Search

Identifying disease-related genes is an ongoing study issue in biomedical analysis. Many research has recently presented various strategies for predicting disease-related genes. However, only a handful of them were capable of identifying or selecting relevant genes with a low computational burden. In order to tackle this issue, we introduce a new filter–wrapper-based gene selection (GS) method based on metaheuristic algorithms (MHAs) in conjunction with the k-nearest neighbors ( k -NN ) classifier. Specifically, we hybridize two MHAs, bat algorithm (BA) and JAYA algorithm (JA), embedded with perturbation as a new perturbation-based exploration strategy (PES), to obtain JAYA–bat algorithm (JBA). The fact that JBA outperforms 10 state-of-the-art GS methods on 12 high-dimensional microarray datasets (ranging from 2000 to 22,283 features or genes) is impressive. It is also noteworthy that relevant genes are first selected via a filter-based method called mutual information (MI), and then further optimized by JBA to select the near-optimal genes in a timely fashion. Comparing the performance analysis of 11 well-known original MHAs, including BA and JA, the proposed JBA achieves significantly better results with improvement rates of 12.36%, 12.45%, 97.88%, 9.84%, 12.45%, and 12.17% in terms of fitness, accuracy, gene selection ratio, precision, recall, and F1-score, respectively. The results of Wilcoxon's signed-rank test at a significance level of α = 0.05 further validate the superiority of JBA over its peers on most of the datasets. The use of PES and the combination of BA and JA's strengths appear to enhance JBA's exploration and exploitation capabilities. This gives it a significant advantage in gene selection ratio, while also ensuring the highest classification accuracy and the lowest computational time among all competing algorithms. Thus, this research could potentially make a significant contribution to the field of biomedical analysis. [ABSTRACT FROM AUTHOR]

In order to achieve accurate fruit classification, an apple classification system based on machine vision and BA-BP was designed with apple as the sorting object. Firstly, the apple image acquired in real time was preprocessed to obtain the apple contour image. The improved Canny edge detection algorithm was used to extract the apple contour, and methods such as minimum circumferential circle method, color model conversion and gray scale co-existence matrix were used to extract the apple diameter, color, roundness and texture features. Secondly, the collected training group data was filtered and normalized, and the processed data was input into the BP neural network model. Then the bat algorithm was used to optimize the BP network model and complete the network model training. Finally, the data of the test group were input into the BA-BP neural network system and the BP neural network system. The experimental results showed that the recognition accuracy of BA-BP neural network system was 96%, the performance was obviously better than BP neural network system, and the average classification time was less than 1.25 s. Therefore, the system could meet the demand of apple grading in actual production and help to realize the accurate identification of apple grade. [ABSTRACT FROM AUTHOR]

Robotics is a vast and growing area in academia and industry, and it is used to solve human problems through artificial intelligent machines. To solve crucial issues or problems such as the survivability of humans in mining, living in Antarctica, Space, mountainous regions, and other challenging terrains, we need an intelligent machine. Working with multiple robots is more beneficial than with a single robot. This article proposed a method to search and track the target in an unknown environment through a multi-agent system using a nature-inspired algorithm (NIA). Here, the location of the target is either known or unknown. To reach the target, mobile agents use two types of movement, either directional-based movement or nature-inspired algorithm-based movement. Directional-based movements help the mobile agents decide the point of interest to move. The nature-inspired algorithm (NIA) based movement helps the agents explore the area in the provided direction. This work uses particle swarm optimization (PSO), bacteria foraging optimization (BFO), and bat algorithm (BA) NIA for the exploration of the area. The proposed method has been tested in simple and complex environments. From the experimental analysis, the proposed method successfully tracks or searches the target in an unknown environment. The experiments show that the agent movement behavior is affected by some factors such as the complexity of the environment, number of agents, sensor range, etc. The results indicate that the bat algorithm outperforms the other two algorithms in terms of fast time completion. [ABSTRACT FROM AUTHOR]

This paper introduces a novel hybrid optimization algorithm named bat-salp swarm algorithm (BASSA). BASSA integrates the local exploitation capability of bat algorithm (BA) and the global exploration capability of salp swarm algorithm (SSA). Firstly, by introducing the echolocation of BA, the follower updating strategy of SSA is improved. Secondly, the algorithm selects between BA and SSA based on specific conditions. Finally, individuals undergo random differential mutation to increase population diversity, thereby avoiding local optima. To verify the effectiveness of the algorithm, we carry out experiments BASSA on 23 benchmark functions with different dimensions and compare it with 7 optimization algorithms, including BA, SSA, and 7 enhanced versions of SSA. Simulation results indicate that BASSA outperforms standard BA, SSA, and other enhanced algorithms in terms of mean and standard deviation. This suggests a significant improvement in optimization performance, with higher solution accuracy and faster convergence speed. Additionally, through performance evaluation on three real engineering problems, the results indicate that BASSA possesses strong optimization capabilities. [ABSTRACT FROM AUTHOR]

