Due to the lack of accurate data and complex parameterization,the prediction of groundwater depth is a chal-lenge for numerical models.Machine learning can effectively solve this issue and has been proven useful in th...Due to the lack of accurate data and complex parameterization,the prediction of groundwater depth is a chal-lenge for numerical models.Machine learning can effectively solve this issue and has been proven useful in the prediction of groundwater depth in many areas.In this study,two new models are applied to the prediction of groundwater depth in the Ningxia area,China.The two models combine the improved dung beetle optimizer(DBO)algorithm with two deep learning models:The Multi-head Attention-Convolution Neural Network-Long Short Term Memory networks(MH-CNN-LSTM)and the Multi-head Attention-Convolution Neural Network-Gated Recurrent Unit(MH-CNN-GRU).The models with DBO show better prediction performance,with larger R(correlation coefficient),RPD(residual prediction deviation),and lower RMSE(root-mean-square error).Com-pared with the models with the original DBO,the R and RPD of models with the improved DBO increase by over 1.5%,and the RMSE decreases by over 1.8%,indicating better prediction results.In addition,compared with the multiple linear regression model,a traditional statistical model,deep learning models have better prediction performance.展开更多
This paper introduces the Surrogate-assisted Multi-objective Grey Wolf Optimizer(SMOGWO)as a novel methodology for addressing the complex problem of empty-heavy train allocation,with a focus on line utilization balanc...This paper introduces the Surrogate-assisted Multi-objective Grey Wolf Optimizer(SMOGWO)as a novel methodology for addressing the complex problem of empty-heavy train allocation,with a focus on line utilization balance.By integrating surrogate models to approximate the objective functions,SMOGWO significantly improves the efficiency and accuracy of the optimization process.The effectiveness of this approach is evaluated using the CEC2009 multi-objective test function suite,where SMOGWO achieves a superiority rate of 76.67%compared to other leading multi-objective algorithms.Furthermore,the practical applicability of SMOGWO is demonstrated through a case study on empty and heavy train allocation,which validates its ability to balance line capacity,minimize transportation costs,and optimize the technical combination of heavy trains.The research highlights SMOGWO's potential as a robust solution for optimization challenges in railway transportation,offering valuable contributions toward enhancing operational efficiency and promoting sustainable development in the sector.展开更多
Stereoscopic agriculture,as an advanced method of agricultural production,poses new challenges for multi-task trajectory planning of unmanned aerial vehicles(UAVs).To address the need for UAVs to perform multi-task tr...Stereoscopic agriculture,as an advanced method of agricultural production,poses new challenges for multi-task trajectory planning of unmanned aerial vehicles(UAVs).To address the need for UAVs to perform multi-task trajectory planning in stereoscopic agriculture,a multi-task trajectory planning model and algorithm(IEP-AO)that synthesizes flight safety and flight efficiency is proposed.Based on the requirements of stereoscopic agricultural geomorphological features and operational characteristics,the multi-task trajectory planning model is ensured by constructing targeted constraints at five aspects,including the path,slope,altitude,corner,energy and obstacle threat,to improve the effectiveness of the trajectory planning model.And combined with the path optimization algorithm,an Aquila optimizer(IEP-AO)based on the interference-enhanced combination model is proposed,which can help UAVs to improve the trajectory search capability in complex operation space and large-scale operation tasks,and jump out of the locally optimal trajectory path region timely,to generate the optimal trajectory planning plan that can adapt to the diversity of the tasks and the flight efficiency.Meanwhile,four simulated flights with different operation scales and different scene constraints were conducted under the constructed real 3Dimension scene,and the experimental results can show that the proposedmulti-task trajectory planning method canmeet themulti-task requirements in stereoscopic agriculture and improve the mission execution efficiency and agricultural production effect of UAV.展开更多
The Internet of Things(IoT)is integral to modern infrastructure,enabling connectivity among a wide range of devices from home automation to industrial control systems.With the exponential increase in data generated by...The Internet of Things(IoT)is integral to modern infrastructure,enabling connectivity among a wide range of devices from home automation to industrial control systems.With the exponential increase in data generated by these interconnected devices,robust anomaly detection mechanisms are essential.Anomaly detection in this dynamic environment necessitates methods that can accurately distinguish between normal and anomalous behavior by learning intricate patterns.This paper presents a novel approach utilizing generative adversarial networks(GANs)for anomaly detection in IoT systems.However,optimizing GANs involves tuning hyper-parameters such as learning rate,batch size,and optimization algorithms,which can be challenging due to the non-convex nature of GAN loss functions.To address this,we propose a five-dimensional Gray wolf optimizer(5DGWO)to optimize GAN hyper-parameters.The 5DGWO introduces two new types of wolves:gamma(γ)for improved exploitation and convergence,and theta(θ)for enhanced exploration and escaping local minima.The proposed system framework comprises four key stages:1)preprocessing,2)generative model training,3)autoencoder(AE)training,and 4)predictive model training.The generative models are utilized to assist the AE training,and the final predictive models(including convolutional neural network(CNN),deep belief network(DBN),recurrent neural network(RNN),random forest(RF),and extreme gradient boosting(XGBoost))are trained using the generated data and AE-encoded features.We evaluated the system on three benchmark datasets:NSL-KDD,UNSW-NB15,and IoT-23.Experiments conducted on diverse IoT datasets show that our method outperforms existing anomaly detection strategies and significantly reduces false positives.The 5DGWO-GAN-CNNAE exhibits superior performance in various metrics,including accuracy,recall,precision,root mean square error(RMSE),and convergence trend.The proposed 5DGWO-GAN-CNNAE achieved the lowest RMSE values across the NSL-KDD,UNSW-NB15,and IoT-23 datasets,with values of 0.24,1.10,and 0.09,respectively.Additionally,it attained the highest accuracy,ranging from 94%to 100%.These results suggest a promising direction for future IoT security frameworks,offering a scalable and efficient solution to safeguard against evolving cyber threats.展开更多
The global incidence of Alzheimer's Disease(AD)is on a swift rise.The Electroencephalogram(EEG)signals is an effective tool for the identification of AD and its initial Mild Cognitive Impairment(MCI)stage using ma...The global incidence of Alzheimer's Disease(AD)is on a swift rise.The Electroencephalogram(EEG)signals is an effective tool for the identification of AD and its initial Mild Cognitive Impairment(MCI)stage using machine learning models.Analysis of AD using EEG involves multi-channel analysis.However,the use of multiple channels may impact the classification performance due to data redundancy and complexity.In this work,a hybrid EEG channel selection is proposed using a combination of Reptile Search Algorithm and Snake Optimizer(RSO)for AD and MCI detection based on decomposition methods.Empirical Mode Decomposition(EMD),Low-Complexity Orthogonal Wavelet Filter Banks(LCOWFB),Variational Mode Decomposition,and discrete-wavelet transform decomposition techniques have been employed for subbands-based EEG analysis.We extracted thirty-four features from each subband of EEG signals.Finally,a hybrid RSO optimizer is compared with five individual metaheuristic algorithms for effective channel selection.The effectiveness of this model is assessed by two publicly accessible AD EEG datasets.An accuracy of 99.22% was achieved for binary classification from RSO with EMD using 4(out of 16)EEG channels.Moreover,the RSO with LCOWFBs obtained 89.68%the average accuracy for three-class classification using 7(out of 19)channels.The performance reveals that RSO performs better than individual Metaheuristic algorithms with 60%fewer channels and improved accuracy of 4%than existing AD detection techniques.展开更多
