Search

We emphasize that interactive evolutionary computation (IEC) can be used not only to optimize a target system based on an IEC user’s subjective evaluations but also to analyze the characteristics of the IEC user. We introduce four research works as concrete examples of this new research direction: measuring a perceived range for emotional expressions, finding unknown auditory knowledge through hearing-aid fitting and cochlear implant fitting, and modeling of human awareness mechanism.

Facility Layout Design is known to be very important for attaining production efficiency because it directly influences manufacturing costs, lead times, work in process and productivity. Facility Layout problems have been addressed using several approaches. Unfortunately, these approaches only take into account quantitative criteria. However, there are qualitative preferences referred to the knowledge and experience of the designer, which should also be considered in facility layout design. These preferences can be subjective, not known in advance and changed during the design process, so that, it is difficult to include them using a classic optimization approach. For that reason, we propose the use of an Interactive Genetic Algorithm (IGA) for designing the layout of two real recycling plants taking into consideration subjective features from the designer. The designer's knowledge guides the evolution of the algorithm evaluating facility layouts in each generation adjusting the search to his/her preferen...

The simultaneous optimization of many objectives (in excess of 3), in order to obtain a full and satisfactory set of tradeoff solutions to support a posteriori decision making, remains a challenging problem. The concept of coevolving a family of decision-maker preferences together with a population of candidate solutions is studied here and demonstrated to have promising performance characteristics for such problems. After introducing the concept of the preference-inspired coevolutionary algorithm (PICEA), a realization of this concept, PICEA-g, is systematically compared with four of the best-in-class evolutionary algorithms (EAs); random search is also studied as a baseline approach. The four EAs used in the comparison are a Pareto-dominance relation-based algorithm (NSGA-II), an e-dominance relation-based algorithm [ e-multiobjective evolutionary algorithm (MOEA)], a scalarizing function-based algorithm (MOEA/D), and an indicator-based algorithm [hypervolume-based algorithm (HypE)]. It is demonstrated that, for bi-objective problems, all of the multi-objective evolutionary algorithms perform competitively. As the number of objectives increases, PICEA-g and HypE, which have comparable performance, tend to outperform NSGA-II, e-MOEA, and MOEA/D. All the algorithms outperformed random search.

This article presents an empirical study devoted to characterize the computational efficiency behavior of an evolutionary algorithm usually called canonical as a C program. The study analyzes the effects of several implementation decisions on the execution time of the resulting evolutionary algorithm. The implementation decisions studied include: memory utilization using dynamic vs.static variables and local vs.global variables, methods for ordering the population, code substitution mechanisms, and the routines for generating pseudorandom numbers within the evolutionary algorithm. The results obtained in the experimental analysis allow us to conclude that significant improvements in efficiency can be gained by applying simple guidelines to best program an evolutionary algorithm in C. Copyright © 2013 John Wiley & Sons, Ltd.

In this paper, we describe a study of the evolution of consensus, a cooperative behavior in which members in both homogeneous and heterogeneous groups, must agree on information sensed in their environment. We conducted the study using digital evolution, a form of evolutionary computation where a population of computer programs (digital organisms) exists in a user-defined computational environment and is subject to instruction-level mutations and natural selection. We placed these digital organisms into groups whose fitness relied upon their ability to perform consensus. We then tested different degrees and types of genetic variation present in the population, based on biologically inspired models of gene flow, including mutation, sexual recombination, migration, and horizontal gene transfer. Our experimental treatments examined the effect of these processes on genetic variation and groups' ability to reach consensus. The results of these experiments demonstrate that while genetic heterogeneity within groups increases the difficulty of the consensus task, a surprising number of groups were able to overcome these obstacles and evolve this cooperative behavior.

We propose a method for accelerating interactive evolutionary computation (IEC) and evolutionary computation (EC) searches using elite obtained in one-dimensional spaces and use benchmark functions to evaluate the proposed method. The method projects individuals onto n one-dimensional spaces corresponding to each of the n searching parameter axes, approximates each landscape using interpolation or an approximation method, finds the best coordinate from the approximated shape, obtains the elite by combining the best n found coordinates, and uses the elite for the next generation of the IEC or EC. The advantage of this method is that the elite may be easily obtained thanks to their projection onto each one-dimensional space and there is a higher possibility that the elite individual locates near the global optimum. We compare the proposal with methods for obtaining the landscape in the original search space, and show that our proposed method can significantly save computational time. Experimental evaluations of the technique with differential evolution using a simulated IEC user (Gaussian mixture model with different dimensions) and 34 benchmark functions show that the proposed method substantially accelerates IEC and EC searches.