Small datasets are frequent in some scientific fields. Such datasets are usually created due to the difficulty or cost of producing laboratory and experimental data. On the other hand, researchers are interested in using machine learning methods to analyze this scale of data. For this reason, in some cases, low-performance, overfitting models are developed for small-scale data. As a result, it appears necessary to develop methods for dealing with this type of data. In this research, we provide a new and innovative framework for regression problems with a small sample size. The base of our proposed method is the K-nearest neighbors (KNN) algorithm. For feature selection, instance selection, and hyperparameter tuning, we use the bat optimization algorithm (BA). Generative Adversarial Networks (GANs) are employed to generate synthetic data, effectively addressing the challenges associated with data sparsity. Concurrently, Deep Neural Networks (DNNs), as a deep learning approach, are utilized for feature extraction from both synthetic and real datasets. This hybrid framework integrates KNN, DNN, and GAN as foundational components and is optimized in multiple aspects (features, instances, and hyperparameters) using BA. The outcomes exhibit an enhancement of up to 5% in the coefficient of determination ( R 2 score) using the proposed method compared to the standard KNN method optimized through grid search. [ABSTRACT FROM AUTHOR]

To ensure effective resource allocation for urban bike demand, it is crucial to accurately predict shared bike rental counts. This prediction process was carried out using the Gradient Boosted Machine (GBM) method optimized with the Bat Algorithm (BA). To demonstrate the effectiveness of the proposed model, its performance was compared with different methods such as Decision Tree (DT), k-Nearest Neighbors (KNN), and Multi-Layer Perceptron (MLP). For this comparison, metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R²) were employed. The best results were achieved by BA-GBM with values of 1.8665 MAE, 2.9588 MSE, 8.7545 RMSE, and 0.9264 R². Additionally, the features with the most and least impact on bike rental prediction were identified. The most influential features were found to be temperature and time of day, while the least influential features were snowfall and year. [ABSTRACT FROM AUTHOR]

Federated learning (FL) is an advanced distributed machine learning (ML) framework designed to address issues related to data silos and data privacy. In real-world applications, common problems like non-convex optimization and nonindependent and identically distributed (Non-IID) client data reduce training efficiency, cause local optima, and degrade performance. Therefore, we propose a FL scheme based on the bat algorithm (FedBat), which leverages the echolocation mechanism of bats to effectively balance global and local search capabilities, enabling the algorithm to escape local optima with a certain probability. By combining global optimal model weight optimization with dynamically adjusted search strategies, FedBat guides weaker client models toward the global optimum, thereby accelerating convergence. Additionally, FedBat allows for adaptive parameter adjustments across various datasets. To mitigate client drift, we extend FedBat with Jensen–Shannon (JS) divergence to quantify differences between local and global models. Clients decide whether to upload their local models based on this divergence, to enhance the global model’s generalization and minimize communication overhead. Experimental results demonstrate that FedBat converges 5 times faster and enhances test accuracy by more than 40 % compared to FedAvg. The extended FedBat effectively mitigates the decrease in the generalization performance of the global model and reduces communication costs by approximately 20 % . Comparing FedPso, FedGwo, and FedProx shows that FedBat demonstrates superior performance in terms of convergence speed and test accuracy. Furthermore, we derive the formula for the expected convergence rate of FedBat, analyze the impact of various parameters on FL performance, and establish the upper bound of FedBat to evaluate its model divergence. [ABSTRACT FROM AUTHOR]

Modern power systems are growing in complexity due to the installation of large generators, long transmission lines, the addition of inertialess renewable energy resources (RESs) with zero inertia, etc., which can all severely degrade the system frequency stability. This can lead to under-/over-frequency load shedding, damage to turbine blades, and affect frequency-sensitive loads. In this study, we propose a methodology to improve the two critical frequency stability indices, i.e., the frequency nadir and the rate of change of frequency (RoCoF), by formulating an optimization problem. The size and placement location of battery energy storage systems (BESSs) are considered to be the constraints for the proposed optimization problem. Thereafter, the optimization problem is solved using the three metaheuristic optimization algorithms: the particle swarm optimization, firefly, and bat algorithm. The best performing algorithm is then selected to find the optimal sizing and placement location of the BESSs. The analyses are all performed on the IEEE 9-bus and IEEE 39-bus test systems. Several scenarios which consider multiple generator outages, increased/decreased loading conditions, and the addition of RESs are also considered for both test systems in this study. The obtained results show that under all scenarios, the proposed method can enhance system frequency compared to the existing method and without BESSs. The proposed method can be easily upscaled for a larger electrical network for obtaining the optimized BESS size and location for the improvement of the system frequency stability.

The solar radiation value parameter is one of the most important parameters in determining the output power value of photovoltaic panels. Accurate prediction of this parameter is crucial for dispatching and load management planning. Managers and designers encounter economic and managerial challenges due to the uncertainty and difficulty in predicting solar radiation levels. This research introduces a highly accurate prediction method utilizing tree-based methods, enhanced by meta-heuristic algorithms to boost performance. The proposed method emphasizes preventing overfitting and ensuring high reliability for use in Internet of Things systems. Meta-heuristic algorithms are utilized for optimizing tree-based methods, as well as for feature and instance selection. Employing meta-heuristic methods as the main innovation in this research not only optimizes machine learning model settings but also mitigates the impact of noise, outliers, and ineffective inputs, thereby enhancing the final output quality. Utilizing an innovative fitness function in model optimization enhances prediction accuracy and adaptability to real photovoltaic power plant environments. The final outcome is a strong model that has a score of 0.95 with the R-square criterion and is optimal model.

