The quantum hybrid algorithm has recently become a very promising and speedy method for solving larger-scale optimization problems in the noisy intermediate-scale quantum(NISQ)era.The unit commitment(UC)problem is a f...The quantum hybrid algorithm has recently become a very promising and speedy method for solving larger-scale optimization problems in the noisy intermediate-scale quantum(NISQ)era.The unit commitment(UC)problem is a fundamental problem in the field of power systems that aims to satisfy the power balance constraint with minimal cost.In this paper,we focus on the implementation of the UC solution using exact quantum algorithms based on the quantum neural network(QNN).This method is tested with a ten-unit system under the power balance constraint.In order to improve computing precision and reduce network complexity,we propose a knowledge-based partially connected quantum neural network(PCQNN).The results show that exact solutions can be obtained by the improved algorithm and that the depth of the quantum circuit can be reduced simultaneously.展开更多
When designing solar systems and assessing the effectiveness of their many uses,estimating sun irradiance is a crucial first step.This study examined three approaches(ANN,GA-ANN,and ANFIS)for estimating daily global s...When designing solar systems and assessing the effectiveness of their many uses,estimating sun irradiance is a crucial first step.This study examined three approaches(ANN,GA-ANN,and ANFIS)for estimating daily global solar radiation(GSR)in the south of Algeria:Adrar,Ouargla,and Bechar.The proposed hybrid GA-ANN model,based on genetic algorithm-based optimization,was developed to improve the ANN model.The GA-ANN and ANFIS models performed better than the standalone ANN-based model,with GA-ANN being better suited for forecasting in all sites,and it performed the best with the best values in the testing phase of Coefficient of Determination(R=0.9005),Mean Absolute Percentage Error(MAPE=8.40%),and Relative Root Mean Square Error(rRMSE=12.56%).Nevertheless,the ANFIS model outperformed the GA-ANN model in forecasting daily GSR,with the best values of indicators when testing the model being R=0.9374,MAPE=7.78%,and rRMSE=10.54%.Generally,we may conclude that the initial ANN stand-alone model performance when forecasting solar radiation has been improved,and the results obtained after injecting the genetic algorithm into the ANN to optimize its weights were satisfactory.The model can be used to forecast daily GSR in dry climates and other climates and may also be helpful in selecting solar energy system installations and sizes.展开更多
Developing an accurate and efficient comprehensive water quality prediction model and its assessment method is crucial for the prevention and control of water pollution.Deep learning(DL),as one of the most promising t...Developing an accurate and efficient comprehensive water quality prediction model and its assessment method is crucial for the prevention and control of water pollution.Deep learning(DL),as one of the most promising technologies today,plays a crucial role in the effective assessment of water body health,which is essential for water resource management.This study models using both the original dataset and a dataset augmented with Generative Adversarial Networks(GAN).It integrates optimization algorithms(OA)with Convolutional Neural Networks(CNN)to propose a comprehensive water quality model evaluation method aiming at identifying the optimal models for different pollutants.Specifically,after preprocessing the spectral dataset,data augmentation was conducted to obtain two datasets.Then,six new models were developed on these datasets using particle swarm optimization(PSO),genetic algorithm(GA),and simulated annealing(SA)combined with CNN to simulate and forecast the concentrations of three water pollutants:Chemical Oxygen Demand(COD),Total Nitrogen(TN),and Total Phosphorus(TP).Finally,seven model evaluation methods,including uncertainty analysis,were used to evaluate the constructed models and select the optimal models for the three pollutants.The evaluation results indicate that the GPSCNN model performed best in predicting COD and TP concentrations,while the GGACNN model excelled in TN concentration prediction.Compared to existing technologies,the proposed models and evaluation methods provide a more comprehensive and rapid approach to water body prediction and assessment,offering new insights and methods for water pollution prevention and control.展开更多
Wireless Sensor Networks(WSNs)have emerged as crucial tools for real-time environmental monitoring through distributed sensor nodes(SNs).However,the operational lifespan of WSNs is significantly constrained by the lim...Wireless Sensor Networks(WSNs)have emerged as crucial tools for real-time environmental monitoring through distributed sensor nodes(SNs).However,the operational lifespan of WSNs is significantly constrained by the limited energy resources of SNs.Current energy efficiency strategies,such as clustering,multi-hop routing,and data aggregation,face challenges,including uneven energy depletion,high computational demands,and suboptimal cluster head(CH)selection.To address these limitations,this paper proposes a hybrid methodology that optimizes energy consumption(EC)while maintaining network performance.The proposed approach integrates the Low Energy Adaptive Clustering Hierarchy with Deterministic(LEACH-D)protocol using an Artificial Neural Network(ANN)and Bayesian Regularization Algorithm(BRA).LEACH-D improves upon conventional LEACH by ensuring more uniform energy usage across SNs,mitigating inefficiencies from random CH selection.The ANN further enhances CH selection and routing processes,effectively reducing data transmission overhead and idle listening.Simulation results reveal that the LEACH-D-ANN model significantly reduces EC and extends the network’s lifespan compared to existing protocols.This framework offers a promising solution to the energy efficiency challenges in WSNs,paving the way for more sustainable and reliable network deployments.展开更多
