Spiking Neural Network(SNN)inspired by the biological triggering mechanism of neurons to provide a novel solution for plant disease detection,offering enhanced performance and efficiency in contrast to Artificial Neur...Spiking Neural Network(SNN)inspired by the biological triggering mechanism of neurons to provide a novel solution for plant disease detection,offering enhanced performance and efficiency in contrast to Artificial Neural Networks(ANN).Unlike conventional ANNs,which process static images without fully capturing the inherent temporal dynamics,our approach represents the first implementation of SNNs tailored explicitly for agricultural disease classification,integrating an encoding method to convert static RGB plant images into temporally encoded spike trains.Additionally,while Bernoulli trials and standard deep learning architectures likeConvolutionalNeuralNetworks(CNNs)and Fully Connected Neural Networks(FCNNs)have been used extensively,our work is the first to integrate these trials within an SNN framework specifically for agricultural applications.This integration not only refines spike regulation and reduces computational overhead by 30%but also delivers superior accuracy(93.4%)in plant disease classification,marking a significant advancement in precision agriculture that has not been previously explored.Our approach uniquely transforms static plant leaf images into time-dependent representations,leveraging SNNs’intrinsic temporal processing capabilities.This approach aligns with the inherent ability of SNNs to capture dynamic,timedependent patterns,making them more suitable for detecting disease activations in plants than conventional ANNs that treat inputs as static entities.Unlike prior works,our hybrid encoding scheme dynamically adapts to pixel intensity variations(via threshold),enabling robust feature extraction under diverse agricultural conditions.The dual-stage preprocessing customizes the SNN’s behavior in two ways:the encoding threshold is derived from pixel distributions in diseased regions,and Bernoulli trials selectively reduce redundant spikes to ensure energy efficiency on low-power devices.We used a comprehensive dataset of 87,000 RGB images of plant leaves,which included 38 distinct classes of healthy and unhealthy leaves.To train and evaluate three distinct neural network architectures,DeepSNN,SimpleCNN,and SimpleFCNN,the dataset was rigorously preprocessed,including stochastic rotation,horizontal flip,resizing,and normalization.Moreover,by integrating Bernoulli trials to regulate spike generation,ourmethod focuses on extracting themost relevant featureswhile reducingcomputational overhead.Using a comprehensivedatasetof87,000RGB images across 38 classes,we rigorously preprocessed the data and evaluated three architectures:DeepSNN,SimpleCNN,and SimpleFCNN.The results demonstrate that DeepSNN outperforms the other models,achieving superior accuracy,efficient feature extraction,and robust spike management,thereby establishing the potential of SNNs for real-time,energy-efficient agricultural applications.展开更多
Rail profile optimization is a critical strategy for mitigating wear and extending service life.However,damage at the wheel-rail contact surface goes beyond simple rail wear,as it also involves fatigue phenomena.Focus...Rail profile optimization is a critical strategy for mitigating wear and extending service life.However,damage at the wheel-rail contact surface goes beyond simple rail wear,as it also involves fatigue phenomena.Focusing solely on wear and not addressing fatigue in profile optimization can lead to the propagation of rail cracks,the peeling of material off the rail,and even rail fractures.Therefore,we propose an optimization approach that balances rail wear and fatigue for heavy-haul railway rails to mitigate rail fatigue damage.Initially,we performed a field investigation to acquire essential data and understand the characteristics of track damage.Based on theory and measured data,a simulation model for wear and fatigue was then established.Subsequently,the control points of the rail profile according to cubic non-uniform rational B-spline(NURBS)theory were set as the research variables.The rail’s wear rate and fatigue crack propagation rate were adopted as the objective functions.A multi-objective,multi-variable,and multi-constraint nonlinear optimization model was then constructed,specifically using a Levenberg Marquardt-back propagation neural network as optimized by the particle swarm optimization algorithm(PSO-LM-BP neural network).Ultimately,optimal solutions from the model were identified using a chaos microvariation adaptive genetic algorithm,and the effectiveness of the optimization was validated using a dynamics model and a rail damage model.展开更多
The increasing global demand for energy,coupled with concerns about environmental sustainability,has underscored the need for a transition toward renewable energy sources.A well-structured teaching program under the f...The increasing global demand for energy,coupled with concerns about environmental sustainability,has underscored the need for a transition toward renewable energy sources.A well-structured teaching program under the framework of sustainable development in renewable energy seeks to give students the information,abilities,and critical thinking needed to solve energy-related problems sustainably.This research proposes AI-powered personalized learning,innovative real-time integration of diverse data,and adaptive teaching strategies to enhance student understanding regarding renewable energy concepts.The sheep flock-optimized innovative recurrent neural network(SFO-IRNN)will recommend relevant topics and resources based on students’performance.Renewable energy teaching data from assessmethments are combined with real-time IoT-based renewable energy data.This dataset contains renewable energy education using AI-driven teaching methods and internet-based learning.The data was preprocessed by handling missing values and min-max scaling.The data features were extracted using Fourier Transform(FT).Further application of 10-fold cross-validation will increase the reliability of the model as it can evaluate its performance metrics like accuracy,F1-score,recall,and precision on different subsets of student data,which improves its robustness and prevents overfitting.The findings showed that the proposed method is significantly better,which ensures that the students have a deeper theoretical and practical understanding of renewable energy technologies.In addition,integrating real-time IoT data from renewable energy sources gives students a chance to do live simulations and problems that would enhance analytical thinking and hands-on learning.The research shows that AI provides context-aware guidance on sustainable energy infrastructure,enhancing interactive and personalized learning.展开更多
Over recent decades,the artificial neural networks(ANNs)have been applied as an effective approach for detecting damage in construction materials.However,to achieve a superior result of defect identification,they have...Over recent decades,the artificial neural networks(ANNs)have been applied as an effective approach for detecting damage in construction materials.However,to achieve a superior result of defect identification,they have to overcome some shortcomings,for instance slow convergence or stagnancy in local minima.Therefore,optimization algorithms with a global search ability are used to enhance ANNs,i.e.to increase the rate of convergence and to reach a global minimum.This paper introduces a two-stage approach for failure identification in a steel beam.In the first step,the presence of defects and their positions are identified by modal indices.In the second step,a feedforward neural network,improved by a hybrid particle swarm optimization and gravitational search algorithm,namely FNN-PSOGSA,is used to quantify the severity of damage.Finite element(FE)models of the beam for two damage scenarios are used to certify the accuracy and reliability of the proposed method.For comparison,a traditional ANN is also used to estimate the severity of the damage.The obtained results prove that the proposed approach can be used effectively for damage detection and quantification.展开更多
