Heart disease remains a leading cause of mortality worldwide,emphasizing the urgent need for reliable and interpretable predictive models to support early diagnosis and timely intervention.However,existing Deep Learni...Heart disease remains a leading cause of mortality worldwide,emphasizing the urgent need for reliable and interpretable predictive models to support early diagnosis and timely intervention.However,existing Deep Learning(DL)approaches often face several limitations,including inefficient feature extraction,class imbalance,suboptimal classification performance,and limited interpretability,which collectively hinder their deployment in clinical settings.To address these challenges,we propose a novel DL framework for heart disease prediction that integrates a comprehensive preprocessing pipeline with an advanced classification architecture.The preprocessing stage involves label encoding and feature scaling.To address the issue of class imbalance inherent in the personal key indicators of the heart disease dataset,the localized random affine shadowsampling technique is employed,which enhances minority class representation while minimizing overfitting.At the core of the framework lies the Deep Residual Network(DeepResNet),which employs hierarchical residual transformations to facilitate efficient feature extraction and capture complex,non-linear relationships in the data.Experimental results demonstrate that the proposed model significantly outperforms existing techniques,achieving improvements of 3.26%in accuracy,3.16%in area under the receiver operating characteristics,1.09%in recall,and 1.07%in F1-score.Furthermore,robustness is validated using 10-fold crossvalidation,confirming the model’s generalizability across diverse data distributions.Moreover,model interpretability is ensured through the integration of Shapley additive explanations and local interpretable model-agnostic explanations,offering valuable insights into the contribution of individual features to model predictions.Overall,the proposed DL framework presents a robust,interpretable,and clinically applicable solution for heart disease prediction.展开更多
Artificial rabbits optimization(ARO)is a recently proposed biology-based optimization algorithm inspired by the detour foraging and random hiding behavior of rabbits in nature.However,for solving optimization problems...Artificial rabbits optimization(ARO)is a recently proposed biology-based optimization algorithm inspired by the detour foraging and random hiding behavior of rabbits in nature.However,for solving optimization problems,the ARO algorithm shows slow convergence speed and can fall into local minima.To overcome these drawbacks,this paper proposes chaotic opposition-based learning ARO(COARO),an improved version of the ARO algorithm that incorporates opposition-based learning(OBL)and chaotic local search(CLS)techniques.By adding OBL to ARO,the convergence speed of the algorithm increases and it explores the search space better.Chaotic maps in CLS provide rapid convergence by scanning the search space efficiently,since their ergodicity and non-repetitive properties.The proposed COARO algorithm has been tested using thirty-three distinct benchmark functions.The outcomes have been compared with the most recent optimization algorithms.Additionally,the COARO algorithm’s problem-solving capabilities have been evaluated using six different engineering design problems and compared with various other algorithms.This study also introduces a binary variant of the continuous COARO algorithm,named BCOARO.The performance of BCOARO was evaluated on the breast cancer dataset.The effectiveness of BCOARO has been compared with different feature selection algorithms.The proposed BCOARO outperforms alternative algorithms,according to the findings obtained for real applications in terms of accuracy performance,and fitness value.Extensive experiments show that the COARO and BCOARO algorithms achieve promising results compared to other metaheuristic algorithms.展开更多
Gorilla troops optimizer(GTO)is a newly developed meta-heuristic algorithm,which is inspired by the collective lifestyle and social intelligence of gorillas.Similar to othermetaheuristics,the convergence accuracy and ...Gorilla troops optimizer(GTO)is a newly developed meta-heuristic algorithm,which is inspired by the collective lifestyle and social intelligence of gorillas.Similar to othermetaheuristics,the convergence accuracy and stability of GTOwill deterioratewhen the optimization problems to be solved becomemore complex and flexible.To overcome these defects and achieve better performance,this paper proposes an improved gorilla troops optimizer(IGTO).First,Circle chaotic mapping is introduced to initialize the positions of gorillas,which facilitates the population diversity and establishes a good foundation for global search.Then,in order to avoid getting trapped in the local optimum,the lens opposition-based learning mechanism is adopted to expand the search ranges.Besides,a novel local search-based algorithm,namely adaptiveβ-hill climbing,is amalgamated with GTO to increase the final solution precision.Attributed to three improvements,the exploration and exploitation capabilities of the basic GTOare greatly enhanced.The performance of the proposed algorithm is comprehensively evaluated and analyzed on 19 classical benchmark functions.The numerical and statistical results demonstrate that IGTO can provide better solution quality,local optimumavoidance,and robustness compared with the basic GTOand five other wellknown algorithms.Moreover,the applicability of IGTOis further proved through resolving four engineering design problems and training multilayer perceptron.The experimental results suggest that IGTO exhibits remarkable competitive performance and promising prospects in real-world tasks.展开更多
As a new bionic algorithm,Spider Monkey Optimization(SMO)has been widely used in various complex optimization problems in recent years.However,the new space exploration power of SMO is limited and the diversity of the...As a new bionic algorithm,Spider Monkey Optimization(SMO)has been widely used in various complex optimization problems in recent years.However,the new space exploration power of SMO is limited and the diversity of the population in SMO is not abundant.Thus,this paper focuses on how to reconstruct SMO to improve its performance,and a novel spider monkey optimization algorithm with opposition-based learning and orthogonal experimental design(SMO^(3))is developed.A position updatingmethod based on the historical optimal domain and particle swarmfor Local Leader Phase(LLP)andGlobal Leader Phase(GLP)is presented to improve the diversity of the population of SMO.Moreover,an opposition-based learning strategy based on self-extremum is proposed to avoid suffering from premature convergence and getting stuck at locally optimal values.Also,a local worst individual elimination method based on orthogonal experimental design is used for helping the SMO algorithm eliminate the poor individuals in time.Furthermore,an extended SMO^(3)named CSMO^(3)is investigated to deal with constrained optimization problems.The proposed algorithm is applied to both unconstrained and constrained functions which include the CEC2006 benchmark set and three engineering problems.Experimental results show that the performance of the proposed algorithm is better than three well-known SMO algorithms and other evolutionary algorithms in unconstrained and constrained problems.展开更多
