the expert knowledge. These analysis are crucial to verify the performance of the proposed method, mainly, in the utility's point of view.

In this paper two solutions to the emission source localization problem are examined. This problem involves monitoring an environment with a distributed sensor network and processing the data to find the source of an emission. Being able to quickly find the source of a chemical leak or radiological dispersion can save lives, and reducing or eliminating the need for people to be involved in the search process further reduces the danger. Previous work presented the benefits of using the Particle Swarm Optimization for emission source localization. This work presents further benefits by using The Firefly Algorithm. The Firefly Algorithm in general only performs better when dealing with lots of noise from the sensors, but is faster under all circumstances.

Parameter setting is very essential for the application of particle swarm optimization (PSO), especially the acceleration coefficients. In this paper, we propose a fast estimation strategy of optimal parameter setting for PSO, in which an estimation distribution algorithm (EDA) is used to co-evolve the acceleration coefficients (!!and !!). The proposed algorithm is validated on two numerical optimization problems and then applied to the urban water distribution network optimization problem. The experimental results show that both of these two parameters converge to a fixed value respectively and the achieved values for !! and !! are consistent as the results of parameter tuning.PSO with the estimated optimal parameters could achieve the best solution on benchmark example and also outperform other methods in terms of reliability and efficiency.

The design of efficient communication networks is a challenging task for modern vehicle development. Due to novel technologies and new degrees of freedom in network design, the decision on a bus topology has a severe impact on the overall system cost and performance. In this work, we propose a topology and routing optimization using Evolutionary Algorithms and problem-specific encoding. Our contribution includes a guided topology mutation operator which outperforms standard random mutation. Further, we propose two routing operators for usage during the optimization process and compare their effectiveness on a network application taken from a series vehicle.

Evac (the evolutionary accompanist) is a system that engages in musical improvisation with the user. Evac uses a genetic algorithm (GA) to invent musical phrases that are neither too similar to the user’s input, nor too different. It is notable for two reasons. First, it uses a novel, implicitly interactive, genetic algorithm, which allows the user’s actions to influence Evac’s musical performance without the need for explicit rating of individuals. Second, in contrast to many pieces of software in the world of evolutionary music and art, Evac runs in real time, allowing the user to experience the same kind of exploration that happens in real life improvisation scenarios with other musicians. Evac must also solve the design problems of dynamic environments, since our GA’s fitness function relies on the user’s input. Sample music resulting from the system is available.

In this paper Evolutionary Strategy for uncorrelated mutations such as self-adaptive one step and self-adaptive k step are compared with correlated mutation. The two offspring selection techniques of direct replacement (μ,λ) and best fit (μ+λ) are used for comparison. These techniques were applied to a standard multi peak function to evaluate their performance. It was found that none of these approaches always found the global maximum. The results were very much dependent on the selection of the initial random parents. Therefore a new approach of correlated mutation using additional geometric translation has been proposed. It is illustrated that this technique was successful in finding the global maximum.

This paper presents a general-purpose algorithm for finding high-quality solutions to hard optimization problems. The method, called the Evolutionary Path Algorithm, finds high-quality solutions by searching the space that separates solutions within the search space. The Evolutionary Path Algorithm performs random search at the far end of its search path, and then as the path from a random sample back to a Candidate solution is built, the search becomes more local. This path traversal allows the algorithm to explore the search space at the far end and improve a known good solution as it returns to the Candidate solution. Unlike many stochastic search algorithms, the Evolutionary Path Algorithm can be implemented with very limited tuning parameters, making it simpler to use for many practitioners. The Evolutionary Path Algorithm has proven reliable with respect to finding good answers, in the cases presented the best answers, to hard problems. We demonstrate EPA here on an NP hard minimal set cover example with known optima and on an integer valued configuration problem.

Genetic Programming (GP) has been employed in many problem domains, and as a result, it has been the subject of much scientific inquiry. The extensive literature body of GP has reported applications in algorithm discovery, image enhancement and cooperative multi-agent systems, as well as many other areas and disciplines, such as agent based modeling in Geography and Social Science. As models become more complex, further research toward higher efficiency have been warranted. We discuss solutions to large scale systems which require automatic programming, and present results of a modified data-parallel implementation of GP based on Gene-expression Programming for Graphical Processing Units (GPUs), as well as a modified Santa Fe Ant Trail problem to measure the efficacy of this algorithm. We present results on algorithm convergence as well as timing performance on both GPU and CPU implementations.