The modeling and optimization of an industrial-scale crude distillation unit （CDU） are addressed. The main spec- ifications and base conditions of CDU are taken from a crude oil refinery in Wuhan, China. For modelin...The modeling and optimization of an industrial-scale crude distillation unit （CDU） are addressed. The main spec- ifications and base conditions of CDU are taken from a crude oil refinery in Wuhan, China. For modeling of a com- plicated CDU, an improved wavelet neural network （WNN） is presented to model the complicated CDU, in which novel parametric updating laws are developed to precisely capture the characteristics of CDU. To address CDU in an economically optimal manner, an economic optimization algorithm under prescribed constraints is presented. By using a combination of WNN-based optimization model and line-up competition algorithm （LCA）, the supe- rior performance of the proposed approach is verified. Compared with the base operating condition, it is validat- ed that the increments of products including kerosene and diesel are up to 20% at least by increasing less than 5% duties of intermediate coolers such as second pump-around （PA2） and third Dump-around （PA3）.展开更多
Organic matters（OMs） and their oxidization products often influence the fate and transport of heavy metals in the subsurface aqueous systems through interaction with the mineral surfaces. This study investigates the...Organic matters（OMs） and their oxidization products often influence the fate and transport of heavy metals in the subsurface aqueous systems through interaction with the mineral surfaces. This study investigates the ethanol（EtO H）-mediated As（Ⅲ） adsorption onto Zn-loaded pinecone（PC） biochar through batch experiments conducted under Box–Behnken design. The effect of EtO H on As（Ⅲ） adsorption mechanism was quantitatively elucidated by fitting the experimental data using artificial neural network and quadratic modeling approaches. The quadratic model could describe the limiting nature of EtO H and pH on As（Ⅲ） adsorption,whereas neural network revealed the stronger influence of Et OH（64.5%） followed by pH（20.75%）and As（Ⅲ） concentration（14.75%） on the adsorption phenomena. Besides, the interaction among process variables indicated that Et OH enhances As（Ⅲ） adsorption over a pH range of2 to 7, possibly due to facilitation of ligand–metal（Zn） binding complexation mechanism.Eventually, hybrid response surface model–genetic algorithm（RSM–GA） approach predicted a better optimal solution than RSM, i.e., the adsorptive removal of As（Ⅲ）（10.47 μg/g） is facilitated at 30.22 mg C/L of Et OH with initial As（Ⅲ） concentration of 196.77 μg/L at pH 5.8. The implication of this investigation might help in understanding the application of biochar for removal of various As（Ⅲ） species in the presence of OM.展开更多
In this paper, we construct two models for the searching task for a lost plane. Model 1 determines the searching area. We predict the trajectory of floats generated after the disintegration of the plane by using RBF n...In this paper, we construct two models for the searching task for a lost plane. Model 1 determines the searching area. We predict the trajectory of floats generated after the disintegration of the plane by using RBF neural network model, and then determine the searching area according to the trajectory. With the pass of time, the searching area will also be constantly moving along the trajectory. Model 2 develops a maritime search plan to achieve the purpose of completing the search in the shortest time. We optimize the searching time and transform the problem into the 0-1 knapsack problem. Solving this problem by improved genetic algorithm, we can get the shortest searching time and the best choice for the search power.展开更多
By combining properly the simulated annealing algorithm and the nonlinear programming neural network, a new hybrid method for comtrained global optimization is proposed in this paper. To maintain the applicability of ...By combining properly the simulated annealing algorithm and the nonlinear programming neural network, a new hybrid method for comtrained global optimization is proposed in this paper. To maintain the applicability of the simulated annealing algorithm used in the hybrid method as general as possible, the nonlinear programming neural network is employed at each iteration to find only a feasible solution to the original constrained problem rather than a local optimal solution. Such a feasible solution is obtained by solving an auxiliary optimization problem with a new objective function. The computational results for two numerical examples indicate that the proposed hybrid method for constrained global optimization is not only highly reliable but also much more effcient than the simulated annealing algorithm using the penalty function method to deal with the constraints.展开更多
A rock-drilling jumbo is the main piece of tunneling equipment used in the energy and infrastructure industries in various countries.The positioning accuracy of its drilling boom greatly affects tunneling efficiency a...A rock-drilling jumbo is the main piece of tunneling equipment used in the energy and infrastructure industries in various countries.The positioning accuracy of its drilling boom greatly affects tunneling efficiency and section-forming quality of mine roadways and engineering tunnels.In order to improve the drilling-positioning accuracy of a three-boom drilling jumbo,we established a kinematics model of the multi-degree-of-freedom(multi-DOF)multi-boom system,using the improved Denavit-Hartenberg(D-H)method,and obtained the mapping relationship between the end position and the amount of motion of each joint.The error of the inverse kinematics calculation for the drilling boom is estimated by an analytical method and a global search algorithm based on particle swarm optimization(PSO)for a straight blasting hole and an inclined blasting hole.On this basis,we propose a back-propagation(BP)neural network optimized by an improved sparrow search algorithm(ISSA)to predict the positioning error of the drilling booms of a three-boom drilling jumbo.In order to verify the accuracy of the proposed error compensation model,we built an automatic-control test platform for the boom,and carried out a positioning error compensation test on the boom.The results show that the average drilling-positioning error was reduced from 9.79 to 5.92 cm,and the error was reduced by 39.5%.Therefore,the proposed method effectively reduces the positioning error of the drilling boom,and improves the accuracy and efficiency of rock drilling.展开更多
我校公共课部英语教研室高雅琳老师撰写的学术论文"Genetically optimized neural network for college English teaching evaluation method"在SSCI期刊《Education and Information Technologies》上发表,被SSCI检索收录,...我校公共课部英语教研室高雅琳老师撰写的学术论文"Genetically optimized neural network for college English teaching evaluation method"在SSCI期刊《Education and Information Technologies》上发表,被SSCI检索收录,该期刊在2025年中国科学院SCI期刊分区表属于2区(教育学大类),IF4.8,我校为独立完成单位。展开更多
