Search

Processes or products are typically complex systems with numerous interrelated procedures and interdependent components. This results in complex relationships between responses and input factors, as well as complex nonlinear correlations among multiple responses. If the two types of complex correlations in the quality design cannot be properly dealt with, it will affect the prediction accuracy of the response surface model, as well as the accuracy and reliability of the recommended optimal solutions. In this paper, we combine kernel trick-based kernel principal component analysis, spline-based Bayesian semiparametric additive model, and normal boundary intersection-based evolutionary algorithm to address these two types of complex correlations. The effectiveness of the proposed method in modeling and optimisation is validated through a simulation study and a case study. The results show that the proposed Bayesian semiparametric additive model can better describe the process relationships compared to least squares regression, random forest regression, and support vector basis regression, and the proposed multi-objective optimisation method performs well on several indicators mentioned in the paper. [ABSTRACT FROM AUTHOR]

The train stowage planning problem (TSPP) of the steel industry aims to select steel coils and allocate them to trains cost-effectively. It is a key component in the transportation of steel products. This study focuses on a multiobjective train stowage planning problem (MoTSPP) that maximises both the loading efficiency of the crane and the loading rate of the train. The MoTSPP also considers operation constraints related to steel coils, train wagons, and stowage modes in real-life railway transportation. An integer programming model is established to mathematically describe this problem. To obtain an efficient solution, a multiobjective analytical evolutionary algorithm (MAEA) that combines evolutionary algorithm (EA) with machine learning (ML) is presented. The EA part is a multiobjective differential evolution that introduces guided evolution and parameter adaptation to produce promising individuals and parameters, respectively. ML part adopts clustering algorithm and surrogate model to accelerate the search. Extensive comparisons and insight analyses are conducted from various perspectives to demonstrate the effectiveness and efficiency of the MAEA for solving the MoTSPP. [ABSTRACT FROM AUTHOR]

As a new production pattern, the hybrid seru system (HSS) originated from the actual production scenario. In the HSS, the implementation of the worker transfer strategy can further enhance the system's flexibility but is rarely studied at present. In this paper, we develop a reinforcement learning driven two-stage evolutionary algorithm (RL-TEA) to address the hybrid seru system scheduling problem with worker transfer (HSSSP-WT). To conquer this complex problem, the HSSSP-WT is divided into worker assignment-related subproblems (WS) and batch scheduling-related subproblems (BS) according to the problem characteristics. To effectively solve the subproblems, a probability modelbased exploration and a lower bound-guided heuristic are presented for the WS, and a greedy search is designed for the BS. Meanwhile, to improve search efficiency and effectiveness, a knowledgebased selection mechanism is proposed to determine which subproblem group to optimise in each generation by fusing a reinforcement learning technique and a lower bound filtering strategy. Moreover, an elite enhancement strategy inspired by the problem property is designed to improve the solution quality. Experimental results demonstrate the effectiveness of the worker transfer strategy and the superior performance of the RL-TEA compared with the state-of-the-art algorithms in solving the HSSSP-WT. [ABSTRACT FROM AUTHOR]

This paper provides a systematic review of the Genetic Algorithm (GA)s proposed to solve planning and scheduling problems in Engineer-To-Order (ETO) contexts. Our review focuses on how the key characteristics of ETO projects affect both the problem studied and the GA algorithmic features. Typical ETO projects consist of one-of-a-kind products with complex structures and uncertain designs. A deep analysis of the papers published between 2000 and 2022 enables identifying 10 main characteristics of ETO projects, six activity types, 10 decision types, eight groups of constraints, and 10 optimisation objectives. Our study shows that none of the reported papers integrates all 10 ETO characteristics. The less studied ETO characteristics are incorporating design and engineering information in the problem definition and the design uncertainty. Our review also identifies 10 recurrent encoding formats and emphasises the most frequently used genetic operators. We observed that most planning and scheduling problems consider objectives and decisions related to product customisation or supply chain configuration yielding multi-objective problems. Most multi-objective GAs use a weighted sum or are based on NSGAII. Diversity maintenance methods, adaptive and parameter tunning mechanisms, or hybridisation with machine learning models are still not used in this context. A systematic review of genetic algorithms dedicated to industrial planning and scheduling Analysis on how the characteristics of ETO projects impact the design of genetic representation and operators Recommendation on approaches employed to reach high-quality solutions [ABSTRACT FROM AUTHOR]

In this paper, an ultra-thin absorber with a total thickness of 9.2 mm is designed and verified at the frequency band of 1–5.34 GHz. The absorber is composed of a layer of metasurface, multi-layered magnetic substrate, a layer of fragmented magnetic structure obtained by improved MOEA/D-GO (Multi-Objective Evolutionary Algorithm based on Decomposition combined with Enhanced Genetic Operators), and a copper back plate. The absorber is achieved by two steps. First, we designed and measured an ultra-thin absorber at 0.78–2.04 GHz by adding a layer metasurface onto the top of a basic multi-layer absorber composed of magnetic materials. The fractional bandwidth (FBW) of the absorber is 89.4%, and the electrical thickness is only 0.024 λ 0 at the lowest operating frequency. Second, to broaden the bandwidth, we use an improved MOEA/D-GO to optimize one magnetic layer of the absorber. The working frequency band of the optimized absorber is 1–5.34 GHz, covering L- (1–2 GHz), S- (2–4 GHz), and partial C-bands (4–8 GHz). Furthermore, we modified the structure of the metasurface to make the absorber polarization-independent. The FBW of the final absorber is 136.4%, and the electrical thickness is 0.031 λ 0 at the lowest operating frequency. The prototype of the absorber is measured, and the experimental results agree well with the simulated performance. The results show that the improved MOEA/D-GO can be used to design and optimize sophisticated electromagnetic (EM) structures with the predesigned properties, and the absorber with ultrathin thickness and light weight verified in this paper have great application potentials in EM compatibility, EM shielding, and radar cross section reduction at the low bands of the microwave spectrum. [ABSTRACT FROM AUTHOR]

The efficiency of material supply for workstations using Automatic Guided Vehicles (AGVs) is largely determined by the performance of the AGV dispatching scheme. This paper proposes a new solution approach for the AGV dispatching problem (AGVDP) for material replenishment in a general manufacturing workshop where workstations are in a matrix layout, and where uncertainty in replenishment time of workstations and stochastic unloading efficiencies of AGVs are dynamic contextual factors. We first extend the literature proposing a mixed integer optimisation model with a delivery satisfaction soft constraint of material orders and two objectives: transportation costs and delivery time deviation. We then develop a new knowledge-guided estimation of distribution algorithm with delivery satisfaction evaluation for solving the model. Our algorithm fuses three knowledge-guided strategies to enhance optimisation capabilities at its respective execution stages. Comprehensive numerical experiments with instances built from a real-world scenario validate the proposed model and algorithm. Results demonstrate that the new algorithm outperforms three popular multi-objective evolutionary algorithms, a discrete version of a recent multi-objective particle swarm optimisation, and a multi-objective estimation of distribution algorithm. Findings of this work provide major implications for workshop management and algorithm design. [ABSTRACT FROM AUTHOR]