Genetic Programming (GP) has been employed in many problem domains, and as a result, it has been the subject of much scientific inquiry. The extensive literature body of GP has reported applications in algorithm discovery, image enhancement and cooperative multi-agent systems, as well as many other areas and disciplines, such as agentbased modelling in Geography and Social Science. As models become more complex, further research toward higher efficiency have been warranted. We discuss solutions to largescale systems which require automatic programming, and present results of a modified data-parallel implementation of GP based on Gene-expression Programming for Graphical Processing Units (GPUs), as well as a modified Santa Fe Ant Trail problem to measure the efficacy of this algorithm. We present results on algorithm convergence as well as timing performance on both GPU and CPU implementations.

The goal of task scheduling in a multiprocessor system is to schedule dependent tasks on processors such that the processing time is minimized. This ensures optimal usage of the processing systems. However this problem is NP-hard in nature and heuristic based techniques are used to obtain a good schedule in polynomial time. Genetic Algorithms (GA) have been proposed over other heuristics because it can use its genetic processes to find multiple solutions faster. The GA proposed is based on a non-preemptive precedence relation between tasks in the task graph. Tasks assignment is prioritized based on the number of tasks dependencies (NTD) and the earliest start time (EST) of each task. For tasks with multiple possible earliest start times, the minimum earliest start time is chosen for such tasks. Java simulations compared the results obtained using the minimum EST and the maximum EST. Our simulation shows that the proposed algorithm with minimum EST achieves faster processing periods compared with the maximum EST.

West Nile Virus (WNV) disease is caused by a flavivirus that is transmitted primarily by the bites of mosquitoes that have bitten infected birds. It was first detected in the US in New York City in 1999. By 2003, it had spread across the state; by September 2012, it had spread to the contiguous 48 states. Given the WNV disease surveillance record, it is now possible to assess how well ecological niche modeling (ENM), given the observed Year 2000 New York State WNV bird-mortality distribution, would have predicted the distribution of the virus across the US. Here I compare a genetic-algorithm- rule-production ENM predictions of the potential geographic distribution of the US avian WNV mortality with the observed distribution of human WNV disease in the US in early October 2012.The analysis shows that despite significant limitations of the WNV surveillance protocols in the US, ENM would have correctly predicted the potential presence or absence, by state, of human WNV disease in the US.

A Chaotic Genetic Algorithm (CGA) for Cognitive Radio spectrum allocation procedure is presented. The development of the Cognitive radio system puts emphasis on the efficient utilization of spectrum for both primary and secondary users. Secondary users make use of the spectrum without degrading the quality of service of the primary user(s). We assume that spectrum sensing has been done; thus a secondary user can specify the Quality of Service (QoS) requirements for a particular application at any given time. A Genetic Algorithm is used for the spectrum allocation. We have compared the performance of a Traditional Genetic Algorithm (TGA) with the chaotic counterpart. The simulation shows that the CGA converges faster with better fitness than the TGA. The simulation has been modeled using MATLAB.

A wireless sensor network is a collection of nodes organised in into a cooperative network. Knowing the locations of the wireless sensor nodes is central to accurate information gathering. Conventional location detection technique such as global positioning system (GPS) and infrared are expensive to deploy. This paper proposes the use of a genetic algorithm (GA) to learn the environment impairments within a wireless sensor network for the purpose of localization for data management. For each coordinate in the grid network area, random perturbations of received signal strength (RSS) were supplied to the GA. The GA is able to learn the environment and reduce the possible errors inherent in the RSSI measurement taken per coordinate. Our simulation modeled in MATLAB shows that the GA can achieve acceptable node location detection with the aid of three anchors.

This paper describes a multi-objective evolutionary approach for solving cloud computing service provider selection problems with dynamic demands. In this investigated problem, not only the service purchase costs and transmission costs of service providers are different, but the demands of service requests also change over the given periods. The objective of this problem is to select a number of cloud service provider while optimizing the total service distance, the total number of serviced demand points, the total service purchase costs, and total transmission costs simultaneously in the given continuous time periods. A multi-objective genetic approach with an inheritance mechanism is proposed to solve the investigated problems. Four trail benchmark problems are designed and solved using the proposed multi-objective evolutionary algorithm. The results indicate that the proposed approach is capable of obtaining a number of non-dominated solutions for decision makers.

Validation of an Attributes Selection System Through Genetic Algorithms for ICU on Severely Burnt Patients (AG-PxQ) According to its Usability on the Clinic