Metaheuristic optimization methods are iterative search processes that aim to efficiently solve complexoptimization problems. These basically find the solution space very efficiently, often without utilizing the gradi...Metaheuristic optimization methods are iterative search processes that aim to efficiently solve complexoptimization problems. These basically find the solution space very efficiently, often without utilizing the gradientinformation, and are inspired by the bio-inspired and socially motivated heuristics. Metaheuristic optimizationalgorithms are increasingly applied to complex feature selection problems in high-dimensional medical datasets.Among these, Teaching-Learning-Based optimization (TLBO) has proven effective for continuous design tasks bybalancing exploration and exploitation phases. However, its binary version (BTLBO) suffers from limited exploitationability, often converging prematurely or getting trapped in local optima, particularly when applied to discrete featureselection tasks. Previous studies reported that BTLBO yields lower classification accuracy and higher feature subsetvariance compared to other hybrid methods in benchmark tests, motivating the development of hybrid approaches.This study proposes a novel hybrid algorithm, BTLBO-Cheetah Optimizer (BTLBO-CO), which integrates the globalexploration strength of BTLBO with the local exploitation efficiency of the Cheetah Optimization (CO) algorithm. Theobjective is to enhance the feature selection process for cancer classification tasks involving high-dimensional data. Theproposed BTLBO-CO algorithm was evaluated on six benchmark cancer datasets: 11 tumors (T), Lung Cancer (LUC),Leukemia (LEU), Small Round Blue Cell Tumor or SRBCT (SR), Diffuse Large B-cell Lymphoma or DLBCL (DL), andProstate Tumor (PT).The results demonstrate superior classification accuracy across all six datasets, achieving 93.71%,96.12%, 98.13%, 97.11%, 98.44%, and 98.84%, respectively.These results validate the effectiveness of the hybrid approachin addressing diverse feature selection challenges using a Support Vector Machine (SVM) classifier.展开更多
Detecting Alzheimer’s disease is essential for patient care,as an accurate diagnosis influences treatment options.Classifying dementia from non-dementia in brain MRIs is challenging due to features such as hippocampa...Detecting Alzheimer’s disease is essential for patient care,as an accurate diagnosis influences treatment options.Classifying dementia from non-dementia in brain MRIs is challenging due to features such as hippocampal atrophy,while manual diagnosis is susceptible to error.Optimal computer-aided diagnosis(CAD)systems are essential for improving accuracy and reducing misclassification risks.This study proposes an optimized ensemble method(CEOE-Net)that initiates with the selection of pre-trained models,including DenseNet121,ResNet50V2,and ResNet152V2 for unique feature extraction.Each selected model is enhanced with the inclusion of a channel attention(CA)block to improve the feature extraction process.In addition,this study employs the Short Time Fourier transform(STFT)technique with each individual model for hierarchical feature extraction before making final predictions in classifying MRI images of dementia and non-demented individuals,considering them as backbone models for building the ensemble method.STFT highlights subtle differences in brain structure and activity,particularly when combined with CA mechanisms that emphasize relevant features by converting spatial data into the frequency domain.The predictions generated from these models are then processed by the Chaotic Evolution Optimization(CEO)algorithm,which determines the optimal weightage set for each backbone model to maximize their contribution.The CEO optimizer explores weight distribution to ensure the most effective combination of model predictions for enhancing classification accuracy,thus significantly improving overall ensemble performance.This study utilized three datasets for validation:two private clinical brain MRI datasets(OSASIS and ADNI)to test the proposed model’s effectiveness.Image augmentation techniques were also employed to enhance dataset diversity and improve classification performance.The proposed CEOE-Net outperforms conventional baseline models and existing methods by showing its effectiveness as a clinical tool for the accurate classification of dementia and non-dementia MRI brain images,as well as autistic and non-autistic facial features.It achieved consistent accuracies of 93.44%on OSASIS and 81.94%on ADNI.展开更多
The dung beetle optimizer(DBO)is a metaheuristic algorithm with fast convergence and powerful search capabilities,which has shown excellent performance in solving various optimization problems.However,it suffers from ...The dung beetle optimizer(DBO)is a metaheuristic algorithm with fast convergence and powerful search capabilities,which has shown excellent performance in solving various optimization problems.However,it suffers from the problems of easily falling into local optimal solutions and poor convergence accuracy when dealing with large-scale complex optimization problems.Therefore,we propose an adaptive DBO(ADBO)based on an elastic annealing mechanism to address these issues.First,the convergence factor is adjusted in a nonlinear decreasing manner to balance the requirements of global exploration and local exploitation,thus improving the convergence speed and search quality.Second,a greedy difference optimization strategy is introduced to increase population diversity,improve the global search capability,and avoid premature convergence.Finally,the elastic annealing mechanism is used to perturb the randomly selected individuals,helping the algorithm escape local optima and thereby improve solution quality and algorithm stability.The experimental results on the CEC 2017 and CEC 2022 benchmark function sets and MCNC benchmark circuits verify the effectiveness,superiority,and universality of ADBO.展开更多
For optimization algorithms,the most important consideration is their global optimization performance.Our research is conducted with the hope that the algorithm can robustly find the optimal solution to the target pro...For optimization algorithms,the most important consideration is their global optimization performance.Our research is conducted with the hope that the algorithm can robustly find the optimal solution to the target problem at a lower computational cost or faster speed.For stochastic optimization algorithms based on population search methods,the search speed and solution quality are always contradictory.Suppose that the random range of the group search is larger;in that case,the probability of the algorithm converging to the global optimal solution is also greater,but the search speed will inevitably slow.The smaller the random range of the group search is,the faster the search speed will be,but the algorithm will easily fall into local optima.Therefore,our method is intended to utilize heuristic strategies to guide the search direction and extract as much effective information as possible from the search process to guide an optimized search.This method is not only conducive to global search,but also avoids excessive randomness,thereby improving search efficiency.To effectively avoid premature convergence problems,the diversity of the group must be monitored and regulated.In fact,in natural bird flocking systems,the distribution density and diversity of groups are often key factors affecting individual behavior.For example,flying birds can adjust their speed in time to avoid collisions based on the crowding level of the group,while foraging birds will judge the possibility of sharing food based on the density of the group and choose to speed up or escape.The aim of this work was to verify that the proposed optimization method is effective.We compared and analyzed the performances of five algorithms,namely,self-organized particle swarm optimization(PSO)-diversity controlled inertia weight(SOPSO-DCIW),self-organized PSO-diversity controlled acceleration coefficient(SOPSO-DCAC),standard PSO(SPSO),the PSO algorithm with a linear decreasing inertia weight(SPSO-LDIW),and the modified PSO algorithm with a time-varying acceleration constant(MPSO-TVAC).展开更多
With the development of composite materials,their lightweight and high-strength characteristics have caused more widespread use from aerospace applications to automotive and rail transportation sectors,significantly r...With the development of composite materials,their lightweight and high-strength characteristics have caused more widespread use from aerospace applications to automotive and rail transportation sectors,significantly reducing the energy consumption during the operation of EMUs(Electric Multiple Units).This study aims to explore the application of composite materials in the lightweight design of EMU front skirts and proposes a design method based on threedimensional Hashin failure criteria and the Cheetah Optimizer(CO)to achieve maximum lightweight efficiency.The UMAT subroutine was developed based on the three-dimensional Hashin failure criteria to calculate failure parameters,which were used as design parameters in the CO.The model calculations and result extraction were implemented in MATLAB,and the Cheetah Optimizer iteratively determined the optimal laminating angle design that minimized the overall failure factor.After 100 iterations,ensuring structural integrity,the optimized design reduced the weight of the skirt panel by 60% compared to the original aluminum alloy structure,achieving significant lightweight benefits.This study provides foundational data for the lightweight design of EMUs.展开更多
