Search

After a software is deployed, every software system will get an upgrade, requiring it to adapt to meet the ever-changing client needs. Thus, regression testing becomes one of the most important operations in any software system. As it is too expensive to repeat the execution of all the test cases available from a previous version of the software system, numerous ways to optimizing the regression test suite have evolved, one of which is test case prioritizing (TCP). This study was carried out to test and compare the effectiveness of evolutionary algorithms and swarm intelligence algorithms, represented by Genetic Algorithm (GA) and Ant Colony Optimization (ACO) algorithms. These algorithms were be implemented to find the Average Percentage Fault Detected (APFD), execution time, and Big O notation, as these are critical aspects in software testing to ensure that high-quality products are produced on time. This study employs data from two separate investigations on comparable issues, denoted as Case Study One and Case Study Two. TCP has been extensively used in recent years, but not much research has been conducted to analyze and evaluate the performance of GA and ACO in a test case prioritization context. The algorithms were compared using APFD and execution time. The APFD and execution time values of 50, 100, 150 and 200 iterations for ACO and GA for both datasets. Both algorithms were determined to work on O(n²) notation, which indicates they should scale up their execution process similarly on different input scales. Both algorithms performed well in their respective roles. ACO has shown to be more valuable than GA in terms of APFD, whereas GA has shown to be more valuable than ACO in terms of execution time. [ABSTRACT FROM AUTHOR]

This paper presents four optimization outcomes for a diesel generator (DG), photovoltaic (PV), and battery hybrid generating radial system, to reduce the network losses and achieve optimum generated power with minimum costs. The effectiveness of the four utilized meta-heuristic algorithms in this paper (firefly algorithm, particle swarm optimization, genetic algorithm, and surrogate optimization) was compared, considering factors such as Cost of Energy (COE), the Loss of Power Supply Probability (LPSP), and the coefficient of determination (R2). The multi-objective function approach was adopted to find the optimal DG allocation sizing and location using the four utilized algorithms separately to achieve the optimal solution. The forward-backward sweep method (FBSM) was employed in this research to compute the network's power flow. Based on the computed outcomes of the algorithms, the inclusion of an additional 300 kW DG in bus 2 was concluded to be an effective strategy for optimizing the system, resulting in maximizing the generated power with minimum network losses and costs. Results reveal that DG allocation using the firefly algorithm outperforms the other three algorithms, reducing the burden on the main DG and batteries by 30.48% and 19.24%, respectively. This research presents an optimization of an existing electricity network case study located on Tomia Island, Southeast Sulawesi, Indonesia. [ABSTRACT FROM AUTHOR]

Copyright of FME Transactions is the property of University of Belgrade, Faculty of Mechanical Engineering 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.)

This paper presents a flexible method for designing a bandpass filter (BPF) using pixel structure and genetic algorithm (GA) optimization. The pixel structure is made up of a grid of metallic microstrip stubs, and the GA is utilized to determine the connections between these stubs. The pixel structure enables the construction of step impedance and shunt branches, which are used to design a traditional BPF. To enhance the design freedom, one side of the discrete grids is connected to the ground via metallic holes. For verification, a BPF was designed, simulated, and measured. The experimental results showed that the 10 dB return loss bandwidth ranges from 1.1 to 1.9 GHz and the insertion loss is approximately 2.5 dB. There is good agreement between the calculation, EM simulation, and measurement results. The proposed GA-based design method offers significant advantages in terms of one-time EM simulation, feasibility, and labor time savings, making it more convenient than the traditional design method. [ABSTRACT FROM AUTHOR]

