Search

Heart disease is a primary cause of death worldwide and is notoriously difficult to cure without a proper diagnosis. Hence, machine learning (ML) can reduce and better understand symptoms associated with heart disease. This study aims to develop a framework for the automatic and accurate classification of heart disease utilizing machine learning algorithms, grid search (GS), and the Aquila optimization algorithm. In the proposed approach, feature selection is used to identify characteristics of heart disease by using a method for dimensionality reduction. First, feature selection is accomplished with the help of the Aquila algorithm. Then, the optimal combination of the hyperparameters is selected using grid search. The experiments were conducted with three datasets fromKaggle: TheHeart Failure Prediction Dataset, Heart Disease Binary Classification, and Heart Disease Dataset. Two classes can be distinguished: diseased and healthy (i.e., uninfected). The Histogram Gradient Boosting (HGB) classifier produced the highest Weighted Sum Metric (WSM) scores of 98.65% concerning the Heart Failure Prediction Dataset. In contrast, the Decision Tree (DT) machine learning classifier had the highestWSMscores of 87.64% concerning theHeart Disease Health Indicators Dataset. Measures of accuracy, specificity, sensitivity, and other metrics are used to evaluate the proposed approach. The presented method demonstrates superior performance compared to different state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Scheduling is one critical issue both in the field of industry engineering and combinatorial optimization research. In order to solve multi-objective scheduling problem with uncertainty, this paper presents a method of enhanced hybrid Estimation of Distribution Algorithm (EDA) with Teaching and Learning-Based Optimization Algorithm (TLBO). First, in order to concentrate their respective advantages, two algorithms of EDA and TLBO are integrated to enhance the capability of both global and local search. Second, scenario-based simulation is adopted to deal with uncertainty, and an adaptive sampling strategy is involved to dynamically adjust the number of scenarios during the evolving process. Third, a problem-specific local search is designed to further improve the optimality of candidate solutions. By comparing with existing algorithms on the benchmark problems of flexible job shop scheduling problem (FJSP), it is to demonstrate that our proposal can obtain better solutions in the aspects of optimality and computational efficiency. [ABSTRACT FROM AUTHOR]

This paper optimizes the frequency response of parallel operation of a grid connected Virtual Synchronous Generators (VSG) using a Gray-Wolf Optimization (GWO). The frequency response is achieved when the VSG is synchronized with the grid. The load demand is covered by using only VSGs (Eliminating the existence of conventional generators). The control scheme includes the active power loop aided with the proportional-integral-derivative (PID) controller with optimized parameters, proportional gain Kp, integral gain Ki, and the derivative gain kd. The PID controller gains are optimized using Grey Wolf Optimization. The control scheme resulted in increasing the stability of the power system. The simulation results show the effectiveness of using GWO to reduce the overshoot and steady state deviation of the frequency through the provided damping torque that enhances the VSG inertia. The overshot in the grid frequency due to synchronization is reduced from 8% to 0% with GWO. Therefore, the effect is a more stable system with less overshoot in the frequency (nearly zero). Moreover, the settling time of optimized response has no changed compared with the original frequency response. The system rated is supposed to be 4 kVA for better indication which simulated using MATLAB/Simulink. [ABSTRACT FROM AUTHOR]

The concept of mobile healthcare systems is promising. It is based on the cloud connected wireless biomedical wearables. In this scenario, the compression, processing, transmission and power effectiveness with precision are the key terms. A novel technique is presented for arrhythmia identification by processing the electrocardiogram signals. The solution is based on an effective hybridization of the multirate processing, QRS selection, variational mode decomposition, features mining from Modes, Metaheuristic optimization based features selection, and machine learning algorithms. The MIT-BIH dataset is used for experimentation. Performance of the Butterfly Optimization Algorithm, Manta Ray Foraging Optimization, and Emperor Penguin Optimization algorithms is investigated for features selection. A multi-subjects and multi-class dataset is used for testing the performance of classification by following the 10-fold cross validation strategy. The multirate processing with QRS selection and Metaheuristic optimization dependent features selection bring compression and aptitude for the processing and data transmission efficiencies. The system efficiently incorporates the multirate processing while securing an effective signal reconstruction. The respective compression gains and classification accuracies for the Butterfly Optimization Algorithm, Manta Ray Foraging Optimization, and Emperor Penguin Optimization algorithms are 27-fold, 29.45-fold & 46.29-fold and 99.14%, 99.08% & 98.65%. [ABSTRACT FROM AUTHOR]