The flying foxes optimization(FFO)algorithm,as a newly introduced metaheuristic algorithm,is inspired by the survival tactics of flying foxes in heat wave environments.FFO preferentially selects the best-performing in...The flying foxes optimization(FFO)algorithm,as a newly introduced metaheuristic algorithm,is inspired by the survival tactics of flying foxes in heat wave environments.FFO preferentially selects the best-performing individuals.This tendency will cause the newly generated solution to remain closely tied to the candidate optimal in the search area.To address this issue,the paper introduces an opposition-based learning-based search mechanism for FFO algorithm(IFFO).Firstly,this paper introduces niching techniques to improve the survival list method,which not only focuses on the adaptability of individuals but also considers the population’s crowding degree to enhance the global search capability.Secondly,an initialization strategy of opposition-based learning is used to perturb the initial population and elevate its quality.Finally,to verify the superiority of the improved search mechanism,IFFO,FFO and the cutting-edge metaheuristic algorithms are compared and analyzed using a set of test functions.The results prove that compared with other algorithms,IFFO is characterized by its rapid convergence,precise results and robust stability.展开更多
To solve the shortcomings of Particle Swarm Optimization(PSO)algorithm,local optimization and slow convergence,an Opposition-based Learning Adaptive Chaotic PSO(LCPSO)algorithm was presented.The chaotic elite oppositi...To solve the shortcomings of Particle Swarm Optimization(PSO)algorithm,local optimization and slow convergence,an Opposition-based Learning Adaptive Chaotic PSO(LCPSO)algorithm was presented.The chaotic elite opposition-based learning process was applied to initialize the entire population,which enhanced the quality of the initial individuals and the population diversity,made the initial individuals distribute in the better quality areas,and accelerated the search efficiency of the algorithm.The inertia weights were adaptively customized during evolution in the light of the degree of premature convergence to balance the local and global search abilities of the algorithm,and the reverse search strategy was introduced to increase the chances of the algorithm escaping the local optimum.The LCPSO algorithm is contrasted to other intelligent algorithms on 10 benchmark test functions with different characteristics,and the simulation experiments display that the proposed algorithm is superior to other intelligence algorithms in the global search ability,search accuracy and convergence speed.In addition,the robustness and effectiveness of the proposed algorithm are also verified by the simulation results of engineering design problems.展开更多
Optical cryptanalysis is essential to the further investigation of more secure optical cryptosystems.Learning-based at-tack of optical encryption eliminates the need for the retrieval of random phase keys of optical e...Optical cryptanalysis is essential to the further investigation of more secure optical cryptosystems.Learning-based at-tack of optical encryption eliminates the need for the retrieval of random phase keys of optical encryption systems but it is limited for practical applications since it requires a large set of plaintext-ciphertext pairs for the cryptosystem to be at-tacked.Here,we propose a two-step deep learning strategy for ciphertext-only attack(COA)on the classical double ran-dom phase encryption(DRPE).Specifically,we construct a virtual DRPE system to gather the training data.Besides,we divide the inverse problem in COA into two more specific inverse problems and employ two deep neural networks(DNNs)to respectively learn the removal of speckle noise in the autocorrelation domain and the de-correlation operation to retrieve the plaintext image.With these two trained DNNs at hand,we show that the plaintext can be predicted in real-time from an unknown ciphertext alone.The proposed learning-based COA method dispenses with not only the retrieval of random phase keys but also the invasive data acquisition of plaintext-ciphertext pairs in the DPRE system.Numerical simulations and optical experiments demonstrate the feasibility and effectiveness of the proposed learning-based COA method.展开更多
The application of machine learning for pyrite discrimination establishes a robust foundation for constructing the ore-forming history of multi-stage deposits;however,published models face challenges related to limite...The application of machine learning for pyrite discrimination establishes a robust foundation for constructing the ore-forming history of multi-stage deposits;however,published models face challenges related to limited,imbalanced datasets and oversampling.In this study,the dataset was expanded to approximately 500 samples for each type,including 508 sedimentary,573 orogenic gold,548 sedimentary exhalative(SEDEX)deposits,and 364 volcanogenic massive sulfides(VMS)pyrites,utilizing random forest(RF)and support vector machine(SVM)methodologies to enhance the reliability of the classifier models.The RF classifier achieved an overall accuracy of 99.8%,and the SVM classifier attained an overall accuracy of 100%.The model was evaluated by a five-fold cross-validation approach with 93.8%accuracy for the RF and 94.9%for the SVM classifier.These results demonstrate the strong feasibility of pyrite classification,supported by a relatively large,balanced dataset and high accuracy rates.The classifier was employed to reveal the genesis of the controversial Keketale Pb-Zn deposit in NW China,which has been inconclusive among SEDEX,VMS,or a SEDEX-VMS transition.Petrographic investigations indicated that the deposit comprises early fine-grained layered pyrite(Py1)and late recrystallized pyrite(Py2).The majority voting classified Py1 as the VMS type,with an accuracy of RF and SVM being 72.2%and 75%,respectively,and confirmed Py2 as an orogenic type with 74.3% and 77.1%accuracy,respectively.The new findings indicated that the Keketale deposit originated from a submarine VMS mineralization system,followed by late orogenic-type overprinting of metamorphism and deformation,which is consistent with the geological and geochemical observations.This study further emphasizes the advantages of Machine learning(ML)methods in accurately and directly discriminating the deposit types and reconstructing the formation history of multi-stage deposits.展开更多
Eavesdropping attacks have become one of the most common attacks on networks because of their easy implementation. Eavesdropping attacks not only lead to transmission data leakage but also develop into other more harm...Eavesdropping attacks have become one of the most common attacks on networks because of their easy implementation. Eavesdropping attacks not only lead to transmission data leakage but also develop into other more harmful attacks. Routing randomization is a relevant research direction for moving target defense, which has been proven to be an effective method to resist eavesdropping attacks. To counter eavesdropping attacks, in this study, we analyzed the existing routing randomization methods and found that their security and usability need to be further improved. According to the characteristics of eavesdropping attacks, which are “latent and transferable”, a routing randomization defense method based on deep reinforcement learning is proposed. The proposed method realizes routing randomization on packet-level granularity using programmable switches. To improve the security and quality of service of legitimate services in networks, we use the deep deterministic policy gradient to generate random routing schemes with support from powerful network state awareness. In-band network telemetry provides real-time, accurate, and comprehensive network state awareness for the proposed method. Various experiments show that compared with other typical routing randomization defense methods, the proposed method has obvious advantages in security and usability against eavesdropping attacks.展开更多