Background and Objectives: Multi-input multi-output (MIMO) antennas have been of interest in wireless communications in recent years. In these systems, many antennas are placed next to each other. The most important issue in the design of MIMO antennas is mutual coupling. Many methods have been proposed to reduce the mutual coupling of MIMO antennas. Many of these methods require an additional substrate on top or bottom of the antenna. In the reduction of mutual couplings electromagnetic band-gap (EBG) structures are preferred because they are coplanar with the antenna and can be compactly designed. In this paper, to reduce mutual coupling in MIMO antennas, a novel compact EBG structure based on the genetic algorithm optimization is proposed. Methods: The method proposed in this paper to design an optimal EBG structure is to use a genetic algorithm (GA). In this method, an EBG unit cell is designed by a binary code, and then the 7×2 EBG structure of the unit cell is placed between two antenna elements with ?/2 distance. The optimization algorithm tries to find the best unit cell to reduce the mutual coupling between two elements. After 70 generations in the genetic algorithm, the GA determines a compact structure of EBG elements which reduces mutual coupling significantly. Results: Two-element patch antennas with and without the proposed EBG structure are fabricated and the mutual couplings between array elements are measured at 5.68GHz in both cases. It is shown that the proposed compact EBG structure reduced the isolation of the two antennas by 27 dB. This decrease in mutual coupling is much higher than in the previous papers. The proposed EBG has little effect on other antenna radiation parameters such as S11 and radiation patterns. Conclusion: In general, in this paper, a compact and coplanar EBG structure is proposed to significantly reduce the mutual coupling in MIMO antennas. The method presented in this paper can be used for other MIMO antenna configurations at other frequencies and the proposed method will create a completely optimal structure to reduce mutual coupling. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Shanghai Jiao Tong University (1006-2467) is the property of Journal of Shanghai Jiao Tong University Editorial Office 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.)

Side-channel analysis (SCA) is a class of attacks on the physical implementation of a cipher, which enables the extraction of confidential key information by exploiting unintended leaks generated by a device. In recent years, researchers have observed that neural networks (NNs) can be utilized to perform highly effective SCA profiling, even against countermeasure-hardened targets. This study investigates a new approach to designing NNs for SCA, called neuroevolution to attack side-channel traces yielding convolutional neural networks (NASCTY-CNNs). This method is based on a genetic algorithm (GA) that evolves the architectural hyperparameters to automatically create CNNs for side-channel analysis. The findings of this research demonstrate that we can achieve performance results comparable to state-of-the-art methods when dealing with desynchronized leakages protected by masking techniques. This indicates that employing similar neuroevolutionary techniques could serve as a promising avenue for further exploration. Moreover, the similarities observed among the constructed neural networks shed light on how NASCTY effectively constructs architectures and addresses the implemented countermeasures. [ABSTRACT FROM AUTHOR]

To stay competitive on the constantly changing and demanding market, production systems need to optimize their performance daily. This is particularly challenging in labour-intensive industries, which is characterized by highly volatile customer demand and significant daily variability of available workers. The Uncertainty related to the key production parameters in the industry is causing disruptions in long-term production planning and optimization, which leads to the long lead production times, operational risks and accumulation of inventory. To address these challenges, production systems need to ensure adequate operational production planning and optimization of all variables that are influencing the productivity of their systems on a daily basis. To tackle the problem, this study elaborates the application of discrete event simulations and genetic algorithm, using the Tecnomatix Plant Simulation software, to support decision-making and operational production planning and optimization in the industry. The simulation model developed for this purpose considers: customers demand changes, variable production times, operationally available resources and production batch size, to provide an optimal production sequence with the highest number of produced pieces and the lowest total work in process (WIP) inventory per day. To demonstrate the efficiency of the methodology and prove the benefits of the selected optimization approach, a case study is conducted in the textile factory. [ABSTRACT FROM AUTHOR]

In this research paper, the application of Artificial Neural Networks (ANN) for designing antennas is introduced. The primary objective of this optimization technique is to focus on the antenna's parameters to achieve a desirable S11 value, which is a key metric of an antenna's performance. To demonstrate the effectiveness of this approach, the optimization method to design three different antennas using the Numerical Analyzer (MATLAB) tool is employed. Through this study, it is tried to provide new insights into the optimization of antenna design using ANN and demonstrate its potential applications in the field of antenna engineering. The results of this research could potentially lead to the development of more efficient and effective antenna systems with improved performance in various applications. [ABSTRACT FROM AUTHOR]

