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]

Instantaneous data processing has the potential to enhance scalability, lessen power usage, and permit and improve data presentation in Consumer Internet of Things (CIoT) devices. In simple terms, cloud-based solutions cannot handle many IoT applications. According to Industrialized IoT (IIoT) technologies, an automated resource allocation system can improve service delivery and minimize healthcare costs. To maximize resource usage and response time for end users, there needs to be an effective method to efficiently distribute workload between Fog Layer and Cloud Connection and enhance cloud network capital allocation. Data analytics of complex and vital healthcare data requires timely responses, making it complicated. This paper proposes a design based on the Lanner Swarm Optimization (LSO) algorithm, which was developed to overcome inefficient heuristic strategies where data is transported to the cloud layer based on traffic type. The LSO algorithm is used to improve resource allocation and workload distribution in cloud-assisted CIoT applications for smart healthcare systems, improving scalability, power consumption, and data processing. The objective function determines if diverse virtual machines (VMs) vary accomplishment time the most, considering this study's updating and pruning restrictions. The experimentation analysis demonstrated that the proposed load balancing and work scheduling method outperforms evolutionary and heuristics algorithms. In experimentation, the research model attains a makespan of 10 s, response time of 5.5 s, resource utilization with a rate of 0.9, execution time of 13 s, latency of 10 ms, throughput of 0.78 s, and delivery rate of 0.74%. At resource scheduling, the LSO model had the best payload routing, latency, packet delivery ratio, and network lifetime. [ABSTRACT FROM AUTHOR]

Lung Cancer is the deadliest cancer with maximum mortality rates all over the world. If lung cancers are not detected at an early stage, they will continue to be the leading cause of death due to cancer. Convolution neural networks (CNNs), a type of deep learning approach, have produced better outcomes for diagnosing malignant lung nodules. However, CNN can have variance in output which can be reduced using the ensemble learning technique. CNN ensemble approach also reduces the generalization error and increases the accuracy of lung nodule malignancy prediction using the ensemble CNN learning technique. In this study we reduce the variance in output and also improve the performance of lung nodule classification by using the weighted average ensemble technique on convolution models such as VGG16, Densenet, and Alexnet, and the weights are optimized using an evolutionary algorithm like grey wolf optimizer, whale swarm optimizer, firefly optimizer, differential evolution, particle swarm optimizer, and bat optimizer. The proposed approach uses a heterogeneous ensemble with a weighted approach and is evaluated on the LUNA 16 dataset, on which it has achieved an accuracy, sensitivity, and specificity of 96%, 97.43%, and 93.08% respectively, with an AUC score of 0.95 using an evolutionary algorithm like Bat Optimizer to optimize the weights. [ABSTRACT FROM AUTHOR]

Introduction: The integration of self-attention mechanisms into Spiking Neural Networks (SNNs) has garnered considerable interest in the realm of advanced deep learning, primarily due to their biological properties. Recent advancements in SNN architecture, such as Spikformer, have demonstrated promising outcomes. However, we observe that Spikformer may exhibit excessive energy consumption, potentially attributable to redundant channels and blocks. Methods: To mitigate this issue, we propose a one-shot Spiking Transformer Architecture Search method, namely Auto-Spikformer. Auto-Spikformer extends the search space to include both transformer architecture and SNN inner parameters. We train and search the supernet based on weight entanglement, evolutionary search, and the proposed Discrete Spiking Parameters Search (DSPS) methods. Benefiting from these methods, the performance of subnets with weights inherited from the supernet without even retraining is comparable to the original Spikformer. Moreover, we propose a newfitness function aiming to find a Pareto optimal combination balancing energy consumption and accuracy. Results and discussion: Our experimental results demonstrate the effectiveness of Auto-Spikformer, which outperforms the original Spikformer and most CNN or ViT models with even fewer parameters and lower energy consumption. [ABSTRACT FROM AUTHOR]

Forecasting of long-term annual electricity demand is studied utilizing historical data for electrical energy consumption and socio-economic indicators—gross domestic product, population, import and export values for the case of Turkey between 1975 and 2020. A quadratic model for electrical energy consumption was applied to define the relation between the historical and predicted data. This model used metaheuristic algorithms; genetic algorithms (GA), differential evolution (DE), particle swarm optimization (PSO), artificial intelligence (AI) approaches; neural networks (NN), and adaptive network fuzzy inference systems (ANFIS), and machine learning (ML) applications; all models undergo testing, but the top four models—stepwise linear regression (SLR), NN, Gaussian process regression (GPR) with exponential, and GPR with squared exponential—are selected for additional research to determine the best forecasting model based on their forecasting performance. Comparing the finalized models SLR produced the best forecasting model with a mean absolute percentage error (MAPE) value of 2.36%, followed by GA with 2.97%. Turkey's yearly electrical energy consumption is projected under three possible scenarios through 2030. Finding the most appropriate forecasting model among the models studied for long-term electrical energy forecasting is ultimately the primary goal of this research. Simulations are done on the MATLAB™ platform. [ABSTRACT FROM AUTHOR]

The selection of weight matrices Q and R in the LQR control strategy for active suspension is susceptible to subjective interference. To address this issue, a modified differential evolutionary algorithm is proposed to optimize the active suspension LQR controller, ensuring that the weighting coefficients are set to their optimal values. The differential evolutionary algorithm exhibits drawbacks in terms of its slow convergence rate and the significant impact of algorithm parameter settings on the obtained results. An modified differential evolutionary algorithm that is adaptive to the two candidate mutation strategies and adaptively adjusts the scaling factor and crossover rate is proposed so as to better improve the ability of jumping out of the local optimum and global search. The algorithm's functionality is verified by constructing a 1/4 suspension model in the Simulink software platform and implementing a modified differential evolution algorithm program written in C++ language using MATLAB. The program iterates through Simulink inputs to obtain the optimal fitness value for three suspension comfort indices. By comparing the results with those obtained from passive suspension and traditional LQR control of active suspension, optimizing the LQR control of active suspension based on the modified differential evolution algorithm can effectively reduce vehicle vibration amplitude while considering overall suspension performance enhancement, thereby significantly improving ride comfort and handling stability. [ABSTRACT FROM AUTHOR]