The total nitrogen(TN)is a major factor contributing to eutrophication and is a crucial parameter in assessing surface water quality.Accurate and rapid methods are crucial for determining the TN content in water.Herei...The total nitrogen(TN)is a major factor contributing to eutrophication and is a crucial parameter in assessing surface water quality.Accurate and rapid methods are crucial for determining the TN content in water.Herein,a fast,highly sensitive,and pollution-free approach is proposed,which combines ultraviolet(UV)absorption spectroscopy with Bayesian optimized least squares support vector machine(LSSVM)for detecting TN content in water.Water samples collected from sampling points near the Yangtze River basin in Chongqing of China were analyzed using national standard methods to measure TN content as reference values.The prediction of TN content in water was achieved by integrating the UV absorption spectra of water samples with LSSVM.To make the model quickly and accurately select the optimal parameters to improve the accuracy of the prediction model,the Bayesian optimization(BO)algorithm was used to optimize the parameters of the LSSVM.Results show that the prediction model performs well in predicting TN concentration,with a high coefficient of prediction determination(R^(2)=0.9413)and a low root mean square error of prediction(RMSE=0.0779 mg/L).Comparative analysis with previous studies indicates that the model used in this paper achieves lower prediction errors and superior predictive performance.展开更多
Accurate daily suspended sediment load(SSL)prediction is essential for sustainable water resource management,sediment control,and environmental planning.However,SSL prediction is highly complex due to its nonlinear an...Accurate daily suspended sediment load(SSL)prediction is essential for sustainable water resource management,sediment control,and environmental planning.However,SSL prediction is highly complex due to its nonlinear and dynamic nature,making traditional empirical models inadequate.This study proposes a novel hybrid approach,integrating the Adaptive Neuro-Fuzzy Inference System(ANFIS)with the Gradient-Based Optimizer(GBO),to enhance SSL forecasting accuracy.The research compares the performance of ANFIS-GBO with three alternative models:standard ANFIS,ANFIS with Particle Swarm Optimization(ANFIS-PSO),and ANFIS with Grey Wolf Optimization(ANFIS-GWO).Historical SSL and streamflow data from the Bailong River Basin,China,are used to train and validate the models.The input selection process is optimized using the Multivariate Adaptive Regression Splines(MARS)method.Model performance is evaluated using statistical metrics such as Root Mean Square Error(RMSE),Mean Absolute Error(MAE),Mean Absolute Percentage Error(MAPE),Nash Sutcliffe Efficiency(NSE),and Determination Coefficient(R^(2)).Additionally,visual assessments,including scatter plots,Taylor diagrams,and violin plots,provide further insights into model reliability.The results indicate that including historical SSL data improves predictive accuracy,with ANFIS-GBO outperforming the other models.ANFIS-GBO achieves the lowest RMSE and MAE and the highest NSE and R^(2),demonstrating its superior learning ability and adaptability.The findings highlight the effectiveness of nature-inspired optimization algorithms in enhancing sediment load forecasting and contribute to the advancement of AI-based hydrological modeling.Future research should explore the integration of additional environmental and climatic variables to enhance predictive capabilities further.展开更多
Assessing the stability of slopes is one of the crucial tasks of geotechnical engineering for assessing and managing risks related to natural hazards,directly affecting safety and sustainable development.This study pr...Assessing the stability of slopes is one of the crucial tasks of geotechnical engineering for assessing and managing risks related to natural hazards,directly affecting safety and sustainable development.This study primarily focuses on developing robust and practical hybrid models to predict the slope stability status of circular failure mode.For this purpose,three robust models were developed using a database including 627 case histories of slope stability status.The models were developed using the random forest(RF),support vector machine(SVM),and extreme gradient boosting(XGB)techniques,employing 5-fold cross validation approach.To enhance the performance of models,this study employs Bayesian optimizer(BO)to fine-tuning their hyperparameters.The results indicate that the performance order of the three developed models is RF-BO>SVM-BO>XGB-BO.Furthermore,comparing the developed models with previous models,it was found that the RF-BO model can effectively determine the slope stability status with outstanding performance.This implies that the RF-BO model could serve as a dependable tool for project managers,assisting in the evaluation of slope stability during both the design and operational phases of projects,despite the inherent challenges in this domain.The results regarding the importance of influencing parameters indicate that cohesion,friction angle,and slope height exert the most significant impact on slope stability status.This suggests that concentrating on these parameters and employing the RF-BO model can effectively mitigate the severity of geohazards in the short-term and contribute to the attainment of long-term sustainable development objectives.展开更多
Aquila Optimizer(AO)is a recently proposed population-based optimization technique inspired by Aquila’s behavior in catching prey.AO is applied in various applications and its numerous variants were proposed in the l...Aquila Optimizer(AO)is a recently proposed population-based optimization technique inspired by Aquila’s behavior in catching prey.AO is applied in various applications and its numerous variants were proposed in the literature.However,chaos theory has not been extensively investigated in AO.Moreover,it is still not applied in the parameter estimation of electro-hydraulic systems.In this work,ten well-defined chaotic maps were integrated into a narrowed exploitation of AO for the development of a robust chaotic optimization technique.An extensive investigation of twenty-three mathematical benchmarks and ten IEEE Congress on Evolutionary Computation(CEC)functions shows that chaotic Aquila optimization techniques perform better than the baseline technique.The investigation is further conducted on parameter estimation of an electro-hydraulic control system,which is performed on various noise levels and shows that the proposed chaotic AO with Piecewise map(CAO6)achieves the best fitness values of and at noise levels and respectively.Friedman test 2.873E-05,1.014E-04,8.728E-031.300E-03,1.300E-02,1.300E-01,for repeated measures,computational analysis,and Taguchi test reflect the superiority of CAO6 against the state of the arts,demonstrating its potential for addressing various engineering optimization problems.However,the sensitivity to parameter tuning may limit its direct application to complex optimization scenarios.展开更多
Accurate prediction of wind energy plays a vital role in maintaining grid stability and supporting the broader shift toward renewable energy systems.Nevertheless,the inherently variable nature of wind and the intricac...Accurate prediction of wind energy plays a vital role in maintaining grid stability and supporting the broader shift toward renewable energy systems.Nevertheless,the inherently variable nature of wind and the intricacy of high-dimensional datasets pose major obstacles to reliable forecasting.To address these difficulties,this study presents an innovative hybrid method for short-term wind power prediction by combining a Long Short-Term Memory(LSTM)network with a Single Candidate Optimizer(SCO)algorithm.In contrast to conventional techniques that rely on random parameter initialization,the proposed LSTM-SCO framework leverages the distinctive capability of SCO to work with a single candidate solution,thereby substantially reducing the computational overhead compared to traditional population-based metaheuristics.The performance of the model was benchmarked against various classical and deep learning models across datasets from three geographically diverse sites,using multiple evaluation metrics.Experimental findings demonstrate that the SCO-optimized model enhances prediction accuracy by up to 12.5%over standard LSTM implementations.展开更多