Because there is neither waste rock nor mill tailings in the gypsum mine, and the buildings on the goaf of gypsum mine are needed to be protected, the research proposed the scheme of the clay filling technology. Gypsu...Because there is neither waste rock nor mill tailings in the gypsum mine, and the buildings on the goaf of gypsum mine are needed to be protected, the research proposed the scheme of the clay filling technology. Gypsum, cement, lime and water glass were used as adhesive, and the strength of different material ratios were investigated in this study. The influence factors of clay strength were obtained in the order of cement, gypsum, water glass and lime. The results show that the cement content is the determinant influence factor, and gypsum has positive effects, while the water glass can enhance both clay strength and the fluidity of the filing slurry. Furthermore, combining chaotic optimization method with neural network, the optimal ratio of composite cementing agent was obtained. The results show that the optimal ratio of water glass, cement, lime and clay (in quality) is 1.17:6.74:4.17:87.92 in the process of bottom self-flow filling, while the optimal ratio is 1.78:9.58:4.71:83.93 for roof-contacted filling. A novel filling process to fill in gypsum mine goaf with clay is established. The engineering practice shows that the filling cost is low, thus, notable economic benefit is achieved.展开更多
Because of the difficulty in deciding on the structure of BP neural network in operational meteorological application and the tendency for the network to transform to an issue of local solution, a hybrid Particle Swar...Because of the difficulty in deciding on the structure of BP neural network in operational meteorological application and the tendency for the network to transform to an issue of local solution, a hybrid Particle Swarm Optimization Algorithm based on Artificial Neural Network (PSO-BP) model is proposed for monthly mean rainfall of the whole area of Guangxi. It combines Particle Swarm Optimization (PSO) with BP, that is, the number of hidden nodes and connection weights are optimized by the implementation of PSO operation. The method produces a better network architecture and initial connection weights, trains the traditional backward propagation again by training samples. The ensemble strategy is carried out for the linear programming to calculate the best weights based on the "east sum of the error absolute value" as the optimal rule. The weighted coefficient of each ensemble individual is obtained. The results show that the method can effectively improve learning and generalization ability of the neural network.展开更多
The digital technologies that run based on users’content provide a platform for users to help air their opinions on various aspects of a particular subject or product.The recommendation agents play a crucial role in ...The digital technologies that run based on users’content provide a platform for users to help air their opinions on various aspects of a particular subject or product.The recommendation agents play a crucial role in personalizing the needs of individual users.Therefore,it is essential to improve the user experience.The recommender system focuses on recommending a set of items to a user to help the decision-making process and is prevalent across e-commerce and media websites.In Context-Aware Recommender Systems(CARS),several influential and contextual variables are identified to provide an effective recommendation.A substantial trade-off is applied in context to achieve the proper accuracy and coverage required for a collaborative recommendation.The CARS will generate more recommendations utilizing adapting them to a certain contextual situation of users.However,the key issue is how contextual information is used to create good and intelligent recommender systems.This paper proposes an Artificial Neural Network(ANN)to achieve contextual recommendations based on usergenerated reviews.The ability of ANNs to learn events and make decisions based on similar events makes it effective for personalized recommendations in CARS.Thus,the most appropriate contexts in which a user should choose an item or service are achieved.This work converts every label set into a Multi-Label Classification(MLC)problem to enhance recommendations.Experimental results show that the proposed ANN performs better in the Binary Relevance(BR)Instance-Based Classifier,the BR Decision Tree,and the Multi-label SVM for Trip Advisor and LDOS-CoMoDa Dataset.Furthermore,the accuracy of the proposed ANN achieves better results by 1.1%to 6.1%compared to other existing methods.展开更多
Hybrid modeling approaches have recently been investigated as an attractive alternative to model fermentation processes. Normally, these approaches require estimation data to train the empirical model part of a hybrid...Hybrid modeling approaches have recently been investigated as an attractive alternative to model fermentation processes. Normally, these approaches require estimation data to train the empirical model part of a hybrid model. This may result in decreasing the generalization ability of the derived hybrid model. Therefore, a simultaneous hybrid modeling approach is presented in this paper. It transforms the training of the empirical model part into a dynamic system parameter identification problem, and thus allows training the empirical model part with only measured data. An adaptive escaping particle swarm optimization(AEPSO) algorithm with escaping and adaptive inertia weight adjustment strategies is constructed to solve the resulting parameter identification problem, and thereby accomplish the training of the empirical model part. The uniform design method is used to determine the empirical model structure. The proposed simultaneous hybrid modeling approach has been used in a lab-scale nosiheptide batch fermentation process. The results show that it is effective and leads to a more consistent model with better generalization ability when compared to existing ones. The performance of AEPSO is also demonstrated.展开更多
In order to design the press bend forming path of aircraft integral panels,a novel optimization method was proposed, which integrates FEM equivalent model based on previous study,the artificial neural network response...In order to design the press bend forming path of aircraft integral panels,a novel optimization method was proposed, which integrates FEM equivalent model based on previous study,the artificial neural network response surface,and the genetic algorithm.First,a multi-step press bend forming FEM equivalent model was established,with which the FEM experiments designed with Taguchi method were performed.Then,the BP neural network response surface was developed with the sample data from the FEM experiments.Furthermore,genetic algorithm was applied with the neural network response surface as the objective function. Finally,verification was carried out on a simple curvature grid-type stiffened panel.The forming error of the panel formed with the optimal path is only 0.098 39 and the calculating efficiency has been improved by 77%.Therefore,this novel optimization method is quite efficient and indispensable for the press bend forming path designing.展开更多
Microstrip antennas are low-profile antennas that are utilized in wireless communication systems.In recent years,communication engineers have been increasingly interested in it.Because of downsizing,novelty,and cost re...Microstrip antennas are low-profile antennas that are utilized in wireless communication systems.In recent years,communication engineers have been increasingly interested in it.Because of downsizing,novelty,and cost reduction,the number of wireless standards has expanded in recent years.Wideband tech-nologies have evolved in addition to analog and digital services.Radars necessi-tate antenna subsystems that are low-profile and lightweight.Microstrip antennas have these qualities and are suited for radars as an alternative to the bulky and heavyweight reflector/slotted waveguide array antennas.A perforated corner single-line fed microstrip antenna is designed here.When compared to the basic square microstrip antenna,this antenna has better specifications.Because key issue is determining the best values for various antenna parameters when devel-oping the patch antenna.Optimized Neural Network(ONN)is one potential tech-nique utilized to solve this issue,and this work also uses Particle Swarm Optimization(PSO)to enhance the antenna performance.Return loss(S11)and Voltage Standing Wave Ratio(VSWR)parameters are considered in all situations,developed with Advanced Design System(ADS)applications.The transmitters are made to emit in the Ku-band,which covers a wide range of wavelengths.From 5–15 GHz,it is used in most current radars.The ADS suite is used to create the simulation design.展开更多