This study utilizes the genetic algorithm (GA) and Levenberg–Marquardt (L–M) algorithm to optimize the parameter acquisition process for two commonly used viscoelastic models: 2S2P1D and Havriliak–Negami (H–N). The effects of the various combinations of the optimization algorithms on the accuracy of the parameter acquisition in these two constitutive equations are investigated. Furthermore, the applicability of the GA among different viscoelastic constitutive models is analyzed and summarized. The results indicate that the GA can ensure a correlation coefficient of 0.99 between the fitting result and the experimental data of the 2S2P1D model parameters, and it is further proved that the fitting accuracy can be achieved through the secondary optimization via the L–M algorithm. Since the H–N model involves fractional power functions, high-precision fitting by directly fitting the parameters to experimental data is challenging. This study proposes an improved semi-analytical method that first fits the Cole–Cole curve of the H–N model, followed by optimizing the parameters of the H–N model using the GA. The correlation coefficient of the fitting result can be improved to over 0.98. This study also reveals a close relationship between the optimization of the H–N model and the discreteness and overlap of experimental data, which may be attributed to the inclusion of fractional power functions in the H–N model. [ABSTRACT FROM AUTHOR]

This study aims to numerically validate and simulate the fatigue crack growth rate (FCGR), tensile, and fracture toughness properties of T3 and T351 tempered aerospace grade Al 2024 alloy. The extended finite element method (XFEM) coupled with a genetic algorithm (GA) was used to predict FCGR behavior in the framework of an in‐house developed MATLAB code. The numerical simulation was performed using three different FCGR models, i.e., Paris, Forman, and Nasgro. The FCGR prediction ability of simulation models was improved and compared further using GA. The Nasgro model with genetically optimized parameters shows the highest FCGR prediction accuracy compared to other FCGR models. The critical stress intensity factor and von Mises stress distribution under static loading were also predicted for C(T) specimen. A similar XFEM approach was used for analyzing the tensile behavior using a center cracked specimen at the gage section of a dog bone‐shaped specimen. Highlights: XFEM‐based MATLAB codes have been developed to analyze FCGR of Aluminum 2024 alloy.Material constant was optimized using genetic algorithm to improve prediction accuracy.The XFEM model could predict FCGR in differently cracked samples.The XFEM model is used to predict the tensile and fracture behavior of Al alloy. [ABSTRACT FROM AUTHOR]

In this comprehensive paper the method of detecting various diseases within short period of time using Audio Reality/ Virtual Reality (AR/VR) techniques is proposed. For proper functioning of AR/VR models in medical applications three distinct algorithms such Genetic Algorithm (GA), Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO) is integrated where the entire operation is performed with respect to search space. Moreover, the detection process in AR/VR models depends on several factors where minimum error functions must be ensured. Hence in the integrated technique both Absolute Errors (AE) and Time Errors (TE) are measured and compared with existing methods. As the performance of detection is greatly improved with search space the fitness function of each algorithm is observed and it is considered as maximization objective in the proposed method. Furthermore, the complexity of AR/VR models in real time detection process is detected and it is realistic that high complex detections are converted to simple detections. In the comparative analysis of three algorithms ACO proves to be much better as errors are minimized with maximization of fitness function. [ABSTRACT FROM AUTHOR]

Blasting operations in open-pit mines generally have various management strategies relating to flyrock. There are empirical models for calculating the flyrock distance, but due to the complexity and uncertainty of rock properties and their interactions with blasting properties, there are still no models that can predict the flyrock distance that may be applicable across mining operations in general. In this regard, the Jajarm bauxite mine complex was used as a case study. The purpose of this study was to develop and evaluate different methods that can predict flyrock distance. For this purpose, soft computing models were developed using generalized regression neural network (GRNN), gene expression programming (GEP) and genetic-algorithm-based GRNN (GA-GRNN) methods. To obtain statistical models, multivariable regression was applied in the form of linear and nonlinear equations. A flyrock index was introduced using a classification system developed by incorporating fuzzy decision-making trial and evaluation methods (fuzzy DEMATEL). In order to achieve this goal, the data of 118 blasts in eight mines of the Jajarm bauxite complex were collected and used. Following this, four performance benchmarks were applied: the coefficient of determination (R2), variance accounted for (VAF), root-mean-square error (RMSE) and mean absolute percentage error (MAPE). The performance of the models was evaluated, and they were compared with each other as well as with the most common previous empirical models. The obtained results indicate that the GA-GRNN model has a higher performance in predicting the flyrock distance in actual cases compared to the other models. At first, data on factors that were the main cause of flyrock (and had a direct impact on it) were collected and classified from different blasts. Then, using the collected data, 19 different combinations were established, which can be used to provide the appropriate predictive equation. The purpose of this work is to more accurately predict flyrock and prevent heavy damage to buildings and mining machines across the mining complex. [ABSTRACT FROM AUTHOR]

