Fitness Function For Optimization Research Articles

Inverse design of chemoenzymatic epoxidation of soyabean oil through artificial intelligence-driven experimental approach

This paper presents an inverse design methodology that utilizes artificial intelligence (AI)-driven experiments to optimize the chemoenzymatic epoxidation of soyabean oil using hydrogen peroxide and lipase (Novozym 435). First, experiments are conducted using a systematic 3-level, 5-factor Box-Behnken design to explore the effect of input parameters on oxirane oxygen content (OOC (%)). Based on these experiments, various AI models are trained, with the support vector regression (SVR) model being found to be the most accurate. SVR is then used as a fitness function in particle swarm optimization, and the suggested optimal conditions, upon experimental validation, resulted in a maximum OOC of 7.19 % (∼98.5 % relative conversion of oil to epoxy). The results demonstrate the superiority of the proposed approach over existing methods. This framework offers a general intensified process optimization strategy with minimal resource utilization that can be applied to any other process.

GA-GBLUP: leveraging the genetic algorithm to improve the predictability of genomic selection.

Genomic selection (GS) has emerged as an effective technology to accelerate crop hybrid breeding by enabling early selection prior to phenotype collection. Genomic best linear unbiased prediction (GBLUP) is a robust method that has been routinely used in GS breeding programs. However, GBLUP assumes that markers contribute equally to the total genetic variance, which may not be the case. In this study, we developed a novel GS method called GA-GBLUP that leverages the genetic algorithm (GA) to select markers related to the target trait. We defined four fitness functions for optimization, including AIC, BIC, R2, and HAT, to improve the predictability and bin adjacent markers based on the principle of linkage disequilibrium to reduce model dimension. The results demonstrate that the GA-GBLUP model, equipped with R2 and HAT fitness function, produces much higher predictability than GBLUP for most traits in rice and maize datasets, particularly for traits with low heritability. Moreover, we have developed a user-friendly R package, GAGBLUP, for GS, and the package is freely available on CRAN (https://CRAN.R-project.org/package=GAGBLUP).

A NOVEL HYBRID HARMONY SEARCH (HS) WITH WAR STRATEGY OPTIMIZATION (WSO) FOR SOLVING OPTIMIZATION PROBLEMS

The usage of nature-inspired meta-heuristic algorithms is increasing due to their simplicity and versatility. These algorithms are widely used in numerous domains, especially in scientific fields such as operations research, computer science, artificial intelligence, and mathematics. Based on the core principles of exploration and exploitation, they provide flexible problem-solving abilities. This study presents a novel method to improve the effectiveness of the War Strategy Optimization (WSO) algorithm for optimization issues. The suggested approach combines the WSO technique with the Harmony Search (HS) algorithm, resulting in a hybrid algorithm called H-WSO. The aim is to enhance the overall optimization performance by leveraging the capabilities of both algorithms through the integration of swarm intelligence approaches. In order to assess the effectiveness of the recently suggested H-WSO algorithm, a set of experiments was carried out on 50 benchmark test functions. These functions included both unimodal and multimodal functions and spanned across different dimensions. The findings from these studies clearly showed a notable enhancement in the efficiency of the H-WSO algorithm when compared to the original WSO algorithm. Various metrics were utilized to evaluate the effectiveness of the proposed algorithm, including the optimal fitness function value (Mean), Standard Deviation (St.d), and Median. The H-WSO algorithm regularly shows higher efficiency than the WSO algorithm, making it a promising and practical approach for addressing complicated optimization challenges

Solving the Binary Puzzle with Genetic Algorithm

The increased internet usage after the pandemic led the UN Forum to improve cybersecurity measures, with zero-knowledge proofs (ZKP) being a viable solution for securing confidential information. ZKP protocols can be demonstrated through the binary puzzle, an NP-complete logic puzzle with four specific constraints. The key contribution of this paper is its successful implementation of the genetic algorithm as a new method to solve the binary puzzle. The optimized fitness function determined the solution at an average of 1.33-2.33 generations for populations ranging from 100 to 500. Its quadratic property calculated the solution faster than the ordinary linear fitness function.