Applying the fault diagnosis techniques to twisted pair copper cable is beneficial to improve the stability and reliability of internet access in Digital Subscriber Line(DSL)Access Network System.The network performan...Applying the fault diagnosis techniques to twisted pair copper cable is beneficial to improve the stability and reliability of internet access in Digital Subscriber Line(DSL)Access Network System.The network performance depends on the occurrence of cable fault along the copper cable.Currently,most of the telecommunication providers monitor the network performance degradation hence troubleshoot the present of the fault by using commercial test gear on-site,which may be resolved using data analytics and machine learning algorithm.This paper presents a fault diagnosis method for twisted pair cable fault detection based on knowledge-based and data-driven machine learning methods.The DSL Access Network is emulated in the laboratory to accommodate VDSL2 Technology with various types of cable fault along the cable distance between 100 m to 1200 m.Firstly,the line operation parameters and loop line testing parameters are collected and used to analyze.Secondly,the feature transformation,a knowledge-based method,is utilized to pre-process the fault data.Then,the random forests algorithms(RFs),a data-driven method,are adopted to train the fault diagnosis classifier and regression algorithm with the processed fault data.Finally,the proposed fault diagnosis method is used to detect and locate the cable fault in the DSL Access Network System.The results show that the cable fault detection has an accuracy of more than 97%,with less minimum absolute error in cable fault localization of less than 11%.The proposed algorithm may assist the telecommunication service provider to initiate automated cable faults identification and troubleshooting in the DSL Access Network System.展开更多
Cryogenic ground support equipment (CGSE) is an important part of a famous particle physics experiment - AMS-02. In this paper a design method which optimizes PID parameters of CGSE control system via the particle swa...Cryogenic ground support equipment (CGSE) is an important part of a famous particle physics experiment - AMS-02. In this paper a design method which optimizes PID parameters of CGSE control system via the particle swarm optimization (PSO) algorithm is presented. Firstly, an improved version of the original PSO, cooperative random learning particle swarm optimization (CRPSO), is put forward to enhance the performance of the conventional PSO. Secondly, the way of finding PID coefficient will be studied by using this algorithm. Finally, the experimental results and practical works demonstrate that the CRPSO-PID controller achieves a good performance.展开更多
Power transformer is one of the most crucial devices in power grid.It is significant to determine incipient faults of power transformers fast and accurately.Input features play critical roles in fault diagnosis accura...Power transformer is one of the most crucial devices in power grid.It is significant to determine incipient faults of power transformers fast and accurately.Input features play critical roles in fault diagnosis accuracy.In order to further improve the fault diagnosis performance of power trans-formers,a random forest feature selection method coupled with optimized kernel extreme learning machine is presented in this study.Firstly,the random forest feature selection approach is adopted to rank 42 related input features derived from gas concentration,gas ratio and energy-weighted dissolved gas analysis.Afterwards,a kernel extreme learning machine tuned by the Aquila optimization algorithm is implemented to adjust crucial parameters and select the optimal feature subsets.The diagnosis accuracy is used to assess the fault diagnosis capability of concerned feature subsets.Finally,the optimal feature subsets are applied to establish fault diagnosis model.According to the experimental results based on two public datasets and comparison with 5 conventional approaches,it can be seen that the average accuracy of the pro-posed method is up to 94.5%,which is superior to that of other conventional approaches.Fault diagnosis performances verify that the optimum feature subset obtained by the presented method can dramatically improve power transformers fault diagnosis accuracy.展开更多
The travel time of rock compressional waves is an essential parameter used for estimating important rock properties,such as porosity,permeability,and lithology.Current methods,like wireline logging tests,provide broad...The travel time of rock compressional waves is an essential parameter used for estimating important rock properties,such as porosity,permeability,and lithology.Current methods,like wireline logging tests,provide broad measurements but lack finer resolution.Laboratory-based rock core measurements offer higher resolution but are resource-intensive.Conventionally,wireline logging and rock core measurements have been used independently.This study introduces a novel approach that integrates both data sources.The method leverages the detailed features from limited core data to enhance the resolution of wireline logging data.By combining machine learning with random field theory,the method allows for probabilistic predictions in regions with sparse data sampling.In this framework,12 parameters from wireline tests are used to predict trends in rock core data.The residuals are modeled using random field theory.The outcomes are high-resolution predictions that combine both the predicted trend and the probabilistic realizations of the residual.By utilizing unconditional and conditional random field theories,this method enables unconditional and conditional simulations of the underlying high-resolution rock compressional wave travel time profile and provides uncertainty estimates.This integrated approach optimizes the use of existing core and logging data.Its applicability is confirmed in an oil project in West China.展开更多
Many traditional denoising methods,such as Gaussian filtering,tend to blur and lose details or edge information while reducing noise.The stationary wavelet packet transform is a multi-scale and multi-band analysis too...Many traditional denoising methods,such as Gaussian filtering,tend to blur and lose details or edge information while reducing noise.The stationary wavelet packet transform is a multi-scale and multi-band analysis tool.Compared with the stationary wavelet transform,it can suppress high-frequency noise while preserving more edge details.Deep learning has significantly progressed in denoising applications.DnCNN,a residual network;FFDNet,an efficient,fl exible network;U-NET,a codec network;and GAN,a generative adversative network,have better denoising effects than BM3D,the most popular conventional denoising method.Therefore,SWP_hFFDNet,a random noise attenuation network based on the stationary wavelet packet transform(SWPT)and modified FFDNet,is proposed.This network combines the advantages of SWPT,Huber norm,and FFDNet.In addition,it has three characteristics:First,SWPT is an eff ective featureextraction tool that can obtain low-and high-frequency features of different scales and frequency bands.Second,because the noise level map is the input of the network,the noise removal performance of diff erent noise levels can be improved.Third,the Huber norm can reduce the sensitivity of the network to abnormal data and enhance its robustness.The network is trained using the Adam algorithm and the BSD500 dataset,which is augmented,noised,and decomposed by SWPT.Experimental and actual data processing results show that the denoising eff ect of the proposed method is almost the same as those of BM3D,DnCNN,and FFDNet networks for low noise.However,for high noise,the proposed method is superior to the aforementioned networks.展开更多