In neuro-oncology, the precise segmentation of brain tumors from Magnetic Resonance Images is crucial for diagnosis, treatment planning, and monitoring disease progression. Accurate segmentation helps determine the tumor's size, location, and growth potential, which is essential for formulating effective treatment strategies. In response to this challenge, we developed a novel approach using Chaotic Local Search-Enhanced Differential Evolution (CJADE). CJADE, particularly its variant CJADE-M, which employs chaotic maps selected through a probability-based approach, has proven effective in optimizing brain tumor segmentation. Our study shows that CJADE-M outperforms traditional metaheuristic algorithms on various evaluation metrics. We further enhanced CJADE-M with an entropy-based hybrid objective function, which improved accuracy and reduced computational time in tumor segmentation compared to conventional methods like Minimum Cross-Entropy and Kapur. This makes our method suitable for real-time medical imaging analysis. Our findings indicate that CJADE-M, equipped with the hybrid objective function, achieves superior segmentation performance for both benign lobulated and malignant irregular tumors across metrics such as PSNR, FSIM, QILV, and HPSI. By providing a more accurate and efficient tool, our approach can significantly enhance the outcomes of brain tumor diagnosis and treatment, improving patient care in neuro-oncology. • CJADE algorithm first considered for Brain Tumor Segmentation (BTS). • A study to determine which CJADE variant is superior for BTS. • Best-performing CJADE-M variant compared with other metaheuristic algorithms. • Enhanced CJADE-M with a hybrid entropy-based objective function introduced. • This function with CJADE-M outperforms traditional objective functions. [ABSTRACT FROM AUTHOR]

In soil slope stability, locating the critical slip surface with the minimum safety factor is a difficult and complicated optimization problem. Most methods fail when proper bounds are not applied to the decision variable. For the first time, the paper uses the prey–predator algorithm to analyze slopes stability with circular slip surfaces making use of meaningful rules, from an engineering point of view, to define these bounds. The Fellenius method based on limit equilibrium technique also serves as the constraint of the mathematical problem adopted to solve the task. A pseudo-analytical study is also carried out on four benchmark literature problems to test the performance and to certify the accuracy of the results obtained with the new application of the prey–predator algorithm. We show that the solutions obtained are accurate and should be assumed as a reference comparing to other methods. • The prey–predator metaheuristic is used for soil slope stability analysis. • A new approach to bound the decision variables which is meaningful from an engineering point of view is proposed. • A pseudo analytical study is proposed to certify the quality of the results. • New best results are presented and validated. [ABSTRACT FROM AUTHOR]

Embedding sampling-based tolerance analysis in tolerance-cost optimization is seen as the key to its industrial establishment as a powerful tool for cost-optimal tolerance allocation. However, the sampling-induced variance of the analysis results in each individual optimization step leads to a noisy optimization and thus significantly affects the stability, reproducibility, and reliability of the optimization process and its results. So far, the interrelations between sampling and optimization as well as specific countermeasures are only insufficiently discussed in literature. With the aim to overcome this shortcoming, the given article introduces several measures to enhance the reliability of sampling-based tolerance-cost optimization by reducing and managing the sampling-induced uncertainties in the definition and solution of the optimization problem as well as in the interpretation of the results. The findings serve as a guideline for both researchers and practitioners ensuring reliable tolerance-cost optimization results. [ABSTRACT FROM AUTHOR]

In this article, a novel technique is proposed, namely rank-based multi-objective antlion optimization (RMOALO), and applied to optimize the performance of the energy harvesting cognitive radio network (EHCRN). The original selection method in multi-objective antlion optimizer (MOALO) is suitably changed to improve the algorithm, thus reaching the optimal solution for the problem. The proposed technique shows considerable performance improvement over the method used in the multi-objective antlion optimizer (MOALO). The performance of the proposed RMOALO is demonstrated on five benchmark mathematical functions and compared to multi-objective particle swarm optimization (MOPSO), multi-objective moth flame optimization (MOMFO), MOALO-Tournament, and MOALO-Roulette. The simulation results show an improved convergence of RMOALO and find the optimal solution to the throughput maximization problem. We show that RMOALO provides 16.33 % improved average throughput with the optimal value of sensing duration for the varying amount of harvested energy compared to MOPSO, MOMFO, MOALO-Roulette, and MOALO-Tournament. [ABSTRACT FROM AUTHOR]

The next generation healthcare systems will be based on the cloud connected wireless biomedical wearables. The key performance indicators of such systems are the compression, computational efficiency, transmission and power effectiveness with precision. The electrocardiogram (ECG) signals processing based novel technique is presented for the diagnosis of arrhythmia. It employs a novel mix of the Level-Crossing Sampling (LCS), Enhanced Activity Selection (EAS) based QRS complex selection, multirate processing, Wavelet Decomposition (WD), Metaheuristic Optimization (MO), and machine learning. The MIT-BIH dataset is used for experimentation. Dataset contains 5 classes namely, "Atrial premature contraction", "premature ventricular contraction", "right bundle branch block", "left bundle branch block" and "normal sinus". For each class, 450 cardiac pulses are collected from 3 different subjects. The performance of Marine Predators Algorithm (MPA) and Artificial Butterfly Optimization Algorithm (ABOA) is investigated for features selection. The selected features sets are passed to classifiers that use machine learning for an automated diagnosis. The performance is tested by using multiple evaluation metrics while following the 10-fold cross validation (10-CV). The LCS and EAS results in a 4.04-times diminishing in the average count of collected samples. The multirate processing lead to a more than 7-times computational effectiveness over the conventional fix-rate counterparts. The respective dimension reduction ratios and classification accuracies, for the MPA and ABOA algorithms, are 29.59-times & 22.19-times and 98.38% & 98.86%. [ABSTRACT FROM AUTHOR]