This paper deals with deriving the properties of updated neural network model that is exploited to identify an unknown nonlinear system via the standard gradient learning algorithm. The convergence of this algorithm f...This paper deals with deriving the properties of updated neural network model that is exploited to identify an unknown nonlinear system via the standard gradient learning algorithm. The convergence of this algorithm for online training the three-layer neural networks in stochastic environment is studied. A special case where an unknown nonlinearity can exactly be approximated by some neural network with a nonlinear activation function for its output layer is considered. To analyze the asymptotic behavior of the learning processes, the so-called Lyapunov-like approach is utilized. As the Lyapunov function, the expected value of the square of approximation error depending on network parameters is chosen. Within this approach, sufficient conditions guaranteeing the convergence of learning algorithm with probability 1 are derived. Simulation results are presented to support the theoretical analysis.展开更多
A novel real coded improved genetic algorithm (GA) of training feed forward neural network is proposed to realize nonlinear system forecast. The improved GA employs a generation alternation model based the minimal gen...A novel real coded improved genetic algorithm (GA) of training feed forward neural network is proposed to realize nonlinear system forecast. The improved GA employs a generation alternation model based the minimal generation gap (MGP) and blend crossover operators (BLX α). Compared with traditional GA implemented in binary number, the processing time of the improved GA is faster because coding and decoding are unnecessary. In addition, it needn t set parameters such as the probability value of crossove...展开更多
Accurate prediction of chemical composition of vacuum gas oil （VGO） is essential for the routine operation of refineries. In this work, a new approach for auto-design of artificial neural networks （ANN） based on a...Accurate prediction of chemical composition of vacuum gas oil （VGO） is essential for the routine operation of refineries. In this work, a new approach for auto-design of artificial neural networks （ANN） based on a genetic algorithm （GA） is developed for predicting VGO saturates. The number of neurons in the hidden layer, the momentum and the learning rates are determined by using the genetic algorithm. The inputs for the artificial neural networks model are five physical properties, namely, average boiling point, density, molecular weight, viscosity and refractive index. It is verified that the genetic algorithm could find the optimal structural parameters and training parameters of ANN. In addition, an artificial neural networks model based on a genetic algorithm was tested and the results indicated that the VGO saturates can be efficiently predicted. Compared with conventional artificial neural networks models, this approach can improve the prediction accuracy.展开更多
This paper introduced the Genetic Algorithms (GAs) and Artificial Neural Networks (ANNs), which have been widely used in optimization of allocating. The combination way of the two optimizing algorithms was used in boa...This paper introduced the Genetic Algorithms (GAs) and Artificial Neural Networks (ANNs), which have been widely used in optimization of allocating. The combination way of the two optimizing algorithms was used in board allocating of furniture production. In the experiment, the rectangular flake board of 3650 mm 1850 mm was used as raw material to allocate 100 sets of Table Bucked. The utilizing rate of the board reached 94.14 % and the calculating time was only 35 s. The experiment result proofed that the method by using the GA for optimizing the weights of the ANN can raise the utilizing rate of the board and can shorten the time of the design. At the same time, this method can simultaneously searched in many directions, thus greatly in-creasing the probability of finding a global optimum.展开更多