Safety and reliability represent indispensable prerequisites for electric rudder systems (ERS), while health states recognition serves as a potent technology that fortifies and optimizes these essential aspects. To address this problem, we present a health‐state recognition muti‐class model BAFAO‐IPBT‐TWSVM for ERS considering several typical operating parameters obtained from intelligent electric rudder system test platform. The twin support vector machine (TWSVM) not only possesses the ability of traditional fault diagnosis methods based on SVM to handle unbalanced data, but also introduces two non‐parallel hyperplanes to replace single hyperplane of traditional SVM. Traditional TWSVM simplifies and streamlines the problem‐solving, but it is limited to binary classification problem. Therefore, the improved separability principle weighting intra‐class distance and inter‐class distance generates the best decision tree structure named improved partial binary tree (IPBT) is to effectively decompose multi‐classification problem into multiple binary classification problems. A novel intelligent algorithms called bat algorithm‐based fruit fly optimization algorithm (BAFOA) is utilized to self‐adaptively optimize the parameters of each sub‐classifier TWSVMi. This strategic integration makes the model more flexible in adapting to the characteristics of electric rudder system and enhances the accuracy and robustness of the model. The performance of the proposed model is validated under real‐world datasets by the results of health states recognition experiments. The Accuracy, Precision, TPR, TNR, F1‐score, G‐mean, and Kappa of the BAFOA‐IPBT‐TWSVM are 0.972, 0.987, 0.982, 0.959, 0.985, 0.970, and 0.954 respectively. The reserved BAFOA‐IPBT‐TWSVM is capable of recognizing the health status with preferable performance compared with other nine models, which could introduce a novel idea for future rudder maintenance approaches. [ABSTRACT FROM AUTHOR]

DNA is a valuable tool for classifying expression of genes in detection of breast cancer. Gene expression data are biological data that extract valuable hidden information from gene datasets. Extracting useful features from datasets is a challenging task. Our gene expression dataset had a small number of samples but many features. This paper compared three types of recurrent deep learning models, including recurrent neural networks (RNN), long short-term memory (LSTM), and gated recurrent unit (GRU), for classification of breast cancer. The goals of the study were to improve the accuracy of classification and to enhance the effectiveness of feature selection; the basic principle was to select the best features from the original datasets. The bat algorithm assists in selecting the best relevant feature when integrated with recurrent deep learning models, which improves breast cancer classification by leveraging training datasets. Data preprocessing involves removing unnecessary columns and filling out missing values with the median value. The result was a comparative study using recurrent deep learning with the bat algorithm to classify breast cancer. The bat algorithm with LSTM achieved higher accuracy than RNN and GRU, where GRU had the lowest accuracy. [ABSTRACT FROM AUTHOR]

In addressing the challenge of diminished intrusion detection accuracy resulting from the abundance of redundant and irrelevant features in high-dimensional network data, an improved multi-factorial optimization bat algorithm (IMFBA) was introduced for precise data feature selection, with the ultimate goal of improving network intrusion detection accuracy. Within the multi-factorial optimization framework, global and local feature selection tasks were formulated. Information exchange between these tasks was facilitated by selection and vertical cultural transmission operators, strategically designed based on the bat algorithm. The global feature selection task was accelerated in identifying optimal solution spaces, thereby enhancing the algorithm's convergence speed and stability. By incorporating the reverse learning strategy and differential evolution into the bat algorithm, the initial solution selection stage and individual updating process were refined to address the absence of a mutation mechanism, fostering solution diversity and aiding the algorithm in escaping local optima. An adaptive parameter adjustment strategy was introduced, determining weightings for guiding individual updates based on potential optimal solution quality. This could mitigate the risk of knowledge negative transfer during multi-task feature selection, achieving a balance between global exploration and local exploitation. The feature subsets selected by IMFBA demonstrate classification accuracy of 95.37% and 85.14% on the KDD CUP 99 and NSL-KDD intrusion detection datasets, respectively. This reflected increased by 3.01 percentage points and 9.78 percentage points compared to the complete dataset. Experiment results confirm the efficacy of EMFBA in selecting higher-quality feature subsets and, consequently, enhancing network intrusion detection accuracy. [ABSTRACT FROM AUTHOR]

Vehicle routing problem (VRP) is a classic NP-hard optimization problem. It is generally accepted that an optimized routing scheme can cause huge difference in the cost in all stages of transportation. Consequently, the VRP has evoked interest among the researchers of the field. Usually, a metaheuristic or an evolutionary algorithm is used for the solution of a VRP variant. In the last years, a number of swarm intelligence algorithms have been used for the solution of the problem. Initially, the two most classic swarm intelligence algorithms, the Ant Colony Optimization and the Particle Swarm Optimization, were used for the solution of this kind of problems. However, in the last years, more and more researchers solved the problem using a different swarm intelligence algorithm. In this paper, we focused in the presentation and analysis of the swarm intelligence algorithms that have been used for the solution of the problem. We give the advantages and disadvantages of each method, we focus in those ones that produced the best results in difficult VRPs and we present directions for the future of this kind of algorithms for the solution of a VRP variant. [ABSTRACT FROM AUTHOR]