A large number of logistics operations are needed to transport fabric rolls and dye barrels to different positions in printing and dyeing plants, and increasing labor cost is making it difficult for plants to recruit ...A large number of logistics operations are needed to transport fabric rolls and dye barrels to different positions in printing and dyeing plants, and increasing labor cost is making it difficult for plants to recruit workers to complete manual operations. Artificial intelligence and robotics, which are rapidly evolving, offer potential solutions to this problem. In this paper, a navigation method dedicated to solving the issues of the inability to pass smoothly at corners in practice and local obstacle avoidance is presented. In the system, a Gaussian fitting smoothing rapid exploration random tree star-smart(GFS RRT^(*)-Smart) algorithm is proposed for global path planning and enhances the performance when the robot makes a sharp turn around corners. In local obstacle avoidance, a deep reinforcement learning determiner mixed actor critic(MAC) algorithm is used for obstacle avoidance decisions. The navigation system is implemented in a scaled-down simulation factory.展开更多
Automatically detecting Ulva prolifera(U.prolifera)in rainy and cloudy weather using remote sensing imagery has been a long-standing problem.Here,we address this challenge by combining high-resolution Synthetic Apertu...Automatically detecting Ulva prolifera(U.prolifera)in rainy and cloudy weather using remote sensing imagery has been a long-standing problem.Here,we address this challenge by combining high-resolution Synthetic Aperture Radar(SAR)imagery with the machine learning,and detect the U.prolifera of the South Yellow Sea of China(SYS)in 2021.The findings indicate that the Random Forest model can accurately and robustly detect U.prolifera,even in the presence of complex ocean backgrounds and speckle noise.Visual inspection confirmed that the method successfully identified the majority of pixels containing U.prolifera without misidentifying noise pixels or seawater pixels as U.prolifera.Additionally,the method demonstrated consistent performance across different im-ages,with an average Area Under Curve(AUC)of 0.930(+0.028).The analysis yielded an overall accuracy of over 96%,with an average Kappa coefficient of 0.941(+0.038).Compared to the traditional thresholding method,Random Forest model has a lower estimation error of 14.81%.Practical application indicates that this method can be used in the detection of unprecedented U.prolifera in 2021 to derive continuous spatiotemporal changes.This study provides a potential new method to detect U.prolifera and enhances our under-standing of macroalgal outbreaks in the marine environment.展开更多
Every second, a large volume of useful data is created in social media about the various kind of online purchases and in another forms of reviews. Particularly, purchased products review data is enormously growing in ...Every second, a large volume of useful data is created in social media about the various kind of online purchases and in another forms of reviews. Particularly, purchased products review data is enormously growing in different database repositories every day. Most of the review data are useful to new customers for theier further purchases as well as existing companies to view customers feedback about various products. Data Mining and Machine Leaning techniques are familiar to analyse such kind of data to visualise and know the potential use of the purchased items through online. The customers are making quality of products through their sentiments about the purchased items from different online companies. In this research work, it is analysed sentiments of Headphone review data, which is collected from online repositories. For the analysis of Headphone review data, some of the Machine Learning techniques like Support Vector Machines, Naive Bayes, Decision Trees and Random Forest Algorithms and a Hybrid method are applied to find the quality via the customers’ sentiments. The accuracy and performance of the taken algorithms are also analysed based on the three types of sentiments such as positive, negative and neutral.展开更多
The field of biometric identification has seen significant advancements over the years,with research focusing on enhancing the accuracy and security of these systems.One of the key developments is the integration of d...The field of biometric identification has seen significant advancements over the years,with research focusing on enhancing the accuracy and security of these systems.One of the key developments is the integration of deep learning techniques in biometric systems.However,despite these advancements,certain challenges persist.One of the most significant challenges is scalability over growing complexity.Traditional methods either require maintaining and securing a growing database,introducing serious security challenges,or relying on retraining the entiremodelwhen new data is introduced-a process that can be computationally expensive and complex.This challenge underscores the need for more efficient methods to scale securely.To this end,we introduce a novel approach that addresses these challenges by integrating multimodal biometrics,cancelable biometrics,and incremental learning techniques.This work is among the first attempts to seamlessly incorporate deep cancelable biometrics with dynamic architectural updates,applied incrementally to the deep learning model as new users are enrolled,achieving high performance with minimal catastrophic forgetting.By leveraging a One-Dimensional Convolutional Neural Network(1D-CNN)architecture combined with a hybrid incremental learning approach,our system achieves high recognition accuracy,averaging 98.98% over incrementing datasets,while ensuring user privacy through cancelable templates generated via a pre-trained CNN model and random projection.The approach demonstrates remarkable adaptability,utilizing the least intrusive biometric traits like facial features and fingerprints,ensuring not only robust performance but also long-term serviceability.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
Soil liquefaction,a seismic-induced phenomenon,is of significant concern in geotechnical engineering due to its potential to cause severe structural damage and ground instability during earthquakes.This study explores...Soil liquefaction,a seismic-induced phenomenon,is of significant concern in geotechnical engineering due to its potential to cause severe structural damage and ground instability during earthquakes.This study explores the prediction of the Liquefaction Severity Index(LSI)by integrating extensive borehole investigation data with seismic records from the Kahramanmara?(M_(w)7.8)and Hatay(M_(w)6.4)earthquakes that occurred in 2023.Nine machine learning models,Random Forest(RF),M5P,REPTree,IBk,Random Tree(RT),Gaussian Processes(GP),SMOreg,Locally Weighted Learning(LWL),and Linear Regression(LR),were employed with 10-fold cross-validation to ensure reliable predictions.Twelve geotechnical and seismic parameters,groundwater level,earthquake magnitude,peak ground acceleration,V_(s30),dominant frequency,dominant period,longitudinal wave velocity,dynamic modulus of elasticity,dynamic shear modulus,modulus of incompressibility,standard penetration test(SPT)values,and cyclic stress ratio(CSR)values,were utilized as inputs.The analysis results were evaluated with respect to RMSE,MAE,R2,RAE,P/M,error category limits,Taylor diagram,and relative importance of input parameters.Among the models,Random Forest outperformed with an R2 of 0.94,MAE of 2.35,with minimal prediction errors,followed by M5P and REPTree.Error analysis indicated that 80%of Random Forest and REPTree predictions fell within±7,while M5P showed slightly higher variability.Model-based feature ranking demonstrated that Cyclic Stress Ratio(CSR),Ground Water Level(GWL),and Standard Penetration Test(SPT)value emerged as dominant predictors.These findings highlight the study’s contribution to developing a reliable,datadriven framework for LSI prediction,offering a robust basis for improving site-specific liquefaction risk assessment and informed geotechnical decisionmaking in future seismic events.展开更多
基金funded by Ongoing Research Funding Program for Project number(ORF-2025-648),King Saud University,Riyadh,Saudi Arabia.