Unifying Assurance A Framework for Ensuring Cloud Compliance in AIML Deployment

Intrusion poses a significant challenge in Cloud networks, necessitating the development of efficient mechanisms to mitigate intrusions and enhance system security. To address this, we propose a novel Artificial Bee-based Elman Neural Security Framework (ABENSF). This framework involves rescaling the raw dataset using preprocessing functions and integrating an optimal fitness function based on artificial bees into the feature extraction phase to identify and extract attack features. Additionally, the monitoring mechanism in ABENSF enhances network security by proactively preventing attacks. By employing tracking and monitoring functions, known and unknown attacks can be effectively thwarted. We validate the proposed framework using the NSL-KDD dataset in Python software and conduct a comparative analysis to assess its performance against existing techniques. Our results demonstrate that the developed model outperforms other methods in terms of attack prevention and overall security enhancement.

Improved Genetic algorithm for fuel loading optimization of the DNRR with HEU fuel

This paper investigates the performance of genetic algorithm (GA) with improved selection techniques, i.e. Tournament and Roulette Wheel, applied to in-core fuel management of the Dalat nuclear research reactor (DNRR). Numerical calculations have been performed based on the DNRR core with 100 HEU fuel bundles. The optimal fitness function was chosen to maximize the keff and minimize the power peaking factor. The statistical analysis using Mann-Whitney test shows that the performance of GA with Tournament selection is advantageous over the Roulette Wheel selection in the ICFM problem of the DNRR. The optimal core configurations obtained with the improved GA methods have the keff values greater by about 500 pcm, and the PPF lower by about 4.0% compared to the reference core.

Determination of the optimal feed recipe of anaerobic digesters using a mathematical model and a genetic algorithm

Recently, numerous experimental studies have been undertaken to understand the interactions between different feedstocks in anaerobic digestion. They have unveiled the potential of blending substrates in the process. Nevertheless, these experiments are time-intensive, prompting the exploration of various optimization approaches. Notably, genetic algorithms have gained interest due to their population-based structures allowing them to efficiently yield multiple Pareto-optimal solutions in a single run. This study uses a simplified static anaerobic co-digestion model as the fitness function for a multi-objective optimization. The optimization aims to achieve a methane production set-point while reducing the output ammonia nitrogen and increasing the recipe’ profitability. Thus, the study employs genetic algorithms to identify Pareto fronts and constraints confined the solution space within feasible boundaries. It also underscores the influence of economic considerations on the viable solution space. Ultimately, the optimal feed recipe not only ensures stable operations within the digester but also enhances associated profits.

Underwater image enhancement method based on golden jackal optimization

The propagation of light underwater is affected by water absorption and scattering, resulting in poor visibility of obtained underwater images, and exhibiting degradation phenomena such as color deviation and low contrast. To improve the quality and visibility of underwater images, a method of underwater image enhancement based on Golden Jackal optimization is proposed. The algorithm consists of two processing stages. The first stage is mainly processed in the RGB color space. Based on the attenuation characteristics of underwater color channels, a constructed color compensation and correction strategy is used to eliminate color deviation caused by water absorption. In second stage, it is mainly processed in the Lab color space, using the Golden Jackal optimization algorithm and fitness function to search the optimal parameters of transformation function to improve the image contrast by optimizing the grey intensity of L component and its histogram distribution. The feasibility and effectiveness of the proposed method have been verified through testing and analysis of much underwater degraded image data. In subjective and objective analysis with multiple state-of-the-art underwater image clarity methods, the proposed method performs excellent in color restoration and detail texture enhancement. Further experiments have shown that the proposed method has strong robustness and universality. It is not only suitable for enhancing various underwater scene images, but also for enhancing environmental images with fog, low lighting, and sandstorms. Meanwhile, the proposed method can effectively improve the performance of underwater image segmentation, keypoint detection, and saliency detection.