Copyright of Systems Engineering & Electronics is the property of Journal of Systems Engineering & Electronics Editorial Department 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.)

The Internet has more than Bronto bytes of available information. However, not all the information matches the appropriate meaning of the search. In information retrieval (IR), the documents are organized based on the terms and inverse document frequencies. The major issues in the information retrieval systems are vocabulary mismatch, lexical similarity, and performance threshold. This paper analyses the query optimization problem for personalized web searching and it proposes an intelligent method for developing an intellectual, personalized searching scheme by machine-learning algorithms. Here, the optimized features are selected by Deep Belief Network (DBN). For accelerating the search process, inverse filtering (IF) is used because text matching is time-consuming. The similarity between the query and the document is estimated using a Genetic Algorithm (GA)-cosine similarity. Furthermore, a user interest prediction scheme by PLS-ANN (partial least squares-artificial neural network) hybrid model is executed and interconnected with a web personalized search engine. To enhance the personalized search query, the feedback module is significant in this search engine. The PLS-ANN is first time developed for web user IR, which has been not yet to be implemented for the feedback module. The proposed approach is implemented in the Python platform and the performances are evaluated using precision, recall, f-measure, and accuracy. Then, the proposed scheme performance is compared with previous machine learning methods and several classical methods. The implementation results proved that the PLS-ANN achieved better performance than the existing algorithms. [ABSTRACT FROM AUTHOR]

Software defect prediction (SDP) is the most fascinating research area in software industry to enhance the quality of software products. SDP classifiers predict the fault-prone modules in early development phases prior to begin testing phase, and thence, the testing efforts can be focused to those predicted fault-prone modules. In this way, the early detection of fault-prone modules increases the chances to release error-free products to the clients with reduced testing efforts and cost. For SDP application, which uses voluminous high-dimensional data, feature selection (FS) has become essential data preprocessing technique. From past three decades, search-based feature selection is prominently deployed to improve the efficiency of predictors. This paper proposes a new approach, namely 3PcGE, for feature selection (FS) based on three-parent child (3Pc) and genetic evolution (GE). The 3PcGE is inspired by evolutionary computation involving three-parent biological evolution process to result an off-spring with best survival capability. The 3Pc separates the spindle from the mother's cell body having defective mitochondria and replaces the separated spindle in the emptied donor cell body having healthy mitochondria. In this way, 3-parent child is healthier than 2-parent child and free from fatal disease. 3PcGE searches the feature space for an optimal feature subset using the performance of classification and number of features selected as fitness function. The FS is modeled as multi-objective optimization problem, and pareto optimal solution is sought using evolutionary algorithm (3PcGE). The performance is compared with the state-of-the-art FS technique. From experimental results, it is clear that the proposed 3PcGE outperforms the competing filter-based FS techniques by 18.98% and wrapper-based FS techniques by 17.5% in AUC measure. The statistical comparison with the baseline technique (NSGA-II) shows that proposed FS technique 3PcGE is effective to select optimal features and results in better accuracy of SDP models. [ABSTRACT FROM AUTHOR]

In this era of trying to get more information from data, demand forecasting plays a very important role for companies. Companies implement many of their plans based on these forecasts. However, forecasting demand is not always easy. Demand is divided into many different classes depending on its structure. One of them is the problem of intermittent demand. Estimating intermittent demand is a more difficult problem than estimating series with low variability and no null demand. When working with intermittent demands, either a good demand forecast or a good inventory policy is required. Determining an efficient inventory policy is important in terms of meeting customer demand and customer satisfaction. In this study, an inventory lower bound and upper bound are calculated to balance the inventory cost of intermittent demand and the lost sale cost. For this purpose, 7 different test data with intermittent demand structure were studied. A mathematical model is proposed to calculate the cost with the upper and lower inventories under intermittent demand. A feasible solution could not be obtained with the proposed model, and a fitness function for the relevant model was proposed. This function was run on test data using genetic algorithm (GA) and particle swarm optimization (PSO). The results and solution times of GA and PSO were compared. In this way, the variability of demand and the difference between arrival times of demands were met with minimal cost. [ABSTRACT FROM AUTHOR]