Portable Document Format (PDF) is a file format created to create portable and printable documents across platforms. PDF files are one of the most widely used application types in computer-based systems. Thanks to the functionality that PDF files provide, they are used by many users around the world. Malware developers can exploit PDF files due to various factors. Malware can integrate embedded files, JavaScript, PDF files, etc. As a result, PDFs are susceptible to security vulnerabilities in computer-based systems. In this study, we utilised the CIC-Evasive-PDFMal2022 dataset, made accessible by the Canadian Cybersecurity Institute in 2022, that includes two categories, namely benign and malicious. In the preprocessing step, the proposed model transformed text-based PDF parameter data into the 2D PDF417 barcode. 2D Convolutional Neural Network (CNN) models (MobileNetV2, ResNet18, and ShuffleNet) are trained using the dataset generated by the preprocessing step. CNN is a type of artificial neural network used in image recognition, processing, and classification. Type/class based feature sets were then obtained by each CNN model. In the last step, the metaheuristic optimization method (Honey Badger Algorithm) was used. Thanks to this method, the best performing feature set was determined among the feature sets of the types extracted from each CNN model. It was then classified by the softmax method, and an overall accuracy of 99.73% was achieved. The proposed approach has successfully trained 1D data with 2D CNNs. In addition, with the barcode imaging technique, direct understanding of the data by the users is prevented. [Display omitted] • Thanks to the proposed approach, the classification of 1D PDF metadata with 2D CNN models has been successfully accomplished. • 1D data was converted to the PDF417 barcode type, resulting in 2D images. • Training of 2D images with 2-D CNN models paved the way and successful trainings took place. • Type-based feature sets were created by adding a new fully connected layer to the last layer of the CNN model. • Thanks to the HBA method, the best feature sets were selected among the types and classified with 99.73% success. [ABSTRACT FROM AUTHOR]

Aiming at the problem of low convergence precision and premature convergence of fruit fly optimization algorithm (FOA), this paper proposes a novel fruit fly optimization algorithm with Levi flight and challenge probability (LCFOA). We introduce the Levi flight mechanism and challenge adjustment process to coordinate the global exploration and local exploitation capabilities of the algorithm. Then, we designed an adaptive challenge factor in the challenge adjustment process to improve the convergence precision of the algorithm. The convergence performance of the algorithm is verified by 6 different benchmark functions. The numerical experimental results comfirmed that the proposed LCFOA has better search precision and convergence speed. [ABSTRACT FROM AUTHOR]

Long Short-Term Memory (LSTM) has been one of the most popular methods in time-series forecasting. Within the LSTM architecture, there are hyperparameters present that need to be optimized in order to achieve the optimum results. In order to optimize these hyperparameters, a metaheuristic optimization method was used. A metaheuristic algorithm was used as a way to reduce both time and computational complexity. We used the Search Economics algorithm because we found the algorithm quite interesting while being unpopular. The evaluation was carried out by using Root Mean Square Error (RMSE) as the primary metric used for the optimization. The dataset being used in this experiment is the stock price of one of the most well-known financial institutes in Indonesia. The SE-Optimized LSTM was able to create a prediction that did not overfit with RMSE of 538.92, which was great compared to the unoptimized LSTM model with RMSE of 661.041 and ARIMA model with RMSE of 2809.015. [ABSTRACT FROM AUTHOR]

A central problem in network dynamics is understanding how influence spreads through a social network. This problem can be studied from an optimization approach. The aim is to find an initial seed of actors, with certain size restrictions, capable of maximizing or minimizing the activation of other actors in the network through a given influence spread model. The maximization and minimization versions of this problem have been extensively studied. In recent years, the min–max multi-objective version was defined, which involves finding the smallest seed capable of maximizing the influence spread in the network. Searching for exact solutions in these optimization problems is not feasible, even for relatively small networks. Hence, various approximation techniques have been proposed in recent years, with bio-inspired algorithms based on metaheuristics standing out among them. However, the max–min multi-objective version of the problem remains open. This article formally defines the max–min influence spread problem, aiming to find the maximum seed with the minimum spread capacity. We propose a strategy that uses solutions from the min–max version of the problem to reduce the search space, allowing us to avoid trivial solutions. The potential applications of this max–min version are diverse, e.g., finding clusters less susceptible to diseases in a contagion network or the most inefficient coalitions in a voting system. Using swarm intelligence metaheuristics methods as in the min–max version, the results obtained on real social networks show that this approach exhibits rapid convergence, reaching a seed encompassing 51.3% of the actors who could not influence others within the network. Similarly, for a more complex network, the approach is able to generate a seed where 71.8% of the actors showed no influence over others. • We define the max–min influence spread problem as multi-objective optimization. • We solve it using swarm intelligence-based methods on real social networks. • The PSO algorithm allows efficient solution sets with non trivial solutions. [ABSTRACT FROM AUTHOR]

