Search

An efficient variant of the recent sea horse optimizer (SHO) called SHO-OBL is presented, which incorporates the opposition-based learning (OBL) approach into the predation behavior of SHO and uses the greedy selection (GS) technique at the end of each optimization cycle. This enhancement was created to avoid being trapped by local optima and to improve the quality and variety of solutions obtained. However, the SHO can occasionally be vulnerable to stagnation in local optima, which is a problem of concern given the low diversity of sea horses. In this paper, an SHO-OBL is suggested for the tackling of genuine and global optimization systems. To investigate the validity of the suggested SHO-OBL, it is compared with nine robust optimizers, including differential evolution (DE), grey wolf optimizer (GWO), moth-flame optimization algorithm (MFO), sine cosine algorithm (SCA), fitness dependent optimizer (FDO), Harris hawks optimization (HHO), chimp optimization algorithm (ChOA), Fox optimizer (FOX), and the basic SHO in ten unconstrained test routines belonging to the IEEE congress on evolutionary computation 2020 (CEC'20). Furthermore, three different design engineering issues, including the welded beam, the tension/compression spring, and the pressure vessel, are solved using the proposed SHO-OBL to test its applicability. In addition, one of the most successful approaches to data transmission in a wireless sensor network that uses little energy is clustering. In this paper, SHO-OBL is suggested to assist in the process of choosing the optimal power-aware cluster heads based on a predefined objective function that takes into account the residual power of the node, as well as the sum of the powers of surrounding nodes. Similarly, the performance of SHO-OBL is compared to that of its competitors. Thorough simulations demonstrate that the suggested SHO-OBL algorithm outperforms in terms of residual power, network lifespan, and extended stability duration. [ABSTRACT FROM AUTHOR]

As potent approaches for addressing computationally expensive optimization problems, surrogate-assisted evolutionary algorithms (SAEAs) have garnered increasing attention. Prevailing endeavors in evolutionary computation predominantly concentrate on expensive continuous optimization problems, with a notable scarcity of investigations directed toward expensive combinatorial optimization problems (ECOPs). Nevertheless, numerous ECOPs persist in practical applications. The widespread prevalence of such problems starkly contrasts the limited development of relevant research. Motivated by this disparity, this paper conducts a comprehensive survey on SAEAs tailored to address ECOPs. This survey comprises two primary segments. The first segment synthesizes prevalent global, local, hybrid, and learning search strategies, elucidating their respective strengths and weaknesses. Subsequently, the second segment furnishes an overview of surrogate-based evaluation technologies, delving into three pivotal facets: model selection, construction, and management. The paper also discusses several potential future directions for SAEAs with a focus towards expensive combinatorial optimization. [ABSTRACT FROM AUTHOR]

Surrogate-Assisted Evolutionary Optimisation algorithms are a specialized brand of optimisers developed to undertake problems with computationally expensive fitness functions. These algorithms work by building a cheap approximation or model of the exact function and using it in the evaluation of solutions within the optimisation process. This use of modelling techniques within optimisation, while offers a practical reduction in function calls, brings along with it some additional questions. This paper starts with a description of the key elements of surrogate-assisted evolutionary optimisation algorithms as they are outlined throughout the literature, and then, proceeds to rearrange these elements using a novel blueprint of the field. The proposed blueprint can be used to represent any surrogate-assisted evolutionary algorithm in a way that illustrates its principles and components in a non-vague manner. In addition, a survey of the most prominent works in the field is conducted using this novel blueprint. Finally, a number of challenges and perspectives are listed before the paper is concluded. [ABSTRACT FROM AUTHOR]

This paper presents an optimal active power dispatch (OAPD) problem that, unlike common economic dispatch problems, precludes unwanted mismatches on realistic power systems. The OAPD is formulated by considering the unified power flow controller (UPFC), a versatile device from the flexible AC transmission systems. However, the resultant turns into a highly nonlinear and complex optimization problem, which requires a powerful evolutionary algorithm to determine the optimal solutions. Toward this end, this paper explores the use of comprehensive learning particle swarm optimization and differential evolution as a hybrid configuration in a fuzzy framework, called hybrid fuzzy-based improved comprehensive learning particle swarm optimization-differential evolution, to address the proposed problem. To demonstrate the performance of the proposed algorithm, a set of benchmark problems, including real-world constrained optimization problems as well as a profound analysis of Schwefel problem 2.26 are provided. Moreover, to authenticate its effectiveness in solving power and energy-related problems with quite a few decision variables, four different power systems, 3-unit, 6-unit IEEE 30-bus, 10-unit, and 40-unit systems, are implemented. The IEEE 30-bus system is opted for profoundly analyzing the performance of the proposed algorithm in handling the optimal power dispatch problem considering security constraints and UPFC device, where an enhancement, at least $74,000 saving in a 365-day horizon, in total generation cost is obtained. Simulation results also validate that evolutionary algorithms need to be improved/hybridized to achieve better equilibrium between exploration and exploitation processes in a timely manner while solving power and energy-related problems. [ABSTRACT FROM AUTHOR]

Understanding of optimization algorithm's behavior is a vital part that is needed for quality progress in the field of stochastic optimization algorithms. To be able to overcome this deficiency, we need to establish new standards for understanding optimization algorithm behavior, which will provide understanding of the working principles behind the stochastic optimization algorithms. In their paper I Evolutionary algorithms and submodular functions: benefits of heavy-tailed mutations i , Quinzan et al. develop suitable Evolutionary Algorithms (EAs) to tackle submodular optimization problems. The paper I Improving convergence in swarm algorithms by controlling range of random movement i by Chaudhary and Banati studies the applicability of the IS technique over different swarm algorithms employing different random distributions. [Extracted from the article]

In recent decades, Estimation of Distribution Algorithms (EDAs) have gained much popularity in the evolutionary computation community for solving optimization problems. Characterized by the use of probabilistic models to represent the solutions and the interactions between the variables of the problem, EDAs can be applied to either discrete, continuous or mixed domain problems. Due to this robustness, these algorithms have been used to solve a diverse set of real-world and academic optimization problems. However, a straightforward application is only limited to a few cases, and for the general case, an efficient application requires intuition from the problem as well as notable understanding in probabilistic modeling. In this paper, we provide a roadmap for solving optimization problems via EDAs. It is not the aim of the paper to provide a thorough review of EDAs, but to present a guide for those practitioners interested in using the potential of EDAs when solving optimization problems. In order to present a roadmap which is as useful as possible, we address the key aspects involved in the design and application of EDAs, in a sequence of stages: (1) the choice of the codification, (2) the choice of the probability model, (3) strategies to incorporate knowledge about the problem to the model, and (4) balancing the diversification-intensification behavior of the EDA. At each stage, first, the contents are presented together with common practices and advice to follow. Then, an illustration is given with an example which shows different alternatives. In addition to the roadmap, the paper presents current open challenges when developing EDAs, and revises paths for future research advances in the context of EDAs. [ABSTRACT FROM AUTHOR]