Autism spectrum disorder(ASD)is a multifaceted neurological developmental condition that manifests in several ways.Nearly all autistic children remain undiagnosed before the age of three.Developmental problems affecti...Autism spectrum disorder(ASD)is a multifaceted neurological developmental condition that manifests in several ways.Nearly all autistic children remain undiagnosed before the age of three.Developmental problems affecting face features are often associated with fundamental brain disorders.The facial evolution of newborns with ASD is quite different from that of typically developing children.Early recognition is very significant to aid families and parents in superstition and denial.Distinguishing facial features from typically developing children is an evident manner to detect children analyzed with ASD.Presently,artificial intelligence(AI)significantly contributes to the emerging computer-aided diagnosis(CAD)of autism and to the evolving interactivemethods that aid in the treatment and reintegration of autistic patients.This study introduces an Ensemble of deep learning models based on the autism spectrum disorder detection in facial images(EDLM-ASDDFI)model.The overarching goal of the EDLM-ASDDFI model is to recognize the difference between facial images of individuals with ASD and normal controls.In the EDLM-ASDDFI method,the primary level of data pre-processing is involved by Gabor filtering(GF).Besides,the EDLM-ASDDFI technique applies the MobileNetV2 model to learn complex features from the pre-processed data.For the ASD detection process,the EDLM-ASDDFI method uses ensemble techniques for classification procedure that encompasses long short-term memory(LSTM),deep belief network(DBN),and hybrid kernel extreme learning machine(HKELM).Finally,the hyperparameter selection of the three deep learning(DL)models can be implemented by the design of the crested porcupine optimizer(CPO)technique.An extensive experiment was conducted to emphasize the improved ASD detection performance of the EDLM-ASDDFI method.The simulation outcomes indicated that the EDLM-ASDDFI technique highlighted betterment over other existing models in terms of numerous performance measures.展开更多
With the emergence of new attack techniques,traffic classifiers usually fail to maintain the expected performance in real-world network environments.In order to have sufficient generalizability to deal with unknown ma...With the emergence of new attack techniques,traffic classifiers usually fail to maintain the expected performance in real-world network environments.In order to have sufficient generalizability to deal with unknown malicious samples,they require a large number of new samples for retraining.Considering the cost of data collection and labeling,data augmentation is an ideal solution.We propose an optimized noise-based traffic data augmentation system,ONTDAS.The system uses a gradient-based searching algorithm and an improved Bayesian optimizer to obtain optimized noise.The noise is injected into the original samples for data augmentation.Then,an improved bagging algorithm is used to integrate all the base traffic classifiers trained on noised datasets.The experiments verify ONTDAS on 6 types of base classifiers and 4 publicly available datasets respectively.The results show that ONTDAS can effectively enhance the traffic classifiers’performance and significantly improve their generalizability on unknown malicious samples.The system can also alleviate dataset imbalance.Moreover,the performance of ONTDAS is significantly superior to the existing data augmentation methods mentioned.展开更多
Promoting the high penetration of renewable energies like photovoltaic(PV)systems has become an urgent issue for expanding modern power grids and has accomplished several challenges compared to existing distribution g...Promoting the high penetration of renewable energies like photovoltaic(PV)systems has become an urgent issue for expanding modern power grids and has accomplished several challenges compared to existing distribution grids.This study measures the effectiveness of the Puma optimizer(PO)algorithm in parameter estimation of PSC(perovskite solar cells)dynamic models with hysteresis consideration considering the electric field effects on operation.The models used in this study will incorporate hysteresis effects to capture the time-dependent behavior of PSCs accurately.The PO optimizes the proposed modified triple diode model(TDM)with a variable voltage capacitor and resistances(VVCARs)considering the hysteresis behavior.The suggested PO algorithm contrasts with other wellknown optimizers from the literature to demonstrate its superiority.The results emphasize that the PO realizes a lower RMSE(Root mean square errors),which proves its capability and efficacy in parameter extraction for the models.The statistical results emphasize the efficiency and supremacy of the proposed PO compared to the other well-known competing optimizers.The convergence rates show good,fast,and stable convergence rates with lower RMSE via PO compared to the other five competitive optimizers.Moreover,the lowermean realized via the PO optimizer is illustrated by the box plot for all optimizers.展开更多
The Multilayer Perceptron(MLP)is a fundamental neural network model widely applied in various domains,particularly for lightweight image classification,speech recognition,and natural language processing tasks.Despite ...The Multilayer Perceptron(MLP)is a fundamental neural network model widely applied in various domains,particularly for lightweight image classification,speech recognition,and natural language processing tasks.Despite its widespread success,training MLPs often encounter significant challenges,including susceptibility to local optima,slow convergence rates,and high sensitivity to initial weight configurations.To address these issues,this paper proposes a Latin Hypercube Opposition-based Elite Variation Artificial Protozoa Optimizer(LOEV-APO),which enhances both global exploration and local exploitation simultaneously.LOEV-APO introduces a hybrid initialization strategy that combines Latin Hypercube Sampling(LHS)with Opposition-Based Learning(OBL),thus improving the diversity and coverage of the initial population.Moreover,an Elite Protozoa Variation Strategy(EPVS)is incorporated,which applies differential mutation operations to elite candidates,accelerating convergence and strengthening local search capabilities around high-quality solutions.Extensive experiments are conducted on six classification tasks and four function approximation tasks,covering a wide range of problem complexities and demonstrating superior generalization performance.The results demonstrate that LOEV-APO consistently outperforms nine state-of-the-art metaheuristic algorithms and two gradient-based methods in terms of convergence speed,solution accuracy,and robustness.These findings suggest that LOEV-APO serves as a promising optimization tool for MLP training and provides a viable alternative to traditional gradient-based methods.展开更多
Fingerprint classification is a biometric method for crime prevention.For the successful completion of various tasks,such as official attendance,banking transactions,andmembership requirements,fingerprint classificati...Fingerprint classification is a biometric method for crime prevention.For the successful completion of various tasks,such as official attendance,banking transactions,andmembership requirements,fingerprint classification methods require improvement in terms of accuracy,speed,and the interpretability of non-linear demographic features.Researchers have introduced several CNN-based fingerprint classification models with improved accuracy,but these models often lack effective feature extractionmechanisms and complex multineural architectures.In addition,existing literature primarily focuses on gender classification rather than accurately,efficiently,and confidently classifying hands and fingers through the interpretability of prominent features.This research seeks to improve a compact,robust,explainable,and non-linear feature extraction-based CNN model for robust fingerprint pattern analysis and accurate yet efficient fingerprint classification.The proposed model(a)recognizes gender,hands,and fingers correctly through an advanced channel-wise attention-based feature extraction procedure,(b)accelerates the fingerprints identification process by applying an innovative fractional optimizer within a simple,but effective classification architecture,and(c)interprets prominent features through an explainable artificial intelligence technique.The encapsulated dependencies among distinct complex features are captured through a non-linear activation operation within a customized CNN model.The proposed fractionally optimized convolutional neural network(FOCNN)model demonstrates improved performance compared to some existing models,achieving high accuracies of 97.85%,99.10%,and 99.29%for finger,gender,and hand classification,respectively,utilizing the benchmark Sokoto Coventry Fingerprint Dataset.展开更多
基金supported by the National Natural Science Foundation of China [grant numbers 42088101 and 42375048]。
文摘Due to the lack of accurate data and complex parameterization,the prediction of groundwater depth is a chal-lenge for numerical models.Machine learning can effectively solve this issue and has been proven useful in the prediction of groundwater depth in many areas.In this study,two new models are applied to the prediction of groundwater depth in the Ningxia area,China.The two models combine the improved dung beetle optimizer(DBO)algorithm with two deep learning models:The Multi-head Attention-Convolution Neural Network-Long Short Term Memory networks(MH-CNN-LSTM)and the Multi-head Attention-Convolution Neural Network-Gated Recurrent Unit(MH-CNN-GRU).The models with DBO show better prediction performance,with larger R(correlation coefficient),RPD(residual prediction deviation),and lower RMSE(root-mean-square error).Com-pared with the models with the original DBO,the R and RPD of models with the improved DBO increase by over 1.5%,and the RMSE decreases by over 1.8%,indicating better prediction results.In addition,compared with the multiple linear regression model,a traditional statistical model,deep learning models have better prediction performance.