Disassembly recovers the valuable parts/subassemblies or materials from old and outdated products. The collected old and outdated products have inherent variability in quality, which frequently results in task failure. In disassembly line balancing literature, the authors have handled task failure situations using a predictive-reactive approach which relaxes the cycle time constraint. This relaxation disturbs the paced setting of the disassembly line, which chokes or blocks the workflow in downstream stations. In this manuscript, a station crashing-based recursive solution approach is proposed and a mathematical model is presented to address the task failure problem without relaxing the cycle time constraint. The aim of the proposed approach is to maximise the profit of the disassembly line and minimise the number of workstations required for accommodating all corrective actions. The proposed algorithm is demonstrated with the help of a case study of a toy car. Numerical experiments are performed on the proposed recursive solution framework to (i) test its compatibility with other evolutionary algorithms; (ii) compare its performance with the predictive-reactive approach; and (iii) validate the use of a probability-based station crashing scheme. The results indicate that the proposed approach can consistently produce a significantly better solution (19–28.5% improvement) than the PR approach. [ABSTRACT FROM AUTHOR]

Regarding to the complex chaotic non-linear behaviour in nature and the impossibility of their accurate modelling with current chaotic models, the development of Cascade Hyper-Chaotic System is necessary. Therefore, in this paper, new cascade hyper chaotic systems are proposed. Cascade hyper-chaotic systems have more parameters than the above-mentioned systems, and in most cases, they show more complex behaviour. On the other hand, due to the complexity of these systems and their high parameters, the identification of this kind of systems is difficult. For this reason, a new Adaptive Chaotic Grey Wolf Optimisation algorithm is presented in this article in order to estimate the parameters of these systems. Numerical simulations have been performed on the above-mentioned systems of Lu-Chen, Chen-Lorenz and Lu-Lorenz cascading. The results show that the systems have more complex behaviour than the seed systems and the proposed grey wolf algorithm is also an effective tool for estimating the parameter of the above-mentioned cascade Hyper-Chaotic System. [ABSTRACT FROM AUTHOR]

This paper introduces a comprehensive three-step framework for fault classification in underground cable systems. The first step involves the implementation of the Cumulative Sum (CUSUM) technique to detect the fault instances, which will help in precisely tracking the affected portions. The second step focuses on parameter estimation techniques, followed by the third step, which incorporates classification techniques. The study employs a range of evolutionary optimization algorithms, including Ant Colony Optimization, Bacteria Foraging Optimization, Simulated Annealing, Genetic Algorithm, and Particle Swarm Optimization. These algorithms are effectively employed to track and estimate parameters like amplitude, phase, frequency, and damping factor associated with various types of permanent faults, such as L-G fault, L-L fault, L-L-G fault, and L-L-L-G fault generated in the underground cable. The optimized parameters extracted through these algorithms are utilized as features within a Support Vector Classifier for fault classification. The overall accuracy of the classifier using these features is reported to be 0.944, which is quite high and indicates a strong performance in classifying faults. The study includes a brief comparison of the performance of these bio-inspired algorithms. The effectiveness of the tracking algorithms is validated through the use of laboratory-tested current signals. In addition, the signals are subjected to varying signal-to-noise ratios to evaluate the robustness of the tracking algorithm. A comparative analysis is performed to estimate the accurate parameters and highlights the significant tracking ability of the Particle Swarm Optimization (PSO) algorithm, which outperforms other algorithms.The Root Mean Squared Percentage Error (RMSPE) for the L-G fault in PSO is 0.3082, showing superior performance compared to other algorithms. [ABSTRACT FROM AUTHOR]

Tactile paving is a ground‐texture display device installed on sidewalks to guide visually impaired people. In recent years, many studies have been conducted on tactile paving detection using cameras to help visually impaired people walk independently. In addition, several computer vision‐based tactile paving detection methods have been proposed. However, it is difficult to compare the detection accuracy of different proposed algorithms because there are no publicly available tactile paving datasets, and the ground truth and evaluation criteria used for evaluation are often inconsistent or not clearly presented. To this end, in this paper, we collect a tactile paving dataset and name it 'Tenji10K'. The dataset is constructed with 20 sequences consisting of 10 K first‐person tactile paving images taken in Japan, and 'Tenji block' refers to Japanese‐style tactile paving. For detailed evaluation analysis, up to six sequence attributes are assigned, taking into account various real‐world situations. On the other hand, we also proposed a tactile paving tracking algorithm based on an evolutionary algorithm. The effectiveness of the dataset is evaluated by conducting a comparative experiment based on Tenji10K with respect to four different methods, including our proposed method. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

Wireless sensor network is large-scale, self-organizing and reliable. It is widely used in the military, disaster management, environmental monitoring, and other fields. Algorithms for localization can be classified as range-based or range-free based on their ability to achieve effective localization. Range-based algorithms require hardware support, which increases deployment costs and complexity. Instead of measuring distance directly, range-free algorithms estimate the position based on hop counts between nodes. While simpler in terms of hardware requirements, this algorithm suffers from large localization errors. To address this problem, this paper proposes an improved 3D DV-Hop localization algorithm (3D DEHDV-Hop) using a differential evolutionary algorithm. First of all, theoretical analysis shows a correlation between the volume of the intersection area containing the communication range between neighbors and the number of shared single-hop nodes. Then, using the number of shared single-hop nodes between nodes, the number of hops is converted from a discrete value to an exact continuous value. Finally, the localization problem is transformed into a minimum optimization problem by incorporating a differential evolutionary algorithm. As compared to the other four algorithms compared, 3D DEHDV-Hop improves localization accuracy by an average of 10.3% under different anchor node densities, 13.7% under different communication radiuses, and 12.1% under different anchor node numbers. [ABSTRACT FROM AUTHOR]

Edge bundling is a technique used to improve the readability of large graph drawings by grouping edges to reduce visual complexity. This paper treats this task as a clustering problem, using compatibility metrics to evaluate solutions in an optimization pipeline combined with a clustering ensemble approach. The aim is to present the Clustering Ensemble-based Edge Bundling (CEBEB) method for solving the General-based Edge Bundling (GBEB) problem and report results for some given graphs. The CEBEB method proved very promising and generated better solutions than an existing evolutionary algorithm. Additionally, the paper introduces a new ensemble algorithm, specific for the GBEB, and reviews some previous results. [ABSTRACT FROM AUTHOR]