In this article, a series of learning strategies are proposed to enhance the optimization ability of the artificial electric field algorithm. Orthogonal learning is an important mathematical tool that can greatly influence the adaptability of population-based optimization algorithms. This article proposes, (i) an orthogonal array-based learning strategy to generate a better initial population for the artificial electric field algorithm. Along with the changes in the initialization mechanism, this article also proposes, (ii) an archive-based self-adaptive learning strategy for an artificial electric field algorithm. The proposed learning strategy divides the population into ordinary and extraordinary sub-populations, each with distinct learning mechanisms. The ordinary sub-population utilizes six learning strategies based on three archives, which contain individuals of different quality levels. We incorporate, (iii) a mutation strategy also to update the extraordinary sub-population. Finally, (iv) a self-adaptive strategy is implemented to dynamically adjust the parameters of the proposed algorithm. The effectiveness of these mechanisms is assessed through an extensive analysis of exploration–exploitation dynamics and diversity. Furthermore, an independent structural study is conducted to examine the impact of implemented mechanisms on the algorithm's behavior and efficiency. The proposed algorithm is evaluated on real parameter CEC 2017 problems across different dimensional search spaces. It is compared to eleven state-of-the-art algorithms, and the results demonstrate superior performance in terms of solution accuracy, convergence rate, search capability, and stability. The overall ranking highlights its exceptional potential for solving challenging optimization problems. Additionally, it outperforms other state-of-the-art algorithms across various dimensions, achieving accuracy rates of 64.48%, 70.05%, 78.73%, and 79.25% for dimensions 10, 30, 50, and 100, respectively. Furthermore, it demonstrates superior performance, outperforming others in 73.13% and 60.61% of the problems concerning average accuracy and statistical significance across all dimensions, respectively. [Display omitted] • Introducing an archive-based self-adaptive artificial electric field algorithm (AEFA) with orthogonal initialization for real-parameter optimization problems. • Proposal of an orthogonal array into the AEFA to initialize the population along with a self-adaptive parameter mechanism. • A novel strategy is proposed to divide the population into two homogeneous sub-populations. • Introduction of six learning strategies based on three elite archives and utilizing mutation mechanism. • A rigorous analysis of the proposed algorithm in terms of diversity, exploration–exploitation, convergence, and statistical validation. [ABSTRACT FROM AUTHOR]

This study aims to increase the effectiveness of photovoltaic pumping systems. A practical installation and cost-effective design are suggested. This paper examines the nonlinear behaviour of photovoltaic generators from a distinct perspective; where it repeatedly transitions between a constant current and a constant voltage source and shows how this affects the behaviour of the induction motors. A Fractional-order Neural Network (FONN) is suggested to forecast the harvested solar-energy. The results showed that FONN improved forecasting accuracy by effectively capturing the nonlinear behaviour of PV panels. A Fractional Order MPPT (FO-MPPT) control augmented with Gray Wolf, Anti-lion, and Whale metaheuristic optimizers is proposed and shows capacity to maximize the harvest power for the PV-driven Induction Motor-Pump. The proposed FO-MPPT is compared to conventional techniques using several performance metrics. According to the comparison study, the optimized FO-MPPT enhances the standard MPPT and shows superiority in managing the nonlinear and unpredictable dynamical loads. [ABSTRACT FROM AUTHOR]

Although the high number of bands in hyperspectral remote sensing images increases their usefulness, it also causes some processing difficulty. In supervised classification, one problem is decreasing classification accuracy due to the insufficient training samples against the bands. A way to deal with this problem is the selection of appropriate bands by the metaheuristic methods. Because of the stochastic search, the selected bands differ in any implementation of a metaheuristic method. So, the results obtained from the classification of these different band subsets will also have some differences. In this study, a fusion-based approach has been proposed to improve the classification of hyperspectral remote sensing images by multiple implementations of a metaheuristic method for band selection. We have tested the proposed method using ten metaheuristic methods with different objective functions on four well-known datasets. The results show the proposed fusion-based approach successfully improves the classification accuracy in all experiments. The accuracy improvement varies depending on the metaheuristic method, the objective function, and the dataset and ranges from 0.4% to 15.7%. The proposed method improves the classification of complex datasets more and affects weaker objective functions considerably. The results also show the proposed method brings the accuracy of different metaheuristic methods close to each other and reduces the sensitivity of selecting the proper ones. Thus, an automated classification system can be obtained using a parameter-less method. • A new fusion-based classification is proposed for hyperspectral images based on stochastic nature of metaheuristic methods. • A fully automated classification system is developed to classify hyperspectral remote sensing images. • Many Traditional and new metaheuristic methods include PSO, CSO, GWO, GEO, JSA, ... are examined in the proposed framework. • The experiments are done in both case of filter and wrapper band selection with different objective function. [ABSTRACT FROM AUTHOR]