Stochastic optimization methods such as evolutionary algorithms and Markov Chain Monte Carlo methods usually involve a Markov search of the optimization domain. Evolutionary annealing is an evolutionary algorithm that leverages all the information gathered by previous queries to the cost function. Evolutionary annealing can be viewed either as simulated annealing with improved sampling or as a non-Markovian selection mechanism for evolutionary algorithms. This article develops the basic algorithm and presents implementation details. Evolutionary annealing is a martingale-driven optimizer, where evaluation yields a source of increasingly refined information about the fitness function. A set of experiments with twelve standard global optimization benchmarks is performed to compare evolutionary annealing with six other stochastic optimization methods. Evolutionary annealing outperforms other methods on asymmetric, multimodal, non-separable benchmarks and exhibits strong performance on others. It is therefore a promising new approach to global optimization.

Learning aesthetic judgements is essential for reducing users' fatigue in evolutionary art systems. Although judging beauty is a highly subjective task, we consider that certain features are important to please users. In this paper, we introduce an adaptive model to learn aesthetic judgements in the task of interactive evolutionary art. Following previous work, we explore a collection of aesthetic measurements based on aesthetic principles. We then reduce them to a relevant subset by feature selection, and build the model by learning the features extracted from previous interactions. To apply a more accurate model, multi-layer perceptron and C4.5 decision tree classifiers are compared. In order to test the efficacy of the approach, an evolutionary art system is built by adopting this model, which analyzes the user's aesthetic judgements and approximates their implicit aesthetic intentions in the subsequent generations. We first tested these aesthetic measurements on different artworks from our selected artists. Then, a series of experiments were performed by a group of users to validate the adaptive learning model. The study reveals that different features are useful for identifying different patterns, but not all are relevant for the description of artists' styles. Our results show that the use of the learning model in evolutionary art systems is sound and promising for predicting users' preferences.

While evolution has inspired algorithmic methods of heuristic optimization, little has been done in the way of using concepts of computation to advance our understanding of salient aspects of biological phenomena. The authors argue under reasonable assumptions, interesting conclusions can be drawn that are of relevance to behavioral evolution. The authors will focus on two important features of life---robustness and fitness---which, they will argue, are related to algorithmic probability and to the thermodynamics of computation, disciplines that may be capable of modeling key features of living organisms, and which can be used in formulating new algorithms of evolutionary computation.

Evolutionary information theory is a constructive approach that studies information in the context of evolutionary processes, which are ubiquitous in nature and society. In this paper, we develop foundations of evolutionary information theory, building several measures of evolutionary information and obtaining their properties. These measures are based on mathematical models of evolutionary computations, machines and automata. To measure evolutionary information in an invariant form, we construct and study universal evolutionary machines and automata, which form the base for evolutionary information theory. The first class of measures introduced and studied in this paper is evolutionary information size of symbolic objects relative to classes of automata or machines. In particular, it is proved that there is an invariant and optimal evolutionary information size relative to different classes of evolutionary machines. As a rule, different classes of algorithms or automata determine different information size for the same object. The more powerful classes of algorithms or automata decrease the information size of an object in comparison with the information size of an object relative to weaker4 classes of algorithms or machines. The second class of measures for evolutionary information in symbolic objects is studied by introduction of the quantity of evolutionary information about symbolic objects relative to a class of automata or machines. To give an example of applications, we briefly describe a possibility of modeling physical evolution with evolutionary machines to demonstrate applicability of evolutionary information theory to all material processes. At the end of the paper, directions for future research are suggested.