文摘Heart disease remains a leading cause of mortality worldwide,emphasizing the urgent need for reliable and interpretable predictive models to support early diagnosis and timely intervention.However,existing Deep Learning(DL)approaches often face several limitations,including inefficient feature extraction,class imbalance,suboptimal classification performance,and limited interpretability,which collectively hinder their deployment in clinical settings.To address these challenges,we propose a novel DL framework for heart disease prediction that integrates a comprehensive preprocessing pipeline with an advanced classification architecture.The preprocessing stage involves label encoding and feature scaling.To address the issue of class imbalance inherent in the personal key indicators of the heart disease dataset,the localized random affine shadowsampling technique is employed,which enhances minority class representation while minimizing overfitting.At the core of the framework lies the Deep Residual Network(DeepResNet),which employs hierarchical residual transformations to facilitate efficient feature extraction and capture complex,non-linear relationships in the data.Experimental results demonstrate that the proposed model significantly outperforms existing techniques,achieving improvements of 3.26%in accuracy,3.16%in area under the receiver operating characteristics,1.09%in recall,and 1.07%in F1-score.Furthermore,robustness is validated using 10-fold crossvalidation,confirming the model’s generalizability across diverse data distributions.Moreover,model interpretability is ensured through the integration of Shapley additive explanations and local interpretable model-agnostic explanations,offering valuable insights into the contribution of individual features to model predictions.Overall,the proposed DL framework presents a robust,interpretable,and clinically applicable solution for heart disease prediction.
基金funded by Firat University Scientific Research Projects Management Unit for the scientific research project of Feyza AltunbeyÖzbay,numbered MF.23.49.
文摘Artificial rabbits optimization(ARO)is a recently proposed biology-based optimization algorithm inspired by the detour foraging and random hiding behavior of rabbits in nature.However,for solving optimization problems,the ARO algorithm shows slow convergence speed and can fall into local minima.To overcome these drawbacks,this paper proposes chaotic opposition-based learning ARO(COARO),an improved version of the ARO algorithm that incorporates opposition-based learning(OBL)and chaotic local search(CLS)techniques.By adding OBL to ARO,the convergence speed of the algorithm increases and it explores the search space better.Chaotic maps in CLS provide rapid convergence by scanning the search space efficiently,since their ergodicity and non-repetitive properties.The proposed COARO algorithm has been tested using thirty-three distinct benchmark functions.The outcomes have been compared with the most recent optimization algorithms.Additionally,the COARO algorithm’s problem-solving capabilities have been evaluated using six different engineering design problems and compared with various other algorithms.This study also introduces a binary variant of the continuous COARO algorithm,named BCOARO.The performance of BCOARO was evaluated on the breast cancer dataset.The effectiveness of BCOARO has been compared with different feature selection algorithms.The proposed BCOARO outperforms alternative algorithms,according to the findings obtained for real applications in terms of accuracy performance,and fitness value.Extensive experiments show that the COARO and BCOARO algorithms achieve promising results compared to other metaheuristic algorithms.
基金This work is financially supported by the Fundamental Research Funds for the Central Universities under Grant 2572014BB06.
文摘Gorilla troops optimizer(GTO)is a newly developed meta-heuristic algorithm,which is inspired by the collective lifestyle and social intelligence of gorillas.Similar to othermetaheuristics,the convergence accuracy and stability of GTOwill deterioratewhen the optimization problems to be solved becomemore complex and flexible.To overcome these defects and achieve better performance,this paper proposes an improved gorilla troops optimizer(IGTO).First,Circle chaotic mapping is introduced to initialize the positions of gorillas,which facilitates the population diversity and establishes a good foundation for global search.Then,in order to avoid getting trapped in the local optimum,the lens opposition-based learning mechanism is adopted to expand the search ranges.Besides,a novel local search-based algorithm,namely adaptiveβ-hill climbing,is amalgamated with GTO to increase the final solution precision.Attributed to three improvements,the exploration and exploitation capabilities of the basic GTOare greatly enhanced.The performance of the proposed algorithm is comprehensively evaluated and analyzed on 19 classical benchmark functions.The numerical and statistical results demonstrate that IGTO can provide better solution quality,local optimumavoidance,and robustness compared with the basic GTOand five other wellknown algorithms.Moreover,the applicability of IGTOis further proved through resolving four engineering design problems and training multilayer perceptron.The experimental results suggest that IGTO exhibits remarkable competitive performance and promising prospects in real-world tasks.
基金supported by the First Batch of Teaching Reform Projects of Zhejiang Higher Education“14th Five-Year Plan”(jg20220434)Special Scientific Research Project for Space Debris and Near-Earth Asteroid Defense(KJSP2020020202)+1 种基金Natural Science Foundation of Zhejiang Province(LGG19F030010)National Natural Science Foundation of China(61703183).
文摘As a new bionic algorithm,Spider Monkey Optimization(SMO)has been widely used in various complex optimization problems in recent years.However,the new space exploration power of SMO is limited and the diversity of the population in SMO is not abundant.Thus,this paper focuses on how to reconstruct SMO to improve its performance,and a novel spider monkey optimization algorithm with opposition-based learning and orthogonal experimental design(SMO^(3))is developed.A position updatingmethod based on the historical optimal domain and particle swarmfor Local Leader Phase(LLP)andGlobal Leader Phase(GLP)is presented to improve the diversity of the population of SMO.Moreover,an opposition-based learning strategy based on self-extremum is proposed to avoid suffering from premature convergence and getting stuck at locally optimal values.Also,a local worst individual elimination method based on orthogonal experimental design is used for helping the SMO algorithm eliminate the poor individuals in time.Furthermore,an extended SMO^(3)named CSMO^(3)is investigated to deal with constrained optimization problems.The proposed algorithm is applied to both unconstrained and constrained functions which include the CEC2006 benchmark set and three engineering problems.Experimental results show that the performance of the proposed algorithm is better than three well-known SMO algorithms and other evolutionary algorithms in unconstrained and constrained problems.
基金support from the Ningxia Natural Science Foundation Project(2023AAC03361).