The primary objective of multi-objective evolutionary algorithms (MOEAs) is to find a set of evenly distributed nondominated solutions that approximate the Pareto front (PF) of a multi-objective optimization problem (MOP) or a many-objective optimization problem (MaOP). This implies that the approximated solution set obtained by MOEAs should be as close to PF as possible while remaining diverse, adhering to criteria of convergence and diversity. However, existing MOEAs exhibit an imbalance between achieving convergence and maintaining diversity in the objective space. As far as the diversity criterion is concerned, it is still a challenge to achieve an evenly distributed approximation set with different sizes for a problem with a complicated PF shape. Furthermore, Pareto dominance has its own weaknesses as the selection criterion in evolutionary multiobjective optimization. Algorithms based on Pareto criterion (PC) can suffer from problems such as slow convergence to the optimal front and inferior performance on problems with many objectives. To effectively address these challenges, we propose a multi-objective bean optimization algorithm (MOBOA). Given that the selection of parent species, representing global optimal solutions, directly influences the convergence and diversity of the algorithm, MOBOA incorporates a preference order equilibrium parent species selection strategy (POEPSS). By extending the Pareto criterion with the preference order optimization criterion, the algorithm effectively enhances parent species selection pressure across multiple objectives. To balance convergence and diversity, MOBOA proposes a multi-population global search strategy explicitly maintaining an external archive during the search process. Leveraging the inherent multi-population advantages of bean optimization algorithm (BOA), the algorithm facilitates information sharing among the main population, auxiliary populations, and historical archive solution sets. Additionally, a diversity enhancement strategy is employed in the environmental selection stage, introducing the environmental selection strategy of the SPEA2 algorithm to generate a set of evenly distributed nondominated solutions. Experimental results on a series of widely used MOPs and MaOPs demonstrate that the proposed algorithm exhibits higher effectiveness and competitiveness compared to state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Although the multiobjective evolutionary algorithms (MOEAs) have been proved to bring promising prospects for solving multiobjective optimization problems (MOPs), the performance of the algorithm deteriorates sharply in high-dimensional objective space due to the weak selection pressure and the unregulated balance, which is caused by the increase of objective space dimension. Some current MOEAs with two-stage strategy (TS) strive to address above issues by dividing the evolutionary process into two independent stages, in which convergence and diversity are handled separately within successive generations of different stages. However, TS-MOEAs have some weaknesses, such as sensitivity to stage division, and incomplete separation of convergence and diversity. In this paper, TS/KW-MaOEA is proposed for solving many-objective optimization problems (MaOPs), which keeps TS as the central and equips a perfect control mechanism for separated balance. More specifically, TS/KW-MaOEA can automatically adjust the balance trend and provide appropriate selection pressure for MaOPs according to the Kondratiev wave (KW) search model and the objective space dimension. To verify the effectiveness of the proposed algorithm, a series of experiments are carried out against seven state-of-the-art many-objective optimization algorithms on 15 benchmark problems with up to 30 objectives. Experimental results indicate that the proposed algorithm is highly competitive against peer competitors. [ABSTRACT FROM AUTHOR]

Many engineering problems are essentially expensive multi-/many-objective optimization problems, and surrogate-assisted evolutionary algorithms have gained widespread attention in dealing with them. As the objective dimension increases, the error of predicting solutions based on surrogate models accumulates. Existing algorithms do not have strong selection pressure in the candidate solution obtaining and adaptive sampling stages. These make the effectiveness and area of application of the algorithms unsatisfactory. Therefore, this paper proposes a two-risk archive algorithm, which contains a strategy for mining high-risk and low-risk archives and a four-state adaptive sampling criterion. In the candidate solution mining stage, two types of Kriging models are trained, then conservative optimization models and non-conservative optimization models are constructed for model searching, followed by archive selection to obtain more reliable two-risk archives. In the adaptive sampling stage, in order to improve the performance of the algorithms, the proposed criterion considers environmental assessment, demand assessment, and sampling, where the sampling approach involves the improvement of the comprehensive performance in reliable environments, convergence and diversity in controversial environments, and surrogate model uncertainty. Experimental results on numerous benchmark problems show that the proposed algorithm is far superior to seven state-of-the-art algorithms in terms of comprehensive performance. [ABSTRACT FROM AUTHOR]

Sparse large-scale multiobjective problems (LSMOPs) are characterized as an NP-hard issue that undergoes a significant presence of zero-valued variables in Pareto optimal solutions. In solving sparse LSMOPs, recent studies typically employ a specialized two-layer encoding, where the low-level layer undertakes the optimization of zero variables and the high-level layer is in charge of non-zero variables. However, such an encoding usually puts the low-level layer in the first place and thus cannot achieve a balance between optimizing zero and non-zero variables. To this end, this paper proposes to build a two-way association between the two layers using a mutual preference calculation method and a two-way matching strategy. Essentially, the two-way association balances the influence of two layers on the encoded individual by relaxing the control of the low-level layer and enhancing the control of the high-level layer, thus reaching the balance between the optimizations of zero and non-zero variables. Moreover, we propose a new evolutionary algorithm equipped with the modules and compare it with several state-of-the-art algorithms on 32 benchmark problems. Extensive experiments verify its effectiveness, as the proposed modules can improve the two-layer encoding and help the algorithm achieve superior performance on sparse LSMOPs. [ABSTRACT FROM AUTHOR]

Many surrogate-assisted evolutionary algorithms (SAEAs) have been shown excellent search performance in solving expensive constrained optimization problems (ECOPs) with continuous variables, but few of them focus on ECOPs with mixed-integer variables (ECOPs-MI). Hence, a population state-driven surrogate-assisted differential evolution algorithm (PSSADE) is proposed for solving ECOPs-MI, in which the adaptive population update mechanism (APUM) and the collaborative framework of global and local surrogate-assisted search (CFGLS) are combined effectively. In CFGLS, a probability-driven mixed-integer mutation (PMIU) is incorporated into the classical global DE/rand/2 and local DE/best/2 for improving the diversity and potentials of candidate solutions, respectively, and the collaborative framework further integrates both the superiority of global and local mutation for the purpose of achieving a good balance between exploration and exploitation. Moreover, the current population is adaptively reselected based on the efficient non-dominated sorting technique in APUM when the population distribution is too dense. Empirical studies on 10 benchmark problems and 2 numerical engineering cases demonstrate that the PSSADE shows a more competitive performance than the existing state-of-the-art algorithms. More importantly, PSSADE provides excellent performance in the design of infrared stealth material film. [ABSTRACT FROM AUTHOR]