This paper presents an evolutionary algorithm for Black-Box Chance-Constrained Function Optimization (BBCCFO). BBCCFO is to minimize the expectation of the objective function under the constraints that the feasibility probability is higher than a userdefined constant in uncertain environments not given the mathematical expressions of objective functions and constraints explicitly. In BBCCFO, only objective function values of solutions and their feasibilities are available because the algebra expressions of objective functions and constraints cannot be used. In approaches to BBCCFO, a method based on an evolutionary algorithm proposed by Loughlin and Ranjithan shows relatively good performance in a realworld application, but this conventional method has a problem in that it requires many samples to obtain a good solution because it estimates the expectation of the objective function and the feasibility probability of an individual by sampling the individual plural times. In this paper, we propose a new evolutionary algorithm that estimates the expectation of the objective function and the feasibility probability of an individual by using the other individuals in the neighborhood of the individual. We show the effectiveness of the proposed method through experiments both in benchmark problems and in the problem of a inverted pendulum balancing with a neural network controller.

This paper examines the stigmergic dimensions of online interactive creativity through the lens of Picbreeder. Picbreeder is a web-based system for collaborative interactive evolution of images. The Picbreeder applet starts by randomly generating several images, which are then mated and mutated based on the user's selections. The user can then publish the image to the Picbreeder website where other users can download and continue the image's evolution. Within this process, users collaboratively create images with significant complexity, all without explicit communication. In short, Picbreeder encourages a new form of stigmergic collaborative creation. The most surprising result of the Picbreeder experiment during more than 3 years of operation has been the quality of the resulting images, despite the limited ways of interacting with other users. This fact challenges some commonly held notions of creativity, both online and offline. While current cognitive research in creativity places significant emphasis of the personal traits and cognitive structures that give rise to creative thought, Picbreeder highlights the potential for the emergence of creativity through stigmergic interaction. Picbreeder offers a rich data set for analysis of collaborative interaction with over 155,000 inputs from hundreds of users combined to create over 7500 images. It is hoped that the insights offered in this paper will influence both the understanding of collaborative creativity and the development of new modes of online creative interaction.

Interactive evolutionary computation (IEC) is an effective solution for problems of user subjectivity. However, a significant problem with IEC is user fatigue. IEC requires direct evaluation, and so increasing the number of generations results in increased fatigue. We previously reported a method for building a three-dimensional (3D) model using interactive evolution. Here, we propose a method of direct manipulation (DM) using IEC to reduce user fatigue, whereby direct encoding is applied to the final results during post-processing. This allowed instant changes to the shape of the final model, reducing user fatigue. This method can manipulate several parameters of 3D models in real-time. Test results show that IEC with DM is superior to IEC alone. © 2013 The Authors. Published by Elsevier B.V. Selection and/or peer-review under responsibility of the Program Committee of IES2013.

In this paper, a multi-objective image segmentation approach with an Interactive Evolutionary Computation IEC-based framework is presented. Two objectives, i.e., the overall deviation and the connectivity measure, are optimized simultaneously using a multi-objective evolutionary algorithm to generate parameters used for segmentation. In addition, an IEC framework to allow users to participate in the parameters optimization process directly is devised. To demonstrate the effectiveness of the proposed IEC-based multi-objective image segmentation approach, a series of experiments is conducted, and the results are compared with those from other segmentation methods. The outcomes ascertain that the proposed approach is effective, as it compares favorably with other classical approaches.

In this article, David Fogel discusses the relationship between evolutionary computation and evolutionary game theory. The mathematics of evolutionary game theory relies on assumptions that often fail to describe the real-world conditions that the theory is intended to model. This article highlights those assumptions and suggests evolutionary computation may ultimately serve as a more useful approach to understanding complex adaptive systems in nature.

An interactive hybrid evolutionary computation (IHC) process for MEMS design synthesis is described, which uses both human expertise and local performance improvement to augment the performance of an evolutionary process. The human expertise identifies good design patterns, and local optimization fine-tunes these designs so that they reach their potential at early stages of the evolutionary process. At the same time, the feedback on local optimal designs confirms and refines the human assessment. The advantages of the IHC process are demonstrated with micromachined resonator test cases. Guidelines on how to set parameters for the IHC algorithm are also made based on experimental observations and results.