文摘The flying foxes optimization(FFO)algorithm,as a newly introduced metaheuristic algorithm,is inspired by the survival tactics of flying foxes in heat wave environments.FFO preferentially selects the best-performing individuals.This tendency will cause the newly generated solution to remain closely tied to the candidate optimal in the search area.To address this issue,the paper introduces an opposition-based learning-based search mechanism for FFO algorithm(IFFO).Firstly,this paper introduces niching techniques to improve the survival list method,which not only focuses on the adaptability of individuals but also considers the population’s crowding degree to enhance the global search capability.Secondly,an initialization strategy of opposition-based learning is used to perturb the initial population and elevate its quality.Finally,to verify the superiority of the improved search mechanism,IFFO,FFO and the cutting-edge metaheuristic algorithms are compared and analyzed using a set of test functions.The results prove that compared with other algorithms,IFFO is characterized by its rapid convergence,precise results and robust stability.
基金supported by the National Natural Science Foundation of China(61572444,62176238)Natural Science Foundation of Henan Province,China(222300420088)+3 种基金Training Program of Young Backbone teachers in Colleges and universities in Henan Province,China(2020GGJS006)Program for Science&Technology Innovation Talents in Universities of Henan Province,China(23HASTIT023)Program for Science&Technology Innovation Teams in Universities of Henan Province,China(23IRTSTHN010)National Key Research and Development Program of China(2022YFD2001205).
文摘To solve the shortcomings of Particle Swarm Optimization(PSO)algorithm,local optimization and slow convergence,an Opposition-based Learning Adaptive Chaotic PSO(LCPSO)algorithm was presented.The chaotic elite opposition-based learning process was applied to initialize the entire population,which enhanced the quality of the initial individuals and the population diversity,made the initial individuals distribute in the better quality areas,and accelerated the search efficiency of the algorithm.The inertia weights were adaptively customized during evolution in the light of the degree of premature convergence to balance the local and global search abilities of the algorithm,and the reverse search strategy was introduced to increase the chances of the algorithm escaping the local optimum.The LCPSO algorithm is contrasted to other intelligent algorithms on 10 benchmark test functions with different characteristics,and the simulation experiments display that the proposed algorithm is superior to other intelligence algorithms in the global search ability,search accuracy and convergence speed.In addition,the robustness and effectiveness of the proposed algorithm are also verified by the simulation results of engineering design problems.
基金financial supports from the National Natural Science Foundation of China(NSFC)(62061136005,61705141,61805152,61875129,61701321)Sino-German Research Collaboration Group(GZ 1391)+2 种基金the Mobility program(M-0044)sponsored by the Sino-German CenterChinese Academy of Sciences(QYZDB-SSW-JSC002)Science and Technology Innovation Commission of Shenzhen(JCYJ20170817095047279)。
文摘Optical cryptanalysis is essential to the further investigation of more secure optical cryptosystems.Learning-based at-tack of optical encryption eliminates the need for the retrieval of random phase keys of optical encryption systems but it is limited for practical applications since it requires a large set of plaintext-ciphertext pairs for the cryptosystem to be at-tacked.Here,we propose a two-step deep learning strategy for ciphertext-only attack(COA)on the classical double ran-dom phase encryption(DRPE).Specifically,we construct a virtual DRPE system to gather the training data.Besides,we divide the inverse problem in COA into two more specific inverse problems and employ two deep neural networks(DNNs)to respectively learn the removal of speckle noise in the autocorrelation domain and the de-correlation operation to retrieve the plaintext image.With these two trained DNNs at hand,we show that the plaintext can be predicted in real-time from an unknown ciphertext alone.The proposed learning-based COA method dispenses with not only the retrieval of random phase keys but also the invasive data acquisition of plaintext-ciphertext pairs in the DPRE system.Numerical simulations and optical experiments demonstrate the feasibility and effectiveness of the proposed learning-based COA method.
基金the National Key Research and Development Program of China(2021YFC2900300)the Natural Science Foundation of Guangdong Province(2024A1515030216)+2 种基金MOST Special Fund from State Key Laboratory of Geological Processes and Mineral Resources,China University of Geosciences(GPMR202437)the Guangdong Province Introduced of Innovative R&D Team(2021ZT09H399)the Third Xinjiang Scientific Expedition Program(2022xjkk1301).
文摘The application of machine learning for pyrite discrimination establishes a robust foundation for constructing the ore-forming history of multi-stage deposits;however,published models face challenges related to limited,imbalanced datasets and oversampling.In this study,the dataset was expanded to approximately 500 samples for each type,including 508 sedimentary,573 orogenic gold,548 sedimentary exhalative(SEDEX)deposits,and 364 volcanogenic massive sulfides(VMS)pyrites,utilizing random forest(RF)and support vector machine(SVM)methodologies to enhance the reliability of the classifier models.The RF classifier achieved an overall accuracy of 99.8%,and the SVM classifier attained an overall accuracy of 100%.The model was evaluated by a five-fold cross-validation approach with 93.8%accuracy for the RF and 94.9%for the SVM classifier.These results demonstrate the strong feasibility of pyrite classification,supported by a relatively large,balanced dataset and high accuracy rates.The classifier was employed to reveal the genesis of the controversial Keketale Pb-Zn deposit in NW China,which has been inconclusive among SEDEX,VMS,or a SEDEX-VMS transition.Petrographic investigations indicated that the deposit comprises early fine-grained layered pyrite(Py1)and late recrystallized pyrite(Py2).The majority voting classified Py1 as the VMS type,with an accuracy of RF and SVM being 72.2%and 75%,respectively,and confirmed Py2 as an orogenic type with 74.3% and 77.1%accuracy,respectively.The new findings indicated that the Keketale deposit originated from a submarine VMS mineralization system,followed by late orogenic-type overprinting of metamorphism and deformation,which is consistent with the geological and geochemical observations.This study further emphasizes the advantages of Machine learning(ML)methods in accurately and directly discriminating the deposit types and reconstructing the formation history of multi-stage deposits.
文摘Eavesdropping attacks have become one of the most common attacks on networks because of their easy implementation. Eavesdropping attacks not only lead to transmission data leakage but also develop into other more harmful attacks. Routing randomization is a relevant research direction for moving target defense, which has been proven to be an effective method to resist eavesdropping attacks. To counter eavesdropping attacks, in this study, we analyzed the existing routing randomization methods and found that their security and usability need to be further improved. According to the characteristics of eavesdropping attacks, which are “latent and transferable”, a routing randomization defense method based on deep reinforcement learning is proposed. The proposed method realizes routing randomization on packet-level granularity using programmable switches. To improve the security and quality of service of legitimate services in networks, we use the deep deterministic policy gradient to generate random routing schemes with support from powerful network state awareness. In-band network telemetry provides real-time, accurate, and comprehensive network state awareness for the proposed method. Various experiments show that compared with other typical routing randomization defense methods, the proposed method has obvious advantages in security and usability against eavesdropping attacks.