Offering Product-Service Systems (PSS) becomes an established strategy for companies to increase the provided customer value and ensure their competitiveness. Designing PSS business models, however, remains a major challenge. One reason for this is the fact that PSS business models are characterized by a long-term nature. Decisions made in the development phase must take into account possible scenarios in the operational phase. Risks must already be anticipated in this phase and mitigated with appropriate measures. Another reason for the design phase being a major challenge is the size of the solution space for a possible business model. Developers are faced with a multitude of possible business models and have the challenge of selecting the best one. In this article, a simheuristic optimization approach is developed to test and evaluate PSS business models in the design phase in order to select the best business model configuration beforehand. For optimization, a proprietary evolutionary algorithm is developed and tested. The results validate the suitability of the approach for the design phase and the quality of the algorithm for achieving good results. This could even be transferred to already established PSS. [ABSTRACT FROM AUTHOR]

This study challenges a long-standing and often uncontested assertion in the forestry discourse that maximizing financial returns always requires ecologically simplified stands. We developed a high-resolution simulation tool for northern hardwood stands in eastern North America and integrated advanced numerical optimization methods to model the tree-level harvest decisions that maximize financial returns. We modeled each individual tree's growth and its probability of natural mortality, conditioned on the evolving neighborhood-scale competitive environment it resides in. We developed size-, species-, and grade-specific price functions to assign potential harvest revenue values to each discrete bole section of each standing tree, and we used an evolutionary search algorithm to specify the financially optimal timing of tree-by-tree removals. We modeled three different case studies, representing a broad range of northern hardwood stand conditions, including a hypothetical 50-year-old, even-aged stand and two inventoried stands in northern New York, USA, with contrasting management histories. We observed consistent results across all three cases: maximizing financial returns from northern hardwood forests requires silvicultural finesse and results in ecologically complicated stands. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicle (UAV) path planning aims to find the optimal flight path from the start point to the destination point for each aerial vehicle. With the rapid development of UAV technology, UAVs are required to tackle missions in increasingly complex environments. Consequently, UAV path planning encounters more challenges, causing traditional deterministic algorithms to struggle to find the optimal path within a certain time. Evolutionary computation (EC) is a series of nature-inspired methodologies and algorithms, which have shown effectiveness and efficiency in solving many complex optimization problems in real-world applications. Recently, EC algorithms have been effectively applied in UAV path planning and have shown encouraging performance in obtaining high-quality solutions. Therefore, it is crucial to review the related research experience and literature in the field of using EC for UAV path planning. This paper presents a comprehensive survey to showcase the existing studies on EC in UAV path planning, especially in complex environments. The paper first proposes a novel taxonomy to categorize the relevant studies into three different categories according to the complex environmental properties of the application scenarios. These environmental properties include complex search space, complex time control, and complex optimization objectives. Then, the EC algorithms for UAV path planning in these complex environments are further systematically surveyed as constrained search space and large-scale search space in complex search space, dynamic UAV path planning and multi-UAV concurrent path planning in complex time control, and expensive objective and multiple objectives in complex optimization objectives. Finally, some potential future research directions for applying EC algorithms to UAV path planning are presented and discussed. [ABSTRACT FROM AUTHOR]

In the past few decades, many multi-objective evolution algorithms (MOEAs) have been proposed, often emphasizing a single crossover operator, which has a significant impact on the algorithm's performance. This paper proposed a novel MOEA, based on the MOEA/D framework and employing Q-learning for adaptive operator selection (QLMOEA/D-AOS). In every Iteration, Q-learning is used to dynamically choose an operator among five crossover operators. To obtain a better distribution of solutions in multi-objective optimization problems with irregular PFs, a new approach for weight vector initializing is proposed. Additionally, to enhance population diversity, a reward calculation method based on two metrics, Spacing and PD, is proposed. Finally, the proposed algorithm is validated for different numbers of objectives, ranging from two to five for multi/many-objective optimization problems. The experimental results demonstrate the significant advantages of the proposed algorithm compared to state-of-the-art MOEAs across multiple test cases. [ABSTRACT FROM AUTHOR]

The realization of a metasurface cloak for the simultaneous invisibility of multiple sources presents a long‐standing scientific challenge. Ideally, for the establishment of a simultaneous multisource invisibility cloak, the metasurface must provide a wide phase coverage and angular stability in a single architecture, especially for broadband, wide‐angle, and even omnidirectional scenarios. However, achieving this goal has proven to be elusive thus far. Current approaches for implementing metasurface‐based invisibility cloak involve both active and passive metasurface. These approaches often rely on phase‐compensation mechanisms, which inevitably encounter issues related to limited incidence angles or narrow working bands. Here, a novel paradigm of synchronization metasurface optimized through an evolution‐optimization strategy, enabling the realization of simultaneous multisource invisibility cloaking, is proposed. The underlying physics of the synchronization metasurface relies on an evolution‐optimization strategy (an evolutionary game algorithm), which is used to get rid of the entanglement between incident directions, frequencies, and metasurface phase gradients. Consequently, the synchronization metasurface is capable of manipulating simultaneous incoming waves at any angle over a wide range (cloak). In experimental validation, the synchronization metasurface demonstrates an impressive capability to cloak both single and simultaneous double sources in any direction, highly resembling background fields. [ABSTRACT FROM AUTHOR]

The research work on optimization has witnessed significant growth in the past few years, particularly within multi- and single-objective optimization algorithm areas. This study provides a comprehensive overview and critical evaluation of a wide range of optimization algorithms from conventional methods to innovative metaheuristic techniques. The methods used for analysis include bibliometric analysis, keyword analysis, and content analysis, focusing on studies from the period 2000–2023. Databases such as IEEE Xplore, SpringerLink, and ScienceDirect were extensively utilized. Our analysis reveals that while traditional algorithms like evolutionary optimization (EO) and particle swarm optimization (PSO) remain popular, newer methods like the fitness-dependent optimizer (FDO) and learner performance-based behavior (LPBB) are gaining attraction due to their adaptability and efficiency. The main conclusion emphasizes the importance of algorithmic diversity, benchmarking standards, and performance evaluation metrics, highlighting future research paths including the exploration of hybrid algorithms, use of domain-specific knowledge, and addressing scalability issues in multi-objective optimization. [ABSTRACT FROM AUTHOR]

The dung beetle optimization (DBO) algorithm is acknowledged for its robust optimization capabilities and rapid convergence as an efficient swarm intelligence optimization technique. Nevertheless, DBO, similar to other swarm intelligence algorithms, often gets trapped in local optima during the later stages of optimization. To mitigate this challenge, we propose the Move-to-Escape dung beetle optimization (MEDBO) algorithm in this paper. MEDBO utilizes a good point set strategy for initializing the swarm's initial population, ensuring a more uniform distribution and diminishing the risk of local optima entrapment. Moreover, it incorporates convergence factors and dynamically balances the number of offspring and foraging individuals, prioritizing global exploration initially and local exploration subsequently. This dynamic adjustment not only enhances the search speed but also prevents local optima stagnation. The algorithm's performance was assessed using the CEC2017 benchmark suite, which confirmed MEDBO's significant improvements. Additionally, we applied MEDBO to three engineering problems: pressure vessel design, three-bar truss design, and spring design. MEDBO exhibited an excellent performance in these applications, demonstrating its practicality and efficacy in real-world problem-solving contexts. [ABSTRACT FROM AUTHOR]