The experiment carried by the author in 2010 is to test if self-organizing systems could be systematically regulated according to the user's preference for global behavior. Self-organizing has been appreciated by architects and urban planners for its richness in the emerging global behaviors; however, design and self-organizing are contradictory in principle. It seems that it is inevitable to balance the design and self-organization if self-organization is employed in a design task. There have been approaches combining self-organizing with optimization process in a parallel manner. This experiment strives to regulate a self-organizing system according to non-defined objectives via real-time interaction between the user and the computer. Particularly, cellular automaton is employed as the self-organizing system to model a city district., Frontiers of Architectural Research, 1 (4), ISSN:2095-2635, ISSN:2095-2643

We propose a method to solve the selection problem of principal components in machine learning algorithms based on orthogonal transformation by using interactive evolutionary computation. One of the addressed subjects for machine learning algorithms based on orthogonal transformation is how to decide the number of principal components, and which of the principal components should be used to reconstruct the original data. In this work, we use the interactive differential evolution algorithm to study these subjects by using real humans' subjective evaluation in an optimization process. An image compression problem using principal component analysis is introduced to study the proposed method. From the evaluation, we do not only solve the selection problem of principal components for machine learning algorithms based on orthogonal transformation, but also can analyse the human aesthetical characteristics on visual perception and feature selection from the designed method and experimental evaluation. We also discuss and analyse potential research subjects and some open topics, which are invited to further investigate.

In this paper, an evolutionary algorithm is applied to tackle Intelligent Curriculum Sequencing issue. The purpose is to align educational technology, for instance, curriculum sequence to: students' characteristics and subject-matter coherence. The algorithm considers both technical and pedagogical point of view. Results show that the proposed Evolutionary Computation Search Algorithm could find optimal learning sequences, under a set of constraints, within a reasonable amount of iterations.

SPEA2 (Strength Pareto Evolutionary Algorithm 2) is an evolutionary algorithm based on population, which is solutions to resolve Multi-objective Optimization Problems (MOPs). It has selection process that to select from dataset or objective problem benchmarking such as DTLZ. Our aim is to improve SPEA2 performance to process a population using parallelism in GPU. By optimization fitness and distance calculations using transposed data to process in CUDA platform. The result shows that speed up increase approximately 1.5 times.

Creating controllers for NPCs in video games is traditionally a challenging and time consuming task. While automated learning methods such as neuroevolution (i.e. evolving artificial neural networks) have shown promise in this context, they often still require carefully designed fitness functions. In this paper, we show how casual users can create controllers for Super Mario Bros. through an interactive evolutionary computation (IEC) approach, without prior domain or programming knowledge. By iteratively selecting Super Mario behaviors from a set of candidates, users are able to guide evolution towards behaviors they prefer. The result of a user test show that the participants are able to evolve controllers with very diverse behaviors, which would be difficult through automated approaches. Additionally, the user-evolved controllers perform as well as controllers evolved with a traditional fitness-based approach in terms of distance traveled. The results suggest that IEC is a viable alternative in designing diverse controllers for video games that could be extended to other games in the future.

The problem of making precise frequency-domain representation of discrete-time signals, knowledge of which is restricted to a very small number of samples, i.e. is based on the number of samples which are equal to or less then several dozen, is discussed in the paper. The proposed approach utilizes adaptive synthesis aided by evolutionary algorithm. One of the main advantages of the presented method is that no spectral leakages can appear when time-domain description is transformed to the frequency-domain. Other superiorities of the proposed algorithm over the classical techniques have been presented in [9, 10]. In this paper, details concerning the most essential problems encountered during practical applications of the evolutionary algorithm to deal with signals of physical nature are considered. It has been shown that the proposed method can work successfully if some necessary conditions are fulfilled. Examples of applying with good results the evolutionary algorithms for building the frequency domain picture of discrete time signals are demonstrated. The obtained results of the performed analysis with the use of the evolutionary technique are promising and further investigation in this field is in progress.