In recent decades, the demand for optimization techniques has grown due to rising complexity in real-world problems. Hence, this work introduces the Hyperbolic Sine Optimizer (HSO), an innovative metaheuristic specifically designed for scientific optimization. Unlike conventional approaches, HSO takes a unique approach by engaging individual members of the population, ensuring a comprehensive exploration of solution spaces. Employing distinctive exploration and exploitation phases, coupled with hyperbolic sinh function convergence, the optimizer enhances speed, simplify parameter adjustment, alleviates slow convergence, and demonstrates efficiency in high-dimensional optimization. This approach is designed to tackle optimization challenges and enhance adaptability in unpredictable real-world scenarios. The evaluation of HSO's performance unfolds through four distinct testing phases. Initially, a set of 65 widely recognized benchmark functions is employed. These functions cover both unimodal and multi-modal varieties across dimensions of 30, 100, 500, and 1000, including fixed-dimensional functions, to comprehensively assess the exploration, exploitation, local optima avoidance, and convergence capabilities of the proposed algorithm. The results of the HSO algorithm are then compared to those of 15 state-of-the-art metaheuristic algorithms and 8 recently published algorithms. Secondly, HSO's performance is assessed in comparison with the benchmark suite from the Institute of Electrical and Electronics Engineers (IEEE) Congress on Evolutionary Computation (CEC). This suite includes 15 benchmark functions for CEC-2015 and an additional 30 benchmark functions for CEC-2017. During the third phase, HSO tackles seven real-world classical engineering design problems by addressing both the constrained and unconstrained optimization challenges of IEEE CEC-2020. Finally, HSO undertakes training for a multilayer perceptron, utilizing four distinct datasets. To qualitatively assess HSO's performance, two statistical analyses—the Friedman and T tests—are employed. The findings of HSO showcase its adaptability and effectiveness as a high-performing optimizer in engineering optimization challenges. Note that the source code of the HSO algorithm are publicly accessible via https://github.com/Shivankur07/Hyperbolic-Sine-Optimizer.git. [ABSTRACT FROM AUTHOR]

Differential evolution algorithm is a very powerful and recently proposed evolutionary algorithm. Generally, only a mutation operator and predefined parameter values of differential evolution algorithm are utilized to solve various optimization problems, which limits the performance of the algorithm. In this paper, six commonly used mutation operators are divided into three categories according to their own features. A mutation pool is established based on the three categories. A parameter pool with three predefined values is designed. During evolution, three mutation operators are randomly chosen from the three categories, and three parameter values are also randomly selected from the parameter pool. The three groups of mutation operators and parameter values are employed to produce trial vectors. The proposed algorithm makes good use of different mutation operators. Three recently proposed differential evolution variants and three non-differential evolution algorithms are used to make comparisons on the 29 testing functions from CEC. The experimental results have demonstrated that the proposed algorithm is very competitive. The proposed algorithm is utilized to solve three real applications, and the results are superior. [ABSTRACT FROM AUTHOR]

A cost-effective approach using metamodel-based design optimization has been employed to determine the optimal configuration of input parameters for a desired output in an industrial engineering problem, with a case study of a bio-filtration system. Inhomogeneous multiphase flow around a simplified bio-filtration system under backwashing conditions was simulated based on parameter sampling through the design of experiments. Metamodeling was conducted along with a sensitivity analysis of input parameters for desired outputs, which helped filter out unimportant parameters and achieve computational benefits during the modeling process. Finally, optimization was performed using the metamodel and an evolutionary algorithm to determine the optimal parameter configuration for the desired outputs, i.e., evenly distributed filter-bed mass flow. The numerical approach can yield well-predicted results with significantly reduced computational time compared to full computational fluid dynamics simulations, potentially reducing the number of expensive simulations required for various industrial engineering problems. [ABSTRACT FROM AUTHOR]

Recently, learning classifier systems (LCS) have been used for a variety of Internet of Things (IoT) devices and multi-cloud services, including cloud-based centralized control of physical robots and actuators in continuous-time environments. Performance analysis of sensors, navigation of humanoid robots and intelligent control of rescue systems. In these systems, we can run evolutionary or intuitive algorithms on cloud servers to search the space of rules and simultaneously other learning processes to assign how to interact with the environment to the rules in the classification. Also, the problem of continuous congestion, traffic reduction, network routing and predicting traffic conditions in wireless networks is the main challenge facing these systems in real environments. Usually such systems are non-Markovian. Therefore, they need memory to save system states. This paper presents a framework for XCS-based memory-based LCS. In addition to identifying optimal rules in overlapping modes, the XCS architecture is equipped with a memory. Memory stores the most efficient classifier rules. These rules reduce the steps to reach the goal. In the first proposed method, only those rules that affect the moving motion are kept in memory. As the number of rules increases, some of them are deleted according to memory space. In the second proposed method, some features are added to the rules of this memory and the performance of the memory is optimized using evolutionary algorithms, which are used to remove the less used rules. The relative success of the proposed LCS architecture in solving well-known maze problems compared to the conventional XCS architecture confirms its efficiency in increasing the number of successes and reducing the steps to reach the goals. The results of this research are suggested as a suitable solution for reducing routing time, reducing network load in the problem of congestion and traffic in solving problems related to wireless networks. [ABSTRACT FROM AUTHOR]