Modern power systems are growing in complexity due to the installation of large generators, long transmission lines, the addition of inertialess renewable energy resources (RESs) with zero inertia, etc., which can all severely degrade the system frequency stability. This can lead to under-/over-frequency load shedding, damage to turbine blades, and affect frequency-sensitive loads. In this study, we propose a methodology to improve the two critical frequency stability indices, i.e., the frequency nadir and the rate of change of frequency (RoCoF), by formulating an optimization problem. The size and placement location of battery energy storage systems (BESSs) are considered to be the constraints for the proposed optimization problem. Thereafter, the optimization problem is solved using the three metaheuristic optimization algorithms: the particle swarm optimization, firefly, and bat algorithm. The best performing algorithm is then selected to find the optimal sizing and placement location of the BESSs. The analyses are all performed on the IEEE 9-bus and IEEE 39-bus test systems. Several scenarios which consider multiple generator outages, increased/decreased loading conditions, and the addition of RESs are also considered for both test systems in this study. The obtained results show that under all scenarios, the proposed method can enhance system frequency compared to the existing method and without BESSs. The proposed method can be easily upscaled for a larger electrical network for obtaining the optimized BESS size and location for the improvement of the system frequency stability. [ABSTRACT FROM AUTHOR]

Bat Algorithm is an evolutionary metaheuristic that is used to find solutions to NP-Hard problems like the Travelling Salesman Problem. A Parallel Bat Colony Optimization Algorithm (PBCOA) based on the introduction of colonies to the popular Bat Algorithm is proposed in this article. The concept of colonies is introduced in the Bat Algorithm along with phenomena like reproductive crossover and migration. The resultant Parallel Bat Colony Optimization Algorithm is tested on 30 standard benchmark Functions, on which it shows clear superiority over 17 other optimization algorithms. PBCOA is applied to evolve CNN architectures over landmark recognition datasets. The learning rate and layers in the network were artificially selected as 0.9 and 3 respectively to quicken the process of training and make the model lesser complex. Even under the specified time and memory constraints, PBCOA improves the network accuracy and F1 Score from around 0.80 and less to more than 0.99. The evolved network, when tested on larger datasets, also shows an unprecedented improvement in performance, thereby meaning that the evolution of CNNs with PBCOA can be highly desirable. [ABSTRACT FROM AUTHOR]

The multi-dimensional investor or backpack problem is an important and well-known difficult constrained combinatorial optimization problem in operations research and optimization. Nowadays, algorithms inspired by nature have become extremely important in solving many mathematical problems, including the investor’s portfolio problem. In order to reach the best solutions, this research reviewed the bat algorithm and the updates that occurred to it in solving this problem. [ABSTRACT FROM AUTHOR]

Stroke is a major cause of mortality worldwide, disrupts cerebral blood flow, leading to severe brain damage. Hemiplegia, a common consequence, results in motor task loss on one side of the body. Many stroke survivors face long-term motor impairments and require great rehabilitation. Electroencephalograms (EEGs) provide a non-invasive method to monitor brain activity and have been used in brain–computer interfaces (BCIs) to help in rehabilitation. Motor imagery (MI) tasks, detected through EEG, are pivotal for developing BCIs that assist patients in regaining motor purpose. However, interpreting EEG signals for MI tasks remains challenging due to their complexity and low signal-to-noise ratio. The main aim of this study is to focus on optimizing channel selection in EEG-based BCIs specifically for stroke rehabilitation. Determining the most informative EEG channels is crucial for capturing the neural signals related to motor impairments in stroke patients. In this paper, a binary bat algorithm (BA)-based optimization method is proposed to select the most relevant channels tailored to the unique neurophysiological changes in stroke patients. This approach is able to enhance the BCI performance by improving classification accuracy and reducing data dimensionality. We use time–entropy–frequency (TEF) attributes, processed through automated independent component analysis with wavelet transform (AICA-WT) denoising, to enhance signal clarity. The selected channels and features are proved through a k-nearest neighbor (KNN) classifier using public BCI datasets, demonstrating improved classification of MI tasks and the potential for better rehabilitation outcomes. [ABSTRACT FROM AUTHOR]

Neutrosophic soft sets (NSS) are highly effective in representing neutral uncertain data. NSS model attracts several authors because it has huge range of applications in several areas such as decision-making, data analysis, smoothness of functions, probability theory, measurement theory, predicting, and operations research. Oral squamous cell carcinoma (OSCC) is the most general tumor around the world and its occurrence is on the increase in several populations. Early diagnosis plays vital role in improving diagnosis, treatment outcomes and survival rates. Although the new developments in understanding molecular mechanisms, late analysis and the implementation of precision medicine for OSCC patients continue to present problems. Early diagnosis and detection can support doctors in offering optimum patient care and effectual treatment. In recent years, the execution of several machine-learning (ML) approaches in cancer analysis has provided valuable insights, facilitating more effective and precise treatment decision-making. Oral Cancer screening can progress with the execution of artificial intelligence (AI) approaches. AI offers support to the oncology region by correctly examining a huge database in many imaging modalities. This article develops a Bat Algorithm with Rough Neutrosophic Soft Set for Oral Cancer Diagnosis (BARNSS-OCD) technique. The main intention of the BARNSSOCD technique is to exploit deep learning (DL) model for enhanced identification of OC. In the BARNSS-OCD technique, median filtering (MF) is used for image pre-processing and the feature extraction takes place using deep convolutional neural network (DCNN) model. In addition, bat algorithm (BA) is used for the hyperparameter selection of the DCNN model. For OC detection process, the BARNSS-OCD technique applies RNSS model. To exhibit the improved performance of the BARNSS-OCD technique, a sequence of experiments is involved. The simulation outcomes indicate that the BARNSS-OCD technique gains better performance compared to other DL models. [ABSTRACT FROM AUTHOR]