Concept drift (CD) in data streams can significantly impact the performance and stability of data stream classification algorithms, diminishing the generalization capabilities of integrated learning models. This paper addresses CD issues in dichotomous data streams by introducing a novel modeling approach that leverages evolutionary computation techniques. The method entails grouping base learners based on their performance within a sliding window and then evolving the base learning periods using evolutionary techniques. Furthermore, the concept of “gene flow” is introduced to enhance diversity among base learners and improve CD prediction performance. Experimental results on real and artificial datasets demonstrate the superior comprehensive performance of the proposed method. Specifically, the BCDECA algorithm outperforms other similar methods, excelling in accuracy, diversity, convergence rate, and robustness on a range of datasets.Article Highlights: Addresses CD issues in dichotomous data streams by introducing a novel modeling approach that leverages evolutionary computation techniques. Grouping base learners based on their performance within a sliding window and then evolving the base learning periods using evolutionary techniques Introduce the concept of "gene flow" [ABSTRACT FROM AUTHOR]

In contemporary particle swarm optimization (PSO) algorithms, to efficiently explore global optimum solutions, it is common practice to set the inertia weight to monotonically decrease over time for stability, while allowing the two acceleration coefficients, representing cognitive and social factors, to adopt decreasing or increasing functions over time, including random variations. However, there has been little discussion on a unified design approach for these time-varying acceleration coefficients. This paper presents a unified methodology for designing monotonic decreasing or increasing functions to construct nonlinear time-varying inertia weight and two acceleration coefficients in PSO, along with a control strategy for exploring global optimum solutions. We first construct time-varying coefficients by linearly amplifying well-posed monotonic functions that decrease or increase over normalized time. Here, well-posed functions ensure satisfaction of specified conditions at the initial and terminal points of the search process. However, many of the functions employed thus far only satisfy well-posedness at either the initial or terminal points of the search time, prompting the proposal of a method to adjust them to virtually meet specified initial or terminal points. Furthermore, we propose a crossing strategy where the developed cognitive and social acceleration coefficients intersect within the search time interval, effectively guiding the search process by pre-determining crossing values and times. The performance of our Nonlinear Crossing Strategy-based Particle Swarm Optimization (NCS-PSO) is evaluated using the CEC2014 (Congress on Evolutionary Computation in 2014) benchmark functions. Through comprehensive numerical comparisons and statistical analyses, we demonstrate the superiority of our approach over seven conventional algorithms. Additionally, we validate our approach, particularly in a drone navigation scenario, through an example of optimal 3D path planning. These contributions advance the field of PSO optimization techniques, providing a robust approach to addressing complex optimization problems. [ABSTRACT FROM AUTHOR]

Distribution system service restoration is a process of restoring power outages through changing the on/off status of sectionalizing and tie switches within the whole power outage in a distribution system altered accordingly with its topological structure. Multi-agent Systems (MASs) can be applied for distribution system service restoration, an engineering optimization problem that can be addressed through metaheuristics, of a distribution system because service restoration planning can be made in parallel among intelligent software agents embedded inside sectionalizing and tie switches and feeders to form a distributed multi-agent environment such that the time of power restoration can be reduced. Service restoration planning can be built upon an MAS. This paper presents a three-tiered MAS-based Multi-Population Parallel Genetic Algorithm (MPPGA) and demonstrates its preliminary implementation to achieve service restoration planning for smart distribution system service restoration, which serves as a meta service restoration planner to perform efficient and fast switching operation for smart distribution system service restoration. The presented three-tiered MAS-based MPPGA is implemented, in Java programming language, on a Java Agent DEvelopment (JADE for short) platform, where in evolutionary computation (1) multiple populations are coevolved and (2) selection, crossover, and mutation operations for genetic search are parallelized. The effectiveness/feasibility of the presented three-tiered MAS-based MPPGA is demonstrated by a simulated distribution system and reported with simulation results. [ABSTRACT FROM AUTHOR]

This paper introduces a novel and complete framework for solving different Internet of Things (IoT) applications, which explores eXplainable AI (XAI), deep learning, and evolutionary computation. The IoT data coming from different sensors is first converted into an image database using the Gamian angular field. The images are trained using VGG16, where XAI technology and hyper-parameter optimization are introduced. Thus, analyzing the impact of the different input values in the output and understanding the different weights of a deep learning model used in the learning process helps us to increase interpretation of the overall process of IoT systems. Extensive testing was conducted to demonstrate the performance of our developed model on two separate IoT datasets. Results show the efficiency of the proposed approach compared to the baseline approaches in terms of both runtime and accuracy. [ABSTRACT FROM AUTHOR]

Particle swarm optimization (PSO) is a population-based swarm intelligence algorithm that falls under the category of nature-inspired algorithms and is similar to evolutionary computing in various ways. Rather than the survival of the fittest, the PSO is driven by a representation of a social psychological model inspired by the group behaviors of birds and other social species. The particle's position is modified in PSO based on its position as well as velocity, while in quantum mechanics, the trajectory idea is absurd; however, the uncertainty principle suggests that a particle's position, as well as velocity, cannot be determined simultaneously. As a result, an advanced version of the quantum mechanics-based PSO method is proposed. The study in this paper is focused on an investigation of a new quantum-behaved PSO (QPSO) method called Gaussian quantum-behaved particle swarm optimization (GQPSO), which uses a mutation operator with a Gaussian distribution and is inspired by classical PSO methods and quantum mechanics concepts. In GQPSO, inadequate control parameter tuning results in poor solutions. To better understand the effect of different control parameters and their implications on GQPSO results, this paper used a full parametric sensitivity analysis on five different problems (the Design of a pressure vessel, Tension/Spring Compression, Rastrigin function, Ackley function, and Constrained Box Volume Problem). By adjusting each parameter one at a time, different optimization problems were used to investigate GQPSO. As a result, to allow particles to change their earliest best solution based on viability, a constraint-handling mechanism was developed. The optimal parameter set for GQPSO is provided based on the analysis of the results. With the help of the proposed optimal parameter set (contraction–expansion coefficient values as (1 = 1.6,2 = 1.3), swarm size as '350', and number of Iterations as '500'), GQPSO returned an optimized solution for Rastrigin and Ackley functions. It also performed better in the case of the design of a pressure vessel and tension/spring compression problems in comparison to the existing solution available in related literature. As per the findings of the sensitivity analysis, GQPSO is the most sensitive to the contraction-expansion coefficient in comparison to the maximum number of iterations (itermax) and swarm size ('n'). [ABSTRACT FROM AUTHOR]