Fuzzy multi-worker and multi-job position assignment problem associated with penalty (FMAPP) is an issue that requires high-performance, low-cost, and reliable operations for manufacturing and service industries. An attempt is made to meet this requirement by solving the problem by applying intelligent water drops (IWDs) algorithms, to find the best answer to minimize the straight, company, and penalty costs, thus the total cost. In the FMAPP, n positions are allocated to m workers, for m > n ; each position is occupied only by one worker at any job position is conditional. To show the outperformance of IWDs algorithms in FMAPP vs. GA, the best combination of parameters in IWDs, the tuning parameters are applied. [ABSTRACT FROM AUTHOR]

Use of Pulse Width Modulation (PWM) techniques has enabled the converters to be used in low‐frequency high‐power applications. The main objectives of PWM are to reduce the line current harmonic, switching energy loss, and torque pulsation and motor acoustic noise (for motor drive applications). This paper mainly deals with selective harmonic elimination PWM (SHEPWM), Hysteresis current controlled PWM (HCPWM), space vector PWM (SVPWM), bus‐clamping PWM (BCPWM), and the most advanced wavelet PWM technique (WPWM). Different conventional as well as advanced soft computing techniques have been discussed for SHEPWM in order to solve the complex non‐linear transcendental equations and obtain the optimized switching angles. The paper also deals with different conventional and advanced bus clamping sequences that have shown superior result in mitigating the switching loss. In order to judge the true performance of SHEPWM and CSVPWM in terms of accuracy of obtaining the switching angles, convergence rate, THD, torque ripple, switching energy loss, etc., a common experimental test bench consisting of three‐phase, two‐level, six switch inverter coupled with a 2 hp, 50 Hz, three‐phase induction machine has been formed. The selected BIA‐based SHEPWM and CSVPWM have been implemented in the MATLAB simulation software, and the same has also been applied to the experimental test bench through dSPACE 1104 DAC card. Performance of HCPWM and different BC‐PWM sequences has also been verified using the same experimental test bench. This manuscript will help the researches and practitioners working in this field, to gain a clear idea about the type of PWM to be used for their specific application in order to achieve superior performance. [ABSTRACT FROM AUTHOR]

Data mining and machine learning algorithms' performance is degraded by data of high-dimensional nature due to an issue called "curse of dimensionality". Feature selection is a hot research topic where a subset of features are selected to reduce the dimensionality and thereby increasing the accuracy of learning algorithms. Redundant and irrelevant features are eliminated. Cervical cancer is most commonly occurring disease and driving reasons for untimely mortality among ladies worldwide especially in emerging low income nations like India. However, literature shows that the early identification and exact conclusion of cervical malignant growth can increase the survival chances. The disease does not show signs of its presence in the early stages of its growth. Automated classification and diagnosis of cervical cancer using machine learning and deep learning techniques is in high demand as it allows timely, accurate and regular study of the patient's health progress. Meta-heuristics algorithms provide a global problem independent optimal solution and applied on feature selection problem since decades. In spite of having a good number of literature, there is no survey on feature selection techniques applied to cervical cancer dataset. This paper presents a brief survey on meta-heuristic, its variants, hybrid meta-heuristic and hyper-heuristic techniques. This survey summarizes the feature selection techniques applied to the cervical cancer data to identify the research gap thereby guiding the researchers in the future research direction. The summary of categorization of the techniques such as nature-inspired or non-nature inspired and trajectory or population based is also highlighted. The survey provides a comparative literature review involving classical feature selection techniques and feature selection using metaheuristic algorithms for cervical cancer classification application. [ABSTRACT FROM AUTHOR]