In this paper, a multi-objective particle swarm optimization （MOPSO） algorithm and a nondominated sorting genetic algorithm II （NSGA-II） are used to optimize the operating parameters of a 1.6 L, spark ignition （S...In this paper, a multi-objective particle swarm optimization （MOPSO） algorithm and a nondominated sorting genetic algorithm II （NSGA-II） are used to optimize the operating parameters of a 1.6 L, spark ignition （SI） gasoline engine. The aim of this optimization is to reduce engine emissions in terms of carbon monoxide （CO）, hydrocarbons （HC）, and nitrogen oxides （NOx）, which are the causes of diverse environmental problems such as air pollution and global warming. Stationary engine tests were performed for data generation, covering 60 operating conditions. Artificial neural networks （ANNs） were used to predict exhaust emissions, whose inputs were from six engine operating parameters, and the outputs were three resulting exhaust emissions. The outputs of ANNs were used to evaluate objective functions within the optimization algorithms： NSGA-II and MOPSO. Then a decision-making process was conducted, using a fuzzy method to select a Pareto solution with which the best emission reductions can be achieved. The NSGA-II algorithm achieved reductions of at least 9.84%, 82.44%, and 13.78% for CO, HC, and NOx, respectively. With a MOPSO algorithm the reached reductions were at least 13.68%, 83.80%, and 7.67% for CO, HC, and NOx, respectively.展开更多
The Volterra feedforward neural network with nonlinear interconnections and related homotopy learning algorithm are proposed in the paper. It is shown that Volterra neural network and the homolopy learning algorithms ...The Volterra feedforward neural network with nonlinear interconnections and related homotopy learning algorithm are proposed in the paper. It is shown that Volterra neural network and the homolopy learning algorithms are significant potentials in nonlinear approximation ability,convergent speeds and global optimization than the classical neural networks and the standard BP algorithm, and related computer simulations and theoretical analysis are given too.展开更多
Objective To investigate the prediction effect of neural networks for seismic response of structure under the Levenberg Marquardt(LM) algorithm. Results Based on identification and prediction ability of neural netw...Objective To investigate the prediction effect of neural networks for seismic response of structure under the Levenberg Marquardt(LM) algorithm. Results Based on identification and prediction ability of neural networks for nonlinear systems, and combined with LM algorithm, a multi layer forward networks is adopted to predict the seismic responses of structure. The networks is trained in batch by the shaking table test data of three floor reinforced concrete structure firstly, then the seismic responses of structure are predicted under the unused excitation data, and the predict responses are compared with the experiment responses. The error curves between the prediction and the experimental results show the efficiency of the method. Conclusion LM algorithm has very good convergence rate, and the neural networks can predict the seismic response of the structure well.展开更多
Considering the indefinite character of the value of design parameters and being satisfied with load-bearing capacity and stiffness, the fuzzy optimization mathematical model is set up to minimize the volume of tooth ...Considering the indefinite character of the value of design parameters and being satisfied with load-bearing capacity and stiffness, the fuzzy optimization mathematical model is set up to minimize the volume of tooth corona of a worm gear in an elevator mechanism. The method of second-class comprehensive evaluation was used based on the optimal level cut set, thus the optimal level value of every fuzzy constraint can be attained; the fuzzy optimization is transformed into the usual optimization. The Fast Back Propagation of the neural networks algorithm are adopted to train feed-forward networks so as to fit a relative coefficient. Then the fitness function with penalty terms is built by a penalty strategy, a neural networks program is recalled, and solver functions of the Genetic Algorithm Toolbox of Matlab software are adopted to solve the optimization model.展开更多
A kind of second order algorithm--recursive approximate Newton algorithm was given by Karayiannis. The algorithm was simplified when it was formulated. Especially, the simplification to matrix Hessian was very reluct...A kind of second order algorithm--recursive approximate Newton algorithm was given by Karayiannis. The algorithm was simplified when it was formulated. Especially, the simplification to matrix Hessian was very reluctant, which led to the loss of valuable information and affected performance of the algorithm to certain extent. For multi layer feed forward neural networks, the second order back propagation recursive algorithm based generalized cost criteria was proposed. It is proved that it is equivalent to Newton recursive algorithm and has a second order convergent rate. The performance and application prospect are analyzed. Lots of simulation experiments indicate that the calculation of the new algorithm is almost equivalent to the recursive least square multiple algorithm. The algorithm and selection of networks parameters are significant and the performance is more excellent than BP algorithm and the second order learning algorithm that was given by Karayiannis.展开更多