To address the symmetry-related resilience issues of stations and lines in urban rail transit networks, we propose a two-stage robust optimization-based approach for urban rail transit network planning. In this context, resilience is conceptualized as the ability of the network to maintain its operational symmetry under normal and disruptive conditions. Firstly, we used passenger flow distributions as decision variables to construct a two-stage symmetry-based urban rail transit network planning model, aiming to simultaneously minimize the total cost and total operating time of the network while preserving its functional symmetry. Secondly, we designed a hybrid evolutionary algorithm with chromosomes having a two-layer encoding structure, where the Niched Pareto Genetic Algorithm served as the main algorithmic framework, and a Large Neighborhood Search mechanism was designed to optimize the connectivity gene layer of individuals, ensuring the symmetry of network connectivity. Finally, we conducted computational verification on randomly generated instances to confirm the effectiveness of the model and algorithm. The experimental results demonstrated that our method could find two sets of Pareto optimal solutions for cost preference and time preference, thereby preserving the operational symmetry of the network under normal and damaged conditions, as well as reducing the total operating time. This effectively improved the overall efficiency and resilience of the network. Our designed hybrid evolutionary algorithm converged to satisfactory objective values in the early iterations, exhibiting strong search and optimization performance and effectively solving the two-stage symmetry-based urban rail transit network planning model. [ABSTRACT FROM AUTHOR]

Genetic programming (GP) has a long-standing tradition in the evolution of computer programs, predominantly utilizing tree and linear paradigms, each with distinct advantages and limitations. Despite the rapid growth of the GP field, there have been disproportionately few attempts to evolve 'real' Turing-like imperative programs (as contrasted with functional programming) from the ground up. Existing research focuses mainly on specific special cases where the structure of the solution is partly known. This paper explores the potential of integrating tree and linear GP paradigms to develop an encoding scheme that universally supports genetic operators without constraints and consistently generates syntactically correct Python programs from scratch. By blending the symmetrical structure of tree-based representations with the inherent asymmetry of linear sequences, we created a versatile environment for program evolution. Our approach was rigorously tested on 35 problems characterized by varying Halstead complexity metrics, to delineate the approach's boundaries. While expected brute-force program solutions were observed, our method yielded more sophisticated strategies, such as optimizing a program by restricting the division trials to the values up to the square root of the number when counting its proper divisors. Despite the recent groundbreaking advancements in large language models, we assert that the GP field warrants continued research. GP embodies a fundamentally different computational paradigm, crucial for advancing our understanding of natural evolutionary processes. [ABSTRACT FROM AUTHOR]

This work describes a new surrogate-assisted constraint-handling technique (CHT) for parametric multi-objective evolutionary algorithms, called Bayesian CHT. Parametric optimization finds optimal solutions as a function of one or more exogenous variables. The solution is a family of Pareto frontiers called the parameterized Pareto frontier (PPF). CHTs from non-parametric multi-objective evolutionary algorithms do not produce a good sampling of solutions on the PPF. The proposed CHT addresses this using Bayesian methods. A Gaussian process classifier serves as an uncertainty-quantified surrogate for problem constraints, enabling active learning and a novel repair mechanism that promotes sampling along the PPF. The new technique is evaluated on a suite of 36 test problems and two engineering cases of structural design. Quantitative results show that the proposed Bayesian CHT outperforms several state-of-the-art algorithms in most cases. From a qualitative perspective, the nondominated solutions are visualized to support the superiority of the new approach, which achieves a better spread of solutions on the PPF. The results of engineering studies also indicate that the new approach is computationally more efficient than the others. [ABSTRACT FROM AUTHOR]

Learners' emotional states might change during the learning process, and unpredictable variations of a person's emotions raise the demand for regular assessment of feelings during learning. In this paper, an AI-based decision framework is proposed and implemented for e-learning systems that identify suitable micro-brake activities based on the learner's emotional state through an evolutionary genetic algorithm to change learner's mood and increase learning performance. This proposed framework was tested using a case study of English as a second language learner during one semester. The students were divided into two groups of participants (each group containing twenty students, forming a total of 40 students). The results of this study demonstrated the importance of learners' emotions in their learning performance and proved the effectiveness of our proposed framework and the success of the recommended micro-break activities chosen based on learners' emotions and preferences. The findings of this study have important practical implications in designing adaptive e-learning systems and learning management systems such as Moodle. They also contribute to theoretical implications in the field of AI and learner emotions by suggesting a novel approach to identifying, categorizing, and offering a learning path that can cater to the needs of individual learners. [ABSTRACT FROM AUTHOR]

An innovative optimal design framework is developed aiming at enhancing the crashworthiness while ensuring the lightweight design of a hybrid two-dimensional triaxial braided composite (2DTBC) tube, drawing insights from the mesostructure of the composite material. To achieve these goals, we first compile the essential mechanical properties of the 2DTBC using a concentric cylinder model (CCM) and an analytical laminate model. Subsequently, a kriging surrogate model to elucidate the intricate relationship between design variables and macroscopic crashworthiness is developed and validated. Finally, employing multi-objective evolutionary optimization, we identify Pareto optimal solutions, highlighting that reducing the total fiber volume and increasing the glass fiber content in the total fiber volume are crucial for optimal crashworthiness and the lightweight design of the hybrid 2DTBC tube. By integrating advanced predictive modeling techniques with multi-objective evolutionary optimization, the proposed approach not only sheds light on the fundamental principles governing the crashworthiness of hybrid 2DTBC but also provides valuable insights for the design of robust and lightweight composite structures. [ABSTRACT FROM AUTHOR]

To address the issue of high communication cost under the federated learning framework in multi-tenant data centers, this paper proposed an optimization algorithm based on ternary evolutionary model parameters. Firstly, it constructed a federated learning architecture tailored to multi-tenant data centers for data privacy protection. Secondly, in response to the excessive communication overhead stemming from the implementation of the federated learning framework, which increasing interactions between tenants and the data center, it proposed an optimization algorithm that utilized ternary evolutionary model parameters. This algorithm aimed to reduce redundant communication in the exchange of model parameters between tenants and the data center by integrating the optimal local model with the evolutionary direction of ternary vectorized model parameters. Moreover, by analyzing privacy research based on federated learning, the algorithm effectively ensured the privacy of tenants participating in the training during the communication process. Finally, experimental results demonstrate that, while maintaining training accuracy, the proposed method can effectively reduce redundant communication costs by 30% compared to the federated averaging baseline algorithm. [ABSTRACT FROM AUTHOR]