A Block chain technology works well in a variety of problem domains is the bat-inspired algorithm (BA). Modified with Enhanced Bat Algorithm (M-EBA) transaction system to overcome the original BA's optimal limitation. In order to improve convergence speed to the optimal solution and avoid local optima trapping, it takes into account the frequency and velocity of the current best solution. The results show that the M-EBA algorithm performs noticeably better than competing algorithms. Additionally, M-EBA analyzes the effects of various parameters to identify the optimal combination of parameter values in the context of numerical optimization and successfully solves a real-world assignment problem which is typically solved using linear programming techniques, with satisfactory results. To detect the fraudulent transaction system in future directions for forthcoming developments are proposed, including the use of BA in large-scale, dynamic, robust, multi-objective optimization as as well as improve BA performance by utilizing election mechanisms, tuning parameters, structure population. [ABSTRACT FROM AUTHOR]

Data processing and storage in outsourced contexts has recently shifted to edge-related smart computing. Smart, interconnected, Internet of Things (IoT) software denied networks prioritize security above all else when it comes to sharing data and making it more scalable and efficient. In real-time computing systems, a variety of securitybased issues may arise in operating resources and sharing data due to the fast expansion of various smart services. Boost the trustworthiness of encrypted data storage while meeting the fundamental needs of smart computing networks associated with the Internet of Things. Therefore, to offer effective and safe data storage for intelligent computer systems. related to the Internet of Things (IoT), suggest and develop a Novel Low Cost based Block chain Secure Model (NLCBSM). Using an AI calculation approach called the Leverage Bat algorithm to investigate intricate aspects, this model can adaptably record user verification for the purpose of detecting various attacks connected to users, such as distributed denial-of-service (DDOS) attacks on data reserve. Construct a a server-side blockchain end to furnish trustworthy data storage and safe transmission on the IoT terminal. As an additional data transmission mechanism, we make use of the Merkle tree, which offers low-cost communication overhead. This method employs a weighted data storage system to organize and categorize information for every individual, along with safe and unsecure storage options available in networks of intelligent computers, and each piece of data is assigned a random hash value to guarantee data integrity in the blockchain. The suggested model's experimental results show that it can investigate intricate secure characteristics, guarantee secure the authentication's operational efficiency for each user, and improve the communications overhead, accuracy, and security of smart computing data storage and sharing systems related to the Internet of Things. [ABSTRACT FROM AUTHOR]

In this study, the scale and shape parameters of the Weibull probability distribution function (W.pdf) used in determining the profitability of wind energy projects are estimated using optimization algorithms and the moment method. These parameters are then used to estimate the wind energy potential (WEP) in Foça region of İzmir in Turkey. The values of Weibull parameters obtained using Particle Swarm Optimization (PSO), Sine Cosine Algorithm (SCA), Social Group Optimization (SGO), and Bat Algorithm (BA) were compared with the estimation results of the Moment Method (MM) as reference. Root mean square error (RMSE) and chi-square (ϣ^2) tests were used to compare the parameter estimation methods. The wind speed measurement values of the observation station in Foça were used. As a result of Foça speed data analysis, the annual average wind speed was determined as 6.15 m/s, and the dominant wind direction was found as northeast. Wind speed frequency distributions were compared with the measurement results and calculated with the estimated parameters. When RMSE and ϣ^2 criteria are evaluated together; it can be concluded that each used method behaves similarly for the given parameter estimation problem, with minor variations. As a result, it has been found that the optimization parameters produce very good results in wind speed distribution and potential calculations. [ABSTRACT FROM AUTHOR]

Bat Algorithm (BA) is a nature-inspired metaheuristic search algorithm designed to efficiently explore complex problem spaces and find near-optimal solutions. The algorithm is inspired by the echolocation behavior of bats, which acts as a signal system to estimate the distance and hunt prey. Although the BA has proven effective for various optimization problems, it exhibits limited exploration ability and susceptibility to local optima. The algorithm updates velocities and positions based on the current global best solution, causing all agents to converge toward a specific location, potentially leading to local optima issues in optimization problems. On this premise, this paper proposes the Modified Bat Algorithm (MBA) as an enhancement to address the local optima limitation observed in the original BA. MBA incorporates the frequency and velocity of the current best solution, enhancing convergence speed to the optimal solution and preventing local optima entrapment. While the original BA faces diversity issues, both the original BA and MBA are introduced. To assess MBA's performance, three sets of test functions (classical benchmark functions, CEC2005, and CEC2019) are employed, with results compared to those of the original BA, Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Dragonfly Algorithm (DA). The outcomes demonstrate the MBA's significant superiority over other algorithms. In addition, MBA successfully addresses a real-world assignment problem (call center problem), traditionally solved using linear programming methods, with satisfactory results. [ABSTRACT FROM AUTHOR]