Sensitivity of Weighing Functions in Genetic Algorithm for Efficiency and Pressure Ratio Optimization in Transonic Axial Flow Compressor

Axial flow compressor design is a multi-objective problem with objectives such as maximization of efficiency, total pressure ratio, mass flow rate and minimization of weight. In this work, validated meanline design process is integrated with genetic algorithm to optimize the compressor design. Fitness function used to evaluate effectiveness of candidate design solutions is arithmetic summation of combination of objective functions and respective weighing functions. Objective functions considered are pressure ratio, efficiency and operating margin in terms of De-Haller Number and Diffusion Factor. The summation of all the weighing functions is unity in all the iterations carried out. Weighing functions of the objective functions used in fitness function dictate the performance. Sensitivity study of weighing functions for multi-objective fitness function has been conducted for the intended mass flow and total pressure ratio. Effect of sensitivity of weighing functions in multi-objective fitness function on efficiency and pressure ratio in transonic axial flow compressor design is studied and discussed. The study carried out shows maximum value of weighing function does not yield maximum value of the objective function. Design trial of weighing function combination of (0.3 pressure ratio and 0.3 efficiency) yields an optimum pressure ratio of 1.588 and 88.1% efficiency for optimized fitness function. The iterative data generated is useful for assigning weighing function value based on design requirement.

Hybrid Marine Predators and Border Collie Optimization algorithm for multipath routing in IoT

SummaryInternet of Things (IoT) is a network of smart things that connects people and objects for gathering and exchanging information by means of embedded sensor. IoT‐based wireless sensor network (WSN) nodes are monitored as a resource parameter at the variety of methods, including resource calculation, energy resource, and storage resource, with multipath routing protocols necessary to enable extended network lifespan and achieve high energy utilization. The existing routing protocols did not provide optimal path from the multipath route. Hence, in this manuscript, a Hybrid Marine Predators and Border Collie Optimization algorithm is proposed for multipath routing in IoTs. The main aim of this endeavor is to “increase network lifetime.” IoT is simulated initially and multipath routing initiates in internet of things network. Multipath routing is achieved by proposed Hyb‐MP‐BCOA; this is the combination of Hybrid Marine Predators Algorithm and Border Collie Optimization algorithm. The proposed Hyb‐MP‐BCOA algorithm chooses the optimum path from the multiple path obtainable for routing, depending upon fitness parameter, like context awareness, network lifetime, residual energy, trust, and delay. Based on the fitness parameter, the optimal path is selected by using Hyb‐MP‐BCOA algorithm. Finally, the proposed Hyb‐MP‐BCOA‐MR‐IoT model is applied in MATLAB, and efficacy of proposed technique is estimated by using various performance metrics, like drop, normalized network energy, lifetime of network, delay, throughput, energy consumed, packet delivery ratio, and number of sensor nodes versus aggregation level. The proposed method attains lower delay of 14.285%, 50%, 53.846%, and 57.142%, lower packet drop of 14.285%, 50%, 53.846%, and 57.142%, lower energy consumption compared with existing methods such as multiobjective sun flower optimization with gray wolf optimizer (GWO) for multipath routing in IoT (SFO‐GWO‐MR‐IoT), multiobjective Whale Lion Fireworks optimization algorithm and fitness function for multipath routing in IoT (WLFA‐MR‐IoT), multipath routing in IoT using shuffled frog leaping algorithm (SFLA‐MR‐IoT), and multipath routing in IoT using hybrid Whale Optimization Algorithm‐Moth Flame Optimization (MFO)(hyb‐WOA‐MFO‐MR‐IoT). Finally, the safe communication is attained in the IoT network.