The weighted set covering problem (WSCP) is a famous NP-hard problem. In order to solve the WSCP efficiently by using artificial bee colony algorithm(ABC), this paper proposed a novel binary ABC(nBABC). In nBABC, it proposed a global evolution operator which combined random learning and inheritance to improve the global exploration ability of the algorithm. Secondly, based on the dynamic adjustment strategy, it proposed an adaptive random inversion operator to maintain the balance between exploration and development. Based on the idea of approximate algorithm, it proposed the repair algorithm WSCP-GRA and optimization algorithm WSCP-GOA for dealing with the infeasible solution of WSCP, on the basis of which a new method for solving WSCP was given by using nBABC. In order to verify the efficiency of nBABC in solving WSCP, using it to solve 45 WSCP instances in OR-Library. The comparison with several algorithms shows that nBABC can obtain the optimal values of all instances, which is more competitive than the existing algorithms for solving WSCP. [ABSTRACT FROM AUTHOR]

Learning optimal policies in sparse rewards settings is difficult as the learning agent has little to no feedback on the quality of its actions. In these situations, a good strategy is to focus on exploration, hopefully leading to the discovery of a reward signal to improve on. A learning algorithm capable of dealing with this kind of setting has to be able to (1) explore possible agent behaviors and (2) exploit any possible discovered reward. Exploration algorithms have been proposed that require the definition of a low-dimension behavior space, in which the behavior generated by the agent's policy can be represented. The need to design a priori this space such that it is worth exploring is a major limitation of these algorithms. In this work, we introduce STAX, an algorithm designed to learn a behavior space on-the-fly and to explore it while optimizing any reward discovered (see Figure 1). It does so by separating the exploration and learning of the behavior space from the exploitation of the reward through an alternating two-step process. In the first step, STAX builds a repertoire of diverse policies while learning a low-dimensional representation of the high-dimensional observations generated during the policies evaluation. In the exploitation step, emitters optimize the performance of the discovered rewarding solutions. Experiments conducted on three different sparse reward environments show that STAX performs comparably to existing baselines while requiring much less prior information about the task as it autonomously builds the behavior space it explores. [ABSTRACT FROM AUTHOR]

Accurate diagnosis and effective treatment of thyroid conditions, such as hypothyroidism and hyperthyroidism, are crucial due to their wide-ranging symptoms and consequences. However, conventional back-propagation neural networks have limitations, including slow convergence and susceptibility to local minima. To deal with these problems, the paper suggests an integrated strategy that includes back-propagation (BP) and genetic algorithms (GA). The suggested method uses evolutionary algorithms to investigate various weight combinations and back-propagation to modify weights in response to the discrepancy between expected and actual results. The study evaluated the method using three steps of experimentation, including network building, local search and optimization, and evaluation, on a real-world dataset of thyroid illnesses. The obtained results are very satisfying and promising, indicating that the MLP-GA/BP model is robust enough to detect and categorize thyroid disorders effectively and efficiently. This makes it a reliable diagnostic tool for medical practitioners, allowing them to effectively diagnose and treat patients with thyroid diseases. [ABSTRACT FROM AUTHOR]

Vehicular fog computing (VFC) is a technology that enhances vehicular applications by offloading the task of the resource-restricted vehicle to the resourceful fog node (vehicle or static fog node). The mobility of vehicles leads to various challenges in task offloading, i.e., low successful offloading ratio, high response time, etc. Apart from this, the available idle computation resource at the fog node is different at the time of advertisement of computation capability and at the time of task allocation. This change results in less efficient resource utilization and unequal load balance at the fog node. Hence to overcome this, we have proposed an approach based on future mobility and imminent computation awareness (FMICA). The future mobility prediction allows us to offload the task to the fog node, which will be near during task retrieval. Additionally, imminent computation awareness of the available resources (at the imminent time τ ) allows us to efficiently utilize the idle resources through offloading higher deadline tasks at the τ time. FMICA optimizes resources according to various criteria such as offloading delay, load variance, within-range ratio, and successful offloading ratio using a Strength Pareto Evolutionary Algorithm 2 (SPEA2). An order preference by similarity to the ideal solution (TOPSIS) and multiple criteria decision-making (MCDM) technique is used to select the best solution. Through the experimental analysis, we have found that the FMICA has an improvement of 37.64%, 25.57%, 9.96%, and 12.62% in metrics average response time, successful offloading ratio, resource utilization, and average load variance against available approach, respectively. [ABSTRACT FROM AUTHOR]

We investigate learning in a repeated bank choice game, where agents first choose a bank to deposit in and then decide to withdraw that deposit or not. This game has a single Nash equilibrium in pure strategies, characterized by all agents depositing in the bank that offers the highest return, even though it may be more vulnerable to bankruptcy if some agents withdraw early. We use an individual evolutionary learning algorithm to model under which circumstances and with which beliefs agents can learn the Nash equilibrium in the repeated game and compare the results to an experiment. We find participants coordinating on the Nash equilibrium in the presence of low or medium vulnerability banks, but efficient coordination fails when both banks are highly vulnerable (irrespective of whether participants have full or only partial information). • We investigate learning in a repeated bank run game with pre-deposit decisions. • We use online experiments as well as individual evolutionary learning algorithms. • We vary the vulnerability of the banks as well as information to participants. • For partial information simulations sophisticated beliefs-updating is crucial. • Agents can learn the unique equilibrium only when banks are not too vulnerable. [ABSTRACT FROM AUTHOR]

Machine configuration is a crucial strategic decision in designing a flow shop system (FSS) and directly affects its performance. This involves selecting device suppliers and determining the number of machines to be configured. This study addresses a bi-objective optimization problem for an FSS that considers repair actions and aims to determine the most suitable machine configuration that balances the production reliability and purchase cost. A nondominated sorting genetic algorithm II (NSGA-II) is used to determine all the Pareto solutions. The technique for order preference by similarity to an ideal solution is then used to identify a compromise alternative. It is necessary to assess the production reliability of any machine configuration identified by the NSGA-II. The FSS under the machine configuration is modeled as a multistate flow shop network, and Absorbing Markov Chain and Recursive Sum of Disjoint Products are integrated into the NSGA-II for reliability evaluation. The experimental results of solar cell manufacturing demonstrate the applicability of the proposed hybrid method and validate the efficiency of the NSGA-II compared with an improved strength Pareto evolutionary algorithm. [ABSTRACT FROM AUTHOR]

Physics-informed neural networks formulation allows the neural network to be trained by both the training data and prior domain knowledge about the physical system that models the data. In particular, it has a loss function for the data and the physics, where the latter is the deviation from a partial differential equation describing the system. Conventionally, both loss functions are combined by a weighted sum, whose weights are usually chosen manually. It is known that balancing between different loss terms can make the training process more efficient. In addition, it is necessary to find the optimal architecture of the neural network in order to find a hypothesis set in which is easier to train the PINN. In our work, we propose a multi-objective optimization approach to find the optimal value for the loss function weighting, as well as the optimal activation function, number of layers, and number of neurons for each layer. We validate our results on the Poisson, Burgers, and advection-diffusion equations and show that we are able to find accurate approximations of the solutions using optimal hyperparameters. [ABSTRACT FROM AUTHOR]