基金supported by the National Natural Science Foundation of China(Project No.5217232152102391)+2 种基金Sichuan Province Science and Technology Innovation Talent Project(2024JDRC0020)China Shenhua Energy Company Limited Technology Project(GJNY-22-7/2300-K1220053)Key science and technology projects in the transportation industry of the Ministry of Transport(2022-ZD7-132).
文摘This paper introduces the Surrogate-assisted Multi-objective Grey Wolf Optimizer(SMOGWO)as a novel methodology for addressing the complex problem of empty-heavy train allocation,with a focus on line utilization balance.By integrating surrogate models to approximate the objective functions,SMOGWO significantly improves the efficiency and accuracy of the optimization process.The effectiveness of this approach is evaluated using the CEC2009 multi-objective test function suite,where SMOGWO achieves a superiority rate of 76.67%compared to other leading multi-objective algorithms.Furthermore,the practical applicability of SMOGWO is demonstrated through a case study on empty and heavy train allocation,which validates its ability to balance line capacity,minimize transportation costs,and optimize the technical combination of heavy trains.The research highlights SMOGWO's potential as a robust solution for optimization challenges in railway transportation,offering valuable contributions toward enhancing operational efficiency and promoting sustainable development in the sector.
基金funded by the Jiangxi Provincial Social Science Planning Project(21GL12)Jiangxi Provincial Higher Education Humanities and Social Sciences Planning Project(GL22232)Jiangxi Province College Students’Innovation and Entrepreneurship Training Program Project(S20241041027).
文摘Stereoscopic agriculture,as an advanced method of agricultural production,poses new challenges for multi-task trajectory planning of unmanned aerial vehicles(UAVs).To address the need for UAVs to perform multi-task trajectory planning in stereoscopic agriculture,a multi-task trajectory planning model and algorithm(IEP-AO)that synthesizes flight safety and flight efficiency is proposed.Based on the requirements of stereoscopic agricultural geomorphological features and operational characteristics,the multi-task trajectory planning model is ensured by constructing targeted constraints at five aspects,including the path,slope,altitude,corner,energy and obstacle threat,to improve the effectiveness of the trajectory planning model.And combined with the path optimization algorithm,an Aquila optimizer(IEP-AO)based on the interference-enhanced combination model is proposed,which can help UAVs to improve the trajectory search capability in complex operation space and large-scale operation tasks,and jump out of the locally optimal trajectory path region timely,to generate the optimal trajectory planning plan that can adapt to the diversity of the tasks and the flight efficiency.Meanwhile,four simulated flights with different operation scales and different scene constraints were conducted under the constructed real 3Dimension scene,and the experimental results can show that the proposedmulti-task trajectory planning method canmeet themulti-task requirements in stereoscopic agriculture and improve the mission execution efficiency and agricultural production effect of UAV.
基金described in this paper has been developed with in the project PRESECREL(PID2021-124502OB-C43)。
文摘The Internet of Things(IoT)is integral to modern infrastructure,enabling connectivity among a wide range of devices from home automation to industrial control systems.With the exponential increase in data generated by these interconnected devices,robust anomaly detection mechanisms are essential.Anomaly detection in this dynamic environment necessitates methods that can accurately distinguish between normal and anomalous behavior by learning intricate patterns.This paper presents a novel approach utilizing generative adversarial networks(GANs)for anomaly detection in IoT systems.However,optimizing GANs involves tuning hyper-parameters such as learning rate,batch size,and optimization algorithms,which can be challenging due to the non-convex nature of GAN loss functions.To address this,we propose a five-dimensional Gray wolf optimizer(5DGWO)to optimize GAN hyper-parameters.The 5DGWO introduces two new types of wolves:gamma(γ)for improved exploitation and convergence,and theta(θ)for enhanced exploration and escaping local minima.The proposed system framework comprises four key stages:1)preprocessing,2)generative model training,3)autoencoder(AE)training,and 4)predictive model training.The generative models are utilized to assist the AE training,and the final predictive models(including convolutional neural network(CNN),deep belief network(DBN),recurrent neural network(RNN),random forest(RF),and extreme gradient boosting(XGBoost))are trained using the generated data and AE-encoded features.We evaluated the system on three benchmark datasets:NSL-KDD,UNSW-NB15,and IoT-23.Experiments conducted on diverse IoT datasets show that our method outperforms existing anomaly detection strategies and significantly reduces false positives.The 5DGWO-GAN-CNNAE exhibits superior performance in various metrics,including accuracy,recall,precision,root mean square error(RMSE),and convergence trend.The proposed 5DGWO-GAN-CNNAE achieved the lowest RMSE values across the NSL-KDD,UNSW-NB15,and IoT-23 datasets,with values of 0.24,1.10,and 0.09,respectively.Additionally,it attained the highest accuracy,ranging from 94%to 100%.These results suggest a promising direction for future IoT security frameworks,offering a scalable and efficient solution to safeguard against evolving cyber threats.
文摘The global incidence of Alzheimer's Disease(AD)is on a swift rise.The Electroencephalogram(EEG)signals is an effective tool for the identification of AD and its initial Mild Cognitive Impairment(MCI)stage using machine learning models.Analysis of AD using EEG involves multi-channel analysis.However,the use of multiple channels may impact the classification performance due to data redundancy and complexity.In this work,a hybrid EEG channel selection is proposed using a combination of Reptile Search Algorithm and Snake Optimizer(RSO)for AD and MCI detection based on decomposition methods.Empirical Mode Decomposition(EMD),Low-Complexity Orthogonal Wavelet Filter Banks(LCOWFB),Variational Mode Decomposition,and discrete-wavelet transform decomposition techniques have been employed for subbands-based EEG analysis.We extracted thirty-four features from each subband of EEG signals.Finally,a hybrid RSO optimizer is compared with five individual metaheuristic algorithms for effective channel selection.The effectiveness of this model is assessed by two publicly accessible AD EEG datasets.An accuracy of 99.22% was achieved for binary classification from RSO with EMD using 4(out of 16)EEG channels.Moreover,the RSO with LCOWFBs obtained 89.68%the average accuracy for three-class classification using 7(out of 19)channels.The performance reveals that RSO performs better than individual Metaheuristic algorithms with 60%fewer channels and improved accuracy of 4%than existing AD detection techniques.