We propose a new method based on discrete Fourier analysis to analyze the time evolutionary algorithms spend on plateaus. This immediately gives a concise proof of the classic estimate of the expected runtime of the (1 + 1) evolutionary algorithm on the Needle problem due to Garnier et al. (Evol Comput 7:173–203, 1999). We also use this method to analyze the runtime of the (1 + 1) evolutionary algorithm on a benchmark consisting of n / ℓ plateaus of effective size 2 ℓ - 1 which have to be optimized sequentially in a LeadingOnes fashion. Using our new method, we determine the precise expected runtime both for static and fitness-dependent mutation rates. We also determine the asymptotically optimal static and fitness-dependent mutation rates. For ℓ = o (n) , the optimal static mutation rate is approximately 1.59/n. The optimal fitness dependent mutation rate, when the first k fitness-relevant bits have been found, is asymptotically 1 / (k + 1) . These results, so far only proven for the single-instance problem LeadingOnes, thus hold for a much broader class of problems. We expect similar extensions to be true for other important results on LeadingOnes. We are also optimistic that the Fourier analysis approach can be applied to other plateau problems as well. [ABSTRACT FROM AUTHOR]

The horse (Equus caballus) varieties from Skyros and Rhodes islands (Greece) in the Aegean archipelago are extremely small, reaching shoulder heights of only about 1 m. Furthermore, the Japanese archipelago is home to eight small, native horse breeds. We investigated the evolutionary morphology and provided a review of historical documentations of these horses of cultural interest in Greece and Japan, thus providing a comparison of the independent evolution of small size in islands. We integrate cranial data from historical literature with data from newly gathered and curated skulls and analyse a measurement dataset featuring various domestic and mainland horse breeds and varieties. We use non-invasive imaging to study and measure 3D models of the bony labyrinth, housing the inner ear, and the braincase endocast. When considering the effects of allometry by regressing each PC1 scores (for each set of measurements) with the cranial geometric mean from linear measurements as a body size proxy, we show that size explains a large amount of the shape variation in horse crania, the bony labyrinths and brain endocasts. We found high intrabreed variation in all the analysed datasets. Globally, there are at least 30 distinct horse populations on islands, offering the chance to further study processes of convergence in morphological divergence and evaluate the effect of drift and the environment. [ABSTRACT FROM AUTHOR]

The current research introduces a multilayer functional structure along with its corresponding multi-objective optimization design strategy intended to improve the design efficiency of materials exhibiting remarkable properties in both load-bearing and electromagnetic wave absorption. The composite structure contains several layers of graphite oxide reinforced epoxy resin, each of which has a different thickness and volume fraction of fillers. The proposed strategy employs the volume fraction of fillers and thickness of each layer as the design variables, with the electromagnetic wave absorption bandwidth and bending stiffness of the entire structure serving as objectives. The multi-objective model was derived using the Maxwell-Garnett Model, Halpin-Tsai Model, Transmission Line Theory and Classical Laminate Theory. To efficiently optimize the multilayer structure, the JAYA, an evolutionary algorithm is employed as optimizer. The results indicate that the optimized structure exhibits a considerable increase in electromagnetic wave absorbing capacity and a slight increase in load-bearing performance relative to the original structure, while the total thickness remains constant. In addition, the whole process takes only a few seconds. [ABSTRACT FROM AUTHOR]

In this paper, genomics and precision medicine have witnessed remarkable progress with the advent of high-throughput sequencing technologies and advances in data analytics. However, because of the data’s great dimensionality and complexity, the processing and interpretation of large-scale genomic data present major challenges. In order to overcome these difficulties, this research suggests a novel Intelligent Mutation-Based Evolutionary Optimization Algorithm (IMBOA) created particularly for applications in genomics and precision medicine. In the proposed IMBOA, the mutation operator is guided by genome-based information, allowing for the introduction of variants in candidate solutions that are consistent with known biological processes. The algorithm’s combination of Differential Evolution with this intelligent mutation mechanism enables effective exploration and exploitation of the solution space. Applying a domain-specific fitness function, the system evaluates potential solutions for each generation based on genomic correctness and fitness. The fitness function directs the search toward ideal solutions that achieve the problem’s objectives, while the genome accuracy measure assures that the solutions have physiologically relevant genomic properties. This work demonstrates extensive tests on diverse genomics datasets, including genotype-phenotype association studies and predictive modeling tasks in precision medicine, to verify the accuracy of the proposed approach. The results demonstrate that, in terms of precision, convergence rate, mean error, standard deviation, prediction, and fitness cost of physiologically important genomic biomarkers, the IMBOA consistently outperforms other cutting-edge optimization methods. [ABSTRACT FROM AUTHOR]

It is crucial to understand and meet the multi-dimensional affective image needs of users for product form in a user demand-oriented product development model. Multi-objective evolutionary algorithms based on decomposition will be introduced into the field of kansei engineering to carry out research on product form optimisation design based on multi-objective evolutionary algorithms. A constrained multi-objective discrete optimisation model was established using the kansei engineering prediction model constructed through machine learning techniques as the objective function, and a reference vector guided evolutionary algorithm was used to solve it. The superiority of this method was verified by comparing it with other commonly used solving methods in this field. Combining entropy weight method and TOPSIS, select the optimisation design scheme that best meets the multi-dimensional affective needs of users from the obtained pareto set. Taking the train as an example, the proposed method was explained. The results indicate that the optimisation scheme obtained by this method can achieve the improvement and optimisation of product form in multiple affective dimensions. Meanwhile, a comparative study on the applicability of multi-objective evolutionary algorithms in the form optimisation problem of different affective dimensions is carried out to provide reference and suggestions for subsequent product design research. [ABSTRACT FROM AUTHOR]