This paper presents a novel two-stage progressive search approach with unsupervised feature learning and Q-learning (TSLL) to enhance surrogate-assisted evolutionary optimization for medium-scale expensive problems. The method attempts to address the challenges posed by multi-polar and multi-variable coupling properties in such problems. During the iteration, TSLL splits the optimization process into two distinct stages. First, two unsupervised feature learning techniques: principal component analysis (PCA) and Autoencoder, are utilized to improve the representation of potential optimal samples in the solution space. PCA is used for feature reduction, extracting the most important features. On the other hand, Autoencoder focuses on reconstructing features within the medium-scale solution space. To ensure comprehensive exploration of the entire solution space, TSLL employs two distinct surrogate modeling approaches along with Q-learning in the second stage to dynamically select the mutation strategy for the differential evolution operator. Numerous experiments demonstrate the superiority of TSLL over five state-of-the-art surrogate-assisted approaches and two sophisticated evolutionary algorithms including the winner of CEC 2017 on medium-scale benchmark problems and a wind farm layout problem. [ABSTRACT FROM AUTHOR]

Traditional path planning algorithms typically focus only on path length, which fails to meet the low energy consumption requirements for wall-climbing robots in bridge inspection. This paper proposes an improved sparrow search algorithm based on logistic–tent chaotic mapping and differential evolution, aimed at addressing the issue of the sparrow search algorithm's tendency to fall into local optima, thereby optimizing path planning for bridge inspection. First, the initial population is optimized using logistic–tent chaotic mapping and refracted opposition-based learning, with dynamic adjustments to the population size during the iterative process. Second, improvements are made to the position updating formulas of both discoverers and followers. Finally, the differential evolution algorithm is introduced to enhance the global search capability of the algorithm, thereby reducing the robot's energy consumption. Benchmark function tests verify that the proposed algorithm exhibits superior optimization capabilities. Further path planning simulation experiments demonstrate the algorithm's effectiveness, with the planned paths not only consuming less energy but also exhibiting shorter path lengths, fewer turns, and smaller steering angles. [ABSTRACT FROM AUTHOR]

The breakthrough of AlphaFold2 and the publication of AlphaFold DB represent a significant advance in the field of predicting static protein structures. However, AlphaFold2 models tend to represent a single static structure, and multiple-conformation prediction remains a challenge. In this work, we proposed a method named MultiSFold, which uses a distance-based multi-objective evolutionary algorithm to predict multiple conformations. To begin, multiple energy landscapes are constructed using different competing constraints generated by deep learning. Subsequently, an iterative modal exploration and exploitation strategy is designed to sample conformations, incorporating multi-objective optimization, geometric optimization and structural similarity clustering. Finally, the final population is generated using a loop-specific sampling strategy to adjust the spatial orientations. MultiSFold was evaluated against state-of-the-art methods using a benchmark set containing 80 protein targets, each characterized by two representative conformational states. Based on the proposed metric, MultiSFold achieves a remarkable success ratio of 56.25% in predicting multiple conformations, while AlphaFold2 only achieves 10.00%, which may indicate that conformational sampling combined with knowledge gained through deep learning has the potential to generate conformations spanning the range between different conformational states. In addition, MultiSFold was tested on 244 human proteins with low structural accuracy in AlphaFold DB to test whether it could further improve the accuracy of static structures. The experimental results demonstrate the performance of MultiSFold, with a TM-score better than that of AlphaFold2 by 2.97% and RoseTTAFold by 7.72%. The online server is at http://zhanglab-bioinf.com/MultiSFold. [ABSTRACT FROM AUTHOR]

The exponential growth of technology and advent of the Internet of Things (IoT) paradigm have caused large volumes of data to be continuously generated from the intelligent devices. One common feature of these devices is their limited capabilities, hence, they are not able to process large volumes of generated data. However, the processing of these data in the cloud leads to high latency and high power consumption. Hence, providing services to the latency-sensitive IoT applications in the cloud is a challenging issue. Fog computing as a complement to the cloud, allows data to be processed near IoT devices. However, the resources in the fog layer are heterogeneous. Thus, the proper distribution of tasks among heterogeneous nodes while serving the task within the intended deadline is of great importance. In this paper, we have presented a task scheduling model in the fog-cloud paradigm, which formulates the task scheduling problem as a multi-objective optimization problem with the aim of minimizing service response time and the total energy consumption of the system, while considers deadline and load balancing constraints. Since the problem of task scheduling is np-hard, we have proposed a modified version of Strength Pareto Evolutionary Algorithm II (SPEA-II) with customized operators to achieve the optimal scheduling strategy. The experimental results reveal that the proposed scheme outperforms some benchmarking algorithms in terms of service response time and energy consumption. Furthermore, by optimal distribution of tasks among heterogeneous computing nodes, it leads to better resource utilization and improvement in the percentage of missed-deadline tasks. [ABSTRACT FROM AUTHOR]

Although Cyber–Physical Systems (CPSs) provide a flexible architecture for enterprises to deal with changing demand, an effective method to organize and allocate resources while considering sustainability factors is required to meet customers' order requirements and mitigate negative impacts on the environment. The planning of processes to achieve sustainable CPSs becomes an important issue to meet demand timely in a dynamic environment. The problem with planning processes in sustainable CPSs is the determination of the configuration of workflows/resources to compose processes with desirable properties, taking into account time and energy consumption factors. The planning problem in sustainable CPSs can be formulated as an integer programming problem with constraints, and this poses a challenge due to computational complexity. Furthermore, the ever-shrinking life cycle of technologies leads to frequent changes in processes and makes the planning of processes a challenging task. To plan processes in a changing environment, an effective planning method must be developed to automate the planning task. To tackle computational complexity, evolutionary computation approaches such as bio-inspired computing and metaheuristics have been adopted extensively in solving complex optimization problems. This paper aims to propose a solution methodology and an effective evolutionary algorithm with a local search mechanism to support the planning of processes in sustainable CPSs based on an auction mechanism. To achieve this goal, we focus on developing a self-adaptive neighborhood search-based Differential Evolution method. An effective planning method should be robust in terms of performance with respect to algorithmic parameters. We assess the performance and robustness of this approach by performing experiments for several cases. By comparing the results of these experiments, it shows that the proposed method outperforms several other algorithms in the literature. To illustrate the robustness of the proposed self-adaptive algorithm, experiments with different settings of algorithmic parameters were conducted. The results show that the proposed self-adaptive algorithm is robust with respect to algorithmic parameters. [ABSTRACT FROM AUTHOR]