This paper presents the application of optimization metaheuristics in direct torque control with space vector modulation (DTC-SVM) of a three-phase induction motor. Two metaheuristic algorithms are considered: Ant Colony Optimization (ACO) and Differential Evolution (DE). These techniques are considered in order to achieve an optimized tuning of proportional-integral (PI) controllers in the DTC-SVM control loops, such as rotor speed, electromagnetic torque, stator flux linkage and estimation of the linkage stator flux. Hence, the paper aims to contribute to adjusting the PI controllers of DTC-SVM. All the optimization procedure is performed via computer simulation. Once the optimized gains are obtained, they are applied to the practical system developed herein. Simulation and experimental results are presented in order to validate the approach proposed. [ABSTRACT FROM AUTHOR]

The I-PD controller, one of the modified versions of the PID controller, was proposed for eliminating the set-point kick caused by proportional and derivative terms appeared during set point change. In this paper, the optimal I-PD controller design for DC motor speed control system by the cuckoo search (CS), one of the most efficient metaheuristic optimization techniques, is proposed. The simulation results show that the I-PD parameters can be optimized by the CS. The controlled system with the I-PD provides better responses with smaller overshoot and faster regulating time once compared to that with the parallel PID controller. [ABSTRACT FROM AUTHOR]

Cancer is one of the most dangerous diseases globally, causing adverse effects on human life, with early detection and treatment planning being crucial for patients. Amongst different malignancies, Lung and Colorectal cancer cause the first and second most cancer deaths in the world, respectively. In this study, the authors aim to analyze LC25000 histopathological image dataset for lung and colon cancer detection. The fundamental goal of the proposed research is to leverage the ensemble learning approach to improve the classification performance of deep learning models. Many previous studies have proposed several ensemble methods and weighting schemes. However, none of them optimized the assigned weights using a meta-heuristic-based approach as per our best knowledge. The authors have applied Differential Evolution optimization to optimize and find the optimal assigned weights to the classifiers while training the ensemble model. In addition, a novel approach to ensemble base learners with majority voting based on Condorcet's Jury Theorem has also been proposed. This proposed method has been shown to save a lot of computational efforts by eliminating the training procedure of meta-learners. Besides this, the authors also demonstrated that Condorcet's Jury Theorem holds while ensembling the N number of classifiers in Neural Networks. Our proposed method and experimental results outperformed compared to the state-of-the-art with the optimized ensemble model showing an accuracy of 99.78% and Condorcet's Jury Theorem-based ensemble model 99.88% on 5-class classification. • Majority voting based on Condorcet's Jury Theorem. • Deep feature extraction using various pre-trained networks. • Novel method to assign weights to the base learners in an ensemble model. • A meta-heuristic-based optimization — Differential Evolution. • Condorcet's Jury Theorem demonstration in neural networks. [ABSTRACT FROM AUTHOR]

Visual sensor networks (VSNs) consist of spatially distributed video cameras that are capable of compressing and transmitting the video sequences they acquire. We consider a direct-sequence code division multiple access (DS-CDMA) VSN, where each node has its individual requirements in compression bit rate and energy consumption, depending on the corresponding application and the characteristics of the monitored scene. We study two optimization criteria for the optimal allocation of the source and channel coding rates, which assume discrete values, as well as for the power levels of all nodes, which are continuous, under transmission bit rate constraints. The first criterion minimizes the average distortion of the video received by all nodes, while the second one minimizes the maximum video distortion among all nodes. The resulting mixed integer optimization problems are tackled with a modern optimization algorithm, namely particle swarm optimization (PSO), as well as a hybrid scheme that combines PSO with the deterministic Active-Set optimization method. Extensive experimentation on interference-limited as well as noisy environments offers significant intuition regarding the effectiveness of the considered optimization schemes, indicating the impact of the video sequence characteristics on the joint determination of the transmission parameters of the VSN. [ABSTRACT FROM AUTHOR]