Tomatoes are recognized for their nutritional value in disease prevention, yet foliar infections often hinder their production. Monitoring and management of tomato leaf disease need much time, cost, and effort. Artificial Intelligence (AI), specifically Deep Neural Networks offers a promising solution for automating disease detection, such as Convolutional Neural Networks (CNN). CNN has several advantages over the traditional machine learning. Selecting the optimal CNN architecture is crucial for accurate feature extraction from image data. Numerous well-known CNN-based architectures have been proposed and used in numerous studies, including VGGNet and DenseNet. DenseNet121 has been proven to produce high classification accuracy. However, the DenseNet121 performance depends on the selection of optimal hyperparameter. This paper proposes an enhancing DenseNet121 performance through hyperparameter optimization using the Bat Algorithm (BA) for classifying tomato leaf disease. BA is used in this research since it has good performance and some advantages. The proposed method achieves better performance than the original DenseNet121 and has a competitive computational time. It produces an accuracy of 0.9465, macroaverage precision of 0.9498, macro-average recall of 0.9465, and macro-average f1-score of 0.9460. This method is prospective to be implemented in devices in the real problem with many various image conditions in the future. [ABSTRACT FROM AUTHOR]

Objective: To solve the problems of low control accuracy and poor motion stability in the trajectory tracking control method of parallel food sorting robots. Methods: On the basis of analyzing the structure of a four degree of freedom parallel robot, a combination of sliding mode control algorithm, fuzzy control algorithm, and improved bat algorithm was proposed for trajectory tracking control of a parallel food sorting robot. Optimizing the bandwidth of fuzzy algorithms by improving the bat algorithm, and adaptively adjusting the fuzzy gain and sliding surface slope of the sliding membrane control algorithm through the optimized fuzzy control algorithm, the tracking error of the controller was reduced, improve anti-interference ability, and verify the superiority of the proposed trajectory tracking control method. Results: The proposed trajectory tracking control method had an actual sorting accuracy of 99.90% and an average sorting time of 0.509 seconds. Conclusion: Compared with conventional methods, the proposed trajectory tracking control method has higher joint trajectory tracking accuracy, stronger anti-interference ability, and smoother output torque.

ABSTRACTThis research introduces innovative approaches to enhance intrusion detection systems (IDSs) by addressing critical challenges in existing methods. Various machine-learning techniques, including nature-inspired metaheuristics, Bayesian algorithms, and swarm intelligence, have been proposed in the past for attribute selection and IDS performance improvement. However, these methods have often fallen short in terms of detection accuracy, detection rate, precision, and F-score. To tackle these issues, the paper presents a novel hybrid feature selection approach combining the Bat metaheuristic algorithm with the Residue Number System (RNS). Initially, the Bat algorithm is utilized to partition training data and eliminate irrelevant attributes. Recognizing the Bat algorithm's slower training and testing times, RNS is incorporated to enhance processing speed. Additionally, principal component analysis (PCA) is employed for feature extraction. In a second phase, RNS is excluded for feature selection, allowing the Bat algorithm to perform this task while PCA handles feature extraction. Subsequently, classification is conducted using naive bayes, and k-Nearest Neighbors. Experimental results demonstrate the remarkable effectiveness of combining RNS with the Bat algorithm, achieving outstanding detection rates, accuracy, and F-scores. Notably, the fusion approach doubles processing speed. The findings are further validated through benchmarking against existing intrusion detection methods, establishing their competitiveness.

In order to ensure the operational efficiency of police personnel under the background of anti-terrorism operation, this paper puts forward the planning and construction method of equipment support system for task demand, and constructs the anti-terrorism equipment support system in Xinjiang region Combined with the constructed system, a mathematical model with time-priority as the objective is established, and a hybrid task planning method based on multidimensional dynamic list programming and chaotic bat algorithm is proposed. A discrete chaotic bat algorithm with adaptive search strategy and mutation operation is designed to allocate resources for selected tasks by multidimensional dynamic list tasks. The research shows that the established support system fully considers the equipment system demand generation mechanism under the Background of anti-terrorism operation, and increases the introduction of the support system and the technical standard system, which can effectively meet the personnel equipment support needs in the anti-terrorism environment. [ABSTRACT FROM AUTHOR]

This research introduces innovative approaches to enhance intrusion detection systems (IDSs) by addressing critical challenges in existing methods. Various machine-learning techniques, including nature-inspired metaheuristics, Bayesian algorithms, and swarm intelligence, have been proposed in the past for attribute selection and IDS performance improvement. However, these methods have often fallen short in terms of detection accuracy, detection rate, precision, and F-score. To tackle these issues, the paper presents a novel hybrid feature selection approach combining the Bat metaheuristic algorithm with the Residue Number System (RNS). Initially, the Bat algorithm is utilized to partition training data and eliminate irrelevant attributes. Recognizing the Bat algorithm's slower training and testing times, RNS is incorporated to enhance processing speed. Additionally, principal component analysis (PCA) is employed for feature extraction. In a second phase, RNS is excluded for feature selection, allowing the Bat algorithm to perform this task while PCA handles feature extraction. Subsequently, classification is conducted using naive bayes, and k-Nearest Neighbors. Experimental results demonstrate the remarkable effectiveness of combining RNS with the Bat algorithm, achieving outstanding detection rates, accuracy, and F-scores. Notably, the fusion approach doubles processing speed. The findings are further validated through benchmarking against existing intrusion detection methods, establishing their competitiveness. [ABSTRACT FROM AUTHOR]