In the context of climate change,countries in West Africa are faced with recurrent flooding with catastrophic consequences,that makes it imperative to have access to rainfall information on fine spatial and temporal s...In the context of climate change,countries in West Africa are faced with recurrent flooding with catastrophic consequences,that makes it imperative to have access to rainfall information on fine spatial and temporal scales for better monitoring and prediction of these phenomena,as could be provided by weather radars.Based on an extensive archive of data from the X-band polarimetric radar and rain gauges observations gathered during the intensive AMMA campaigns in 2006–2007 and the Megha-Tropiques satellite measurement validation programme in 2010 in West Africa,we(i)simulated jointly realistic data for polarimetric radar variables and rain intensity using copula,and(ii)assessed rain rate estimation methods based on neural network(NN)inversion techniques and non-linearly calibrated parametric algorithms.The assessment of rainfall rate retrieval by these estimators is carried out using the part of the observations database not employed for calibration steps.The multiparametric algorithms R(ZH,K_(DP))and R(Z_(DR),K_(DP))perform better than R(ZH,Z_(DR))and R(ZH,Z_(DR),K_(DP)),especially since they are calibrated using copulas with upper tail dependencies,with KGE ranging in 0.68–0.75 and 0.79–0.82,respectively versus ranges of 0.40–0.64 and 0.20–0.51,for the two latter estimators.The neural network-based estimators RNN(Z_(DR),K_(DP))and RNN(ZH,K_(DP)),show KGE score characteristics comparable to those obtained from the best parametric relations,specifically optimized for the synthetic copula-based dataset.However,the neural network-based estimators were shown to be more robust when applied to a specific rainfall event.More specifically,neural network-based estimators trained on synthetic data are sensitive to the copulas’ability to capture the dependence between the variables of interest over the entire distribution of joint values.This leads to a near-cancellation of sensitivity to variability in the raindrop size distribution,as shown the coefficients of correlation near 1,especially for RNN(Z_(DR),K_(DP)),and for less extent RNN(Z_(H),K_(DP)).展开更多
A brief review of color matching technology and its application of printing RGB images by CMY or CMYK ink jet printers is presented, followed by an explanation to the conventional approaches that are commonly used in ...A brief review of color matching technology and its application of printing RGB images by CMY or CMYK ink jet printers is presented, followed by an explanation to the conventional approaches that are commonly used in color matching. Then, a four color matching method combining neural network with genetic algorithm is proposed. The initial weights and thresholds of the BP neural network for RGB to CMY color conversion are optimized by the new genetic algorithm based on evolutionarily stable strategy. The fourth component K is generated by using GCR (Gray Component Replacement) concept. Simulation experiments show that it is well behaved in both accuracy and generalization performance.展开更多
As a most popular learning algorithm for the feedforward neural networks, the classic BP algorithm has its many shortages. To overcome some of the shortages, a modified learning algorithm is proposed in the article. A...As a most popular learning algorithm for the feedforward neural networks, the classic BP algorithm has its many shortages. To overcome some of the shortages, a modified learning algorithm is proposed in the article. And the simulation result illustrate the modified algorithm is more effective and practicable.展开更多
. This paper proposes a novel remote sensing signal de-noising algorithm based on neural networks and tensor analysis. The defects exist in a constant deviation between the wavelet coeffi cients and that the wavelet c.... This paper proposes a novel remote sensing signal de-noising algorithm based on neural networks and tensor analysis. The defects exist in a constant deviation between the wavelet coeffi cients and that the wavelet coefficients of the noisy signal to estimate the discontinuity of hard threshold function and soft threshold function, limiting its further application in order to overcome this shortcoming, this paper proposes a new threshold function, compared with the original threshold function, a new threshold function is simple and easy to calculate, not only with the soft threshold function is continuous. To deal with this drawback, we integrate the NN to enhance the model. Neural network belongs to the basic unsupervised learning of neural networks, the principle of competition based on the mechanism of learning and biological and the memory capacity can be increased as the number of learning patterns increases, not only offi ine learning can also be carried out on-line ＂learning while learning＂ type. The integrated algorithm can host better performance.展开更多