Objectives: This paper aims to find optimal resource schedule in Architectural level synthesis using Evolutionary Computation. Methods and Statistical Analysis: The paper is a comparative study of four Evolutionary Computations Algorithm: Differential Evolution (DE), Genetic Algorithm (GA), Evolutionary Programming (EP) and Particle Swarm Optimization (PSO). The problem area chosen is Hardware Abstraction Layer (HAL) benchmark scheduling problem using Integer Linear Programming method. Findings: The nature inspired computation algorithms should satisfy the Latency constrained Schedule, simulation results are implemented using MATLAB software. Conclusion/Application: The performance with respect to optimal resource schedule, number of generations, convergence time is compared among the four optimized algorithm are presented. The results prove Differential Evolution is better among the other optimized algorithm.

Problems involving multiple conflicting objectives arise in most real world optimization problems. Evolutionary Algorithms (EAs) have gained a wide interest and success in solving problems of this nature for two main reasons: (1) EAs allow finding several members of the Pareto optimal set in a single run of the algorithm and (2) EAs are less susceptible to the shape of the Pareto front. Thus, Multi-objective EAs (MOEAs) have often been used to solve Multi-objective Problems (MOPs). This chapter aims to summarize the efforts of various researchers algorithmic processes for MOEAs in an attempt to provide a review of the use and the evolution of the field. Hence, some basic concepts and a summary of the main MOEAs are provided. We also propose a classification of the existing MOEAs in order to encourage researchers to continue shaping the field. Furthermore, we suggest a classification of the most popular performance indicators that have been used to evaluate the performance of MOEAs.

Based on evolutionary algorithms and complex networks, dynamic complex network in evolutionary computation is briefly summarized. First, the history of evolutionary computation is discussed in general as well as its faultiness. Second, the research progress of complex network is presented. And the complex networks can remedy the defect that ignores the intermediate process. Third, the prospect and visualization steps of complex network dynamics in evolutionary computation are discussed. In brief, this paper not only makes an overview of an alternative way how evolutionary algorithms can be visualized, analyzed and controlled, but analyzes the characteristics for the complex network structure in evolutionary computation.

Interactive Evolutionary Computation (IEC) is a method for creating media contents suited to user's feelings. IEC is originally used for personal objectives. Recent IEC studies apply it to common objectives between multiple users. For obtaining fitness value of multiple users, the previous IEC studies include interesting schemes, vote, parallel distributed method, and summarization of multiple fitness values. Target of these previous IEC studies was visual contents. This study proposes a method for creating sound contents suited to multiple users' feelings based on Interactive Differential Evolution (IDE). In the proposed method, multiple users' subjective evaluation is obtained by vote for paired solution candidates: the solution candidate gathered larger number of votes retains as a solution candidate in the next generation. The efficiency of the proposed IDE was investigated through listening experiment. Target of creation was "warning sound". The target and parameters of IDE were set by referring to the author's previous study. In the experiment 1, the subjects searched better warning sounds with vote. As result, slow convergence of searching space was observed. In the experiment 2, the subjects evaluated two sign sounds created in the experiment 1. No significant increase in fitness value was observed. These poor results might come from summarization of multiple users' feeling as the selection. Based on the results, improvement method is discussed.

This paper reviews recent patents that make use of Interactive Evolutionary Computation (IEC) technology. The patents are classified into optimisation in engineering design, health management, consumer surveying, music generation and image processing. It is pointed that the coupling of multi-objective optimisation and IEC in engineering design, the use of prediction tools to reduce user fatigue, engaging multiple users in consumer product surveys are the new areas in IEC research that has shown a trend for commercialisation. The increasing number of recent patents in these areas shows that IEC continues to be a promising solution to meet humanised computational intelligence requirements today and tomorrow.

This paper emphasizes the necessity of formally bringing qualitative and quantitative criteria of ergonomic design together, and provides a novel complementary design framework with this aim. Within this framework, different design criteria are viewed as optimization objectives; and design solutions are iteratively improved through the cooperative efforts of computer and user. The framework is rooted in multi-objective optimization, genetic algorithms and interactive user evaluation. Three different algorithms based on the framework are developed, and tested with an ergonomic chair design problem. The parallel and multi-objective approaches show promising results in fitness convergence, design diversity and user satisfaction metrics.