This paper introduces an evolutionary algorithm for objective functions defined over clouds of points of varying sizes. Such design variables are modeled as uniform discrete measures with finite support and the crossover and mutation operators of the algorithm are defined using the Wasserstein barycenter. We prove that the Wasserstein-based crossover has a contracting property in the sense that the support of the generated measure is included in the closed convex hull of the union of the two parents' supports. We introduce boundary mutations to counteract this contraction. Variants of evolutionary operators based on Wasserstein barycenters are studied. We compare the resulting algorithm to a more classical, sequence-based, evolutionary algorithm on a family of test functions that include a wind-farm layout problem. The results show that Wasserstein-based evolutionary operators better capture the underlying geometrical structures of the considered test functions and outperform a reference evolutionary algorithm in the vast majority of the cases. The tests indicate that the mutation operators play a major part in the performances of the algorithms. [ABSTRACT FROM AUTHOR]

Numerous surrogate-assisted evolutionary algorithms have been proposed for expensive optimization problems. However, each surrogate model has its own characteristics and different applicable situations, which caused a serious challenge for model selection. To alleviate this challenge, this paper proposes an adaptive surrogate-assisted particle swarm optimization (ASAPSO) algorithm by effectively combining global and local surrogate models, which utilizes the uncertainty level of the current population state to evaluate the approximation ability of the surrogate model in its predictions. In ASAPSO, the transformation between local and global surrogate models is controlled by an adaptive Gaussian distribution parameter with a gauge of the advisability to improve the search process with better local exploration and diversity in uncertain solutions. Four expensive optimization benchmark functions and an airfoil aerodynamic real-world engineering optimization problem are utilized to validate the effectiveness and performance of ASAPSO. Experimental results demonstrate that ASAPSO has superiority in terms of solution accuracy compared with state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

The product form serves as a crucial information carrier for expressing design concepts and encompasses significant valuable references. During the product iteration process, changes in design subjects, such as designers and decision-makers, result in substantial variability and uncertainty in the direction of product form evolution. To address these issues, an evolutionary design method for product forms based on the gray Markov model and an evolutionary algorithm is proposed in this study. Firstly, quadratic curvature entropy is utilized to quantify historical form features of product evolution. Subsequently, the original data on product form feature evolution are fitted and predicted using the gray Markov model, thereby obtaining the predicted value of the latest generation of product form features, which is determined to be 0.14586. Finally, this study uses this predicted value to construct a fitness function in the framework of an evolutionary algorithm, which in turn identifies next-generation product forms that can stimulate designers' creative thinking. The method's application is illustrated using the side outer contour of the Audi A4 automobile as an example. The research findings demonstrate that combining the gray Markov model with an evolutionary algorithm can effectively simulate designers' understanding of previous generations' design concepts and achieve stable inheritance of these design concepts during product iteration. This approach mitigates the risk of abrupt changes in design concepts caused by designers and decision-makers due to personal cognitive biases, thereby enhancing product development efficiency. [ABSTRACT FROM AUTHOR]

This study examines the absorption performance of rectangular sonic black holes (SBHs), which are designed to provide broadband anechoic termination for rectangular waveguides. The SBHs explored in this work consist of a series of opposing rib pairs embedded within the waveguide, where the distance between the ribs in each pair decreases towards the end of the structure according to a specific profile. A computationally efficient mathematical model, combined with an evolutionary optimization algorithm, is employed to determine the optimal geometrical parameters, including the SBH profile, which maximize absorption performance over a broad frequency range. As the optimal geometries feature very fine internal structures, which pose challenges for practical implementation, micro-perforated plates are incorporated to introduce additional losses. Numerical simulations and optimizations are again utilized to identify the geometrical and physical parameters that maximize the absorption performance of these modified structures. The results demonstrate superior absorption performance, even with internal structures compatible with contemporary manufacturing processes. The results of the numerical simulations are validated via a comparison with detailed and accurate mathematical model. [ABSTRACT FROM AUTHOR]

Evolutionary Algorithms (EAs), including Evolutionary Strategies (ES) and Genetic Algorithms (GAs), have been widely accepted as competitive alternatives to Policy Gradient techniques for Deep Reinforcement Learning (DRL). However, they remain eclipsed by cutting-edge DRL algorithms in terms of time efficiency, sample complexity, and learning effectiveness. In this paper, aiming at advancing evolutionary DRL research, we develop an evolutionary policy optimization algorithm with three key technical improvements. First, we design an efficient layer-wise strategy for training DNNs through Covariance Matrix Adaptation Evolutionary Strategies (CMA-ES) in a highly scalable manner. Second, we establish a surrogate model based on proximal performance lower bound for fitness evaluations with low sample complexity. Third, we embed a gradient-based local search technique within the evolutionary policy optimization process to further improve the learning effectiveness. The three technical innovations jointly forge a new EA for DRL method named Proximal Evolutionary Strategies (PES). Our experiments on ten continuous control problems show that PES with layer-wise training can be more computationally efficient than CMA-ES; our surrogate model can remarkably reduce the sample complexity of PES in comparison to latest EAs for DRL including CMA-ES, OpenAI-ES, and Uber-GA; PES with gradient-based local search can significantly outperform several promising DRL algorithms including TRPO, AKCTR, PPO, OpenAI-ES, and Uber-GA. [ABSTRACT FROM AUTHOR]

The complexity of next-generation wireless communications, especially Beyond 5G and 6G communication systems, will be handled by artificial intelligence-based management paradigms. The joint selection of routes and functional split levels involves critical decisions that network infrastructure providers need to make to support requests from virtual Mobile Network Operators (vMNOs). These decisions comprise the assignment and configuration of physical network resources, which must comply with the specific quality of service restrictions of each vMNO request. Recent work defined a detailed mathematical model for this complex challenge, its formulation as a constrained, discrete optimization problem, and the first algorithmic approaches. It was also found that an evolutionary algorithm delivers higher-quality solutions than an ad-hoc heuristic, and faster running times compared to a well-known commercial solver. This paper introduces a memetic algorithm that exploits the strengths of the former evolutionary method while incorporating several key innovations: a domain-specific recombination operator; a specialized repairing procedure; an enhanced fitness evaluation scheme; and a multiobjective archiving strategy that preserves promising solution trade-offs. We conduct a comprehensive evaluation of the performance and behavior of this proposal, as well as the contribution of each specific design component. The results highlight that our memetic algorithm consistently outperforms previous approaches from the literature, providing better trade-offs in terms of solution quality and the rate at which vMNO requests are successfully fulfilled. [ABSTRACT FROM AUTHOR]

Copyright of Przegląd Elektrotechniczny is the property of Przeglad Elektrotechniczny and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)