Fast and accurate detections of state-of-health (SoH) are urgently required by various industrial sectors to facilitate reuse and recycling of Li-ion batteries. However, existing SoH identification methods rarely reconcile the monitoring speed and accuracy, which results in redundant carbon footprints and electronic wastes. To address this critical issue, an ultrafast and accurate SoH monitoring is proposed in this paper. The proposed variable forgetting factor Recursive Least Squares (VFFRLS) method is designed based on a least square method with forgetting factors to determine the electrical parameters of a simple electrical model. The established electrical model can be easily implemented using cost-effective micro-controller units (MCUs). The weighting factors of the objective function is automatically determined based on the Genetic Algorithm (GA). Experimental results validate the superior performance of the proposed strategy over conventional methods in detecting the SoH of one new and three aged batteries. For the new battery, the relative error of the estimated SoH is almost 0%. For the aged batteries, the relative error of the estimated SoH is less than 2.78%.

Optimization performances of three most frequently utilized optimization algorithms, GA (Genetic Algorithm), PSO (Particle Swarm Optimization), and SCE (Shuffled Complex Evolution), are compared to examine their accuracy, computation efficiency, and convergence efficiency. Micro scale TGA (thermogravimetric analysis) experiments of wood were conducted at three heating rates to collect the necessary data for analysis. Gauss multi-peak fitting method was first applied to identify the contribution of each component of wood to the mass loss rate (MLR) curves. Then the Kissinger method and three isoconversional methods, including KAS, Tang, and DAEM methods, were employed to extract kinetics of wood pyrolysis. The average values of the four sets of solutions were adopted to determine the search range in the following optimizations. A thermally thin numerical model was developed to inversely model the collected experimental data combining the three algorithms. The results showed that wood pyrolysis can be described by a four-component parallel reaction scheme. The four sets of kinetic parameters derived using different analytical methods are very close to each other. When extracting kinetics from experimental data using numerical model and optimization algorithms, the accuracies of the three algorithms are ranked as SCE > PSO > GA. While the computation efficiencies and convergency efficiencies are ranked as GA ≈ PSO > SCE and PSO > SCE > GA, indicating each algorithm has its inherent advantages and limits. In most optimization applications, PSO is more favorable considering its better overall performance.

This paper examines the side brush control technologies for a novelty semi-autonomous road sweeper design. This study proposes a side brush structure and offers a brush control solution to improve working efficiency and reduce abrasive brush. For the mechanical system using a parallelogram mechanism, the direction of movement when raising and lowering the brush is always parallel to the road surface. The modeling of the side brush mechanism shows that this is a nonlinear system. Therefore, the Sliding Mode Control(SMC) was proposed and established from the dynamics equation. The Lyapunov theorem demonstrates its stability. Besides, we also consider the proportional-integral-derivative (PID) controller to evaluate the responsiveness of the linear controller for a nonlinear system. Finally, the parameters of the controllers are optimized by a genetic algorithm to consider the response of the sliding mode control compared to the PID controller to control the road sweeper side brush with different references.

Recently, considerable attention has focused on enhancing the security and safety of industries with high-risk level activities in order to protect the equipment and environment. In particular, chemical processes and nuclear power generation may have a deep impact on their surroundings. In the case of major events, such as chemical spills, oil rig explosions, or nuclear accidents, collecting accurate and rapidly evolving data becomes a challenging task. So, coordinating a fleet of autonomous mobile robots is a very promising way to deal with unpredicted events and also prevent malicious actions. This paper addresses the problem of assigning optimally a set of tasks to a set of mobile robots equipped with different sensors to minimize a global objective function. The robots perform sensing tasks in order to monitor the area and to facilitate firefighters and inspectors work if a disaster occurs by providing the necessary measures. For this purpose, a centralized Genetic Algorithm (GA) is proposed to determine the task each robot will perform and the order of execution. The proposed approach is tested through a simulation scenario of a grid map environment that represents an industrial area of the city of Le Havre, France. Moreover, a comparative study is conducted with the Hybrid Filtered Beam Search (HFBS) approach and the Mixed-Integer Linear Programming (MILP) solver Cplex. The results demonstrate that the GA approach offers a favorable balance between optimality and execution time.