Decreasing the acetic acid consumption in purified terephthalic acid （PTA） solvent system has become a hot issue with common concern. In accordance with the technical features, the electrical conductivity is in dire...Decreasing the acetic acid consumption in purified terephthalic acid （PTA） solvent system has become a hot issue with common concern. In accordance with the technical features, the electrical conductivity is in direct proportion to the acetic acid content. General regression neural network （GRNN） is used to establish the model of electrical conductivity on the basis of mechanism analysis, and then particle swarm optimization （PSO） algorithm with the improvement of inertia weight and population diversity is proposed to regulate the operating conditions. Thus, the method of decreasing the acid loss is derived and applied to PTA solvent system in a chemical plant. Cases studies show that the precision of modeling and optimization are higher. The results also provide the optimal operating conditions, which decrease the cost and improve the profit.展开更多
A genetic-fuzzy HEV control strategy based on driving cycle recognition （DCR） was built. Six driving cycles were selected to represent different traffic conditions e.g. freeway, urban, suburb. A neural algorithm was...A genetic-fuzzy HEV control strategy based on driving cycle recognition （DCR） was built. Six driving cycles were selected to represent different traffic conditions e.g. freeway, urban, suburb. A neural algorithm was used for traffic condition recognition based on ten parameters of each driving cycle. The DCR was utilized for optimization of the HEV control parameters using a genetic-fuzzy approach. A fuzzy logic controller （FLC） was designed to be intelligent to manage the engine to work in the vicinity of its optimal condition. The fuzzy membership function parameters were optimized using the genetic algorithm （GA） for each driving cycle. The result is that the DCR_ fuzzy controller can reduce the fuel consumption by 1. 9%, higher than only CYC _ HWFET optimized fuzzy （0.2%） or CYC _ WVUSUB optimized fuzzy （0.7%）. The DCR_ fuzzy method can get the better result than only optimizing one cycle on the complex real traffic conditions.展开更多
Coal flotation is widely used to separate commercially valuable coal from the fine ore slurry, and is an industrial process with nonlinear, multivariable, time-varying and long time-delay characteristics. The online d...Coal flotation is widely used to separate commercially valuable coal from the fine ore slurry, and is an industrial process with nonlinear, multivariable, time-varying and long time-delay characteristics. The online detection of ash content of products as the operation performance evaluation in the flotation system is extraordinarily difficult because of the low solid content and numerous micro-bubbles in the slurry. Moreover, it is time-consuming by manual analysis. Consequently, the optimal separation is not usually maintained. A novel technique, called the neuro-immune algorithm (NIA) inspired by the biological nervous and immune systems, is presented in this paper for predicting the ash content of clean coal and performing the optimizing control to the coal flotation system. The proposed algorithm integrates the deeply-studied artificial neural network (ANN) and the developing artificial immune system (AIS). A two-layer back-propagation network was constructed offline based on the historical process data under the best system situation, using five parameters: the flow and the density of raw slurry, the input flows of water, the kerosene and the GF oil, as the inputs and the ash content of clean coal as the output. The immune cell of AIS is made up of six parameters above as the antigen. The cytokine based clone selection algorithm is used to produce the relative antibody. The detailed computation procedures about the hybrid neuro-immune algorithm are minutely discussed. The ash content of clean coal was predicted by NIA using the practical process data s: (308.6 174.7 146.1 43.6 4.0 9.4), and the absolute difference between the actual and computed ash content values was 0.0967%. The optimizing control on NIA was simulated considering two different situations where the ash content of clean coal was controlled downward from 10.00% or upward from 9.20% predicted by ANN to the target value 9.50%. The results indicate that the target ash content and the value of controlling parameters are obtained after several control cycles.展开更多
Background:In the visual system,one of the most explored neural behaviors is the response of cells to changes in visual contrast.This neural response to visual contrast,also known as the contrast response function(CRF...Background:In the visual system,one of the most explored neural behaviors is the response of cells to changes in visual contrast.This neural response to visual contrast,also known as the contrast response function(CRF),can be fitted with the Naka-Rushton equation(NRE).Assessing the CRF of many neurons at the same time is critical to establishing functional visual properties.However,maximizing the performance of neurons to fit the NRE,while minimizing their time acquisitions is a challenge.We present a method to accurately obtain reliable NRE fits from experimental data,that ensure a reasonable time of record acquisition.Methods:We simulated CRF of cortical neurons with a toy model based on the response of Poisson spike trains to varied levels of contrasts.We first tested whether mean values or the whole set of contrast responses fit better the NRE.Then,we analyzed what were the boundaries to optimize the fit of the NRE,and after we explore the consequences of fitting the NRE with single-or multi-units.With these outcomes,we varied experimental parameters such as the number of trials,number of input contrasts and length of time acquisition to calculate the errors of fitting CRFs.Those data sets that maximize the CRF fit but minimize the time of recording were selected.The selected data set was then evaluated in visual cortical neurons of anesthetized cats from areas 17,18 and 21a.Results:First,we found that is always better to fit the NRE with mean values rather than the whole set of points.Then,we noticed that either removing or imposing loose boundaries to the CRF parameters lead to an increase in the performance of the NRE fit.Afterward,we found that single units(SU)or assume multi-unit formed of several SUs(>30)adjusted considerably better the NRE fit.Finally,the experiments showed that specific sets of patterns(number of trials,number of input contrasts and length of time acquisition)satisfied our two constraints:minimize the error of the NRE fit while maximizing the acquisition time of recording.The most characteristic pattern was the one with 6 points,15 repetitions and 1 second of duration.However,cortical areas varied in the representation of the patterns.Conclusions:Theoretical simulations of many different sets of patterns and their following experimental validation suggest strongly that a particular set of patterns can satisfy the imposed constraints.With this approach,we provided a tool that allows an optimal design of stimuli to assess the CRF of large neuronal populations and guarantees the finest fit for each unit analyzed.展开更多
基金supported in part by the Basic Science Research Program through the National Research Foundation of Korea(NRF),funded by the Ministry of Education(NRF-2021R1A6A1A03039493).