基金The authors received the funding from Smart Challenge Fund(SR0218I100)GPPS Grant VOT H404,from Ministry of Science,Technology and Innovation Malaysia,and Research Management Centre(RMC)of Universiti Tun Hussein Onn Malaysia(UTHM)。
文摘Applying the fault diagnosis techniques to twisted pair copper cable is beneficial to improve the stability and reliability of internet access in Digital Subscriber Line(DSL)Access Network System.The network performance depends on the occurrence of cable fault along the copper cable.Currently,most of the telecommunication providers monitor the network performance degradation hence troubleshoot the present of the fault by using commercial test gear on-site,which may be resolved using data analytics and machine learning algorithm.This paper presents a fault diagnosis method for twisted pair cable fault detection based on knowledge-based and data-driven machine learning methods.The DSL Access Network is emulated in the laboratory to accommodate VDSL2 Technology with various types of cable fault along the cable distance between 100 m to 1200 m.Firstly,the line operation parameters and loop line testing parameters are collected and used to analyze.Secondly,the feature transformation,a knowledge-based method,is utilized to pre-process the fault data.Then,the random forests algorithms(RFs),a data-driven method,are adopted to train the fault diagnosis classifier and regression algorithm with the processed fault data.Finally,the proposed fault diagnosis method is used to detect and locate the cable fault in the DSL Access Network System.The results show that the cable fault detection has an accuracy of more than 97%,with less minimum absolute error in cable fault localization of less than 11%.The proposed algorithm may assist the telecommunication service provider to initiate automated cable faults identification and troubleshooting in the DSL Access Network System.
基金the National Basic Research Program (973) of China (No. 2004CB720703)
文摘Cryogenic ground support equipment (CGSE) is an important part of a famous particle physics experiment - AMS-02. In this paper a design method which optimizes PID parameters of CGSE control system via the particle swarm optimization (PSO) algorithm is presented. Firstly, an improved version of the original PSO, cooperative random learning particle swarm optimization (CRPSO), is put forward to enhance the performance of the conventional PSO. Secondly, the way of finding PID coefficient will be studied by using this algorithm. Finally, the experimental results and practical works demonstrate that the CRPSO-PID controller achieves a good performance.
基金support of national natural science foundation of China(No.52067021)natural science foundation of Xinjiang(2022D01C35)+1 种基金excellent youth scientific and technological talents plan of Xinjiang(No.2019Q012)major science and technology special project of Xinjiang Uygur Autonomous Region(2022A01002-2).
文摘Power transformer is one of the most crucial devices in power grid.It is significant to determine incipient faults of power transformers fast and accurately.Input features play critical roles in fault diagnosis accuracy.In order to further improve the fault diagnosis performance of power trans-formers,a random forest feature selection method coupled with optimized kernel extreme learning machine is presented in this study.Firstly,the random forest feature selection approach is adopted to rank 42 related input features derived from gas concentration,gas ratio and energy-weighted dissolved gas analysis.Afterwards,a kernel extreme learning machine tuned by the Aquila optimization algorithm is implemented to adjust crucial parameters and select the optimal feature subsets.The diagnosis accuracy is used to assess the fault diagnosis capability of concerned feature subsets.Finally,the optimal feature subsets are applied to establish fault diagnosis model.According to the experimental results based on two public datasets and comparison with 5 conventional approaches,it can be seen that the average accuracy of the pro-posed method is up to 94.5%,which is superior to that of other conventional approaches.Fault diagnosis performances verify that the optimum feature subset obtained by the presented method can dramatically improve power transformers fault diagnosis accuracy.
基金the Australian Government through the Australian Research Council's Discovery Projects funding scheme(Project DP190101592)the National Natural Science Foundation of China(Grant Nos.41972280 and 52179103).
文摘The travel time of rock compressional waves is an essential parameter used for estimating important rock properties,such as porosity,permeability,and lithology.Current methods,like wireline logging tests,provide broad measurements but lack finer resolution.Laboratory-based rock core measurements offer higher resolution but are resource-intensive.Conventionally,wireline logging and rock core measurements have been used independently.This study introduces a novel approach that integrates both data sources.The method leverages the detailed features from limited core data to enhance the resolution of wireline logging data.By combining machine learning with random field theory,the method allows for probabilistic predictions in regions with sparse data sampling.In this framework,12 parameters from wireline tests are used to predict trends in rock core data.The residuals are modeled using random field theory.The outcomes are high-resolution predictions that combine both the predicted trend and the probabilistic realizations of the residual.By utilizing unconditional and conditional random field theories,this method enables unconditional and conditional simulations of the underlying high-resolution rock compressional wave travel time profile and provides uncertainty estimates.This integrated approach optimizes the use of existing core and logging data.Its applicability is confirmed in an oil project in West China.
文摘Many traditional denoising methods,such as Gaussian filtering,tend to blur and lose details or edge information while reducing noise.The stationary wavelet packet transform is a multi-scale and multi-band analysis tool.Compared with the stationary wavelet transform,it can suppress high-frequency noise while preserving more edge details.Deep learning has significantly progressed in denoising applications.DnCNN,a residual network;FFDNet,an efficient,fl exible network;U-NET,a codec network;and GAN,a generative adversative network,have better denoising effects than BM3D,the most popular conventional denoising method.Therefore,SWP_hFFDNet,a random noise attenuation network based on the stationary wavelet packet transform(SWPT)and modified FFDNet,is proposed.This network combines the advantages of SWPT,Huber norm,and FFDNet.In addition,it has three characteristics:First,SWPT is an eff ective featureextraction tool that can obtain low-and high-frequency features of different scales and frequency bands.Second,because the noise level map is the input of the network,the noise removal performance of diff erent noise levels can be improved.Third,the Huber norm can reduce the sensitivity of the network to abnormal data and enhance its robustness.The network is trained using the Adam algorithm and the BSD500 dataset,which is augmented,noised,and decomposed by SWPT.Experimental and actual data processing results show that the denoising eff ect of the proposed method is almost the same as those of BM3D,DnCNN,and FFDNet networks for low noise.However,for high noise,the proposed method is superior to the aforementioned networks.