Agriculture directly affects the economic conditions of countries around the world; it is a sector that determines the prosperity and standard of living of people. The history of agriculture covers the process from the existence of man to the present. The crops obtained from agriculture are the source of food that humans and many other living beings need to sustain their life activities. Every year, crops derived from agricultural products suffer significant losses in their productivity and quantity due to weed infestation. Depending on the level of weed control, yield losses can range from 10% to 100%. In this study, an artificial intelligence based approach was proposed to identify weeds unintentionally growing on agricultural land and increase the control rate, considering technological developments. A dataset consisting of twelve species of seedlings and weeds was used for the analysis of the study. The proposed approach trained the dataset using pre-trained deep learning models and was optimized by metaheuristic optimization methods by selecting the species-based activations that were transferred to Softmax, which is in the final layer of the deep learning models. Then, the species-based activations that were improved by the optimization methods were reclassified by Softmax. The result of the experimental analysis was an overall accuracy of 99.39%. This overall accuracy was achieved by jointly using the DarkNet model and the Gaining-sharing knowledge-based optimization method together. [Display omitted] • Depending on the degree of weed control, yield losses can range from 10% to 100%. • In this study, an AI-based approach is proposed to identify weeds that grow unintentionally on agricultural land. • The class-based activation sets were obtained from DarkNet models. • Metaheuristic optimizations were compared in the selection of activation sets for classes. • The result of the experimental analysis is an overall accuracy of 99.39% for 12 weed types. [ABSTRACT FROM AUTHOR]

This paper proposes Komodo Mlipir Algorithm (KMA) as a new metaheuristic optimizer. It is inspired by two phenomena: the behavior of Komodo dragons living in the East Nusa Tenggara, Indonesia, and the Javanese gait named mlipir. Adopted the foraging and reproduction of Komodo dragons, the population of a few Komodo individuals (candidate solutions) in KMA are split into three groups based on their qualities: big males, female, and small males. First, the high-quality big males do a novel movement called high-exploitation low-exploration to produce better solutions. Next, the middle-quality female generates a better solution by either mating the highest-quality big male (exploitation) or doing parthenogenesis (exploration). Finally, the low-quality small males diversify candidate solutions using a novel movement called mlipir (a Javanese term defined as a walk on the side of the road to reach a particular destination safely), which is implemented by following the big males in a part of their dimensions. A self-adaptation of the population is also proposed to control the exploitation–exploration balance. An examination using the well-documented twenty-three benchmark functions shows that KMA outperforms the recent metaheuristic algorithms. Besides, it provides high scalability to optimize thousand-dimensional functions. The source code of KMA is publicly available at: https://suyanto.staff.telkomuniversity.ac.id/komodo-mlipir-algorithm and https://www.mathworks.com/matlabcentral/fileexchange/102514-komodo-mlipir-algorithm. • A Komodo Mlipir Algorithm (KMA) is proposed as a novel metaheuristic optimizer. • A new coordination is created by three groups of individuals with different strategies. • A mlipir movement is introduced as a low-exploitation high-exploration strategy. • KMA is stable and scalable for thousand-dimensional classic benchmark functions. [ABSTRACT FROM AUTHOR]

Deep learning techniques usually face drawbacks related to the vanishing gradient problem, i.e., the gradient becomes gradually weaker when propagating from one layer to another until it finally vanishes away and no longer helps in the learning process. Works have addressed this problem by introducing residual connections, thus assisting gradient propagation. However, such a subject of study has been poorly considered for Deep Belief Networks. In this paper, we propose a weighted layer-wise information reinforcement approach concerning Deep Belief Networks. Moreover, we also introduce metaheuristic optimization to select proper weight connections that improve the network's learning capabilities. Experiments conducted over public datasets corroborate the effectiveness of the proposed approach in image classification tasks. • Novel DBN with weight-based residual connections between layers. • Reinforcement and regularization of the information flow. • Application of metaheuristic optimization to fine-tune Res-DBN hyperparameters; [ABSTRACT FROM AUTHOR]

A reliable and accurate prediction of the tunnel boring machine (TBM) performance can assist in minimizing the relevant risks of high capital costs and in scheduling tunneling projects. This research aims to develop six hybrid models of extreme gradient boosting (XGB) which are optimized by gray wolf optimization (GWO), particle swarm optimization (PSO), social spider optimization (SSO), sine cosine algorithm (SCA), multi verse optimization (MVO) and moth flame optimization (MFO), for estimation of the TBM penetration rate (PR). To do this, a comprehensive database with 1286 data samples was established where seven parameters including the rock quality designation, the rock mass rating, Brazilian tensile strength (BTS), rock mass weathering, the uniaxial compressive strength (UCS), revolution per minute and trust force per cutter (TFC), were set as inputs and TBM PR was selected as model output. Together with the mentioned six hybrid models, four single models i.e., artificial neural network, random forest regression, XGB and support vector regression were also built to estimate TBM PR for comparison purposes. These models were designed conducting several parametric studies on their most important parameters and then, their performance capacities were assessed through the use of root mean square error, coefficient of determination, mean absolute percentage error, and a10-index. Results of this study confirmed that the best predictive model of PR goes to the PSO-XGB technique with system error of (0.1453, and 0.1325), R2 of (0.951, and 0.951), mean absolute percentage error (4.0689, and 3.8115), and a10-index of (0.9348, and 0.9496) in training and testing phases, respectively. The developed hybrid PSO-XGB can be introduced as an accurate, powerful and applicable technique in the field of TBM performance prediction. By conducting sensitivity analysis, it was found that UCS, BTS and TFC have the deepest impacts on the TBM PR. [Display omitted] • Six XGBoost-based hybrid models for predicting TBM penetration rate are proposed. • GWO, PSO, SSO, SCA, MVO and MFO can assist the hyper-parameters tuning of XGBoost. • The prediction performance from high to low is PSO-XGB, MFO-XGB, GWO-XGB, MVO-XGB, SCA-XGB, SSO-XGB. • The Mutual information method is applied to demonstrate the relative importance of each input indicator. [ABSTRACT FROM AUTHOR]