文摘Spiking Neural Network(SNN)inspired by the biological triggering mechanism of neurons to provide a novel solution for plant disease detection,offering enhanced performance and efficiency in contrast to Artificial Neural Networks(ANN).Unlike conventional ANNs,which process static images without fully capturing the inherent temporal dynamics,our approach represents the first implementation of SNNs tailored explicitly for agricultural disease classification,integrating an encoding method to convert static RGB plant images into temporally encoded spike trains.Additionally,while Bernoulli trials and standard deep learning architectures likeConvolutionalNeuralNetworks(CNNs)and Fully Connected Neural Networks(FCNNs)have been used extensively,our work is the first to integrate these trials within an SNN framework specifically for agricultural applications.This integration not only refines spike regulation and reduces computational overhead by 30%but also delivers superior accuracy(93.4%)in plant disease classification,marking a significant advancement in precision agriculture that has not been previously explored.Our approach uniquely transforms static plant leaf images into time-dependent representations,leveraging SNNs’intrinsic temporal processing capabilities.This approach aligns with the inherent ability of SNNs to capture dynamic,timedependent patterns,making them more suitable for detecting disease activations in plants than conventional ANNs that treat inputs as static entities.Unlike prior works,our hybrid encoding scheme dynamically adapts to pixel intensity variations(via threshold),enabling robust feature extraction under diverse agricultural conditions.The dual-stage preprocessing customizes the SNN’s behavior in two ways:the encoding threshold is derived from pixel distributions in diseased regions,and Bernoulli trials selectively reduce redundant spikes to ensure energy efficiency on low-power devices.We used a comprehensive dataset of 87,000 RGB images of plant leaves,which included 38 distinct classes of healthy and unhealthy leaves.To train and evaluate three distinct neural network architectures,DeepSNN,SimpleCNN,and SimpleFCNN,the dataset was rigorously preprocessed,including stochastic rotation,horizontal flip,resizing,and normalization.Moreover,by integrating Bernoulli trials to regulate spike generation,ourmethod focuses on extracting themost relevant featureswhile reducingcomputational overhead.Using a comprehensivedatasetof87,000RGB images across 38 classes,we rigorously preprocessed the data and evaluated three architectures:DeepSNN,SimpleCNN,and SimpleFCNN.The results demonstrate that DeepSNN outperforms the other models,achieving superior accuracy,efficient feature extraction,and robust spike management,thereby establishing the potential of SNNs for real-time,energy-efficient agricultural applications.
基金supported by the National Natural Science Foundation of China(No.52388102)the Sichuan Science and Technology Program(No.2023ZDZX0008)China.The authors would like to thank the Guoneng Shuo-Huang Railway Development Company,China for providing vehicle parameters and line data for this project.The authors would also like to acknowledge the Xplorer Prize for sponsoring the project.
文摘Rail profile optimization is a critical strategy for mitigating wear and extending service life.However,damage at the wheel-rail contact surface goes beyond simple rail wear,as it also involves fatigue phenomena.Focusing solely on wear and not addressing fatigue in profile optimization can lead to the propagation of rail cracks,the peeling of material off the rail,and even rail fractures.Therefore,we propose an optimization approach that balances rail wear and fatigue for heavy-haul railway rails to mitigate rail fatigue damage.Initially,we performed a field investigation to acquire essential data and understand the characteristics of track damage.Based on theory and measured data,a simulation model for wear and fatigue was then established.Subsequently,the control points of the rail profile according to cubic non-uniform rational B-spline(NURBS)theory were set as the research variables.The rail’s wear rate and fatigue crack propagation rate were adopted as the objective functions.A multi-objective,multi-variable,and multi-constraint nonlinear optimization model was then constructed,specifically using a Levenberg Marquardt-back propagation neural network as optimized by the particle swarm optimization algorithm(PSO-LM-BP neural network).Ultimately,optimal solutions from the model were identified using a chaos microvariation adaptive genetic algorithm,and the effectiveness of the optimization was validated using a dynamics model and a rail damage model.
文摘The increasing global demand for energy,coupled with concerns about environmental sustainability,has underscored the need for a transition toward renewable energy sources.A well-structured teaching program under the framework of sustainable development in renewable energy seeks to give students the information,abilities,and critical thinking needed to solve energy-related problems sustainably.This research proposes AI-powered personalized learning,innovative real-time integration of diverse data,and adaptive teaching strategies to enhance student understanding regarding renewable energy concepts.The sheep flock-optimized innovative recurrent neural network(SFO-IRNN)will recommend relevant topics and resources based on students’performance.Renewable energy teaching data from assessmethments are combined with real-time IoT-based renewable energy data.This dataset contains renewable energy education using AI-driven teaching methods and internet-based learning.The data was preprocessed by handling missing values and min-max scaling.The data features were extracted using Fourier Transform(FT).Further application of 10-fold cross-validation will increase the reliability of the model as it can evaluate its performance metrics like accuracy,F1-score,recall,and precision on different subsets of student data,which improves its robustness and prevents overfitting.The findings showed that the proposed method is significantly better,which ensures that the students have a deeper theoretical and practical understanding of renewable energy technologies.In addition,integrating real-time IoT data from renewable energy sources gives students a chance to do live simulations and problems that would enhance analytical thinking and hands-on learning.The research shows that AI provides context-aware guidance on sustainable energy infrastructure,enhancing interactive and personalized learning.