Recent studies showed that deep learning techniques and image processing can identify the distinguishing design principles in architectural façades. However, predicting the strength of a principle is still a challenging task, as it requires a huge amount of annotated design variations. The difficulties in both searching such big numbers of data – and its labelling by experts – slow down the research. This paper proposes a computation approach for obtaining this type of data faster. With the help of parametric modelling and evolutionary algorithms, we could manipulate the design elements, and thereby generate different solutions. An integrated fuzzy logic decision mechanism could enable to carry human knowledge in the judging and labelling of alternatives automatically. The final synthetic data developed from real building images could be used for machine learning applications to enhance our understanding of artistic expression. [ABSTRACT FROM AUTHOR]

In this paper, with the development of an intelligent power system idea, sustainable energy sources were increasingly deployed, including transmission and distribution systems networks. As a result, optimal use of cascaded H-bridge inverter topologies (MLIs) and power distribution operations is critical for long-term power generation. Traditionally, selective harmonics reduction models must be performed to achieve the optimal switching frequency of multilevel inverters. This research aims to determine the switching frequency for wind-incorporated multilevel inverters to reduce overall harmonic components used in grid applications. This research adds towards the best possible solution by employing multiple newly established adaptive optimization techniques: MNSGA-II and salp swarm. The well-known genetic algorithm and particle swarm optimization are used for the wind-tied multilevel inverters optimization issue. Sevenlevel, eleven-level, and fifteen-level MLIs were employed to reduce overall harmonic distortion. The reliability and convergence rate of simulated data with various modulation indices for seven-, eleven-, and fifteen-level MLIs are obtained and compared. Models are developed based on MATLAB Simulink and are used to validate quantitative measurements. [ABSTRACT FROM AUTHOR]

With the increasing complexity of unmanned aerial vehicle (UAV) missions, single-objective optimization for UAV trajectory planning proves inadequate in handling multiple conflicting objectives. There is a notable absence of research on multi-objective optimization for UAV trajectory planning. This study introduces a novel two-stage co-evolutionary multi-objective evolutionary algorithm for UAV trajectory planning (TSCEA). Firstly, two primary optimization objectives were defined: minimizing total UAV flight distance and obstacle threats. Five constraints were defined: safe distances between UAV trajectory and obstacles, maximum flight altitude, speed, flight slope, and flight corner limitations. In order to effectively cope with UAV constraints on object space limitations, the evolution of the TSCEA algorithm is divided into an exploration phase and an exploitation phase. The exploration phase employs a two-population strategy where the main population ignores UAV constraints while an auxiliary population treats them as an additional objective. This approach enhances the algorithm's ability to explore constrained solutions. In contrast, the exploitation phase aims to converge towards the Pareto frontier by leveraging effective population information, resulting in multiple sets of key UAV trajectory points. Three experimental scenarios were designed to validate the effectiveness of TSCEA. Results demonstrate that the proposed algorithm not only successfully navigates UAVs around obstacles but also generates multiple sets of Pareto-optimal solutions that are well-distributed across objectives. Therefore, compared to single-objective optimization, TSCEA integrates the UAV mathematical model comprehensively and delivers multiple high-quality, non-dominated trajectory planning solutions. [ABSTRACT FROM AUTHOR]

Increasing energy utilization is one of the main obstacles to reliable interaction in dynamic digital networks. We concentrate on improving the network's topology by taking this difficulty into account. In this study, we build a hybrid star-mesh topology to minimize both the energy usage and latency of the network. AOMDV routes is used in hybrid network topologies to create various pathways in the distance from the point of origin and the goal. When a routing path loses its energy level, the best path is selected using ChOA from the available options. The system's energy efficiency is improved by choosing the best route. According to mimicry findings, the suggested method performs better when thinking of supply number, energy consumption, delay, and throughput. [ABSTRACT FROM AUTHOR]

Sustainable energies from weather are the most ubiquitous and non-depleted resources. However, existing devices exploiting weather-dependent energies are sensitive to weather conditions and geographical locations, making their universal applicability challenging. Herein, we propose an all-weather sustainable glass surface integrating a triboelectric nanogenerator and radiative cooler, which serves as a sustainable device, harvesting energy from raindrops and saving energy on sunny days. By systematically designing transparent, high-performance triboelectric layers, functioning as thermal emitters simultaneously, particularly compatible with radiative cooling components optimized with an evolutionary algorithm, our proposed device achieves optimal performance for all-weather-dependent energies. We generate 248.28 Wm−2 from a single droplet with an energy conversion ratio of 2.5%. Moreover, the inner temperature is cooled down by a maximum of 24.1 °C compared to pristine glass. Notably, as the proposed device is realized to provide high transparency up to 80% in the visible range, we are confident that our proposed device can be applied to versatile applications. Weather-dependent energies are sensitive to weather and geographical conditions. Here, authors propose an all-weather sustainable device integrating a triboelectric nanogenerator and radiative cooler, enabling energy harvesting from rain and saving energy on a sunny day. [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]

Constrained multiobjective optimization problems (CMOPs) are widespread in reality. The presence of constraints complicates the feasible region of the original problem and increases the difficulty of problem solving. There are not only feasible regions, but also large areas of infeasible regions in the objective space of CMOPs. Inspired by this, this paper proposes a bidirectional coevolution method with reverse search (BCRS) combined with a two-stage approach. In the first stage of evolution, constraints are ignored and the population is pushed toward promising regions. In the second stage, evolution is divided into two parts, i.e., the main population evolves toward the constrained Pareto front (CPF) within the feasible region, while the reverse population approaches the CPF from the infeasible region. Then a solution exchange strategy similar to weak cooperation is used between the two populations. The experimental results on benchmark functions and real-world problems show that the proposed algorithm exhibits superior or at least competitive performance compared to other state-of-the-art algorithms. It demonstrates BCRS is an effective algorithm for addressing CMOPs. [ABSTRACT FROM AUTHOR]