Evolutionary computing paradigms offer robust and powerful adaptive search mechanisms for system design. This book includes thirteen chapters covering a wide area of topics in evolutionary computing and applications including: Introduction to evolutionary computing in system design; evolutionary neuro-fuzzy systems; evolution of fuzzy controllers; genetic algorithms for multi-classifier design; evolutionary grooming of traffic; evolutionary particle swarms; fuzzy logic systems using genetic algorithms; evolutionary algorithms and immune learning for neural network-based controller design; distributed problem solving using evolutionary learning; evolutionary computing within grid environment; evolutionary game theory in wireless mesh networks; hybrid multiobjective evolutionary algorithms for the sailor assignment problem; evolutionary techniques in hardware optimization. This book will be useful to researchers in intelligent systems with interest in evolutionary computing, application engineers and system designers. The book can also be used by students and lecturers as an advanced reading material for courses on evolutionary computing.

Creating controllers for NPCs in video games is traditionally a challenging and time consuming task. Automated learning methods such as neuroevolution (i.e. evolving artificial neural networks) have shown promise in this context but they often require carefully designed fitness functions to encourage the evolution of desired behaviors. In this paper, we show how casual users can create controllers for \emph{Super Mario Bros} through an interactive evolutionary computation (IEC) approach, without prior domain or programming knowledge. By iteratively selecting Super Mario behaviors from a set of candidates, users are able to guide evolution towards a variety of different behaviors, which would be difficult with an automated approach. Additionally, the user-evolved controllers perform similarly well as controllers evolved with a traditional fitness-based approach when comparing distance traveled. The results suggest that IEC is a viable alternative in designing complex controllers for video games that could be extended to other games in the future.

For some probabilistic model-based multi-objective evolutionary algorithms (MOEAs), the probability model established may not accurate enough due to the lack of effective distribution information in the early evolutionary stage. To improve this problem, a novel hybrid multi-objective optimization algorithm is proposed in this paper. Specifically, traditional crossover and mutation operation are used in the early evolutionary stage to explore the promising search areas. Moreover, the locally linear embedding (LLE) with low neighbor parameter approach is involved to enhance the exploitation ability of the proposed algorithm. In addition, an entropy-based criterion is introduced to judge whether certain regularity is presented in population's distribution. The probabilistic model-based approach will be used to reproduce new offspring if some certain regularity is presented. The hybrid two-stage multi-objective evolutionary algorithm proposed in this paper is called entropy determined hybrid two-stage multi-objective evolutionary algorithm combining locally linear embedding (EHMOEA_LLE). To verify the performance of EHMOEA_LLE, several test problems used widely are employed to conduct the comparison experiments with two state-of-the-art multi-objective evolutionary algorithms NSGA-II and RM-MEDA. The simulation results show that the entropy-based criterion is effective and the proposed algorithm is better optimization performance.

As a pivotal component in multi-objective evolutionary algorithms (MOEAs), the environmental selection determines the quality of candidate solutions to survive at each generation. In practice, different environmental selection strategies can be based on different selection criteria, where the performance metrics (or indicators) are shown to be among the most effective ones. This paper proposes an MOEA whose environmental selection is based on an enhanced inverted generational distance metric that is able to detect noncontributing solutions (termed IGD-NS), thereby considerably accelerating the convergence of the evolutionary search. Experimental results on ZDT and DTLZ test suites demonstrate the competitive performance of the proposed MOEA/IGD-NS in comparison with some representative MOEAs.

In this paper, a multi-phase strategy for dynamic resource allocation is proposed for some special optimization problems where the evolutionary process cannot be explicitly divided into two phases, under the decomposition-based multiobjective evolutionary optimization framework. Based on the evolutionary status, a switching mechanism is adopted to adaptively use either convergence or diversity information in the external archive, to guide the evolutionary search in the working population. The proposed algorithm is compared with six well-known multiobjective evolutionary algorithms on multiobjective travelling salesman problem (MOTSP). Experimental results show that our proposed algorithm performs better than other compared algorithms.