This paper presents a method of determining the friction coefficient in metal forming using multilayer artificial neural networks based on experimental data obtained from strip drawing test.The number of input variabl...This paper presents a method of determining the friction coefficient in metal forming using multilayer artificial neural networks based on experimental data obtained from strip drawing test.The number of input variables of the artificial neural network has been optimized using genetic algorithm.This process is based on surface parameters of the sheet and dies,sheet material parameters and clamping force as input parameters to train the neural network.In addition to demonstrating the fact that regression statistics model using genetic selection and intelligent problem solver are better than models without preprocessing of input data,the sensitivity analysis of the input variables has been conducted.This avoids the time-consuming testing of neurons in finding the best network architecture.The obtained results from this study have also pointed out that genetic algorithm can successfully be applied to optimize the training set and the outputs agree with experimental results.This allows reduction or elimination of expensive experimental tests to determine friction coefficient value.展开更多
Artificial neural networks(ANNs)have led to landmark changes in many fields,but they still differ significantly fromthemechanisms of real biological neural networks and face problems such as high computing costs,exces...Artificial neural networks(ANNs)have led to landmark changes in many fields,but they still differ significantly fromthemechanisms of real biological neural networks and face problems such as high computing costs,excessive computing power,and so on.Spiking neural networks(SNNs)provide a new approach combined with brain-like science to improve the computational energy efficiency,computational architecture,and biological credibility of current deep learning applications.In the early stage of development,its poor performance hindered the application of SNNs in real-world scenarios.In recent years,SNNs have made great progress in computational performance and practicability compared with the earlier research results,and are continuously producing significant results.Although there are already many pieces of literature on SNNs,there is still a lack of comprehensive review on SNNs from the perspective of improving performance and practicality as well as incorporating the latest research results.Starting from this issue,this paper elaborates on SNNs along the complete usage process of SNNs including network construction,data processing,model training,development,and deployment,aiming to provide more comprehensive and practical guidance to promote the development of SNNs.Therefore,the connotation and development status of SNNcomputing is reviewed systematically and comprehensively from four aspects:composition structure,data set,learning algorithm,software/hardware development platform.Then the development characteristics of SNNs in intelligent computing are summarized,the current challenges of SNNs are discussed and the future development directions are also prospected.Our research shows that in the fields of machine learning and intelligent computing,SNNs have comparable network scale and performance to ANNs and the ability to challenge large datasets and a variety of tasks.The advantages of SNNs over ANNs in terms of energy efficiency and spatial-temporal data processing have been more fully exploited.And the development of programming and deployment tools has lowered the threshold for the use of SNNs.SNNs show a broad development prospect for brain-like computing.展开更多
Wind speed forecasting is of great importance for wind farm management and plays an important role in grid integration. Wind speed is volatile in nature and therefore it is difficult to predict with a single model. In...Wind speed forecasting is of great importance for wind farm management and plays an important role in grid integration. Wind speed is volatile in nature and therefore it is difficult to predict with a single model. In this study, three hybrid multi-step wind speed forecasting models are developed and compared — with each other and with earlier proposed wind speed forecasting models. The three models are based on wavelet decomposition(WD), the Cuckoo search(CS) optimization algorithm, and a wavelet neural network(WNN). They are referred to as CS-WD-ANN(artificial neural network), CS-WNN, and CS-WD-WNN, respectively. Wind speed data from two wind farms located in Shandong, eastern China, are used in this study. The simulation result indicates that CS-WD-WNN outperforms the other two models, with minimum statistical errors. Comparison with earlier models shows that CS-WD-WNN still performs best, with the smallest statistical errors. The employment of the CS optimization algorithm in the models shows improvement compared with the earlier models.展开更多
基金supported in part by the China Postdoctoral Science Foundation(Grant No.2023M740874)。
文摘The quantum hybrid algorithm has recently become a very promising and speedy method for solving larger-scale optimization problems in the noisy intermediate-scale quantum(NISQ)era.The unit commitment(UC)problem is a fundamental problem in the field of power systems that aims to satisfy the power balance constraint with minimal cost.In this paper,we focus on the implementation of the UC solution using exact quantum algorithms based on the quantum neural network(QNN).This method is tested with a ten-unit system under the power balance constraint.In order to improve computing precision and reduce network complexity,we propose a knowledge-based partially connected quantum neural network(PCQNN).The results show that exact solutions can be obtained by the improved algorithm and that the depth of the quantum circuit can be reduced simultaneously.