'On the Mapping of Genotype to Phenotype in Evolutionary Algorithms,' by Peter A. Whigham, Grant Dick, and James Maclaurin, is a welcome reminder that evolutionary computation practitioners should be wary of taking their biological analogies too seriously. But more importantly, it is a reminder to practitioners to consider carefully their representations and operators, rather than blindly implementing a biological analogy without sufficient attention to the constraints of software engineering. 'It works in biology, so it should work in EC' is poor, even lazy, software design. The primary contribution of this paper is exactly what a commentary should be: to (re)ignite discussions about how biological inspiration should inform EC practice. [ABSTRACT FROM AUTHOR]

This paper is the guest editors message to the Special Issue on Parallel Evolutionary Algorithms on Grid and Cloud. Although this special issue includes extended version of selected papers presented at the last three EvoPar Conferences, the reviewing and selection process was made under a strict peer reviewing process and after a call for papers open for submission from out of the conference. We briefly introduce the accepted papers in this message. [ABSTRACT FROM AUTHOR]

Much of what we know, we know thanks to our interactions with others. There is a variety of ways in which we learn from others. We sometimes simply adopt the viewpoints of those we regard as experts, but we also sometimes change our viewpoints in more subtle ways based on the viewpoints of people we regard as our peers. Both forms of social learning have been receiving increasing attention. However, studies investigating how best to combine them, and how to combine the two with individual forms of learning, are still few and far between. This paper looks at ways to integrate various forms of social learning with learning at an individual level within a broadly Bayesian framework. Using agent-based models, we compare the different ways in terms of accuracy of belief states as well as in terms of evolutionary viability. The outcomes of our simulations suggest that agents are best off spending most of their time engaging in social learning, reserving only a limited amount of time for individual learning. [ABSTRACT FROM AUTHOR]

Cluster labeling is a problem of finding optimal clusters by maximizing the similarity within clusters. Generally, classical optimization methods are used for clustering, which depends upon initial estimates. Meta-heuristic optimization techniques came into existence to avoid this shortcoming as they are not problem-specific and do not dependent on the initial estimates. Optimal threshold selection is a widely known problem for image clustering that optimizes the entropy of image clusters. But for region-wise clustering, the sheer amount of literature is available that uses evolutionary techniques. Sub-optimal cluster selection and slow convergence are the problems that arise in meta-heuristics approaches. In this paper, we optimize the region-wise cluster labels for an efficient objective function. In particular, we consider the cluster label optimization problems in tumour-based magnetic resonance (MR) images. In order to solve the problem, a meta-heuristic approaches is used. The stable random walk is incorporated with the BAT algorithm to avoid the potential endangerment of local minima trapping. Further, the objective improvement is carried out by hybridizing the intra-cluster and inter-cluster-based objectives. To assess the efficiency of the proposed approach, we evaluated the proposed method against the recently proposed techniques. The evolutionary technique is well performed in various aspects of cluster label evaluation and paves new ideas for future research lines. [ABSTRACT FROM AUTHOR]

This review aims to exploit a study on different benchmark test functions used to evaluate the performance of Meta-Heuristic (MH) optimization techniques. The performance of the MH optimization techniques is evaluated with the different sets of mathematical benchmark test functions and various real-world engineering design problems. These benchmark test functions can help to identify the strengths and weaknesses of newly proposed MH optimization techniques. This review paper presents 215 mathematical test functions, including mathematical equations, characteristics, search space and global minima of the objective function and 57 real-world engineering design problems, including mathematical equations, constraints, and boundary conditions of the objective functions carried out from the literature. The MATLAB code references for mathematical benchmark test functions and real-world design problems, including the Congress of Evolutionary Computation (CEC) and Genetic and Evolutionary Computation Conference (GECCO) test suite, are presented in this paper. Also, the winners of CEC are highlighted with their reference papers. This paper also comprehensively reviews the literature related to benchmark test functions and real-world engineering design challenges using a bibliometric approach. This bibliometric analysis aims to analyze the number of publications, prolific authors, academic institutions, and country contributions to assess the field's growth and development. This paper will inspire researchers to innovate effective approaches for handling inequality and equality constraints. [ABSTRACT FROM AUTHOR]

One of the first and easy to use techniques for proving run time bounds for evolutionary algorithms is the so-called method of fitness levels by Wegener. It uses a partition of the search space into a sequence of levels which are traversed by the algorithm in increasing order, possibly skipping levels. An easy, but often strong upper bound for the run time can then be derived by adding the reciprocals of the probabilities to leave the levels (or upper bounds for these). Unfortunately, a similarly effective method for proving lower bounds has not yet been established. The strongest such method, proposed by Sudholt (2013), requires a careful choice of the viscosity parameters γ i , j , 0 ≤ i < j ≤ n . In this paper we present two new variants of the method, one for upper and one for lower bounds. Besides the level leaving probabilities, they only rely on the probabilities that levels are visited at all. We show that these can be computed or estimated without greater difficulties and apply our method to reprove the following known results in an easy and natural way. (i) The precise run time of the (1+1) EA on LeadingOnes. (ii) A lower bound for the run time of the (1+1) EA on OneMax, tight apart from an O(n) term. (iii) A lower bound for the run time of the (1+1) EA on long k-paths (which differs slightly from the previous result due to a small error in the latter). We also prove a tighter lower bound for the run time of the (1+1) EA on jump functions by showing that, regardless of the jump size, only with probability O (2 - n) the algorithm can avoid to jump over the valley of low fitness. [ABSTRACT FROM AUTHOR]

Supercritical airfoils are critical components in the design of commercial wide-body aircraft wings due to their ability to enhance aerodynamic performance in transonic flow regimes. However, traditional design methods for supercritical airfoils can be time-consuming and require significant manual effort, not to mention the high cost associated with computational fluid dynamics analysis. To address these challenges, this paper introduces a highly automated approach for supercritical airfoil design, called Evolutionary Generative Design (EvoGD). The EvoGD approach is based on the framework of Evolutionary Computation and employs a series of sophisticated data-driven generative models incorporated with physical information to iteratively refine initial airfoil shapes, resulting in improved aerodynamic performances and reduced constraint violations. Moreover, to speed up the evaluation of the generated airfoils, a series of accurate and efficient data-driven predictors are utilized. The efficacy of the EvoGD approach was demonstrated through experiments on a dataset of 501 supercritical airfoils, including one baseline design and 500 randomly perturbed airfoils. On average, the generated airfoils showed improved performance in terms of buffet lift coefficient, cruise lift-to-drag ratio, and thickness by 5%, 4%, and 1%, respectively. The best generated airfoil outperformed the baseline design in terms of critical buffet lift coefficient and cruise lift-to-drag ratio by 7.1% and 6.4%, respectively. The entire design process was completed in less than an hour on a personal computer, highlighting the high efficiency and scalability of the EvoGD approach. [ABSTRACT FROM AUTHOR]