Study on influencing factors and distribution probability of asphalt mixtures’ rutting samples physical indices

Rutting deformation is one of the most prominent diseases in asphalt pavement’s early damage. In this study, the main influencing factors, mechanism, and distribution law of the principal physical indices of AC-13 asphalt mixture rutting specimens were analyzed based upon the rutting test and statistical principles. Firstly, the main influencing factors, mechanism, and changes law of AC-13 asphalt mixture rutting specimens’ main physical indices were analyzed, based upon a large number rutting test results. Secondly, it analyzes the optimum fitting distribution of the main indices based upon statistical principles. The results showed that, as the asphalt content increased, the mixture rutting samples’ ρf and VMA indices increased firstly and then decreased, VV increased and VFA changed in the converse direction. There was a good linear correlation between the indices Sa and Vbe and asphalt content, in which the indices showed an opposite change trend. The content of coarse aggregate increased by 5.5% in the asphalt mixture, the rutting samples’ ρf increased by 2.03%, and the indices VV, VMA, VFA, Sa, and Vbe decreased by 35.23, 9.1, 8.86, 35.79, and 7.60% on average, respectively. The Marshall testing specimens’ ρf, VV, and VMA were similar to those that were wheel rolled 18 times, and VFA was similar when rolled 12 times. As the number of times the mixtures were rolled increased by 6, the asphalt mixtures’ ρf, VFA, and Vbe increased by 2.05, 8.47, and 1.44%, while the indices VV, VMA, and Sa decreased by 29.49, 8.81, and 11.55%, respectively. The optimal distribution fitting function of the asphalt mixtures’ ρf, VFA, and Sa was the Weibull distribution, that of the Vbe indices was the Normal distribution, that of the VMA in asphalt mixtures was the Lognormal distribution, and that of VV was the Gamma distribution, which can provide a reference for the design and construction of highways’ pavement in this areas.

Easy-to-Manufacture In-Line 2D Nano Antenna for Enhanced Radiation-Cooled IR Camouflage

Deterministic control of infrared (IR) emitting is attractive for applications in sensors and camouflage. Functional materials and structures that can restrain the surface temperature rise via radiation cooling and inhibit the detectable emitting for camouflage have been developed, yet ideal coordination between the cooling and camouflage considering both design and manufacture purposes remains challenging. Here, we reported an in-line 2D nano antenna for IR camouflage. The in-line 2D configuration was intended for rapid and easy-to-manufacture via efficient direct-writing techniques, e.g., femtosecond laser. We innovatively adopted the detectable IR radiation power as the optimization fitness function, based on the particle swarm optimization (PSO) algorithm, to execute powerful cooling and simultaneously minimize the emitting within the atmospheric window for enhanced camouflage. The optimized structure was manufactured and was compared with the previous IR camouflage structures. The PSO structure reduced the detectable IR radiation power by 55.5–73.6% and suppressed the lock-on range by 33.3–48.6%. Moreover, the function of the in-line 2D nano antenna is insensitive to polarization and angle incidence, which is essential for industrial use. Our work proposed new examples of functional structure design-manufacture strategy for applications including but certainly not limited to cooling, sensors, and camouflage of high-power density advanced systems.

An Advanced Fitness Function Optimization Algorithm for Anomaly Intrusion Detection Using Feature Selection

Cyber-security systems collect information from multiple security sensors to detect network intrusions and their models. As attacks become more complex and security systems diversify, the data used by intrusion-detection systems becomes more dimensional and large-scale. Intrusion detection based on intelligent anomaly detection detects attacks based on machine-learning classification models, soft computing, and rule sets. Feature-selection methods are used for efficient intrusion detection and solving high-dimensional problems. Optimized feature selection can maximize the detection model performance; thus, a fitness function design is required. We proposed an optimization algorithm-based feature-selection algorithm to improve anomaly-detection performance. We used a genetic algorithm and proposed an advanced fitness function that finds the most relevant feature set, increasing the detection rate, reducing the error rate, and enhancing analysis speed. An improved fitness function for the selection of optimized features is proposed; this function can address overfitting by solving the problem of anomaly-detection performance from imbalanced security datasets. The proposed algorithm outperformed other feature-selection algorithms. It outperformed the PCA and wrapper-DR methods, with 0.99564 at 10%, 0.996455 at 15%, and 0.996679 at 20%. It performed higher than wrapper-DR by 0.95% and PCA by 3.76%, showing higher differences in performance than in detection rates.