文摘When designing solar systems and assessing the effectiveness of their many uses,estimating sun irradiance is a crucial first step.This study examined three approaches(ANN,GA-ANN,and ANFIS)for estimating daily global solar radiation(GSR)in the south of Algeria:Adrar,Ouargla,and Bechar.The proposed hybrid GA-ANN model,based on genetic algorithm-based optimization,was developed to improve the ANN model.The GA-ANN and ANFIS models performed better than the standalone ANN-based model,with GA-ANN being better suited for forecasting in all sites,and it performed the best with the best values in the testing phase of Coefficient of Determination(R=0.9005),Mean Absolute Percentage Error(MAPE=8.40%),and Relative Root Mean Square Error(rRMSE=12.56%).Nevertheless,the ANFIS model outperformed the GA-ANN model in forecasting daily GSR,with the best values of indicators when testing the model being R=0.9374,MAPE=7.78%,and rRMSE=10.54%.Generally,we may conclude that the initial ANN stand-alone model performance when forecasting solar radiation has been improved,and the results obtained after injecting the genetic algorithm into the ANN to optimize its weights were satisfactory.The model can be used to forecast daily GSR in dry climates and other climates and may also be helpful in selecting solar energy system installations and sizes.
基金Supported by Natural Science Basic Research Plan in Shaanxi Province of China(Program No.2022JM-396)the Strategic Priority Research Program of the Chinese Academy of Sciences,Grant No.XDA23040101+4 种基金Shaanxi Province Key Research and Development Projects(Program No.2023-YBSF-437)Xi'an Shiyou University Graduate Student Innovation Fund Program(Program No.YCX2412041)State Key Laboratory of Air Traffic Management System and Technology(SKLATM202001)Tianjin Education Commission Research Program Project(2020KJ028)Fundamental Research Funds for the Central Universities(3122019132)。
文摘Developing an accurate and efficient comprehensive water quality prediction model and its assessment method is crucial for the prevention and control of water pollution.Deep learning(DL),as one of the most promising technologies today,plays a crucial role in the effective assessment of water body health,which is essential for water resource management.This study models using both the original dataset and a dataset augmented with Generative Adversarial Networks(GAN).It integrates optimization algorithms(OA)with Convolutional Neural Networks(CNN)to propose a comprehensive water quality model evaluation method aiming at identifying the optimal models for different pollutants.Specifically,after preprocessing the spectral dataset,data augmentation was conducted to obtain two datasets.Then,six new models were developed on these datasets using particle swarm optimization(PSO),genetic algorithm(GA),and simulated annealing(SA)combined with CNN to simulate and forecast the concentrations of three water pollutants:Chemical Oxygen Demand(COD),Total Nitrogen(TN),and Total Phosphorus(TP).Finally,seven model evaluation methods,including uncertainty analysis,were used to evaluate the constructed models and select the optimal models for the three pollutants.The evaluation results indicate that the GPSCNN model performed best in predicting COD and TP concentrations,while the GGACNN model excelled in TN concentration prediction.Compared to existing technologies,the proposed models and evaluation methods provide a more comprehensive and rapid approach to water body prediction and assessment,offering new insights and methods for water pollution prevention and control.