In this paper, a genetic algorithm, one of the evolutionary algorithm optimization methods, is used for the first time for the problem of computing extremal binary self-dual codes. We present a comparison of the computational times between the genetic algorithm and a linear search for different size search spaces and show that the genetic algorithm is capable of computing binary self-dual codes significantly faster than the linear search. Moreover, by employing a known matrix construction together with the genetic algorithm, we are able to obtain new binary self-dual codes of lengths 68 and 72 in a significantly short time. In particular, we obtain 11 new binary self-dual codes of length 68 and 17 new binary self-dual codes of length 72. [ABSTRACT FROM AUTHOR]

Methaheuristics (MHs) are techniques widely used for solving complex optimization problems. In recent years, the interest in combining MH and machine learning (ML) has grown. This integration can occur mainly in two ways: ML-in-MH and MH-in-ML. In the present work, we combine the techniques in both ways—ML-in-MH-in-ML, providing an approach in which ML is considered to improve the performance of an evolutionary algorithm (EA), whose solutions encode parameters of an ML model—artificial neural network (ANN). Our approach called TS in EA in ANN employs a reinforcement learning neighborhood (RLN) mutation based on Thompson sampling (TS). TS is a parameterless reinforcement learning method, used here to boost the EA performance. In the experiments, every candidate ANN solves a regression problem known as protein structure prediction deviation. We consider two protein datasets, one with 16,382 and the other with 45,730 samples. The results show that TS in EA in ANN performs significantly better than a canonical genetic algorithm (GA in ANN) and the evolutionary algorithm without reinforcement learning (EA in ANN). Analyses of the parameter's frequency are also performed comparing the approaches. Finally, comparisons with the literature show that except for one particular case in the largest dataset, TS in EA in ANN outperforms other approaches considered the state of the art for the addressed datasets. [ABSTRACT FROM AUTHOR]

Manually designed convolutional neural networks have demonstrated excellent performance in various domains, but designing neural networks suitable for specific tasks poses significant challenges, and the emergence of Neural Structure Search (NAS) provides a new solution to this problem. However, existing algorithms either focus solely on network lightweight, resulting in subpar network performance, or excessively emphasize performance, leading to substantial network redundancy. With consideration for both network parameters and performance, this paper designs a hybrid search space based on residual modules and RepVGG modules using genetic algorithm, and stacks them together to form a more efficient network. To achieve this, we propose an efficient variable-length encoding strategy, utilizing units as the fundamental encoding space to encode variable-length individuals; we design evolutionary operations encompassing single-point crossover and three types of mutation operators to ensure population diversity; during training, a random forest-based performance predictor is employed to significantly shorten the network search time. To demonstrate the effectiveness of the proposed algorithm, we introduce the concept of transfer learning, which involves decoding the globally optimal solution, fine-tuning it, and then transferring it to three categories of real-world application datasets. Through comparisons with various algorithms, our approach consistently achieved leading performance. [ABSTRACT FROM AUTHOR]

The use of search‐based software engineering to address model‐driven engineering activities (SBMDE) is becoming more popular. Many maintenance tasks can be reformulated as a search problem, and, when those tasks are applied to software models, the search strategy has to retrieve a model fragment. There are no studies on the influence of the search parameters when applied to software models. This article evaluates the impact of different search parameter values on the performance of an evolutionary algorithm whose population is in the form of software models. Our study takes into account the nature of the model fragment location problems (MFLPs) in which the evolutionary algorithm is applied. The evaluation searches 1895 MFLPs (characterized through five measures that define MFLPs) from two industrial case studies and uses 625 different combinations of search parameter values. The results show that the impact on the performance when varying the population size, the replacement percentage, or the crossover rate produces changes of around 30% in performance. With regard to the nature of the problems, the size of the search space has the largest impact. Search parameter values and the nature of the MFLPs influence the performance when applying an evolutionary algorithm to perform fragment location on models. Search parameter values have a greater effect on precision values, and the nature of the MFLPs has a greater effect on recall values. Our results should raise awareness of the relevance of the search parameters and the nature of the problems for the SBMDE community. [ABSTRACT FROM AUTHOR]

Artificial neural network (NN) architecture design is a nontrivial and time-consuming task that often requires a high level of human expertise. Neural architecture search (NAS) serves to automate the design of NN architectures and has proven to be successful in automatically finding NN architectures that outperform those manually designed by human experts. NN architecture performance can be quantified based on multiple objectives, which include model accuracy and some NN architecture complexity objectives, among others. The majority of modern NAS methods that consider multiple objectives for NN architecture performance evaluation are concerned with automated feed forward NN architecture design, which leaves multi-objective automated recurrent neural network (RNN) architecture design unexplored. RNNs are important for modeling sequential datasets, and prominent within the natural language processing domain. It is often the case in real world implementations of machine learning and NNs that a reasonable trade-off is accepted for marginally reduced model accuracy in favour of lower computational resources demanded by the model. This paper proposes a multi-objective evolutionary algorithm-based RNN architecture search method. The proposed method relies on approximate network morphisms for RNN architecture complexity optimisation during evolution. The results show that the proposed method is capable of finding novel RNN architectures with comparable performance to state-of-the-art manually designed RNN architectures, but with reduced computational demand. [ABSTRACT FROM AUTHOR]

To calculate the losses of distribution feeders, this paper uses an iterative method that is limited to restricted measurements. The approach presented in this paper uses bill data in addition to output information from a very small number of real-time measurements located on the secondary side of distribution transformers. This method attempts to estimate the load of distribution transformers injected into LV feeders. Energy losses for LV feeders are evaluated by first estimating the power and periodic energy injected to each of the LV feeders and then subtracting the total consumption bills from these estimated values. By using this method, the amount of energy loss is estimated. In this article, a new method called iterative power factor adjustment method is considered as a potential method for estimating losses. The power factor can be increased by repeatedly using evolutionary algorithms and including capacitors in the system. In order to reduce system losses and increase network effectiveness. In this paper, a new method for examining and evaluating Non-Technical Losses (NTL) is proposed. This method considers load estimation and limited measurement to place high priority feeders. [ABSTRACT FROM AUTHOR]