The privacy-preserving data publishing (PPDP) problem has gained substantial attention from research communities, industries, and governments due to the increasing requirements for data publishing and concerns about data privacy. However, achieving a balance between preserving privacy and maintaining data quality remains a challenging task in PPDP. This paper presents an information-driven distributed genetic algorithm (ID-DGA) that aims to achieve optimal anonymization through attribute generalization and record suppression. The proposed algorithm incorporates various components, including an information-driven crossover operator, an information-driven mutation operator, an information-driven improvement operator, and a two-dimensional selection operator. Furthermore, a distributed population model is utilized to improve population diversity while reducing the running time. Experimental results confirm the superiority of ID-DGA in terms of solution accuracy, convergence speed, and the effectiveness of all the proposed components. [ABSTRACT FROM AUTHOR]

Evolutionary multi-objective multi-task optimization is an emerging paradigm for solving multi-objective multi-task optimization problem (MO-MTOP) using evolutionary computation. However, most existing methods tend to directly treat the multiple multi-objective tasks as different problems and optimize them by different populations, which face the difficulty in designing good knowledge transferring strategy among the tasks/populations. Different from existing methods that suffer from the difficult knowledge transfer, this paper proposes to treat the MO-MTOP as a multi-objective multi-criteria optimization problem (MO-MCOP), so that the knowledge of all the tasks can be inherited in a same population to be fully utilized for solving the MO-MTOP more efficiently. To be specific, the fitness evaluation function of each task in the MO-MTOP is treated as an evaluation criterion in the corresponding MO-MCOP, and therefore, the MO-MCOP has multiple relevant evaluation criteria to help the individual selection and evolution in different evolutionary stages. Furthermore, a probability-based criterion selection strategy and an adaptive parameter learning method are also proposed to better select the fitness evaluation function as the criterion. By doing so, the algorithm can use suitable evaluation criteria from different tasks at different evolutionary stages to guide the individual selection and population evolution, so as to find out the Pareto optimal solutions of all tasks. By integrating the above, this paper develops a multi-objective multi-criteria evolutionary algorithm framework for solving MO-MTOP. To investigate the proposed algorithm, extensive experiments are conducted on widely used MO-MTOPs to compare with some state-of-the-art and well-performing algorithms, which have verified the great effectiveness and efficiency of the proposed algorithm. Therefore, treating MO-MTOP as MO-MCOP is a potential and promising direction for solving MO-MTOP. [ABSTRACT FROM AUTHOR]

Differential evolutionary (DE) algorithm is one of the most frequently used evolutionary computation method for the solution of non-differentiable, complex and discontinuous real value numerical problems. The analytical structure of the mutation and crossover operators used by DE and the initial values of the parameters of the relevant operators affect the problem-solving ability of DE. Unfortunately, there is no analytical method for selecting and initializing the best artificial genetic operators that DE can use to solve a problem. Therefore, there is a need to develop new evolutionary search methods that are parameter-free and insensitive to the artificial genetic operators they use. In this paper, the Bernstein–Levy differential evolution (BDE) algorithm, which has a unique elitist-mutation operator and a Bernstein polynomials-based stochastic parameter-free crossover operator, is introduced. The numerical problem-solving success of BDE is statistically evaluated by using 30 benchmark problems of CEC2014 in the numerical experiments presented. BDE's success in solving the related benchmark problems is statistically compared with six state-of-the-art comparison algorithms. In this paper, three real-world optimization problems are also solved by using the proposed algorithm, BDE. According to statistics generated from the experimental results, BDE is statistically better than comparison methods in solving the related real-world problems. [ABSTRACT FROM AUTHOR]

Language is a complex evolving system and it is not a trivial task to model the dynamics of processes occurring during its evolution. Therefore, modeling language evolution has attracted the interest of several researchers giving rise to a lot of models in the literature of the last millennium. This work reviews the literature devoted to computationally represent the evolution of human language through formal models and provides an analysis of the bibliographic production and scientific impact of the surveyed language evolution models to give some conclusions about current trends and future perspectives of this research field. The survey provides also an overview of the strategies for validating and comparing the different language evolution models and how these techniques have been applied by the surveyed models. [ABSTRACT FROM AUTHOR]

It is well recognized that human societies and their problem-solving capabilities have evolved much faster than biological evolution. The inspiration from human behaviors, knowledge exchange, and transformation has given rise to a new evolutionary computation paradigm. Multiple research endeavors have been reported in the literature inspired by the diverse aspects of human societies with corresponding terminologies to describe the algorithm. These endeavors have resulted in piles of algorithms, worded differently but with more or less similar underlying mechanisms causing immense confusion for a new reader. This paper presents a generalized framework for these socio-inspired evolutionary algorithms (SIEAs) or socio-inspired meta-heuristic algorithms. A survey of various SIEAs is provided to highlight the working of these algorithms on a common framework, their variations and improved versions proposed in the literature, and their applications in various fields of search and optimization. The algorithmic description and the comparison of each SIEA with the general framework enable a clearer understanding of the similarities and differences between these methodologies. Efforts have been made to provide an extensive list of references with due context. This paper could become an excellent reference as a starting point for anyone interested in this fascinating field of research. [ABSTRACT FROM AUTHOR]

Feature selection aims to find a best feature subset from all feature sets of a given dataset, which represents the whole feature space to reduce redundancy and improve classification accuracy. The evolutionary computation algorithm is often applied to feature selection, but there exists low efficiency in the search process. With the increase of the number of features, solving the feature selection problem become more and more difficult. Existing evolutionary algorithms have many defects, such as slow convergence speed, low convergence accuracy and easy to fall into local optimum. Therefore, the research of more effective evolutionary algorithms has important theoretical significance and application value. Binary Particle Swarm Optimization (BPSO) is a kind of evolutionary computation algorithm and has a good performance in feature selection problems. It uses transfer function to convert the continuous search space to the binary one. Transfer function plays an important role in BPSO. So this paper proposes an improved BPSO by combining V-shaped and U-shaped transfer function, and introduces a new learning strategy and a local search strategy based on adaptive mutation. The improved BPSO enhances its optimization ability in feature selection problem. The experimental results show that the improved BPSO has better dimension reduction ability and classification performance than other algorithms. [ABSTRACT FROM AUTHOR]