An Intelligent Optimal Secure Framework for Malicious Events Prevention in IOT Cloud Networks

The intrusion is considered a significant problematic parameter in Cloud networks. Thus, an efficient mechanism is required to avoid intrusion and provide more security to the cloud system. Therefore, the novel Artificial Bee-based Elman Neural Security Framework (ABENSF) is developed in this article. The developed model rescales the raw dataset using the pre-processing function. Moreover, the artificial bee's optimal fitness function is integrated into the feature extraction phase to track and extract the attack features. In addition, the monitoring mechanism in the developed model provides high security to the network by preventing attacks. Thus, the tracking and monitoring functions avoid intrusion by eliminating known and unknown attacks. The presented work was designed and validated with an NSL-KDD dataset in python software. Finally, the performance parameters of the presented work are estimated and verified with the existing techniques in a comparative analysis. The comparative performance shows that the developed model has earned better outcomes than others.

Research on optimization of aiming point of sub cluster anti-airport runway based on particle swarm optimization algorithm

A particle swarm optimization algorithm is proposed in this study to optimize the fire distribution, so as to solve the fire distribution problem of cluster warhead anti-airport runway. The particle swarm optimization fitness function is built based on the calculation model of cluster warhead anti-airport runway blocking probability using the Monte Carlo method, and the optimal cluster warhead aiming point allocation scheme is obtained using the particle swarm optimization algorithm. Moreover, the feasibility and advantages of the algorithm are compared and analyzed in the case of different size airports and different number of submunitions. The results provide a reference for the formulation of operational scheme when the cluster bomb strikes the airport runway.

Analysis of various algorithms for optimizing the wave energy converters associated with a sloped wall-type breakwater

The optimal arrangement of multiple wave energy converters (WECs) is an important topic that can greatly affect the efficiency of ocean energy extraction. This study used various algorithms to optimize multiple heaving-buoy-type hemispherical WEC associated with a sloped wall-type breakwater. To this end, a calculation framework linking a three-dimensional frequency-domain numerical wave tank (FR-NWT) based on the Rankin panel method and an optimization algorithm was established. The fitness function for optimization was set to the power efficiency of WEC. The algorithms used were a genetic algorithm, simulated annealing algorithm, particle swarm optimization algorithm (PSO), and advanced PSO algorithm. Under irregular wave conditions, optimization of the spacing between each WEC, the distance between the WEC and the breakwater, the diameter and draft of the WEC, the bottom length and slope angle of the breakwater were performed. The results of the advanced PSO algorithm were consistent and did not converge to local maxima. The excellence of the advanced PSO algorithm in this study was demonstrated.

Optimal FOPI Error Voltage Control Dead-Time Compensation for PMSM Servo System

This paper proposed a dead-time compensation method with fractional-order proportional integral (FOPI) error voltage control. The disturbance voltages caused by the power devices’ dead time and non-ideal switching characteristics are compensated for with the FOPI controller and fed to the reference voltage. In this paper, the actual error voltage is calculated based on the model and actual voltage of the permanent magnet synchronous motor. Considering the parameter error of the permanent magnet synchronous motor and the voltage error caused by the dead-time effect, a FOPI controller is used to calculate the compensation voltage. An improved particle swarm optimization (PSO) algorithm is utilized to design the parameters of the FOPI controller in order to eliminate the dead-time effect, and the optimal fitness function is designed. Compared with other optimization algorithms, the improved PSO algorithm can achieve faster convergence speed in the error voltage controller parameter design. The proposed dead-time compensation method can improve the performance of the current response and eliminate the dead-time effect. This method also eliminates all harmonic disturbances and has a good suppression effect on high-frequency harmonics. The simulation and experimental results show that the dead-time compensation method using optimal FOPI error voltage control makes the current ripple smaller and the response speed faster than that of the traditional optimal integer-order PI control, thus demonstrating the effectiveness and advantages of the proposed method.