Introduction: Epilepsy is a common neurological condition that affects a large number of individuals worldwide. One of the primary challenges in epilepsy is the accurate and timely detection of seizure. Recently, the graph regularized broad learning system (GBLS) has achieved superior performance improvement with its flat structure and less time-consuming training process compared to deep neural networks. Nevertheless, the number of feature and enhancement nodes in GBLS is predetermined. These node settings are also randomly selected and remain unchanged throughout the training process. The characteristic of randomness is thus more easier to make non-optimal nodes generate, which cannot contribute significantly to solving the optimization problem. Methods: To obtain more optimal nodes for optimization and achieve superior automatic detection performance, we propose a novel broad neural network named self-adaptive evolutionary graph regularized broad learning system (SaE-GBLS). Self-adaptive evolutionary algorithm, which can construct mutation strategies in the strategy pool based on the experience of producing solutions for selecting network parameters, is incorporated into SaE-GBLS model for optimizing the node parameters. The epilepsy seizure is automatic detected by our proposed SaE-GBLS model based on three publicly available EEG datasets and one private clinical EEG dataset. Results and discussion: The experimental results indicate that our suggested strategy has the potential to perform as well as current machine learning approaches. [ABSTRACT FROM AUTHOR]

AbstractIn order to improve the global search ability of the optimization algorithm when solving the path synthesis problem, this paper proposes a synthesis method of a four-bar mechanism based on the bisection strategy of the Lévy-PSO evolutionary algorithm. First, a synthesis equation of the target point is established based on the closed-loop vector method. Use the bisection strategy to cut the hinge coordinate variation range to reduce the probability of premature maturity of the algorithm. The error algorithm of the circular proximity function is used to reduce the search dimension of the optimization algorithm and improve search efficiency. Use the improved particle swarm algorithm based on Lévy to improve global search capabilities. Four multi-point path synthesis problem examples are given to verify the effectiveness and accuracy of the method. [ABSTRACT FROM AUTHOR]

Image forgery is one of the issues that can create challenges for law enforcement. Digital devices can easily Copy-move images, forging medical photos. In the insurance industry, forensics, and sports, image forgery has become very common and has created problems. Copy-Move Forgery in Medical Images (CMFMI) has led to abuses in areas where access to advanced medical devices is unavailable. The proposed model (SEC) is a three-part model based on an evolutionary algorithm that can detect fake blocks well. In the first part, suspicious points are discovered with the help of the SIFT algorithm. In the second part, suspicious blocks are found using the equilibrium optimization algorithm. Finally, color histogram Matching (CHM) matches questionable points and blocks. The proposed method (SEC) was evaluated based on accuracy, recall, and F1 criteria, and 100, 97.00, and 98.47% were obtained for the fake medical images, respectively. Experimental results show robustness against different transformation and post-processing operations on medical images. [ABSTRACT FROM AUTHOR]

Human capital management is a strategic element for companies in a globalized world. Therefore, they must use strategies and methods to recruit and select personnel assertively to focus their training, strengthening, and business growth efforts. Personnel selection can be seen as a decision problem and can be addressed in a multi-criteria decision-making context. This work aims to present the selection process of a barista in a Mexican coffee shop. The baristas could be the face of the company to customers, and they could significantly impact their overall experience. The personnel selection process included eleven candidates and three criteria. This process was performed using the ELECTRE-III to model the preferences of a decision-maker and RP2-NSGA-II+H, a multi-objective evolutionary algorithm that exploits fuzzy outranking relations to derive multi-criteria rankings. The ordering obtained with the algorithm did not have any inconsistency concerning the integral preference model, and it allowed for the selection of a candidate to occupy the barista position. The results show the relevance of combining preference modeling with multi-criteria analysis methods for decision-making and artificial intelligence techniques. [ABSTRACT FROM AUTHOR]

Without a well-defined energy management plan, achieving meaningful improvements in human lifestyle becomes challenging. Adequate energy resources are essential for development, but they are both limited and costly. In the literature, several solutions have been proposed for energy management but they either minimize energy consumption or improve the occupant's comfort index. The energy management problem is a multi-objective problem where the user wants to reduce energy consumption while keeping the occupant's comfort index intact. To address the multi-objective problem this paper proposed an energy control system for a green environment called PMC (Power Management and Control). The system is based on hybrid energy optimization, energy prediction, and multi-preprocessing. The combination of GA (Genetic Algorithm) and PSO (Particle Swarm Optimization) is performed to make a fusion methodology to improve the occupant comfort index (OCI) and decrease energy utilization. The proposed framework gives a better OCI when compared with its counterparts, the Ant Bee Colony Knowledge Base framework (ABCKB), GA-based prediction framework (GAP), Hybrid Prediction with Single Optimization framework (SOHP), and PSO-based power consumption framework. Compared with the existing AEO framework, the PMC gives practically the same OCI but consumes less energy. The PMC framework additionally accomplished the ideal OCI (i-e 1) when compared with the existing model, FA–GA (i-e 0.98). The PMC model consumed less energy as compared to existing models such as the ABCKB, GAP, PSO, and AEO. The PMC model consumed a little bit more energy than the SOHP but provided a better OCI. The comparative outcomes show the capability of the PMC framework to reduce energy utilization and improve the OCI. Unlike other existing methodologies except for the AEO framework, the PMC technique is additionally confirmed through a simulation by controlling the indoor environment using actuators, such as fan, light, AC, and boiler. [ABSTRACT FROM AUTHOR]