In recent years, swarm intelligence algorithms have received extensive attention and research. Swarm intelligence algorithms are a biological heuristic method, which is widely used in solving optimization problems. The traditional swarm intelligence algorithms provide new ideas and new ways to solve some practical problems, and they have made positive progress in fields such as combinatorial optimization, task scheduling, process control, engineering prediction, and image processing. In particular, the sparrow search algorithm is a new type of group intelligence optimization algorithm inspired by the group foraging behavior to perform local and global search by imitating the foraging and anti-predation behavior of sparrows. In view of the shortcomings of the original sparrow search algorithm, such as its easy fall into local optimum, slow convergence speed, and low convergence accuracy, scholars at home and abroad have improved the sparrow search algorithm and have made practical applications in various fields. Firstly, this paper introduces the basic principle of sparrow search algorithm, analyzes the factors affecting the performance of the algorithm, further proposes the improvement strategy of the algorithm, and performs function test comparison and performance analysis with particle swarm optimization algorithm, monarch butterfly algorithm, colony spider algorithm, and pigeon swarm optimization algorithm. After that, the application and development of the sparrow search algorithm in power grid load forecasting, image processing, path tracking, wireless sensor network routing performance optimization, wireless location, and fault diagnosis are described. Finally, combined with the performance characteristics and application direction of the sparrow search algorithm, the future research and development direction of the sparrow search algorithm is prospected. [ABSTRACT FROM AUTHOR]

Complex system optimization is an emerging research topic in the field of evolutionary computation, whose goal is to handle complex systems with multiple coupled subsystems, each including multiple objectives and multiple constraints in real-world applications. This paper proposes a multi-system genetic algorithm (MSGA), stemming from implicit parallelism in population-based search algorithms, to solve multiple coupled subsystems simultaneously in a complex system. The proposed MSGA is composed of within-subsystem evolution and cross-subsystem migration operators. The objective of the former is to optimize each subsystem by appropriate search strategies, and the objective of the latter is to exchange information between multiple subsystems by migration, which is based on the similarity probability of objectives and constraints, and the intersection probability of solutions in different subsystems. During migration across subsystems, three statistical approaches of measuring similarity and three metrics of solution intersection in information theory are used to calculate these probabilities. Performance is tested on a set of multi-subsystem benchmark functions, and the simulation results show that cross-subsystem migration plays the key role for the performance of MSGA. Furthermore, the proposed MSGA is compared with other competitive algorithms, and results show that it is a promising multi-system optimization algorithm. In summary, the contribution of this paper is the introduction of multi-system optimization to the EA community. [ABSTRACT FROM AUTHOR]

An introduction is presented in which the author discusses various topics including the advances in evolutionary computation, fuzzy systems and neural networks, genetic algorithm for solving the many-objective optimization problem and methods for accomplishing annotation tasks using crowdsourcing.

The main goal of this paper is to develop a new class of sixth- and fourth-order implicit Runge–Kutta methods to treat linear and nonlinear initial value ordinary differential equations (ODEs) in applied science and engineering. In this regard, a completely unconventional approach is taken to derive the new formulations. They are derived through a computational approach without involving in the rigorous theory of order conditions. The new formulation has two distinctive parts, namely integration and interpolation. In the first part, we introduce a form of multi-stage single-step numerical integrator with unknown weights. These weights are determined by four simple interconnectivity rules that relate them to minimize the error of the integrator. Some of these rules are based on our expertise gathered from the available prominent quadratures. However, the most important one, the so-called fundamental weighting rule (FWR), is obtained from evolutionary and statistical computations. The second part of this research focuses on developing efficient tools for evaluating the internal stages of the integrator. Accordingly, a series of strong Hermite interpolators has been extended to approximate the solution values at the internal stages. They effectively collaborate with the integrator in several numerical algorithms, the so-called α I I - (q + r) P algorithms, to solve applied ODEs. Development of the integrator, its weighting rules, and the interpolators constitutes the central contribution of this research. Numerical studies demonstrate that the presented algorithms exhibit a high level of accuracy when approximating high-frequency problems as well as long-term solutions of linear and nonlinear ODEs. [ABSTRACT FROM AUTHOR]

In recent years, evolutionary algorithms have shown great advantages in the field of feature selection because of their simplicity and potential global search capability. However, most of the existing feature selection algorithms based on evolutionary computation are wrapper methods, which are computationally expensive, especially for high-dimensional biomedical data. To significantly reduce the computational cost, it is essential to study an effective evaluation method. In this paper, a two-stage improved gray wolf optimization (IGWO) algorithm for feature selection on high-dimensional data is proposed. In the first stage, a multilayer perceptron (MLP) network with group lasso regularization terms is first trained to construct an integer optimization problem using the proposed algorithm for pre-selection of features and optimization of the hidden layer structure. The dataset is compressed using the feature subset obtained in the first stage. In the second stage, a multilayer perceptron network with group lasso regularization terms is retrained using the compressed dataset, and the proposed algorithm is employed to construct the discrete optimization problem for feature selection. Meanwhile, a rapid evaluation strategy is constructed to mitigate the evaluation cost and improve the evaluation efficiency in the feature selection process. The effectiveness of the algorithm was analyzed on ten gene expression datasets. The experimental results show that the proposed algorithm not only removes almost more than 95.7% of the features in all datasets, but also has better classification accuracy on the test set. In addition, the advantages of the proposed algorithm in terms of time consumption, classification accuracy and feature subset size become more and more prominent as the dimensionality of the feature selection problem increases. This indicates that the proposed algorithm is particularly suitable for solving high-dimensional feature selection problems. [ABSTRACT FROM AUTHOR]

Back propagation (BP) is widely used for parameter search of fully-connected layers in many neural networks. Although BP has the potential of quickly converging to a solution, due to its gradient-based nature, it tends to fall into a local optimum. Metaheuristics such as evolutionary computation (EC) techniques, as gradient-free methods, may have excellent global search capability due to their stochastic nature. However, these techniques tend to perform worse than BP in terms of convergence speed. In this paper, a hybrid gradient descent search algorithm (HGDSA) is proposed for training the parameters in fully-connected neural networks. HGDSA initially searches the space extensively by means of an ensemble of gradient descent strategies in the early stage and then uses BP as an exploitative local search operator. Moreover, a self-adaptive method which selects strategies and updates the learning rates of strategies has been designed and embedded in the global search operators to prevent stagnation in local optima. To verify the effectiveness of HGDSA, experiments were performed on eleven classification datasets. Experimental results demonstrate that the proposed HGDSA possesses both powerful global and local search abilities. Furthermore, the proposed approach appears to be promising also on high-dimensional datasets. [ABSTRACT FROM AUTHOR]

Evolutionary computing algorithms are computational intelligent systems that are used in a wide range of research applications, primarily for optimization. In this paper, an artificial neural network (ANN), a machine learning technique, is used to classify the data. The weights associated with each neuron and the architecture of the neural network always bias the output of the network model. With prior knowledge or trial and error techniques, different metrics or objectives can be used to optimise these weights. The optimization of weights using multiple objectives refers to a "multi-objective optimization problem." In this paper, an evolutionary cultural algorithm is used to optimise weights in ANN, and the results are reported with improved accuracy. Three benchmark datasets for autism screening data are used, trained, and tested for model accuracy in the classification: toddlers (1054,19), children (292,21), and adults (704,21).With the support of the domain expert, real-time data were collected from parents and caregivers and totalled over 1000 records, with a moderate difference in attributes based on CARS-2 (Childhood Autism Rating Scale, 2nd Edition) for ASD screening. In this paper, the proposed model is compared using a curve-fitting mathematical technique. The proposed model is trained and tested, and the results showed that it outperformed other algorithms in terms of precision, accuracy, sensitivity, and specificity. [ABSTRACT FROM AUTHOR]