In numerous industries, especially in automation and industrial processes, the linear servo mechanism is used. However, the parameters of the friction and backlash models are frequently unknown for servomechanism systems, resulting in system uncertainty. High steady-state inaccuracy is caused by friction, whereas undesired vibration is caused by blowback. In servomechanism systems, friction is an issue that is still not sufficiently addressed by a realistic model. To address these challenges, this research on the linear servo system is controlled by a proportional-integral (PI-Cascaded) controller, which enables systems to respond more rapidly, reduce or reject disturbance, and arrive at a steady state more quickly. Moreover, the controller’s parameters are crucial to getting the best performance from a particular controller. As a result, the controller settings were adjusted using four different meta-heuristic optimization algorithms: Surrogate Based Optimization (SBO), Hybrid Genetic Pattern Search Algorithm (HGSPA), Particle Swarm Optimization (PSO), and Simulated Annealing (SA) with four objective functions: Integral Square Error (ISE), Integral Absolute Error (IAE), Integral Time Square Error (ITSE), and Integral Time Absolute Error (ITAE). Throughout the system’s experimental testing, 50 cm was employed as the reference input. Negligible overshoot, quick rise and settling times, and excellent responsiveness are all characteristics of the PSO algorithm with ITSE objective function. Moreover, to assess the system’s robustness. A 50 N force was applied to the system, and a sine wave signal is input into the system. The system shows remarkable stability and resilience throughout the 50 N load experimentation test.

Electricity is undeniably one of the most crucial building blocks of high-quality life all over the world. Like many other African countries, Nigeria is still grappling with the challenge of the energy crisis. However, accurate prediction of electricity consumption is vital for the operation of electric utility companies and policymakers. In response, this study underlines the application of hybrid modelling techniques for the accurate prediction of electricity consumption, using Lagos districts, Nigeria, as a case study. To begin with, this research investigates the performance of three evolutionary algorithms — Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Differential Evolution (DE) — to optimize the parameters of adaptive network-based fuzzy inference systems (ANFIS). In addition, the impact of renowned clustering techniques such as grid partitioning (GP), fuzzy c-means (FCM), and subtractive clustering (SC) on other pivotal key hyperparameters of the ANFIS was examined and analyzed. Furthermore, the robustness of the optimal sub-model was evaluated by comparing it with other hybrid models that are based on six different variants of PSO. The efficacy of the proposed model was evaluated using four standard statistical measures. Finally, the results showed that the combination of the ANFIS approach and PSO under an SC approach and clustering radius of 0.6 delivered the best forecast scheme with the highest accuracy of the MAPE (8.8418%), the MAE (872.1784), the CVRMSE (10.7895), and the RMSE (1.0945E+03). The simulation results were analyzed and compared to other approaches, revealing that the suggested model is better.

In this paper, a mathematical model is proposed to govern the phase distribution on a reconfigurable intelligent surface (RIS) for anomalously reflecting the beam towards the directions of interest. To this end, two operational modes are defined with respect to the reflected pattern. In the first mode, the RIS is configured to form multi-reflected beams toward the directions of interest capable of being controlled independently. The second mode is when the RIS provides a wide reflected beam. Regarding to each mode, a cost function is derived and then, in order to enhance the reflected pattern characteristics, a genetic algorithm (GA) is employed to the model as optimization method. To validate the practicality of the method, the proposed model is applied to a fabricated RIS to assess its performance in a real-world outdoor scenario. In the first mode, an asymmetric dual-beam reflected pattern is obtained and tested with tilt angles of $\theta _{0}=60^{\circ }$ and $\theta _{1}=135^{\circ }$ . Furthermore, a wide-reflected beam is generated in the second mode with half-power beamwidth of $\theta _{HPBW}=30^{\circ }$ and tilt angle of $\theta _{0}=75^{\circ }$ . At both modes, the measured data are well aligned with the simulated results.