文摘Wireless Sensor Networks(WSNs)have emerged as crucial tools for real-time environmental monitoring through distributed sensor nodes(SNs).However,the operational lifespan of WSNs is significantly constrained by the limited energy resources of SNs.Current energy efficiency strategies,such as clustering,multi-hop routing,and data aggregation,face challenges,including uneven energy depletion,high computational demands,and suboptimal cluster head(CH)selection.To address these limitations,this paper proposes a hybrid methodology that optimizes energy consumption(EC)while maintaining network performance.The proposed approach integrates the Low Energy Adaptive Clustering Hierarchy with Deterministic(LEACH-D)protocol using an Artificial Neural Network(ANN)and Bayesian Regularization Algorithm(BRA).LEACH-D improves upon conventional LEACH by ensuring more uniform energy usage across SNs,mitigating inefficiencies from random CH selection.The ANN further enhances CH selection and routing processes,effectively reducing data transmission overhead and idle listening.Simulation results reveal that the LEACH-D-ANN model significantly reduces EC and extends the network’s lifespan compared to existing protocols.This framework offers a promising solution to the energy efficiency challenges in WSNs,paving the way for more sustainable and reliable network deployments.
文摘This paper deals with deriving the properties of updated neural network model that is exploited to identify an unknown nonlinear system via the standard gradient learning algorithm. The convergence of this algorithm for online training the three-layer neural networks in stochastic environment is studied. A special case where an unknown nonlinearity can exactly be approximated by some neural network with a nonlinear activation function for its output layer is considered. To analyze the asymptotic behavior of the learning processes, the so-called Lyapunov-like approach is utilized. As the Lyapunov function, the expected value of the square of approximation error depending on network parameters is chosen. Within this approach, sufficient conditions guaranteeing the convergence of learning algorithm with probability 1 are derived. Simulation results are presented to support the theoretical analysis.
文摘A novel real coded improved genetic algorithm (GA) of training feed forward neural network is proposed to realize nonlinear system forecast. The improved GA employs a generation alternation model based the minimal generation gap (MGP) and blend crossover operators (BLX α). Compared with traditional GA implemented in binary number, the processing time of the improved GA is faster because coding and decoding are unnecessary. In addition, it needn t set parameters such as the probability value of crossove...
文摘Accurate prediction of chemical composition of vacuum gas oil （VGO） is essential for the routine operation of refineries. In this work, a new approach for auto-design of artificial neural networks （ANN） based on a genetic algorithm （GA） is developed for predicting VGO saturates. The number of neurons in the hidden layer, the momentum and the learning rates are determined by using the genetic algorithm. The inputs for the artificial neural networks model are five physical properties, namely, average boiling point, density, molecular weight, viscosity and refractive index. It is verified that the genetic algorithm could find the optimal structural parameters and training parameters of ANN. In addition, an artificial neural networks model based on a genetic algorithm was tested and the results indicated that the VGO saturates can be efficiently predicted. Compared with conventional artificial neural networks models, this approach can improve the prediction accuracy.
基金This paper is supported by the Nature Science Foundation of Heilongjiang Province.
文摘This paper introduced the Genetic Algorithms (GAs) and Artificial Neural Networks (ANNs), which have been widely used in optimization of allocating. The combination way of the two optimizing algorithms was used in board allocating of furniture production. In the experiment, the rectangular flake board of 3650 mm 1850 mm was used as raw material to allocate 100 sets of Table Bucked. The utilizing rate of the board reached 94.14 % and the calculating time was only 35 s. The experiment result proofed that the method by using the GA for optimizing the weights of the ANN can raise the utilizing rate of the board and can shorten the time of the design. At the same time, this method can simultaneously searched in many directions, thus greatly in-creasing the probability of finding a global optimum.