基金funded by the Deanship of Research andGraduate Studies at King Khalid University through the Large Research Project under grant number RGP2/417/46.
文摘Metaheuristic optimization methods are iterative search processes that aim to efficiently solve complexoptimization problems. These basically find the solution space very efficiently, often without utilizing the gradientinformation, and are inspired by the bio-inspired and socially motivated heuristics. Metaheuristic optimizationalgorithms are increasingly applied to complex feature selection problems in high-dimensional medical datasets.Among these, Teaching-Learning-Based optimization (TLBO) has proven effective for continuous design tasks bybalancing exploration and exploitation phases. However, its binary version (BTLBO) suffers from limited exploitationability, often converging prematurely or getting trapped in local optima, particularly when applied to discrete featureselection tasks. Previous studies reported that BTLBO yields lower classification accuracy and higher feature subsetvariance compared to other hybrid methods in benchmark tests, motivating the development of hybrid approaches.This study proposes a novel hybrid algorithm, BTLBO-Cheetah Optimizer (BTLBO-CO), which integrates the globalexploration strength of BTLBO with the local exploitation efficiency of the Cheetah Optimization (CO) algorithm. Theobjective is to enhance the feature selection process for cancer classification tasks involving high-dimensional data. Theproposed BTLBO-CO algorithm was evaluated on six benchmark cancer datasets: 11 tumors (T), Lung Cancer (LUC),Leukemia (LEU), Small Round Blue Cell Tumor or SRBCT (SR), Diffuse Large B-cell Lymphoma or DLBCL (DL), andProstate Tumor (PT).The results demonstrate superior classification accuracy across all six datasets, achieving 93.71%,96.12%, 98.13%, 97.11%, 98.44%, and 98.84%, respectively.These results validate the effectiveness of the hybrid approachin addressing diverse feature selection challenges using a Support Vector Machine (SVM) classifier.
基金supported in part by the Science and Technology Major Special Project Fund of Changsha(No.kh2401010)in part by the High-Performance Computing Center of Central South University+3 种基金supported by the National Natural Science Foundation of China(Grants Nos.82022024,31970572)The Science and Technology Innovation Program of Hunan Province(2021RC4018,2021RC5027)Innovation-Driven Project of Central South University(Grant No.2020CX003)NIH grants U01 MH122591,1U01MH116489,1R01MH110920,R01MH126459.
文摘Detecting Alzheimer’s disease is essential for patient care,as an accurate diagnosis influences treatment options.Classifying dementia from non-dementia in brain MRIs is challenging due to features such as hippocampal atrophy,while manual diagnosis is susceptible to error.Optimal computer-aided diagnosis(CAD)systems are essential for improving accuracy and reducing misclassification risks.This study proposes an optimized ensemble method(CEOE-Net)that initiates with the selection of pre-trained models,including DenseNet121,ResNet50V2,and ResNet152V2 for unique feature extraction.Each selected model is enhanced with the inclusion of a channel attention(CA)block to improve the feature extraction process.In addition,this study employs the Short Time Fourier transform(STFT)technique with each individual model for hierarchical feature extraction before making final predictions in classifying MRI images of dementia and non-demented individuals,considering them as backbone models for building the ensemble method.STFT highlights subtle differences in brain structure and activity,particularly when combined with CA mechanisms that emphasize relevant features by converting spatial data into the frequency domain.The predictions generated from these models are then processed by the Chaotic Evolution Optimization(CEO)algorithm,which determines the optimal weightage set for each backbone model to maximize their contribution.The CEO optimizer explores weight distribution to ensure the most effective combination of model predictions for enhancing classification accuracy,thus significantly improving overall ensemble performance.This study utilized three datasets for validation:two private clinical brain MRI datasets(OSASIS and ADNI)to test the proposed model’s effectiveness.Image augmentation techniques were also employed to enhance dataset diversity and improve classification performance.The proposed CEOE-Net outperforms conventional baseline models and existing methods by showing its effectiveness as a clinical tool for the accurate classification of dementia and non-dementia MRI brain images,as well as autistic and non-autistic facial features.It achieved consistent accuracies of 93.44%on OSASIS and 81.94%on ADNI.
基金Project supported by the National Natural Science Foundation of China(No.62102130)the Central Government Guides Local Science and Technology Development Fund Project of China(No.226Z0201G)+4 种基金the Natural Science Foundation of Hebei Province of China(Nos.F2020204003 and F2024204001)the Hebei Youth Talents Support Project of China(No.BJ2019008)the Science and Technology Research Projects of Higher Education Institutions in Hebei Province of China(No.QN2024138)the Basic Scientific Research Funds Research Project of Hebei Provincial Colleges and Universities of China(No.KY2022073)the Hebei Province Higher Education Institution Scientific Research Project of China(No.QN2025192)。
文摘The dung beetle optimizer(DBO)is a metaheuristic algorithm with fast convergence and powerful search capabilities,which has shown excellent performance in solving various optimization problems.However,it suffers from the problems of easily falling into local optimal solutions and poor convergence accuracy when dealing with large-scale complex optimization problems.Therefore,we propose an adaptive DBO(ADBO)based on an elastic annealing mechanism to address these issues.First,the convergence factor is adjusted in a nonlinear decreasing manner to balance the requirements of global exploration and local exploitation,thus improving the convergence speed and search quality.Second,a greedy difference optimization strategy is introduced to increase population diversity,improve the global search capability,and avoid premature convergence.Finally,the elastic annealing mechanism is used to perturb the randomly selected individuals,helping the algorithm escape local optima and thereby improve solution quality and algorithm stability.The experimental results on the CEC 2017 and CEC 2022 benchmark function sets and MCNC benchmark circuits verify the effectiveness,superiority,and universality of ADBO.
文摘For optimization algorithms,the most important consideration is their global optimization performance.Our research is conducted with the hope that the algorithm can robustly find the optimal solution to the target problem at a lower computational cost or faster speed.For stochastic optimization algorithms based on population search methods,the search speed and solution quality are always contradictory.Suppose that the random range of the group search is larger;in that case,the probability of the algorithm converging to the global optimal solution is also greater,but the search speed will inevitably slow.The smaller the random range of the group search is,the faster the search speed will be,but the algorithm will easily fall into local optima.Therefore,our method is intended to utilize heuristic strategies to guide the search direction and extract as much effective information as possible from the search process to guide an optimized search.This method is not only conducive to global search,but also avoids excessive randomness,thereby improving search efficiency.To effectively avoid premature convergence problems,the diversity of the group must be monitored and regulated.In fact,in natural bird flocking systems,the distribution density and diversity of groups are often key factors affecting individual behavior.For example,flying birds can adjust their speed in time to avoid collisions based on the crowding level of the group,while foraging birds will judge the possibility of sharing food based on the density of the group and choose to speed up or escape.The aim of this work was to verify that the proposed optimization method is effective.We compared and analyzed the performances of five algorithms,namely,self-organized particle swarm optimization(PSO)-diversity controlled inertia weight(SOPSO-DCIW),self-organized PSO-diversity controlled acceleration coefficient(SOPSO-DCAC),standard PSO(SPSO),the PSO algorithm with a linear decreasing inertia weight(SPSO-LDIW),and the modified PSO algorithm with a time-varying acceleration constant(MPSO-TVAC).