基金the Vlaamse Interuniversitaire Raad University Development Cooperation(VLIR-UOS)Team Project(No.VN2018TEA479A103)the Flemish Government,Belgium。
文摘Over recent decades,the artificial neural networks(ANNs)have been applied as an effective approach for detecting damage in construction materials.However,to achieve a superior result of defect identification,they have to overcome some shortcomings,for instance slow convergence or stagnancy in local minima.Therefore,optimization algorithms with a global search ability are used to enhance ANNs,i.e.to increase the rate of convergence and to reach a global minimum.This paper introduces a two-stage approach for failure identification in a steel beam.In the first step,the presence of defects and their positions are identified by modal indices.In the second step,a feedforward neural network,improved by a hybrid particle swarm optimization and gravitational search algorithm,namely FNN-PSOGSA,is used to quantify the severity of damage.Finite element(FE)models of the beam for two damage scenarios are used to certify the accuracy and reliability of the proposed method.For comparison,a traditional ANN is also used to estimate the severity of the damage.The obtained results prove that the proposed approach can be used effectively for damage detection and quantification.
基金Supported by the National Natural Science Foundation of China(No.21376185)
文摘The modeling and optimization of an industrial-scale crude distillation unit （CDU） are addressed. The main spec- ifications and base conditions of CDU are taken from a crude oil refinery in Wuhan, China. For modeling of a com- plicated CDU, an improved wavelet neural network （WNN） is presented to model the complicated CDU, in which novel parametric updating laws are developed to precisely capture the characteristics of CDU. To address CDU in an economically optimal manner, an economic optimization algorithm under prescribed constraints is presented. By using a combination of WNN-based optimization model and line-up competition algorithm （LCA）, the supe- rior performance of the proposed approach is verified. Compared with the base operating condition, it is validat- ed that the increments of products including kerosene and diesel are up to 20% at least by increasing less than 5% duties of intermediate coolers such as second pump-around （PA2） and third Dump-around （PA3）.
基金supported by the research funds from the University of Ulsan in South Korea during the financial year 2012–2013
文摘Organic matters（OMs） and their oxidization products often influence the fate and transport of heavy metals in the subsurface aqueous systems through interaction with the mineral surfaces. This study investigates the ethanol（EtO H）-mediated As（Ⅲ） adsorption onto Zn-loaded pinecone（PC） biochar through batch experiments conducted under Box–Behnken design. The effect of EtO H on As（Ⅲ） adsorption mechanism was quantitatively elucidated by fitting the experimental data using artificial neural network and quadratic modeling approaches. The quadratic model could describe the limiting nature of EtO H and pH on As（Ⅲ） adsorption,whereas neural network revealed the stronger influence of Et OH（64.5%） followed by pH（20.75%）and As（Ⅲ） concentration（14.75%） on the adsorption phenomena. Besides, the interaction among process variables indicated that Et OH enhances As（Ⅲ） adsorption over a pH range of2 to 7, possibly due to facilitation of ligand–metal（Zn） binding complexation mechanism.Eventually, hybrid response surface model–genetic algorithm（RSM–GA） approach predicted a better optimal solution than RSM, i.e., the adsorptive removal of As（Ⅲ）（10.47 μg/g） is facilitated at 30.22 mg C/L of Et OH with initial As（Ⅲ） concentration of 196.77 μg/L at pH 5.8. The implication of this investigation might help in understanding the application of biochar for removal of various As（Ⅲ） species in the presence of OM.
文摘In this paper, we construct two models for the searching task for a lost plane. Model 1 determines the searching area. We predict the trajectory of floats generated after the disintegration of the plane by using RBF neural network model, and then determine the searching area according to the trajectory. With the pass of time, the searching area will also be constantly moving along the trajectory. Model 2 develops a maritime search plan to achieve the purpose of completing the search in the shortest time. We optimize the searching time and transform the problem into the 0-1 knapsack problem. Solving this problem by improved genetic algorithm, we can get the shortest searching time and the best choice for the search power.
文摘By combining properly the simulated annealing algorithm and the nonlinear programming neural network, a new hybrid method for comtrained global optimization is proposed in this paper. To maintain the applicability of the simulated annealing algorithm used in the hybrid method as general as possible, the nonlinear programming neural network is employed at each iteration to find only a feasible solution to the original constrained problem rather than a local optimal solution. Such a feasible solution is obtained by solving an auxiliary optimization problem with a new objective function. The computational results for two numerical examples indicate that the proposed hybrid method for constrained global optimization is not only highly reliable but also much more effcient than the simulated annealing algorithm using the penalty function method to deal with the constraints.
基金National Natural Science Foundation of China(No.12472038)Natural Science Foundation of Jiangsu Province(No.BK20230688)+2 种基金Natural Science Foundation of the Jiangsu Higher Education Institutions of China(No.22KJB440004)Key Research and Development Program of Xuzhou(No.KC22404)Research Fund for Doctoral Degree Teachers of Jiangsu Normal University of China(No.22XFRS011).
文摘A rock-drilling jumbo is the main piece of tunneling equipment used in the energy and infrastructure industries in various countries.The positioning accuracy of its drilling boom greatly affects tunneling efficiency and section-forming quality of mine roadways and engineering tunnels.In order to improve the drilling-positioning accuracy of a three-boom drilling jumbo,we established a kinematics model of the multi-degree-of-freedom(multi-DOF)multi-boom system,using the improved Denavit-Hartenberg(D-H)method,and obtained the mapping relationship between the end position and the amount of motion of each joint.The error of the inverse kinematics calculation for the drilling boom is estimated by an analytical method and a global search algorithm based on particle swarm optimization(PSO)for a straight blasting hole and an inclined blasting hole.On this basis,we propose a back-propagation(BP)neural network optimized by an improved sparrow search algorithm(ISSA)to predict the positioning error of the drilling booms of a three-boom drilling jumbo.In order to verify the accuracy of the proposed error compensation model,we built an automatic-control test platform for the boom,and carried out a positioning error compensation test on the boom.The results show that the average drilling-positioning error was reduced from 9.79 to 5.92 cm,and the error was reduced by 39.5%.Therefore,the proposed method effectively reduces the positioning error of the drilling boom,and improves the accuracy and efficiency of rock drilling.