Optimal parameters extracting of fuel cell based on Gorilla Troops Optimizer

Proton exchange membrane fuel cell (PEMFC) designs include multiple variable quantities with various nonlinear factors, which must be determined precisely to guarantee reliable modeling. The characteristic model of fuel cells (FCs) has an essential role in examining these cells' effective investigation. The FC design substantially influences simulation investigations of such methods, which has emerged in various applications. In this paper, a new identification method for the parameters' of the PEMFC is proposed based on using Gorilla Troops Optimizer (GTO). The optimized fitness function in the proposed method is used by the minimum value of the sum of squared errors (SSEs) of the current and estimated voltage cases. Various test cases are utilized to validate the effectiveness of the proposed method. After carrying many independent runs, the comparative algorithms are analyzed using SSEs, and the standard deviation measures. The high ability of the proposed method is investigated using steady-state and dynamic situations. The results showed that the proposed method got promising results and achieved better performance than other well-known comparative methods.

Optimization of fuzzy photovoltaic maximum power point tracking controller using chimp algorithm

<span>In this paper, a photovoltaic (PV) fuzzy maximum power point tracking (MPPT) method optimized by the chimp algorithm is presented. The fuzzy logic controller (FLC) of seven triangular membership functions (MFs) is used. The optimization fitness function is composed of transient and steady-state indices under different irradiation and temperature operating conditions. By using MATLAB package, the performance of optimized method is examined and compared with asymmetrical FLC and well-known perturb and observe (P&O) tracking methods at different operating conditions in terms of: transient rising time (tr) and energy yield during 30 s. Moreover, the tracking methods are also compared in terms of the fitness <span>function value. From the comparison of simulation results, a more energy can be</span> harvested by using the proposed optimized tracking method compared to the <span>other methods. Consequently, at the various operating conditions, the proposed</span> method can be used as a more reliable tracking method for PV systems.</span>

Three-Dimensional Force Sensor Based on Fiber Bragg Grating for Medical Puncture Robot

In medical puncture robots, visible light, infrared and ultrasound images are currently used to guide punctures. The lack of information about the interaction forces between the puncture needle and soft tissue in different directions during the puncture process can easily lead to soft tissue being damaged. The current three-dimensional force sensors are large and can only be mounted on the base of the puncture needle, which does not allow for easy integration. Moreover, the force transfer to the base introduces various disturbing forces and the measurement accuracy is low. To reduce the risk of soft tissue being damaged and to enhance the intelligent control strategy of the puncture robot, this paper designs a three-dimensional force sensor based on fiber Bragg gratings. The sensor is very small and can be integrated into the back end of the puncture needle to accurately measure the interaction forces between the puncture needle and the soft tissue in different directions. The puncture needle wall is designed with notched bending of a multilayer continuous beam, which can increase the sensitivity of axial stiffness, while maintaining the sensitivity of the sensor to lateral bending and torsion, and also reduce the crosstalk between the axial and lateral forces. The finite element method is used to optimize its structural parameters, and a BP neural network based on the global optimal fitness function is proposed to solve the decoupling problem between the three-dimensional forces, which effectively improves the detection accuracy of the force sensor. The experimental results show that the measurement error of the sensor is less than 1.5%, which can accurately measure the interaction force between the puncture needle and the soft tissue and improve the safety of the puncture process.