In the 19th and 20th centuries, social networks have been an important topic in a wide range of fields from sociology to education. However, with the advances in computer technology in the 21st century, significant changes have been observed in social networks, and conventional networks have evolved into online social networks. The size of these networks, along with the large amount of data they generate, has introduced new social networking problems and solutions. Social network analysis methods are used to understand social network data. Today, several methods are implemented to solve various social network analysis problems, albeit with limited success in certain problems. Thus, the researchers develop new methods or recommend solutions to improve the performance of the existing methods. In the present paper, a novel optimization method that aimed to classify social network analysis problems was proposed. The problem of stance detection, an online social network analysis problem, was first tackled as an optimization problem. Furthermore, a new hybrid metaheuristic optimization algorithm was proposed for the first time in the current study, and the algorithm was compared with various methods. The analysis of the findings obtained with accuracy, precision, recall, and F-measure classification metrics demonstrated that our method performed better than other methods. • A novel method for solving the problem of Stance detection has been proposed. • Stance detection problem has been handled as an optimization problem for the first time. • A new area has been addressed for optimization. • An efficient novel hybrid optimization algorithm has been developed. [ABSTRACT FROM AUTHOR]

Image segmentation is an essential part of image analysis, which has a direct impact on the quality of image analysis results. Thresholding is one of the simplest and widely used methods for image segmentation. Thresholding can be either bi-level, which involves partitioning of an image into two segments, or multilevel, which partitions an image into multiple segments using multiple thresholds values. This paper focuses on multilevel thresholding. A good segmentation scheme through multilevel thresholding identifies suitable threshold values to optimize between-class variance or entropy criterion. For such optimizations, nature inspired metaheuristic algorithms are commonly used. This paper presents a Kapur's entropy based Crow Search Algorithm (CSA) to estimate optimal values of multilevel thresholds. Crow Search Algorithm is based on the intelligent behavior of crow flock. Crow Search Algorithm have shown better results because of less number of parameters, no premature convergence, and better exploration–exploitation balance in the search strategy. Kapur's entropy is used as an objective function during the optimization process. The experiments have been performed on benchmarked images for different threshold values (i.e. 2, 4, 8, 16, 32 thresholds). The proposed method has been assessed and performance is compared with well-known metaheuristic optimization methods like Particle Swarm Optimization (PSO), Differential Evolution (DE), Grey Wolf Optimizer (GWO), Moth-Flame Optimization (MFO) and Cuckoo Search (CS). Experimental results have been evaluated qualitatively and quantitatively by using well-performed evaluation methods namely PSNR, SSIM, and FSIM. Computational time and Wilcoxon p-type value also compared. Experimental results show that proposed algorithm performed better than PSO, DE, GWO, MFO and CS in terms of quality and consistency. [ABSTRACT FROM AUTHOR]

This study developed a novel optimization algorithm, called Forensic-Based Investigation (FBI), inspired by the suspect investigation–location–pursuit process that is used by police officers. Although numerous unwieldy optimization algorithms hamper their usability by requiring predefined operating parameters, FBI is a user-friendly algorithm that does not require predefined operating parameters. The performance of parameter-free FBI was validated using four experiments: (1) The robustness and efficiency of FBI were compared with those of 12 representations of the top leading metaphors by using 50 renowned multidimensional benchmark problems. The result indicated that FBI remarkably outperformed all other algorithms. (2) FBI was applied to solve a resource-constrained scheduling problem associated with a highway construction project. The experiment demonstrated that FBI yielded the shortest schedule with a success rate of 100%, indicating its stability and robustness. (3) FBI was utilized to solve 30 benchmark functions that were most recently presented at the IEEE Congress on Evolutionary Computation (CEC) competition on bound-constrained problems. Its performance was compared with those of the three winners in CEC to validate its effectiveness. (4) FBI solved high-dimensional problems, by increasing the number of dimensions of benchmark functions to 1000. FBI is efficient because it requires a relatively short computational time for solving problems, it reaches the optimal solution more rapidly than other algorithms, and it efficaciously solves high-dimensional problems. Given that the experiments demonstrated FBI's robustness, efficiency, stability, and user-friendliness, FBI is promising for solving various complex problems. Finally, this study provided the scientific community with a metaheuristic optimization platform for graphically and logically manipulating optimization algorithms. • A novel metaheuristic Forensic-Based Investigation (FBI) algorithm is proposed. • The FBI algorithm does not require to preset the tuning parameters. • The robustness and efficiency of FBI algorithm are compared with those of leading metaphors in solving high-dimensional and real problems. • FBI outperforms all other algorithms with faster convergence and a shorter computational time. • A graphical platform for implementing the new algorithm and others is provided for the ease of use. [ABSTRACT FROM AUTHOR]