文摘With the development of composite materials,their lightweight and high-strength characteristics have caused more widespread use from aerospace applications to automotive and rail transportation sectors,significantly reducing the energy consumption during the operation of EMUs(Electric Multiple Units).This study aims to explore the application of composite materials in the lightweight design of EMU front skirts and proposes a design method based on threedimensional Hashin failure criteria and the Cheetah Optimizer(CO)to achieve maximum lightweight efficiency.The UMAT subroutine was developed based on the three-dimensional Hashin failure criteria to calculate failure parameters,which were used as design parameters in the CO.The model calculations and result extraction were implemented in MATLAB,and the Cheetah Optimizer iteratively determined the optimal laminating angle design that minimized the overall failure factor.After 100 iterations,ensuring structural integrity,the optimized design reduced the weight of the skirt panel by 60% compared to the original aluminum alloy structure,achieving significant lightweight benefits.This study provides foundational data for the lightweight design of EMUs.
基金supported by the National Natural Science Foundation of China(Nos.32171627 and 62105252)the Science and Technology Research Program of Chongqing Municipal Education Commission(No.KJZD-M202200602)the Hangzhou Science and Technology Development Project(No.202204T04).
文摘The total nitrogen(TN)is a major factor contributing to eutrophication and is a crucial parameter in assessing surface water quality.Accurate and rapid methods are crucial for determining the TN content in water.Herein,a fast,highly sensitive,and pollution-free approach is proposed,which combines ultraviolet(UV)absorption spectroscopy with Bayesian optimized least squares support vector machine(LSSVM)for detecting TN content in water.Water samples collected from sampling points near the Yangtze River basin in Chongqing of China were analyzed using national standard methods to measure TN content as reference values.The prediction of TN content in water was achieved by integrating the UV absorption spectra of water samples with LSSVM.To make the model quickly and accurately select the optimal parameters to improve the accuracy of the prediction model,the Bayesian optimization(BO)algorithm was used to optimize the parameters of the LSSVM.Results show that the prediction model performs well in predicting TN concentration,with a high coefficient of prediction determination(R^(2)=0.9413)and a low root mean square error of prediction(RMSE=0.0779 mg/L).Comparative analysis with previous studies indicates that the model used in this paper achieves lower prediction errors and superior predictive performance.
基金supported by the National Natural Science Foundation of China(52350410465)the General Projects of Guangdong Natural Science Research Projects(2023A1515011520).
文摘Accurate daily suspended sediment load(SSL)prediction is essential for sustainable water resource management,sediment control,and environmental planning.However,SSL prediction is highly complex due to its nonlinear and dynamic nature,making traditional empirical models inadequate.This study proposes a novel hybrid approach,integrating the Adaptive Neuro-Fuzzy Inference System(ANFIS)with the Gradient-Based Optimizer(GBO),to enhance SSL forecasting accuracy.The research compares the performance of ANFIS-GBO with three alternative models:standard ANFIS,ANFIS with Particle Swarm Optimization(ANFIS-PSO),and ANFIS with Grey Wolf Optimization(ANFIS-GWO).Historical SSL and streamflow data from the Bailong River Basin,China,are used to train and validate the models.The input selection process is optimized using the Multivariate Adaptive Regression Splines(MARS)method.Model performance is evaluated using statistical metrics such as Root Mean Square Error(RMSE),Mean Absolute Error(MAE),Mean Absolute Percentage Error(MAPE),Nash Sutcliffe Efficiency(NSE),and Determination Coefficient(R^(2)).Additionally,visual assessments,including scatter plots,Taylor diagrams,and violin plots,provide further insights into model reliability.The results indicate that including historical SSL data improves predictive accuracy,with ANFIS-GBO outperforming the other models.ANFIS-GBO achieves the lowest RMSE and MAE and the highest NSE and R^(2),demonstrating its superior learning ability and adaptability.The findings highlight the effectiveness of nature-inspired optimization algorithms in enhancing sediment load forecasting and contribute to the advancement of AI-based hydrological modeling.Future research should explore the integration of additional environmental and climatic variables to enhance predictive capabilities further.
文摘Assessing the stability of slopes is one of the crucial tasks of geotechnical engineering for assessing and managing risks related to natural hazards,directly affecting safety and sustainable development.This study primarily focuses on developing robust and practical hybrid models to predict the slope stability status of circular failure mode.For this purpose,three robust models were developed using a database including 627 case histories of slope stability status.The models were developed using the random forest(RF),support vector machine(SVM),and extreme gradient boosting(XGB)techniques,employing 5-fold cross validation approach.To enhance the performance of models,this study employs Bayesian optimizer(BO)to fine-tuning their hyperparameters.The results indicate that the performance order of the three developed models is RF-BO>SVM-BO>XGB-BO.Furthermore,comparing the developed models with previous models,it was found that the RF-BO model can effectively determine the slope stability status with outstanding performance.This implies that the RF-BO model could serve as a dependable tool for project managers,assisting in the evaluation of slope stability during both the design and operational phases of projects,despite the inherent challenges in this domain.The results regarding the importance of influencing parameters indicate that cohesion,friction angle,and slope height exert the most significant impact on slope stability status.This suggests that concentrating on these parameters and employing the RF-BO model can effectively mitigate the severity of geohazards in the short-term and contribute to the attainment of long-term sustainable development objectives.
基金funded by Taif University,Saudi Arabia,Project No.(TU-DSPP-2024-52).
文摘Aquila Optimizer(AO)is a recently proposed population-based optimization technique inspired by Aquila’s behavior in catching prey.AO is applied in various applications and its numerous variants were proposed in the literature.However,chaos theory has not been extensively investigated in AO.Moreover,it is still not applied in the parameter estimation of electro-hydraulic systems.In this work,ten well-defined chaotic maps were integrated into a narrowed exploitation of AO for the development of a robust chaotic optimization technique.An extensive investigation of twenty-three mathematical benchmarks and ten IEEE Congress on Evolutionary Computation(CEC)functions shows that chaotic Aquila optimization techniques perform better than the baseline technique.The investigation is further conducted on parameter estimation of an electro-hydraulic control system,which is performed on various noise levels and shows that the proposed chaotic AO with Piecewise map(CAO6)achieves the best fitness values of and at noise levels and respectively.Friedman test 2.873E-05,1.014E-04,8.728E-031.300E-03,1.300E-02,1.300E-01,for repeated measures,computational analysis,and Taguchi test reflect the superiority of CAO6 against the state of the arts,demonstrating its potential for addressing various engineering optimization problems.However,the sensitivity to parameter tuning may limit its direct application to complex optimization scenarios.
文摘Accurate prediction of wind energy plays a vital role in maintaining grid stability and supporting the broader shift toward renewable energy systems.Nevertheless,the inherently variable nature of wind and the intricacy of high-dimensional datasets pose major obstacles to reliable forecasting.To address these difficulties,this study presents an innovative hybrid method for short-term wind power prediction by combining a Long Short-Term Memory(LSTM)network with a Single Candidate Optimizer(SCO)algorithm.In contrast to conventional techniques that rely on random parameter initialization,the proposed LSTM-SCO framework leverages the distinctive capability of SCO to work with a single candidate solution,thereby substantially reducing the computational overhead compared to traditional population-based metaheuristics.The performance of the model was benchmarked against various classical and deep learning models across datasets from three geographically diverse sites,using multiple evaluation metrics.Experimental findings demonstrate that the SCO-optimized model enhances prediction accuracy by up to 12.5%over standard LSTM implementations.