This paper investigates the integration of a surrogate-assisted multi-objective evolutionary algorithm (MOEA) and a parallel computation scheme to reduce the computing time until obtaining the optimal solutions in evolutionary algorithms (EAs). A surrogate-assisted MOEA solves multi-objective optimization problems while estimating the evaluation of solutions with a surrogate function. A surrogate function is produced by a machine learning model. This paper uses an extreme learning surrogate-assisted MOEA/D (ELMOEA/D), which utilizes one of the well-known MOEA algorithms, MOEA/D, and a machine learning technique, extreme learning machine (ELM). A parallelization of MOEA, on the other hand, evaluates solutions in parallel on multiple computing nodes to accelerate the optimization process. We consider a synchronous and an asynchronous parallel MOEA as a master-slave parallelization scheme for ELMOEA/D. We carry out an experiment with multi-objective optimization problems to compare the synchronous parallel ELMOEA/D with the asynchronous parallel ELMOEA/D. In the experiment, we simulate two settings of the evaluation time of solutions. One determines the evaluation time of solutions by the normal distribution with different variances. On the other hand, another evaluation time correlates to the objective function value. We compare the quality of solutions obtained by the parallel ELMOEA/D variants within a particular computing time. The experimental results show that the parallelization of ELMOEA/D significantly reduces the computational time. In addition, the integration of ELMOEA/D with the asynchronous parallelization scheme obtains higher quality of solutions quicker than the synchronous parallel ELMOEA/D. [ABSTRACT FROM AUTHOR]

COVID-19 disease, which highly affected global life in 2020, led to a rapid scientific response. Versatile optimization methods found their application in scientific studies related to COVID-19 pandemic. Differential Evolution (DE) and Particle Swarm Optimization (PSO) are two metaheuristics that for over two decades have been widely researched and used in various fields of science. In this paper a survey of DE and PSO applications for problems related with COVID-19 pandemic that were rapidly published in 2020 is presented from two different points of view: 1. practitioners seeking the appropriate method to solve particular problem, 2. experts in metaheuristics that are interested in methodological details, inter comparisons between different methods, and the ways for improvement. The effectiveness and popularity of DE and PSO is analyzed in the context of other metaheuristics used against COVID-19. It is found that in COVID-19 related studies: 1. DE and PSO are most frequently used for calibration of epidemiological models and image-based classification of patients or symptoms, but applications are versatile, even interconnecting the pandemic and humanities; 2. reporting on DE or PSO methodological details is often scarce, and the choices made are not necessarily appropriate for the particular algorithm or problem; 3. mainly the basic variants of DE and PSO that were proposed in the late XX century are applied, and research performed in recent two decades is rather ignored; 4. the number of citations and the availability of codes in various programming languages seems to be the main factors for choosing metaheuristics that are finally used. [ABSTRACT FROM AUTHOR]

Mutation testing is a well-established but costly technique to assess and improve the fault detection ability of test suites. This technique consists of introducing subtle changes in the code of a program, which are expected to be detected by the designed test cases. Among the strategies conceived to reduce its cost, evolutionary mutation testing (EMT) has been revealed as a promising approach to select a subset of the whole set of mutants based on a genetic algorithm (GA). However, like any other metaheuristic approach, EMT's execution depends on a set of parameters (both classical of GAs and context-specific ones), so different configurations can greatly vary its performance. Currently, it is difficult to clarify what are the best values for those parameters by applying manual parameter tuning and whether new design choices could improve its effectiveness with other combinations of values. The experience carried out in this paper applying iterated racing, a well-known automated configuration algorithm, reveals that EMT's performance has been undervalued in previous studies; the new configuration found by iterated racing was able to enhance EMT's results in all C++ object-oriented programs used in the experiments. This study also confirms alternative design choices as convenient options to improve EMT in this context, namely, detecting and penalizing equivalent mutants by means of Trivial Compiler Equivalence, and learning which mutation operators produced live mutants in the past generations. [ABSTRACT FROM AUTHOR]

Multi-objective evolutionary algorithms (MOEAs) are a practical tool to solve non-linear problems with multiple objective functions. However, when applied to expensive black-box scenario-based optimization problems, MOEA's performance becomes constrained due to computational or time limitations. Scenario-based optimization refers to problems that are subject to uncertainty, where each solution is evaluated over an ensemble of scenarios to reduce risks. A primary reason for MOEA's failure is that algorithm development is challenging in these cases as many of these problems are black-box, high-dimensional, discrete, and computationally expensive. For this reason, this paper proposes a benchmark generator to create fast-to-compute scenario-based discrete test problems with different degrees of complexity. Our framework uses the structure of the Multi-Objective Knapsack Problem to create test problems that simulate characteristics of expensive scenario-based discrete problems. To validate our proposition, we tested four state-of-the-art MOEAs in 30 test instances generated with our framework, and the empirical results demonstrate that the suggested benchmark generator can analyze the ability of MOEAs in tackling expensive scenario-based discrete optimization problems. [ABSTRACT FROM AUTHOR]

In a bike-sharing system, the user route planning problem (URPP) is significant because it helps users to plan the route and to choose appropriate intermediate stations to transfer bikes, so as to reduce riding costs. To efficiently solve the URPP, this paper models it as a discrete optimization problem with constraints and proposes a knowledge learning and random pruning-based memetic algorithm (KLRP-MA), with three main contributions. First, the proposed URPP model is from the perspective of users and is suitable for not only static situations but also dynamic situations, which is novel from existing work that mainly focuses on the perspective of bike companies in a static situation. Second, three novel evolutionary operators named knowledge learning-based crossover, random pruning-based mutation, and two-phase local search are proposed and integrated into the KLRP-MA for dealing with the challenges of the URPP. Third, based on the dynamic URPP model, the KLRP-MA is further extended to a dynamic KLRP-MA (DyKLRP-MA) to quickly search for a reasonable route for users when the availability status of the bike stations changes over time, so as to deal with URPP in dynamic situations. Experimental results on 180 generated instances and 10 real-world instances show that when compared with the traditional and state-of-the-art methods, the KLRP-MA and the DyKLRP-MA can find the best solution in a short time. Moreover, in a dynamic situation, the DyKLRP-MA can quickly respond to changes and re-optimize the current planning route. [ABSTRACT FROM AUTHOR]