Neuroevolution is a promising approach for designing artificial neural networks using an evolutionary algorithm. Unlike recent trending methods that rely on gradient-based algorithms, neuroevolution can simultaneously evolve the topology and weights of neural networks. In neuroevolution with topological evolution, handling crossover is challenging because of the competing conventions problem. Mutation-based evolving artificial neural network is an alternative topology and weights neuroevolution approach that omits crossover and uses only mutations for genetic variation. This study enhances the performance of mutation-based evolving artificial neural network in two ways. First, the mutation step size controlling the magnitude of the parameter perturbation is automatically adjusted by a self-adaptive mutation mechanism, enabling a balance between exploration and exploitation during the evolution process. Second, the structural mutation probabilities are automatically adjusted depending on the network size, preventing excessive expansion of the topology. The proposed methods are compared with conventional neuroevolution algorithms using locomotion tasks provided in the OpenAI Gym benchmarks. The results demonstrate that the proposed methods with the self-adaptive mutation mechanism can achieve better performance. In addition, the adjustment of structural mutation probabilities can mitigate topological bloat while maintaining performance. [ABSTRACT FROM AUTHOR]

The intrusion detection system is responsible for revealing different intrusion activities, including the denial of service, man-in-middle, Mirai, Scan, and other types of intrusion activities. It is used in many applications, including the smart home Internet of Things networks, where security risks threaten the privacy of individuals. In this context, many works were proposed for detecting and classifying the different types of attacks. However, many challenges are identified for this type of problem, such as the large amount of data available, the imbalanced nature of the data, and the quality of detection and classification outcomes. This paper aims to address these challenges by proposing an approach that considers a metaheuristic-based random weight neural network to detect intrusion activities and classify the different types and subtypes of activities. The following points summarize the contribution of this paper. First, the automatic tuning of the neural network parameters where the weights, biases, regularization value, the number of neurons, and the type of activation function are optimized by different metaheuristic algorithms to produce high-quality results. Second, the proposed approach adopts a clustering with reduction technique to tackle the challenge of processing large volumes of data. Third, oversampling the dataset is also embedded in the proposed approach to avoid a biased classification of the majority class. The experiments are conducted based on a large dataset with more than half a million instances. The results show that the proposed approach outperforms the other classification approaches in geometric mean (G-Mean) and has promising results. [ABSTRACT FROM AUTHOR]

Evolutionary multitask optimization (EMTO) has developed fast recently, and many algorithms have emerged that solve several different problems simultaneously through knowledge transfer. Most algorithms use a single search operator in their processing. However, different tasks have distinct characteristics, and a single operator is often inadequate to adapt to different stages of the same task. In this paper, we propose a multiple search operator selection strategy by adaptive probability allocation, named adaptive multi-operator selection (AMOS) to address EMTO that features rapid convergence of populations. It can automatically select the best multiple search operators based on the characteristics of specific tasks and different stages of evolution. The primary contributions of the proposed algorithm are as follows: (1) It combines the basic concepts of multi-operator integration and adaptive search operator selection to select the best multiple search operators for each task at different evolutionary stages; (2) It facilitates the knowledge transfer through different solving operators between tasks; (3) It can be flexibly embedded into various frameworks of general EMTO algorithms with good results. In the experiments, we validate the performance of AMOS on CEC2017 benchmark suite, CMTOPs benchmark suite, and real-world EMTO problems, and experimental results demonstrate the effectiveness and generality of the proposed strategy. [ABSTRACT FROM AUTHOR]

Nonlinear equation systems (NESs) are ubiquitous in scientific and engineering domains, necessitating efficient methods for discovering multiple roots simultaneously. Employing evolutionary algorithms to solve NESs has received significant attention. To simultaneously locate multiple roots in a single run, this paper proposes a differential evolution algorithm with adaptive niching and reinitialisation (DE-ANR). The proposed differential evolution algorithm integrates four strategies to address the challenges posed by NESs. Firstly, DE-ANR employs a dynamic niche size control mechanism to adjust the niche size during evolution, striking a balance between exploration and exploitation. Secondly, a lifetime mechanism is introduced to identify stagnating individuals for reinitialisation, ensuring diversity of the population and preventing premature convergence. Thirdly, an improved archive technique is employed to conserve computational resources by eliminating redundant solutions, directing the algorithm's efforts toward unexplored regions of the solution space. Finally, an adaptive strategy is introduced to dynamically adjust the scaling factor F based on the feedback of evolving population, simplifying parameter tuning. Extensive evaluations on 30 diverse NES problems and the comparison results with 12 state-of-the-art algorithms clearly show the superiority of proposed method. [ABSTRACT FROM AUTHOR]

In order to achieve maximum carbon reduction during the operation of pure electric buses, the author proposes a re estimation of carbon emissions in international trade based on evolutionary algorithm analysis of electric vehicle green energy regeneration systems. On the basis of analyzing single line scheduling, the author focuses on studying the regional scheduling mode of pure electric buses, and establishes a multi-objective optimization model for pure electric bus regional scheduling considering carbon benefits with the goals of minimizing the number of operating vehicles, minimizing the empty distance, and maximizing carbon benefits. Based on the actual operation data of pure electric buses 146 and 149 in a certain city, the author used an improved particle swarm optimization algorithm to solve the regional scheduling problem of pure electric buses according to the characteristics of the model. The results indicate that assuming other conditions remain unchanged, when the price of diesel rises to around 7.9 yuan, its operating costs will exceed those of pure electric buses, and the cost advantage of diesel vehicles will gradually decrease. Other conditions remain unchanged, and when the battery price per vehicle drops to around 300,000 yuan, the operating cost of pure electric buses will be lower than that of diesel vehicles. Conclusion: Under the premise of considering carbon benefits, adopting regional dispatch mode for pure electric buses has better economic efficiency and is more conducive to the promotion of pure electric buses. [ABSTRACT FROM AUTHOR]