文摘我校公共课部英语教研室高雅琳老师撰写的学术论文"Genetically optimized neural network for college English teaching evaluation method"在SSCI期刊《Education and Information Technologies》上发表,被SSCI检索收录,该期刊在2025年中国科学院SCI期刊分区表属于2区(教育学大类),IF4.8,我校为独立完成单位。
基金supported by the National Basic Research and Development Program of China (No. 2010CB732004)the joint funding of the National Natural Science Foundation and Shanghai Baosteel Group Corporation of China (No. 51074177)
文摘Because there is neither waste rock nor mill tailings in the gypsum mine, and the buildings on the goaf of gypsum mine are needed to be protected, the research proposed the scheme of the clay filling technology. Gypsum, cement, lime and water glass were used as adhesive, and the strength of different material ratios were investigated in this study. The influence factors of clay strength were obtained in the order of cement, gypsum, water glass and lime. The results show that the cement content is the determinant influence factor, and gypsum has positive effects, while the water glass can enhance both clay strength and the fluidity of the filing slurry. Furthermore, combining chaotic optimization method with neural network, the optimal ratio of composite cementing agent was obtained. The results show that the optimal ratio of water glass, cement, lime and clay (in quality) is 1.17:6.74:4.17:87.92 in the process of bottom self-flow filling, while the optimal ratio is 1.78:9.58:4.71:83.93 for roof-contacted filling. A novel filling process to fill in gypsum mine goaf with clay is established. The engineering practice shows that the filling cost is low, thus, notable economic benefit is achieved.
基金Natural Science Foundation of Guangxi (0832019Z)Natural Science Foundation of China (40675023)
文摘Because of the difficulty in deciding on the structure of BP neural network in operational meteorological application and the tendency for the network to transform to an issue of local solution, a hybrid Particle Swarm Optimization Algorithm based on Artificial Neural Network (PSO-BP) model is proposed for monthly mean rainfall of the whole area of Guangxi. It combines Particle Swarm Optimization (PSO) with BP, that is, the number of hidden nodes and connection weights are optimized by the implementation of PSO operation. The method produces a better network architecture and initial connection weights, trains the traditional backward propagation again by training samples. The ensemble strategy is carried out for the linear programming to calculate the best weights based on the "east sum of the error absolute value" as the optimal rule. The weighted coefficient of each ensemble individual is obtained. The results show that the method can effectively improve learning and generalization ability of the neural network.
文摘The digital technologies that run based on users’content provide a platform for users to help air their opinions on various aspects of a particular subject or product.The recommendation agents play a crucial role in personalizing the needs of individual users.Therefore,it is essential to improve the user experience.The recommender system focuses on recommending a set of items to a user to help the decision-making process and is prevalent across e-commerce and media websites.In Context-Aware Recommender Systems(CARS),several influential and contextual variables are identified to provide an effective recommendation.A substantial trade-off is applied in context to achieve the proper accuracy and coverage required for a collaborative recommendation.The CARS will generate more recommendations utilizing adapting them to a certain contextual situation of users.However,the key issue is how contextual information is used to create good and intelligent recommender systems.This paper proposes an Artificial Neural Network(ANN)to achieve contextual recommendations based on usergenerated reviews.The ability of ANNs to learn events and make decisions based on similar events makes it effective for personalized recommendations in CARS.Thus,the most appropriate contexts in which a user should choose an item or service are achieved.This work converts every label set into a Multi-Label Classification(MLC)problem to enhance recommendations.Experimental results show that the proposed ANN performs better in the Binary Relevance(BR)Instance-Based Classifier,the BR Decision Tree,and the Multi-label SVM for Trip Advisor and LDOS-CoMoDa Dataset.Furthermore,the accuracy of the proposed ANN achieves better results by 1.1%to 6.1%compared to other existing methods.
基金Supported by the Specialized Research Fund for the Doctoral Program of Higher Education(No.20120042120014)
文摘Hybrid modeling approaches have recently been investigated as an attractive alternative to model fermentation processes. Normally, these approaches require estimation data to train the empirical model part of a hybrid model. This may result in decreasing the generalization ability of the derived hybrid model. Therefore, a simultaneous hybrid modeling approach is presented in this paper. It transforms the training of the empirical model part into a dynamic system parameter identification problem, and thus allows training the empirical model part with only measured data. An adaptive escaping particle swarm optimization(AEPSO) algorithm with escaping and adaptive inertia weight adjustment strategies is constructed to solve the resulting parameter identification problem, and thereby accomplish the training of the empirical model part. The uniform design method is used to determine the empirical model structure. The proposed simultaneous hybrid modeling approach has been used in a lab-scale nosiheptide batch fermentation process. The results show that it is effective and leads to a more consistent model with better generalization ability when compared to existing ones. The performance of AEPSO is also demonstrated.
基金Project(20091102110021)supported by the Specialized Research Fund for the Doctoral Program of Higher Education of China
文摘In order to design the press bend forming path of aircraft integral panels,a novel optimization method was proposed, which integrates FEM equivalent model based on previous study,the artificial neural network response surface,and the genetic algorithm.First,a multi-step press bend forming FEM equivalent model was established,with which the FEM experiments designed with Taguchi method were performed.Then,the BP neural network response surface was developed with the sample data from the FEM experiments.Furthermore,genetic algorithm was applied with the neural network response surface as the objective function. Finally,verification was carried out on a simple curvature grid-type stiffened panel.The forming error of the panel formed with the optimal path is only 0.098 39 and the calculating efficiency has been improved by 77%.Therefore,this novel optimization method is quite efficient and indispensable for the press bend forming path designing.