Evolutionary Algorithms have found great utility in most engineering applications, especially in control systems engineering in which tuning optimization problems may be nonlinear, multimodal and discontinuous functions of the optimization parameters. The performance of most Evolutionary Algorithms is quite sensitive to their control parameters. This paper considers the tuning problem for a variant of Evolutionary Algorithms known as Differential Evolution (DE). Differential Evolution is sensitive to loss of diversity because its mutation is a function of the hamming distance of the genotypes. Using the joint genotypic and phenotypic entropies, the paper proposes a fully adaptive Differential Evolution which requires no parameter tuning; the user is only required to set the population size. Furthermore, when tested on a standard set of benchmark objective functions the proposed algorithm shows improvements in convergence rate and the number of objective function evaluations compared to a standard, optimally tuned, and a self-adaptive differential evolution.

Evolutionary algorithms are the most studied and successful population-based algorithms for solving single- and multi-objective optimization problems. However, many studies have shown that these algorithms fail to perform well when handling many-objective (more than three objectives) problems due to the loss of selection pressure to pull the population towards the Pareto front. As a result, there has been a number of efforts towards developing evolutionary algorithms that can successfully handle many-objective optimization problems without deteriorating the effect of evolutionary operators. A reference-point based NSGA-II (NSGA-III) is one such algorithm designed to deal with many-objective problems, where the diversity of the solution is guided by a number of well-spread reference points. However, NSGA-III still has difficulty preserving elite population as new solutions are generated. In this paper, we propose an improved NSGA-III algorithm, called EliteNSGA-III to improve the diversity and accuracy of the NSGA-III algorithm. EliteNSGA-III algorithm maintains an elite population archive to preserve previously generated elite solutions that would probably be eliminated by NSGA-III's selection procedure. The proposed EliteNSGA-III algorithm is applied to II many-objective test problems with three to I5 objectives. Experimental results show that the proposed EliteNSGA-III algorithm outperforms the NSGA-III algorithm in terms of diversity and accuracy of the obtained solutions, especially for test problems with higher objectives.

Automatic Programming has long been a sub-goal of Artificial Intelligence (AI). It is feasible in limited domains. Genetic Improvement (GI) has expanded these dramatically to more than 100 000 lines of code by building on human written applications. Further scaling may need key advances in both Search Based Software Engineering (SBSE) and Evolutionary Computation (EC) research, particularly on representations, genetic operations, fitness landscapes, fitness surrogates, multi objective search and co-evolution.

This paper investigates how to use a pre-selection approach to improve the performance of the multiobjective evolutionary algorithm based on decomposition (MOEA/D). It proposes a novel MOEA/D algorithm with classification to serve this purpose. The proposed algorithm builds a classification model on the search space to filter all new generated solutions, and mainly evaluates those promising solutions for reducing real function evaluation costs during the search process. Experimental study on different test instances validates that the pre-selection approach can significantly improve the performance of a classical MOEA/D.

With the increase of dimensions and complexity of current engineering problems, parallel evolutionary algorithm which take advantage of population division and information exchange among processors has been introduced for years. However, low solution ability of each sub-group and high communication load between them are always seen as the biggest bottlenecks which hinder parallel evolutionary algorithm to be more efficient. To overcome this two problems, a multi operators-based partial connected parallel evolutionary algorithm, i.e. MO-PCPEA is proposed. By combining multiple evolutionary operators, an adaptive strategy for operator configuration inside each parallel group is designed to ensure the searching ability of the algorithm for wider range of problems. More importantly, a partial connection topology is proposed to guide the periodic communication between each group. Computational results in two typical permutation combinatorial optimization benchmarks and one practical case study demonstrate that MO-PCPEA is highly competitive compared with most tailored serial and parallel evolutionary algorithms in terms of not only searching time, but also solution quality.

We use an evolutionary algorithm in which we change the fitness function periodically to model the fact that objectives can change during creative problem solving. We performed an experiment to observe the behavior of the evolutionary algorithm regarding its response to these changes and its ability to successfully generate solutions for its creative task despite the changes. An analysis of the results of this experiment sheds some light into the conditions under which the evolutionary algorithm can respond with varying degrees of robustness to the changes.