Assembly line balancing problem is the process of assigning a set of tasks to a group of stations, considering the precedence relations between tasks. Precedence relations are commonly definite; however, tasks may have alternative precedence relations due to different mounting alternatives. In the presence of alternative precedence relations, the classical balancing problem becomes more complicated given that two interdependent problems, namely selection and balancing, must be solved hierarchically. This type of balancing problem is named as the Alternative Subgraph Assembly Line Balancing Problem (ASALBP). This current paper concerns itself to develop an efficient solution procedure for the ASALBP by hybridizing the firefly and bat algorithms. The proposed hybrid algorithm is evaluated on a set of benchmark problems taken from the related literature and numerically compared against the standard firefly and bat algorithms, and some formerly developed heuristic methods. Computational results reveal the satisfactory performance of the proposed algorithm in solving ASALBP instances. [ABSTRACT FROM AUTHOR]

Swarm robotics show collective behavior in order to work in multi agent scenario, where spatial area coverage is an emergent area of research. This work introduces a hybrid technique for optimized spatial area coverage. A combination of Dragonfly Algorithm (DA) and chaotic mapping is proposed and the entire study is carried out in two phases. In the first phase, DA's parameters are measured on the basis of percentage of area covered, entropy and number of pop-up threats detected. In the second phase, Chaotic distribution is applied in swarm algorithms (i.e. DA along with Bat Algorithm and Accelerated Particle Swarm Optimization) to implement hybridized models. Chaotic Dragonfly Algorithm along with Chaotic Bat Algorithm and Chaotic Accelerated Particle Swarm Optimization) is implemented. To evaluate the performance of hybridized models, a comprehensive comparison is drawn among the Levy and Chaotic versions of all three swarm algorithms. It is concluded that the proposed DA outperforms the rest. DA not only showed better results for the mentioned metrics, but also displayed uniform behavior over multiple runs. [ABSTRACT FROM AUTHOR]

Power system operators are faced with the problem of unit commitment belonging to mixed integer programming, which becomes very complicated, as units become large-scale and highly constrained. Because unit commitment problem is a binary problem with commitment and de-commitment, a discrete/binary optimization algorithm with superior performance is required. This paper proposes a novel hybrid binary bat algorithm for unit commitment problem, which consists of two process. To begin with, the proposed binary bat algorithm is applied to determining the commitment schedule of unit commitment problem. Specifically, an improved crossover operator based on exponential-logic-modulo map is proposed to enhance the convergence and maintain the diversity of populations. To prevent the algorithm from falling into a local optimum, a local mutation strategy performs local perturbation. Chaotic map is responsible for updating some parameters to increase the performance of the proposed algorithm. Furthermore, Lambda-iteration method is adopted to solve economic load dispatch in continuous space. Constraint handling is performed using the heuristic constraint produce. The effectiveness of the proposed algorithm is verified by benchmark functions and test systems. Additionally, the simulation results are compared with other well-established heuristic and binary approaches. [ABSTRACT FROM AUTHOR]

This research emphasizes a meta-heuristic modified ant lion optimizer (MALO) optimization approach for the simultaneous utilization of DSTATCOM devices and distributed photovoltaic (PV) sources with network reconfiguration in a radial power distribution scheme. In a radial power distribution network with network reconfiguration, the majority of the research is based on constant power model analysis. However, it is noticed that load models have a substantial impact on the distributed PV sources and the DSTATCOM device's optimal size and position. The effect of the constant power (CP) and polynomial (ZIP) with load growth load models for the simultaneous insertion of distributed PV sources and DSTATCOM devices with network reconfiguration is examined in this research work for power system planning. The penetration levels of distributed PV sources considered for the investigation are 25%, 50%, 75%, and 100%. The principal objective of this research is to reduce network total power losses, enhance the voltage magnitude profile at all buses, and reduce the overall operating cost while adhering to equality and inequality constraints. The proposed algorithm is verified on 118-node test systems. The investigation is carried out for planning network upgrading to a high-voltage distribution system (HVDS) on 317 nodes in the rural Bangalore Electricity Supply Company Limited (BESCOM) radial distribution scheme. The simulated results obtained with this method are validated with the BAT algorithm and techniques available in the literature. It is observed that in the IEEE 118-bus system, via the simultaneous placement and sizing of PV sources considering a 25% penetration level and DSTATCOM devices during network reconfiguration, the total power loss reduction is 41.47% and 42.98% for the constant power model and ZIP with the load growth model. For the 317-bus system, the total power loss reduction observed for 11 kV is 49.77% and 59.34% for the constant power model and ZIP model with load growth. Similarly, for the 22 kV system, the power loss reduction observed is 51.69% and 55.75% for the constant power model and ZIP with the load growth model. [ABSTRACT FROM AUTHOR]