文摘Microstrip antennas are low-profile antennas that are utilized in wireless communication systems.In recent years,communication engineers have been increasingly interested in it.Because of downsizing,novelty,and cost reduction,the number of wireless standards has expanded in recent years.Wideband tech-nologies have evolved in addition to analog and digital services.Radars necessi-tate antenna subsystems that are low-profile and lightweight.Microstrip antennas have these qualities and are suited for radars as an alternative to the bulky and heavyweight reflector/slotted waveguide array antennas.A perforated corner single-line fed microstrip antenna is designed here.When compared to the basic square microstrip antenna,this antenna has better specifications.Because key issue is determining the best values for various antenna parameters when devel-oping the patch antenna.Optimized Neural Network(ONN)is one potential tech-nique utilized to solve this issue,and this work also uses Particle Swarm Optimization(PSO)to enhance the antenna performance.Return loss(S11)and Voltage Standing Wave Ratio(VSWR)parameters are considered in all situations,developed with Advanced Design System(ADS)applications.The transmitters are made to emit in the Ku-band,which covers a wide range of wavelengths.From 5–15 GHz,it is used in most current radars.The ADS suite is used to create the simulation design.
基金Supported by the National Natural Science Foundation of China （60774079）, the National High Technology Research and Development Program of China （2006AA04Z184）, and Sinopec Science ＆ Technology Development Project of China （205073）.
文摘Decreasing the acetic acid consumption in purified terephthalic acid （PTA） solvent system has become a hot issue with common concern. In accordance with the technical features, the electrical conductivity is in direct proportion to the acetic acid content. General regression neural network （GRNN） is used to establish the model of electrical conductivity on the basis of mechanism analysis, and then particle swarm optimization （PSO） algorithm with the improvement of inertia weight and population diversity is proposed to regulate the operating conditions. Thus, the method of decreasing the acid loss is derived and applied to PTA solvent system in a chemical plant. Cases studies show that the precision of modeling and optimization are higher. The results also provide the optimal operating conditions, which decrease the cost and improve the profit.
文摘A genetic-fuzzy HEV control strategy based on driving cycle recognition （DCR） was built. Six driving cycles were selected to represent different traffic conditions e.g. freeway, urban, suburb. A neural algorithm was used for traffic condition recognition based on ten parameters of each driving cycle. The DCR was utilized for optimization of the HEV control parameters using a genetic-fuzzy approach. A fuzzy logic controller （FLC） was designed to be intelligent to manage the engine to work in the vicinity of its optimal condition. The fuzzy membership function parameters were optimized using the genetic algorithm （GA） for each driving cycle. The result is that the DCR_ fuzzy controller can reduce the fuel consumption by 1. 9%, higher than only CYC _ HWFET optimized fuzzy （0.2%） or CYC _ WVUSUB optimized fuzzy （0.7%）. The DCR_ fuzzy method can get the better result than only optimizing one cycle on the complex real traffic conditions.
基金the financial support from the Fundamental Research Funds for the Central universities of China (No. 2009KH07)
文摘Coal flotation is widely used to separate commercially valuable coal from the fine ore slurry, and is an industrial process with nonlinear, multivariable, time-varying and long time-delay characteristics. The online detection of ash content of products as the operation performance evaluation in the flotation system is extraordinarily difficult because of the low solid content and numerous micro-bubbles in the slurry. Moreover, it is time-consuming by manual analysis. Consequently, the optimal separation is not usually maintained. A novel technique, called the neuro-immune algorithm (NIA) inspired by the biological nervous and immune systems, is presented in this paper for predicting the ash content of clean coal and performing the optimizing control to the coal flotation system. The proposed algorithm integrates the deeply-studied artificial neural network (ANN) and the developing artificial immune system (AIS). A two-layer back-propagation network was constructed offline based on the historical process data under the best system situation, using five parameters: the flow and the density of raw slurry, the input flows of water, the kerosene and the GF oil, as the inputs and the ash content of clean coal as the output. The immune cell of AIS is made up of six parameters above as the antigen. The cytokine based clone selection algorithm is used to produce the relative antibody. The detailed computation procedures about the hybrid neuro-immune algorithm are minutely discussed. The ash content of clean coal was predicted by NIA using the practical process data s: (308.6 174.7 146.1 43.6 4.0 9.4), and the absolute difference between the actual and computed ash content values was 0.0967%. The optimizing control on NIA was simulated considering two different situations where the ash content of clean coal was controlled downward from 10.00% or upward from 9.20% predicted by ANN to the target value 9.50%. The results indicate that the target ash content and the value of controlling parameters are obtained after several control cycles.
文摘Background:In the visual system,one of the most explored neural behaviors is the response of cells to changes in visual contrast.This neural response to visual contrast,also known as the contrast response function(CRF),can be fitted with the Naka-Rushton equation(NRE).Assessing the CRF of many neurons at the same time is critical to establishing functional visual properties.However,maximizing the performance of neurons to fit the NRE,while minimizing their time acquisitions is a challenge.We present a method to accurately obtain reliable NRE fits from experimental data,that ensure a reasonable time of record acquisition.Methods:We simulated CRF of cortical neurons with a toy model based on the response of Poisson spike trains to varied levels of contrasts.We first tested whether mean values or the whole set of contrast responses fit better the NRE.Then,we analyzed what were the boundaries to optimize the fit of the NRE,and after we explore the consequences of fitting the NRE with single-or multi-units.With these outcomes,we varied experimental parameters such as the number of trials,number of input contrasts and length of time acquisition to calculate the errors of fitting CRFs.Those data sets that maximize the CRF fit but minimize the time of recording were selected.The selected data set was then evaluated in visual cortical neurons of anesthetized cats from areas 17,18 and 21a.Results:First,we found that is always better to fit the NRE with mean values rather than the whole set of points.Then,we noticed that either removing or imposing loose boundaries to the CRF parameters lead to an increase in the performance of the NRE fit.Afterward,we found that single units(SU)or assume multi-unit formed of several SUs(>30)adjusted considerably better the NRE fit.Finally,the experiments showed that specific sets of patterns(number of trials,number of input contrasts and length of time acquisition)satisfied our two constraints:minimize the error of the NRE fit while maximizing the acquisition time of recording.The most characteristic pattern was the one with 6 points,15 repetitions and 1 second of duration.However,cortical areas varied in the representation of the patterns.Conclusions:Theoretical simulations of many different sets of patterns and their following experimental validation suggest strongly that a particular set of patterns can satisfy the imposed constraints.With this approach,we provided a tool that allows an optimal design of stimuli to assess the CRF of large neuronal populations and guarantees the finest fit for each unit analyzed.