This paper proposes the multi-objective variant of the recently-introduced fitness dependent optimizer (FDO). The algorithm is called a multi-objective fitness dependent optimizer (MOFDO) and is equipped with all five types of knowledge (situational, normative, topographical, domain, and historical knowledge) as in FDO. MOFDO is tested on two standard benchmarks for the performance-proof purpose: classical ZDT test functions, which is a widespread test suite that takes its name from its authors Zitzler, Deb, and Thiele, and on IEEE Congress of Evolutionary Computation benchmark (CEC-2019) multi-modal multi-objective functions. MOFDO results are compared to the latest variant of multi-objective particle swarm optimization, non-dominated sorting genetic algorithm third improvement (NSGA-III), and multi-objective dragonfly algorithm. The comparative study shows the superiority of MOFDO in most cases and comparative results in other cases. Moreover, MOFDO is used for optimizing real-world engineering problems (e.g., welded beam design problems). It is observed that the proposed algorithm successfully provides a wide variety of well-distributed feasible solutions, which enable the decision-makers to have more applicable-comfort choices to consider. [ABSTRACT FROM AUTHOR]

This paper proposes a novel meta-heuristic optimization method, namely "Chernobyl Disaster Optimizer (CDO)". The underlying concepts and principles behind the proposed approach is inspired by the nuclear reactor core explosion of Chernobyl. In CDO, radioactivity happened because of nuclear instability, which different types of radiations are emitted from nuclei. The most common kinds of these radiations are called gamma, beta, and alpha particles. These particles fly away from the explosion point (high pressure point) to the low pressure point (the human standing point), which are harmful to the humans. The CDO mimics the process of nuclear radiation while attaching human after the nuclear explosion. The main steps of nuclear explosion and attaching human are implemented in which gamma, beta, and alpha particles are involved in this process. The CDO is evaluated with optimizing "Congress on Evolutionary Computation (CEC 2017)" test bed suites. In addition, it is compared against well-known optimization methods, such as "Sperm Swarm Optimization" and "Gravitational Search Algorithm". The experimental results prove its efficiency, which can be considered as viable alternative. [ABSTRACT FROM AUTHOR]

Sparse large-scale multi-objective optimization problems (LSMOPs) widely exist in real-world applications, which have the properties of involving a large number of decision variables and sparse Pareto optimal solutions, i.e., most decision variables of these solutions are zero. In recent years, sparse LSMOPs have attracted increasing attentions in the evolutionary computation community. However, all the recently tailored algorithms for sparse LSMOPs put the sparsity detection and maintenance in the first place, where the nonzero variables can hardly be optimized sufficiently within a limited budget of function evaluations. To address this issue, this paper proposes to enhance the connection between real variables and binary variables within the two-layer encoding scheme with the assistance of variable grouping techniques. In this way, more efforts can be devoted to the real part of nonzero variables, achieving the balance between sparsity maintenance and variable optimization. According to the experimental results on eight benchmark problems and three real-world applications, the proposed algorithm is superior over existing state-of-the-art evolutionary algorithms for sparse LSMOPs. [ABSTRACT FROM AUTHOR]

This paper presents a population-based evolutionary computation model for solving continuous constrained nonlinear optimization problems. The primary goal is achieving better solutions in a specific problem type, regardless of metaphors and similarities. The proposed algorithm assumes that candidate solutions interact with each other to have better fitness values. The interaction between candidate solutions is limited with the closest neighbors by considering the Euclidean distance. Furthermore, Tabu Search Algorithm and Elitism selection approach inspire the memory usage of the proposed algorithm. Besides, this algorithm is structured on the principle of the multiplicative penalty approach that considers satisfaction rates, the total deviations of constraints, and the objective function value to handle continuous constrained problems very well. The performance of the algorithm is evaluated with real-world engineering design optimization benchmark problems that belong to the most used cases by evolutionary optimization researchers. Experimental results show that the proposed algorithm produces satisfactory results compared to the other algorithms published in the literature. The primary purpose of this study is to provide an algorithm that reaches the best-known solution values rather than duplicating existing algorithms through a new metaphor. We constructed the proposed algorithm with the best combination of features to achieve better solutions. Different from similar algorithms, constrained engineering problems are handled in this study. Thus, it aims to prove that the proposed algorithm gives better results than similar algorithms and other algorithms developed in the literature. [ABSTRACT FROM AUTHOR]

Effective exploration is key to a successful search process. The recently proposed negatively correlated search (NCS) tries to achieve this by coordinated parallel exploration, where a set of search processes are driven to be negatively correlated so that different promising areas of the search space can be visited simultaneously. Despite successful applications of NCS, the negatively correlated search behaviors were mostly devised by intuition, while deeper (e.g., mathematical) understanding is missing. In this paper, a more principled NCS, namely NCNES, is presented, showing that the parallel exploration is equivalent to a process of seeking probabilistic models that both lead to solutions of high quality and are distant from previous obtained probabilistic models. Reinforcement learning, for which exploration is of particular importance, are considered for empirical assessment. The proposed NCNES is applied to directly train a deep convolution network with 1.7 million connection weights for playing Atari games. Empirical results show that the significant advantages of NCNES, especially on games with uncertain and delayed rewards, can be highly owed to the effective parallel exploration ability. [ABSTRACT FROM AUTHOR]

This paper suggests a novel robust formulation designed for optimizing the parameters of the turning process in an uncertain environment for the first time. The aim is to achieve the lowest energy consumption and highest precision. With this aim, the current paper considers uncertain parameters, objective functions, and constraints in the offered mathematical model. We proposed several uncertain models and validated the results in real-world case studies. In addition, several artificial intelligence-based solution techniques are designed to solve the complex nonlinear problem. We determined the most efficient solution approach by solving various test problems. Then, simulated several scenarios to demonstrate the robustness of our results. The results showed that the solutions provided by the offered model significantly reduce energy consumption in different setups. To ensure the reliability of the results, we carried out worst-case sensitivity analyses and found the most critical parameters. The results of the worst-case analyses indicated that the offered robust model is efficient and saves a significant amount of energy comparing to traditional models. It is shown that the provided solution by the presented robust formulation is reliable in all situations and results in the lowest energy and the best machining precision. [ABSTRACT FROM AUTHOR]

Deep learning (DL) is gaining significant prevalence in every field of study due to its domination in training large data sets. However, several applications are utilizing machine learning (ML) methods from the past several years and reported good performance. However, their limitations in terms of data complexity give rise to DL methods. Intrusion detection is one of the prominent areas in which researchers are extending DL methods. Even though several excellent surveys cover the growing body of research on this subject, the literature lacks a detailed comparison of ML methods such as ANN, SVM, fuzzy approach, swarm intelligence and evolutionary computation methods in intrusion detection, particularly on recent research. In this context, the present paper deals with the systematic review of ML methods and DL methods in intrusion detection. In addition to reviewing ML and DL methods, this paper also focuses on benchmark datasets, performance evaluation measures and various applications of DL methods for intrusion detection. The present paper summarizes the recent work, compares their experimental results for detecting network intrusions. Furthermore, current research challenges are identified for helping fellow researchers in the era of DL-based intrusion detection. [ABSTRACT FROM AUTHOR]