Crop drought diagnosis has been an urgent need to be solved with the development of precision irrigation. It is a high demand to improve the accuracy and timeliness of crop water phenotype diagnosis in the field of intelligent irrigation. In this study, an intelligent diagnosis of winter wheat drought was proposed using improved machine vision. Field experiments were carried out to verify. Three treatments were set in the pit test: suitable, moderate drought and severe drought treatment. The early RGB HD images were capture from the winter wheat by digital camera. The sensitive areas of wheat images were segmented by K-means clustering with the improved by HSV color space. The color and texture features were then extracted as principal components. The support vector machine (SVM) that optimized by bat algorithm (BA) was used to classify the data after dimensionality reduction. Compared with the SVM with/without optimization by Genetic Algorithm, the BA-SVM model was more efficient in diagnosis. The K-means clustering combined with HSV color shared the better segmentation than the traditional one. There were the extract seven-dimensional color features of red channel (R), green channel (G), blue channel (B), brightness (V), 2G-R, 2G-B, (G+R+B)/3 and four-dimensional texture features Energy, Homogeneity, Contrast, Correlation. The principal component analysis was used to reduce the dimensionality of 11 dimensional features. There were the first 3-dimensional principal components with a cumulative contribution rate of 97.2%. The BA was used to optimize the penalty factor and kernel parameters of SVM. The recognition accuracy after dimensionality reduction by principal component analysis was superior to other feature combinations. The recognition accuracy was 96.1% and the running time was 31s, which was 8.3%, 7.2% and 4.4% higher than those of color feature, texture feature and color + texture feature, respectively. The running time was shortened by 14, 21 and 25 s, respectively. Compared with the genetic algorithm SVM (GA-SVM) and unoptimized SVM, the dimensionality reduction features were improved by 6.1% and 8.9%, and shortened by 7 and 14 s, respectively. Therefore, the intelligent diagnosis of winter wheat drought was constructed using improved algorithms, such as image segmentation, feature extraction, data dimensionality reduction, data recognition and classification. The finding can provide the real-time diagnosis of winter wheat drought for the decision-making on intelligent irrigation. [ABSTRACT FROM AUTHOR]

With the development of micro-electro-mechanical-system, energy harvesting (EH)-enabled sensor nodes may be used in many applications. WSNs without EH-enabled nodes still have limited applicability due to limited battery resources. The introduction of EH-enabled sensor nodes in the network increases costs and reduces performance due to environmental factors. We propose the clustering-based BAT algorithm for energy harvesting (CBA-EH) in IoT-enable wireless sensor networks to maximize the network performance. The Bat Optimization Algorithm is employed to optimize the fitness factors associated with CH selection. These factors include residual energy, intra-cluster distance, inter-cluster distance, and distance between EH-nodes and sink. The utilization of EH-enabled nodes enables us to effectively manage and minimize the network's operational costs. The simulation results show that the suggested approach significantly improves network stability and operating time compared to current methods. In comparison to the GAOC protocol, simulation findings demonstrate that CBA-EH enhances stability, network lifetime, and throughput by 45%, 42.13%, and 48%, respectively. [ABSTRACT FROM AUTHOR]

Vector quantization (VQ) is a block coding method that is famous for its high compression ratio and simple encoder and decoder implementation. Linde–Buzo–Gray (LBG) is a renowned technique for VQ that uses a clustering-based approach for finding the optimum codebook. Numerous algorithms, such as Particle Swarm Optimization (PSO), the Cuckoo search algorithm (CS), bat algorithm, and firefly algorithm (FA), are used for codebook design. These algorithms are primarily focused on improving the image quality in terms of the PSNR and SSIM but use exhaustive searching to find the optimum codebook, which causes the computational time to be very high. In our study, our algorithm enhances LBG by minimizing the computational complexity by reducing the total number of comparisons among the codebook and training vectors using a match function. The input image is taken as a training vector at the encoder side, which is initialized with the random selection of the vectors from the input image. Rescaling using bilinear interpolation through the nearest neighborhood method is performed to reduce the comparison of the codebook with the training vector. The compressed image is first downsized by the encoder, which is then upscaled at the decoder side during decompression. Based on the results, it is demonstrated that the proposed method reduces the computational complexity by 50.2% compared to LBG and above 97% compared to the other LBG-based algorithms. Moreover, a 20% reduction in the memory size is also obtained, with no significant loss in the image quality compared to the LBG algorithm. [ABSTRACT FROM AUTHOR]

Regarding the regional area target collaborative tracking problem widely existing in intelligent scenarios, this paper built a distributed UAV swarm framework inspired by natural intelligence to heighten intricate missions' efficiency. Also, a standoff collaboratively continuous tracking strategy was proposed based on a lateral guidance law with an improved Reference Point Guidance (RPG) and a longitudinal guidance law with an improved phase collaboration. Under an uncertain environment, this framework used an improved bat algorithm (IBA) to optimize the speed allocation of the UAV swarm's online control strategy with information consensus estimation. Compared with a case without the designed transformation, statistically, the results demonstrate that the framework operates efficiently and robustly in phase error convergence, swarm flight distance, and fuel consumption, where a dynamic target exists. [ABSTRACT FROM AUTHOR]

Many studies have addressed supply chain that shows the importance of the subject and the competition in the supply chain consisting of several companies. The previous studies address the issue of reducing the Bullwhip Effect in the supply chain, which is possible by predicting the correct amount of customer demand. This paper improves the accuracy of the model prediction and reduces the existing error in the previous models to attain an accurate and very close-to-reality forecast and also to reduce the Bullwhip Effect in the supply chain. Literature shows the absence of research on the presentation of a metaheuristic algorithm consisting of a neural network and bat algorithm to forecast supply chain demand in manufacturing companies; therefore, this article is innovative. On the other hand, no researchers have addressed Bullwhip Effect reduction using mixed metaheuristic algorithms. Therefore, this article improves the previous models, reduces the number of errors in demand forecasting, and reduces the Bullwhip Effect. For this purpose, the scalable gradient algorithm method is used for better network training. The results indicate the optimal performance of neural network training with a comparable gradient and bat algorithm on reducing the Bullwhip Effect. [ABSTRACT FROM AUTHOR]