It is not usual practice in the evolutionary algorithms area to benchmark different operations in order to choose the best language for a single or multilanguage implementation. Researchers rely instead on common practice or frameworks using mainstream languages. That is why it is usual practice to choose compiled languages (namely Java or C/C++) when implementing evolutionary algorithms, without considering other languages or rejecting them outright on the basis of performance. Since there is a myriad of languages nowadays, we considered it an interesting challenge to measure their speed when performing frequent operations in evolutionary algorithms. In this paper we have tested three basic evolutionary algorithm operations over binary chromosomes: bitflip mutation, crossover and the OneMax fitness function. As a performance measure, the speed for both popular and not so popular computer languages have been used. In general, the results confirm that compiled languages scale and perform better, but also in some cases have a behaviour that is independent of the size of the chromosome. Additionally, results show that other languages, such as Go (compiled) or Python (interpreted) are fast enough for most purposes. Besides, these experiments show which of these operations are, in fact, the best for choosing an implementation language based on its performance.

During the past decade, continuum topology optimization became an important industrial tool for the conceptual design of mechanical structures. The field of evolutionary computation provides suitable stochastic optimization algorithms for problems involving strong non-linearities or black-box simulations, for which existing gradient-based methods are not feasible. Due to the high design freedom of the phenotypic space, the encoding of the structural design is a critical aspect when applying evolutionary algorithms. Currently, the encoding approaches are scattered throughout different literature fields. This paper gathers them and provides a contemporary overview on the various structural representations used in conjunction with evolutionary computation for topology optimization. The important influence of the representation on the scalability of the approaches motivates the proposed categorization in three groups: Grid, Geometric and Indirect Representations. The existing representations are described and discussed on a conceptual level and chances and challenges are outlined.

This study aims to propose an Interactive Evolutionary Computation that creates sound contents for multiple users. Sound contents including music pieces and sign sounds are often used in our daily life for creating common atmosphere and transmitting a certain message to everyone. The proposed method is based on parallel distributed Interactive Genetic Algorithm (IGA), which creates visual media contents commonly suited to multiple users. In this method, each of the users proceeds general IGA process by evaluating solution candidates of the IGA. As a special property of this method, in some generations, solution candidates are exchanged between the users. With the exchange, each of the users is affected by other users' feelings. It is expected that good solution evaluated as best solution by all of the users is obtained. Based on the concept of the proposed method, we constructed an IGA system for fundamentally investigating efficiencies of the proposed method. Aim of the IGA system is to create a short music melody commonly affording bright image. Key of the notes was treated as gene of IGA. Music chord progression called Canon chord is attached to the melody when it is presented to the subjects. 10 persons participated in the experiment as subjects. In the IGA system, two users participated in the evaluation process simultaneously. Experimental results showed almost continuous increase in mean and maximum fitness values between the subjects. To clarify the efficiency of the exchange of the proposed method, further study with comparing experiment including conditions with/without the exchange is needed.

Interactive evolutionary computation (IEC) is a powerful human-machine optimisation procedure for evolving solutions to complex design problems. In this paper we introduce the novel concept of Tangible Interactive EvolutionaryComputation (TIEC), leveraging the benefits of tangible user interfaces to enhance the IEC process and experience to alleviate user fatigue. An example TIEC system is presented and used to evolve biomorph images, with a recreationof the canonical IEC application: The Blind Watchmaker program. An expanded version of the system is also used to design visual states for an atomic visualisation platform called danceroom Spectroscopy, that allows participantsto explore quantum phenomena through movement and dance. Initial findings from an informal observational test are presented along with the results from a pilot study to evaluate the potential for TIEC.

We propose an interactive multiobjective evolutionary algorithm that attempts to discover the most preferred part of the Pareto-optimal set. Preference information is elicited by asking the user to compare some solutions pairwise. This information is then used to curb the set of compatible user’s value functions, and the multiobjective evolutionary algorithm is run to simultaneously search for all solutions that could potentially be the most preferred. Compared to previous similar approaches, we implement a much more efficient way of determining potentially preferred solutions, that is, solutions that are best for at least one value function compatible with the preference information provided by the decision maker. For the first time in the context of evolutionary computation, we apply the Choquet integral as a user’s preference model, allowing us to capture interactions between objectives. As there is a trade-off between the flexibility of the value function model and the complexity of learning a faithful model of user’s preferences, we propose to start the interactive process with a simple linear model but then to switch to the Choquet integral as soon as the preference information can no longer be represented using the linear model. An experimental analysis demonstrates the effectiveness of the approach.