基金Researchers supporting Project number(RSPD2025R1107),King Saud University,Riyadh,Saudi Arabia.
文摘Autism spectrum disorder(ASD)is a multifaceted neurological developmental condition that manifests in several ways.Nearly all autistic children remain undiagnosed before the age of three.Developmental problems affecting face features are often associated with fundamental brain disorders.The facial evolution of newborns with ASD is quite different from that of typically developing children.Early recognition is very significant to aid families and parents in superstition and denial.Distinguishing facial features from typically developing children is an evident manner to detect children analyzed with ASD.Presently,artificial intelligence(AI)significantly contributes to the emerging computer-aided diagnosis(CAD)of autism and to the evolving interactivemethods that aid in the treatment and reintegration of autistic patients.This study introduces an Ensemble of deep learning models based on the autism spectrum disorder detection in facial images(EDLM-ASDDFI)model.The overarching goal of the EDLM-ASDDFI model is to recognize the difference between facial images of individuals with ASD and normal controls.In the EDLM-ASDDFI method,the primary level of data pre-processing is involved by Gabor filtering(GF).Besides,the EDLM-ASDDFI technique applies the MobileNetV2 model to learn complex features from the pre-processed data.For the ASD detection process,the EDLM-ASDDFI method uses ensemble techniques for classification procedure that encompasses long short-term memory(LSTM),deep belief network(DBN),and hybrid kernel extreme learning machine(HKELM).Finally,the hyperparameter selection of the three deep learning(DL)models can be implemented by the design of the crested porcupine optimizer(CPO)technique.An extensive experiment was conducted to emphasize the improved ASD detection performance of the EDLM-ASDDFI method.The simulation outcomes indicated that the EDLM-ASDDFI technique highlighted betterment over other existing models in terms of numerous performance measures.
基金supported in part by the National Key Research and Development Program of China(No.2022YFB4500800)the National Science Foundation of China(No.42071431).
文摘With the emergence of new attack techniques,traffic classifiers usually fail to maintain the expected performance in real-world network environments.In order to have sufficient generalizability to deal with unknown malicious samples,they require a large number of new samples for retraining.Considering the cost of data collection and labeling,data augmentation is an ideal solution.We propose an optimized noise-based traffic data augmentation system,ONTDAS.The system uses a gradient-based searching algorithm and an improved Bayesian optimizer to obtain optimized noise.The noise is injected into the original samples for data augmentation.Then,an improved bagging algorithm is used to integrate all the base traffic classifiers trained on noised datasets.The experiments verify ONTDAS on 6 types of base classifiers and 4 publicly available datasets respectively.The results show that ONTDAS can effectively enhance the traffic classifiers’performance and significantly improve their generalizability on unknown malicious samples.The system can also alleviate dataset imbalance.Moreover,the performance of ONTDAS is significantly superior to the existing data augmentation methods mentioned.
基金supported via funding from Prince Sattam Bin Abdulaziz University project number(PSAU/2025/R/1446).
文摘Promoting the high penetration of renewable energies like photovoltaic(PV)systems has become an urgent issue for expanding modern power grids and has accomplished several challenges compared to existing distribution grids.This study measures the effectiveness of the Puma optimizer(PO)algorithm in parameter estimation of PSC(perovskite solar cells)dynamic models with hysteresis consideration considering the electric field effects on operation.The models used in this study will incorporate hysteresis effects to capture the time-dependent behavior of PSCs accurately.The PO optimizes the proposed modified triple diode model(TDM)with a variable voltage capacitor and resistances(VVCARs)considering the hysteresis behavior.The suggested PO algorithm contrasts with other wellknown optimizers from the literature to demonstrate its superiority.The results emphasize that the PO realizes a lower RMSE(Root mean square errors),which proves its capability and efficacy in parameter extraction for the models.The statistical results emphasize the efficiency and supremacy of the proposed PO compared to the other well-known competing optimizers.The convergence rates show good,fast,and stable convergence rates with lower RMSE via PO compared to the other five competitive optimizers.Moreover,the lowermean realized via the PO optimizer is illustrated by the box plot for all optimizers.
基金supported by the National Natural Science Foundation of China(Grant Nos.62376089,62302153,62302154)the Key Research and Development Program of Hubei Province,China(Grant No.2023BEB024)+1 种基金the Young and Middle-Aged Scientific and Technological Innovation Team Plan in Higher Education Institutions in Hubei Province,China(Grant No.T2023007)the National Natural Science Foundation of China(Grant No.U23A20318).
文摘The Multilayer Perceptron(MLP)is a fundamental neural network model widely applied in various domains,particularly for lightweight image classification,speech recognition,and natural language processing tasks.Despite its widespread success,training MLPs often encounter significant challenges,including susceptibility to local optima,slow convergence rates,and high sensitivity to initial weight configurations.To address these issues,this paper proposes a Latin Hypercube Opposition-based Elite Variation Artificial Protozoa Optimizer(LOEV-APO),which enhances both global exploration and local exploitation simultaneously.LOEV-APO introduces a hybrid initialization strategy that combines Latin Hypercube Sampling(LHS)with Opposition-Based Learning(OBL),thus improving the diversity and coverage of the initial population.Moreover,an Elite Protozoa Variation Strategy(EPVS)is incorporated,which applies differential mutation operations to elite candidates,accelerating convergence and strengthening local search capabilities around high-quality solutions.Extensive experiments are conducted on six classification tasks and four function approximation tasks,covering a wide range of problem complexities and demonstrating superior generalization performance.The results demonstrate that LOEV-APO consistently outperforms nine state-of-the-art metaheuristic algorithms and two gradient-based methods in terms of convergence speed,solution accuracy,and robustness.These findings suggest that LOEV-APO serves as a promising optimization tool for MLP training and provides a viable alternative to traditional gradient-based methods.
文摘Fingerprint classification is a biometric method for crime prevention.For the successful completion of various tasks,such as official attendance,banking transactions,andmembership requirements,fingerprint classification methods require improvement in terms of accuracy,speed,and the interpretability of non-linear demographic features.Researchers have introduced several CNN-based fingerprint classification models with improved accuracy,but these models often lack effective feature extractionmechanisms and complex multineural architectures.In addition,existing literature primarily focuses on gender classification rather than accurately,efficiently,and confidently classifying hands and fingers through the interpretability of prominent features.This research seeks to improve a compact,robust,explainable,and non-linear feature extraction-based CNN model for robust fingerprint pattern analysis and accurate yet efficient fingerprint classification.The proposed model(a)recognizes gender,hands,and fingers correctly through an advanced channel-wise attention-based feature extraction procedure,(b)accelerates the fingerprints identification process by applying an innovative fractional optimizer within a simple,but effective classification architecture,and(c)interprets prominent features through an explainable artificial intelligence technique.The encapsulated dependencies among distinct complex features are captured through a non-linear activation operation within a customized CNN model.The proposed fractionally optimized convolutional neural network(FOCNN)model demonstrates improved performance compared to some existing models,achieving high accuracies of 97.85%,99.10%,and 99.29%for finger,gender,and hand classification,respectively,utilizing the benchmark Sokoto Coventry Fingerprint Dataset.