A precise control in the stopband attenuation characteristics can be achieved by using the fractional-step filters instead of the traditional integer-order filters. In this paper, nine nature-inspired optimization algorithms, such as five advanced variants of differential evolution (DE), three advanced variants of particle swarm optimization (PSO), and an efficient evolutionary strategy method (CMA-ES-RIS) are employed to design the fractional-step low pass Butterworth filter (FLBF). The proposed (1 + α) and (2 + α) order models, where α ∈ (0 , ​ 1) , are optimally approximated as an integer-order transfer function by using the magnitude-frequency information of the ideal FLBF. Comparisons regarding the solution quality and robustness reveal an improved accuracy for the DE variants and CMA-ES-RIS over all the PSO variants. Results from the pair-wise Wilcoxon rank-sum test demonstrate the superiority of enhanced fitness-adaptive differential evolution (EFADE) algorithm as the most efficient optimization tool for solving this problem. Comparisons with the state-of-the-art approaches also confirm the superior modelling accuracy of the proposed FLBFs. The canonical structure circuit realization of the FLBFs using current feedback operational amplifiers is presented. Simulations carried out in OrCAD PSPICE platform suggest proximity in the magnitude responses between the proposed and the theoretical models. The optimal design of stable, minimum-phase (2 + α) order FLBFs is also presented for the first time without employing the cascading concept involving the integer-order Butterworth polynomials. [ABSTRACT FROM AUTHOR]

The constant development of new metaheuristic algorithms has led to a saturation in the field of stochastic search. There are now hundreds of different algorithms that can be used to solve any problem. To produce a good performance, every metaheuristic method needs to address a satisfactory equilibrium between exploration and exploitation of the search space. Although exploration and exploitation represent two fundamental concepts in metaheuristics, the main questions about their combination and balance have not been yet completely understood. Most of the existent analyzes conducted on metaheuristic techniques consider only the comparison of their final results which cannot evaluate the nature of a good or bad balance. This paper presents an experimental analysis that quantitatively evaluates the balance between exploration and exploitation of several of the most important and better-known metaheuristic algorithms. In the study, a dimension-wise diversity measurement is used to assess the balance of each scheme considering a representative set of 42 benchmark problems that involve multimodal, unimodal, composite and shifted functions. As a result, the analysis provides several observations that allow understanding how this balance affects the results in each type of functions, and which balance is producing better solutions. [ABSTRACT FROM AUTHOR]

Simulated Annealing (SA) is a single-solution-based metaheuristic technique based on the annealing process in metallurgy. It is also one of the best-known metaheuristic algorithms due to its simplicity and good performance. Despite its interesting characteristics, SA suffers from several limitations such as premature convergence. On the other hand, Japanese swordsmithing refers to the manual-intensive process for producing high-quality bladed weapons from impure raw metals. During this process, Japanese smiths fold and reheat pieces of metal multiple times in order to eliminate impurities and defects. In this paper, an improved version of the SA algorithm is presented. In the new approach, a population of agents is considered. Each agent conducts a search strategy based on a modification of the SA scheme. The proposed algorithm modifies the original SA incorporating two new operators, folding and reheating, inspired by the ancient Japanese Swordsmithing technique. Under the new approach, the process of folding is conceived as a compression of the search space, while the reheating mechanism considers a reinitialization of the cooling process in the original SA scheme. With this inclusion, the new algorithm maintains the computational structure of the SA method but improving its search capacities. In order to evaluate its performance, the proposed algorithm is tested in a set of 28 benchmark functions, which include multimodal, unimodal, composite and shifted functions, and 3 real world optimization problems. The results demonstrate the high performance of the proposed method when compared to the original SA and other popular state-of-the-art algorithms. • A novel metaheuristic method has been introduced based on the SA algorithm. • Two new operators have been designed to handle exploitation and exploration. • Both operators have been included in the original SA to improve its search abilities. • Experimental results demonstrate the superiority of the proposed approach. [ABSTRACT FROM AUTHOR]