基金National Natural Science Foundation of China (No.61903078)。
文摘A large number of logistics operations are needed to transport fabric rolls and dye barrels to different positions in printing and dyeing plants, and increasing labor cost is making it difficult for plants to recruit workers to complete manual operations. Artificial intelligence and robotics, which are rapidly evolving, offer potential solutions to this problem. In this paper, a navigation method dedicated to solving the issues of the inability to pass smoothly at corners in practice and local obstacle avoidance is presented. In the system, a Gaussian fitting smoothing rapid exploration random tree star-smart(GFS RRT^(*)-Smart) algorithm is proposed for global path planning and enhances the performance when the robot makes a sharp turn around corners. In local obstacle avoidance, a deep reinforcement learning determiner mixed actor critic(MAC) algorithm is used for obstacle avoidance decisions. The navigation system is implemented in a scaled-down simulation factory.
基金Under the auspices of National Natural Science Foundation of China(No.42071385)National Science and Technology Major Project of High Resolution Earth Observation System(No.79-Y50-G18-9001-22/23)。
文摘Automatically detecting Ulva prolifera(U.prolifera)in rainy and cloudy weather using remote sensing imagery has been a long-standing problem.Here,we address this challenge by combining high-resolution Synthetic Aperture Radar(SAR)imagery with the machine learning,and detect the U.prolifera of the South Yellow Sea of China(SYS)in 2021.The findings indicate that the Random Forest model can accurately and robustly detect U.prolifera,even in the presence of complex ocean backgrounds and speckle noise.Visual inspection confirmed that the method successfully identified the majority of pixels containing U.prolifera without misidentifying noise pixels or seawater pixels as U.prolifera.Additionally,the method demonstrated consistent performance across different im-ages,with an average Area Under Curve(AUC)of 0.930(+0.028).The analysis yielded an overall accuracy of over 96%,with an average Kappa coefficient of 0.941(+0.038).Compared to the traditional thresholding method,Random Forest model has a lower estimation error of 14.81%.Practical application indicates that this method can be used in the detection of unprecedented U.prolifera in 2021 to derive continuous spatiotemporal changes.This study provides a potential new method to detect U.prolifera and enhances our under-standing of macroalgal outbreaks in the marine environment.
文摘Every second, a large volume of useful data is created in social media about the various kind of online purchases and in another forms of reviews. Particularly, purchased products review data is enormously growing in different database repositories every day. Most of the review data are useful to new customers for theier further purchases as well as existing companies to view customers feedback about various products. Data Mining and Machine Leaning techniques are familiar to analyse such kind of data to visualise and know the potential use of the purchased items through online. The customers are making quality of products through their sentiments about the purchased items from different online companies. In this research work, it is analysed sentiments of Headphone review data, which is collected from online repositories. For the analysis of Headphone review data, some of the Machine Learning techniques like Support Vector Machines, Naive Bayes, Decision Trees and Random Forest Algorithms and a Hybrid method are applied to find the quality via the customers’ sentiments. The accuracy and performance of the taken algorithms are also analysed based on the three types of sentiments such as positive, negative and neutral.
基金the Deputyship for Research&Innovation,Ministry of Education in Saudi Arabia for funding this research work through project number RI-44-0833.
文摘The field of biometric identification has seen significant advancements over the years,with research focusing on enhancing the accuracy and security of these systems.One of the key developments is the integration of deep learning techniques in biometric systems.However,despite these advancements,certain challenges persist.One of the most significant challenges is scalability over growing complexity.Traditional methods either require maintaining and securing a growing database,introducing serious security challenges,or relying on retraining the entiremodelwhen new data is introduced-a process that can be computationally expensive and complex.This challenge underscores the need for more efficient methods to scale securely.To this end,we introduce a novel approach that addresses these challenges by integrating multimodal biometrics,cancelable biometrics,and incremental learning techniques.This work is among the first attempts to seamlessly incorporate deep cancelable biometrics with dynamic architectural updates,applied incrementally to the deep learning model as new users are enrolled,achieving high performance with minimal catastrophic forgetting.By leveraging a One-Dimensional Convolutional Neural Network(1D-CNN)architecture combined with a hybrid incremental learning approach,our system achieves high recognition accuracy,averaging 98.98% over incrementing datasets,while ensuring user privacy through cancelable templates generated via a pre-trained CNN model and random projection.The approach demonstrates remarkable adaptability,utilizing the least intrusive biometric traits like facial features and fingerprints,ensuring not only robust performance but also long-term serviceability.
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.
基金supported by Osmaniye Korkut Ata University Scientific Research Projects Unit(Project No:OKüBAP-2024-PT1-015)。
文摘Soil liquefaction,a seismic-induced phenomenon,is of significant concern in geotechnical engineering due to its potential to cause severe structural damage and ground instability during earthquakes.This study explores the prediction of the Liquefaction Severity Index(LSI)by integrating extensive borehole investigation data with seismic records from the Kahramanmara?(M_(w)7.8)and Hatay(M_(w)6.4)earthquakes that occurred in 2023.Nine machine learning models,Random Forest(RF),M5P,REPTree,IBk,Random Tree(RT),Gaussian Processes(GP),SMOreg,Locally Weighted Learning(LWL),and Linear Regression(LR),were employed with 10-fold cross-validation to ensure reliable predictions.Twelve geotechnical and seismic parameters,groundwater level,earthquake magnitude,peak ground acceleration,V_(s30),dominant frequency,dominant period,longitudinal wave velocity,dynamic modulus of elasticity,dynamic shear modulus,modulus of incompressibility,standard penetration test(SPT)values,and cyclic stress ratio(CSR)values,were utilized as inputs.The analysis results were evaluated with respect to RMSE,MAE,R2,RAE,P/M,error category limits,Taylor diagram,and relative importance of input parameters.Among the models,Random Forest outperformed with an R2 of 0.94,MAE of 2.35,with minimal prediction errors,followed by M5P and REPTree.Error analysis indicated that 80%of Random Forest and REPTree predictions fell within±7,while M5P showed slightly higher variability.Model-based feature ranking demonstrated that Cyclic Stress Ratio(CSR),Ground Water Level(GWL),and Standard Penetration Test(SPT)value emerged as dominant predictors.These findings highlight the study’s contribution to developing a reliable,datadriven framework for LSI prediction,offering a robust basis for improving site-specific liquefaction risk assessment and informed geotechnical decisionmaking in future seismic events.