This review comprehensively examines the burgeoning field of intelligent techniques to enhance power systems' stability, control, and protection. As global energy demands increase and renewable energy sources become more integrated, maintaining the stability and reliability of both conventional power systems and smart grids is crucial. Traditional methods are increasingly insufficient for handling today's power grids' complex, dynamic nature. This paper discusses the adoption of advanced intelligence methods, including artificial intelligence (AI), deep learning (DL), machine learning (ML), metaheuristic optimization algorithms, and other AI techniques such as fuzzy logic, reinforcement learning, and model predictive control to address these challenges. It underscores the critical importance of power system stability and the new challenges of integrating diverse energy sources. The paper reviews various intelligent methods used in power system analysis, emphasizing their roles in predictive maintenance, fault detection, real-time control, and monitoring. It details extensive research on the capabilities of AI and ML algorithms to enhance the precision and efficiency of protection systems, showing their effectiveness in accurately identifying and resolving faults. Additionally, it explores the potential of fuzzy logic in decision-making under uncertainty, reinforcement learning for dynamic stability control, and the integration of IoT and big data analytics for real-time system monitoring and optimization. Case studies from the literature are presented, offering valuable insights into practical applications. The review concludes by identifying current limitations and suggesting areas for future research, highlighting the need for more robust, flexible, and scalable intelligent systems in the power sector. This paper is a valuable resource for researchers, engineers, and policymakers, providing a detailed understanding of the current and future potential of intelligent techniques in power system stability, control, and protection. [ABSTRACT FROM AUTHOR]

Deep neural networks have played a crucial role in the field of deep learning, achieving significant success in practical applications. The architecture of neural networks is key to their performance. In the past few years, these architectures have been manually designed by experts with rich domain knowledge. Additionally, the optimal neural network architecture can vary depending on specific tasks and data distributions. Neural Architecture Search (NAS) is a class of techniques aimed at automatically searching for and designing neural network architectures according to the given tasks and data. Specifically, evolutionary-computation-based NAS methods are known for their strong global search capability and have aroused widespread interest in recent years. Although evolutionary-computation-based NAS has achieved success in a wide range of research and applications, it still faces bottlenecks in training and evaluating a large number of individuals during optimization. In this study, we first devise a multi-objective evolutionary NAS framework based on a weight-sharing supernet to improve the search efficiency of traditional evolutionary-computation-based NAS. This framework combines the population optimization characteristic of evolutionary algorithms with the weight-sharing ideas in one-shot models. We then design a bi-population MOEA/D algorithm based on the proposed framework to effectively solve the NAS problem. By constructing two sub-populations with different optimization objectives, the algorithm can effectively explore network architectures of various sizes in complex search spaces. An inter-population communication mechanism further enhances the algorithm's exploratory capability, enabling it to find network architectures with uniform distribution and high diversity. Finally, we conduct performance comparison experiments on image classification datasets of different scales and complexities. Experimental results demonstrate the effectiveness of the proposed multi-objective evolutionary NAS framework and the practicality and transferability of the introduced bi-population MOEA/D-based NAS method compared to existing state-of-the-art NAS methods. [ABSTRACT FROM AUTHOR]

With recent methodological advances in the field of computational protein design, in particular those based on deep learning, there is an increasing need for frameworks that allow for coherent, direct integration of different models and objective functions into the generative design process. Here we demonstrate how evolutionary multiobjective optimization techniques can be adapted to provide such an approach. With the established Non-dominated Sorting Genetic Algorithm II (NSGA-II) as the optimization framework, we use AlphaFold2 and ProteinMPNN confidence metrics to define the objective space, and a mutation operator composed of ESM-1v and ProteinMPNN to rank and then redesign the least favorable positions. Using the two-state design problem of the foldswitching protein RfaH as an in-depth case study, and PapD and calmodulin as examples of higher-dimensional design problems, we show that the evolutionary multiobjective optimization approach leads to significant reduction in the bias and variance in RfaH native sequence recovery, compared to a direct application of ProteinMPNN. We suggest that this improvement is due to three factors: (i) the use of an informative mutation operator that accelerates the sequence space exploration, (ii) the parallel, iterative design process inherent to the genetic algorithm that improves upon the ProteinMPNN autoregressive sequence decoding scheme, and (iii) the explicit approximation of the Pareto front that leads to optimal design candidates representing diverse tradeoff conditions. We anticipate this approach to be readily adaptable to different models and broadly relevant for protein design tasks with complex specifications. Author summary: Proteins are the fundamental building blocks of life, and engineering them has broad applications in medicine and biotechnology. Computational methods that seek to model and predict the protein sequence-structure-function relationship have seen significant advancement from the recent development in deep learning. As more models become available, it remains an open question how to effectively combine them into a coherent computational design approach. One approach is to perform computational design with one model, and filter the design candidates with the others. In this work, we demonstrate how an optimization algorithm inspired by evolution can be adapted to provide an alternative framework that outperforms the post hoc filtering approach, especially for problems with multiple competing design specifications. Such a framework may enable researchers to more effectively integrate the strengths of different modeling approaches to tackle more complex design problems. [ABSTRACT FROM AUTHOR]

This paper focuses on robustly stabilizing stable and unstable fractional-order plants with one uncertain fractional-order term and interval uncertainties using fractional order $ PI^{\mu }D^{\lambda } $ PIμDλ controllers. Two necessary and sufficient conditions are provided to check the robust stability of the closed-loop control system. Moreover, the D-decomposition technique is utilized to determine the robust stability region of the system. Subsequently, evolutionary algorithms, such as the Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Differential Evolution (DE), can be utilized to discover a fractional-order controller within the region of robust stability. This work introduces three primary contributions, outlined as follows: (1) Utilizing a graphical approach, a set of stabilizing controller is obtained. (2) Rather than employing just a single stabilizing fractional-order controller, a collection of controllers is provided for the control system. (3) Employing evolutionary algorithms to find an optimal fractional-order controller. Finally, four numerical examples are presented to validate the results. [ABSTRACT FROM AUTHOR]