Hyperspectral images (HSIs) are a powerful source of reliable data in various remote sensing applications. But due to the large number of bands, HSI has information redundancy, and methods are often used to reduce the number of spectral bands. Band selection (BS) is used as a preprocessing solution to reduce data volume, increase processing speed, and improve methodology accuracy. However, most conventional BS approaches are unable to fully explain the interaction between spectral bands and evaluate the representation and redundancy of the selected band subset. This study first examines a supervised BS method that allows the selection of the required number of bands. A deep network with 3D-convolutional layers embedded in a genetic algorithm (GA). The GA uses embedded 3D-CNN (CNNeGA) as a fitness function. GA also considers the parent check box. The parent check box (parent subbands) is designed to make genetic operators more effective. In addition, the effectiveness of increasing the attention layer to a 3D-CNN and converting this model to spike neural networks has been investigated in terms of accuracy and complexity over time. The evaluation of the proposed method and the obtained results are satisfactory. The accuracy improved from 6% to 21%. Accuracy between 90% and 99% has been obtained in each evaluation mode.

Accurate land use and land cover (LULC) maps are effective tools to help achieve sound urban planning and precision agriculture. As an intelligent optimization technology, genetic algorithm (GA) has been successfully applied to various image classification tasks in recent years. However, simple GA faces challenges, such as complex calculation, poor noise immunity, and slow convergence. This research proposes a two-step ensemble protocol for LULC classification using a grayscale-spatial-based GA model. The first ensemble framework uses fuzzy c-means to classify pixels into those that are difficult to cluster and those that are easy to cluster, which aids in reducing the search space for evolutionary computation. The second ensemble framework uses neighborhood windows as heuristic information to adaptively modify the objective function and mutation probability of the GA, which brings valuable benefits to the discrimination and decision of GA. In this study, three research areas in Dangyang, China, are utilized to validate the effectiveness of the proposed method. The experiments show that the proposed method can effectively maintain the image details, restrain noise, and achieve rapid algorithm convergence. Compared with the reference methods, the best overall accuracy obtained by the proposed algorithm is 88.72%.

Two hybrid back-propagation neural network (BPNN) models optimized by two heuristic search algorithms, namely genetic algorithm (GA-BP) and particle swarm optimization (PSO-BP), are proposed in this paper to predict radial maximum wall shear stress instead of traditional computational fluid dynamics (CFD) methods. The two proposed models are trained and validated using a database of 150 radial maximum wall-shear-stress values obtained via CFD simulations. The best fit model is identified from various BPNN models based on the Akaike information criterion (AIC) and the Bayesian information criterion (BIC), balancing the trade-off between goodness-of-fit and model complexity. The model performance is evaluated by MAE, RMSE, regression coefficient (R), and Nash-Sutcliffe efficiency (NSE). The best fit model is a three-layered BPNN model consisting of a 4:4:1 topology. In almost all evaluation indicators, the two hybrid BPNN methods outperform three existing algorithms, namely classical BPNN, random forest (RF), and gradient boosting decision tree (GBDT). Both PSO-BP and GA-BP can provide a more precise assessment of radial maximum wall shear stress, with maximum errors being 5.81% and 8.24% respectively. The proposed PSO-BP prediction model is promising and has great feasibility in predicting the radial maximum wall shear stress of UHP water-jet nozzle in engineering applications.

With the popularity of electric vehicles (EVs), the application of wireless power transfer (WPT) in EVs has attracted more and more attention. The coupling coil is the key component to realize the stable transmission of electric energy, but in the process of wireless charging, the position of the primary and secondary coils may be misaligned, resulting in the change of mutual inductance and the instability of output current and power. Therefore, the study of the structure of the coupling coil is helpful to improve the transmission performance of WPT. In order to improve the anti-offset ability of the coupling coil, a DS (Double tangent semicircle) coil model based on the DD (Double D) coil is proposed in this paper, which can improve the pick-up ability and anti-offset ability of the receiver coil. Through theoretical analysis, genetic algorithm (GA) optimization, simulation analysis and experiments, it is verified that DS coil is better than DD coil in horizontal offset state and rotary offset state. At the same time, the experiments show when the rotation angle is in the range of −45° to 45° and 135° to 225°, that the current at the receiving end remains stable, and the maximum change rate is only 0.3%. This paper is of great significance to the optimal design of WPT coupling coil.