The class imbalance learning problem is an important topic that has attracted considerable attention in machine learning and data mining. The most common method of addressing imbalanced datasets is the synthetic minority oversampling technique (SMOTE). However, the SMOTE and its variants suffer from the noise derived from the interpolation of synthetic examples. In this paper, an overproduce-and-choose strategy, which is divided into the overproduction and selection phases, is proposed to generate an appropriate set of synthetic examples for imbalance learning problems. In the overproduction phase, a new interpolation mechanism is developed to produce numerous synthetic examples, while in the selection phase, the synthetic examples that are beneficial to the classification task are selected by using instance selection based on evolutionary computation. Experiments are conducted on a large number of datasets selected from the real-world applications. The experimental results demonstrate that the proposed method is significantly better than SMOTE and its well-known variants in terms of several metrics, including G-mean (GM) and area under the curve. [ABSTRACT FROM AUTHOR]

This paper presents a parallel evolutionary metaheuristic which includes different threads aimed at balancing exploration versus exploitation. Exploring different areas of the search space independently, each thread also communicates with other threads, and exploits the search space by improving a common high quality solution. The presented metaheuristic has been applied to three famous and hard-to-solve optimization problems, namely the job shop scheduling, the permutation flowshop scheduling, and the quadratic assignment problems. The results of computational experiments indicate that it is effective, versatile and robust, competing with the-state-of-art procedures presented for these three problems. In effect, in terms of solution quality, and average required running time to reach a high quality solution, the procedure outperforms several state-of-the-art procedures on multiple benchmark instances. [ABSTRACT FROM AUTHOR]

Multifactorial evolution algorithm (MFEA) is a powerful search paradigm with the purpose of addressing multiple optimization tasks simultaneously in the field of evolutionary computation. The assortative mating of MFEA is a key component to make it outperform traditional single-task optimization algorithms. However, the optimal solution of each generation has still not been well utilized to accelerate convergence in the process of assortative mating operation for existing MFEAs. This paper proposes a multifactorial differential evolution algorithm with optima-based transformation (MFDE-OBT), which employs the optimal solution of each generation to design an improved assortative mating operation based on the DE/rand/2 mutation. The improved operation generates an offspring for each individual by running a perturbation around a current optimal individual. The object of the assortative mating is a vector added for the perturbation, which is the sum of two difference vectors generated by a random sample with a certain probability from an individual set that can be same as or different from the one of the task involving the optimal individual. In addition, MFDE-OBT integrates an opposition-based search strategy behind the assortative mating operation to balance exploitation and exploration of each search space. Experimental results on benchmark problems constituted by tasks with different degree of similarity and intersection demonstrate the advantage of the proposed MFDE-OBT algorithm over some state-of-the-art algorithms, in terms of solution precision and convergence performance. [ABSTRACT FROM AUTHOR]

In this paper, a flexible large-scale ensemble-based optimization algorithm is presented for complex optimization problems. According to the no free lunch theorem, no single optimization algorithm demonstrates superior performance across all optimization problems. Therefore, with the animorphic ensemble optimization (AEO) algorithm presented here, a set of algorithms can be used as an ensemble which demonstrate stronger performance across a wider range of optimization problems than any standalone algorithm. AEO is a high-level ensemble designed to handle large ensembles using a well-defined stochastic migration process. The high-level nature of AEO allows for an arbitrary number of diverse standalone algorithms to interface with one another through an island model interface strategy, where various populations change size according to the performance of the algorithm associated with each population. In this study, AEO is demonstrated using ensembles of both evolutionary and swarm algorithms such as differential evolution, particle swarm, gray wolf optimization, moth-flame optimization, and more, and strong performance is observed. Quantitative diagnostics metrics to describe the migration of individuals across populations are also presented and observed with application to some test problems. In the end, AEO demonstrated strong consistent performance across more than 150 benchmark functions of 10–50 dimensions. [ABSTRACT FROM AUTHOR]

This paper proposes a new optimized Deep Learning (DL) network design for time series load forecasting. At first, DL's hyper parameters are optimized using the Levy flight-particle swarm optimization (LF-PSO) technique; then, the optimized DL model is used for load prediction. Furthermore, the results are compared with the existing state-of-the-art techniques to show prediction accuracy. Experiment and measured values indicate that the proposed new DL model is highly efficient for load prediction. [ABSTRACT FROM AUTHOR]

Most text clustering algorithms adopt a single criterion optimization approach, which often fails to find good clustering solutions for a wide diversity of datasets with different clustering characteristics. The multi-objective meta-heuristic approach is utilized to seek optimal clustering by maximizing (or minimizing) more than two objective functions. In this paper, we propose a multi-objective memetic differential evolution algorithm (MOMDE) for text clustering. The MOMDE text clustering algorithm combines memetic and differential evolution algorithms to improve the search for optimal clustering by improving the balance between exploitation and exploration. Moreover, a combination with the dominance-based multi-objective approach is employed, which may improve the search for optimal clustering by maximizing or/and minimizing two cluster quality measures. The proposed algorithm is tested on six text clustering datasets from the Laboratory of Computational Intelligence. Our experimental results revealed that the performance of the MOMDE algorithm is better than state-of-the-art text clustering algorithms. Further validation is provided using the F-measure to assess the efficiency of the obtained clustering of MOMDE, whilst the multi-objective performance assessment matrices are used to evaluate the quality of Pareto-optimality. [ABSTRACT FROM AUTHOR]

In this paper, Energy Valley Optimizer (EVO) is proposed as a novel metaheuristic algorithm inspired by advanced physics principles regarding stability and different modes of particle decay. Twenty unconstrained mathematical test functions are utilized in different dimensions to evaluate the proposed algorithm's performance. For statistical purposes, 100 independent optimization runs are conducted to determine the statistical measurements, including the mean, standard deviation, and the required number of objective function evaluations, by considering a predefined stopping criterion. Some well-known statistical analyses are also used for comparative purposes, including the Kolmogorov–Smirnov, Wilcoxon, and Kruskal–Wallis analysis. Besides, the latest Competitions on Evolutionary Computation (CEC), regarding real-world optimization, are also considered for comparing the results of the EVO to the most successful state-of-the-art algorithms. The results demonstrate that the proposed algorithm can provide competitive and outstanding results in dealing with complex benchmarks and real-world problems. [ABSTRACT FROM AUTHOR]