文摘In this paper, a multi-objective particle swarm optimization （MOPSO） algorithm and a nondominated sorting genetic algorithm II （NSGA-II） are used to optimize the operating parameters of a 1.6 L, spark ignition （SI） gasoline engine. The aim of this optimization is to reduce engine emissions in terms of carbon monoxide （CO）, hydrocarbons （HC）, and nitrogen oxides （NOx）, which are the causes of diverse environmental problems such as air pollution and global warming. Stationary engine tests were performed for data generation, covering 60 operating conditions. Artificial neural networks （ANNs） were used to predict exhaust emissions, whose inputs were from six engine operating parameters, and the outputs were three resulting exhaust emissions. The outputs of ANNs were used to evaluate objective functions within the optimization algorithms： NSGA-II and MOPSO. Then a decision-making process was conducted, using a fuzzy method to select a Pareto solution with which the best emission reductions can be achieved. The NSGA-II algorithm achieved reductions of at least 9.84%, 82.44%, and 13.78% for CO, HC, and NOx, respectively. With a MOPSO algorithm the reached reductions were at least 13.68%, 83.80%, and 7.67% for CO, HC, and NOx, respectively.
文摘The Volterra feedforward neural network with nonlinear interconnections and related homotopy learning algorithm are proposed in the paper. It is shown that Volterra neural network and the homolopy learning algorithms are significant potentials in nonlinear approximation ability,convergent speeds and global optimization than the classical neural networks and the standard BP algorithm, and related computer simulations and theoretical analysis are given too.
文摘Objective To investigate the prediction effect of neural networks for seismic response of structure under the Levenberg Marquardt(LM) algorithm. Results Based on identification and prediction ability of neural networks for nonlinear systems, and combined with LM algorithm, a multi layer forward networks is adopted to predict the seismic responses of structure. The networks is trained in batch by the shaking table test data of three floor reinforced concrete structure firstly, then the seismic responses of structure are predicted under the unused excitation data, and the predict responses are compared with the experiment responses. The error curves between the prediction and the experimental results show the efficiency of the method. Conclusion LM algorithm has very good convergence rate, and the neural networks can predict the seismic response of the structure well.
文摘Considering the indefinite character of the value of design parameters and being satisfied with load-bearing capacity and stiffness, the fuzzy optimization mathematical model is set up to minimize the volume of tooth corona of a worm gear in an elevator mechanism. The method of second-class comprehensive evaluation was used based on the optimal level cut set, thus the optimal level value of every fuzzy constraint can be attained; the fuzzy optimization is transformed into the usual optimization. The Fast Back Propagation of the neural networks algorithm are adopted to train feed-forward networks so as to fit a relative coefficient. Then the fitness function with penalty terms is built by a penalty strategy, a neural networks program is recalled, and solver functions of the Genetic Algorithm Toolbox of Matlab software are adopted to solve the optimization model.
文摘A kind of second order algorithm--recursive approximate Newton algorithm was given by Karayiannis. The algorithm was simplified when it was formulated. Especially, the simplification to matrix Hessian was very reluctant, which led to the loss of valuable information and affected performance of the algorithm to certain extent. For multi layer feed forward neural networks, the second order back propagation recursive algorithm based generalized cost criteria was proposed. It is proved that it is equivalent to Newton recursive algorithm and has a second order convergent rate. The performance and application prospect are analyzed. Lots of simulation experiments indicate that the calculation of the new algorithm is almost equivalent to the recursive least square multiple algorithm. The algorithm and selection of networks parameters are significant and the performance is more excellent than BP algorithm and the second order learning algorithm that was given by Karayiannis.
文摘In the context of climate change,countries in West Africa are faced with recurrent flooding with catastrophic consequences,that makes it imperative to have access to rainfall information on fine spatial and temporal scales for better monitoring and prediction of these phenomena,as could be provided by weather radars.Based on an extensive archive of data from the X-band polarimetric radar and rain gauges observations gathered during the intensive AMMA campaigns in 2006–2007 and the Megha-Tropiques satellite measurement validation programme in 2010 in West Africa,we(i)simulated jointly realistic data for polarimetric radar variables and rain intensity using copula,and(ii)assessed rain rate estimation methods based on neural network(NN)inversion techniques and non-linearly calibrated parametric algorithms.The assessment of rainfall rate retrieval by these estimators is carried out using the part of the observations database not employed for calibration steps.The multiparametric algorithms R(ZH,K_(DP))and R(Z_(DR),K_(DP))perform better than R(ZH,Z_(DR))and R(ZH,Z_(DR),K_(DP)),especially since they are calibrated using copulas with upper tail dependencies,with KGE ranging in 0.68–0.75 and 0.79–0.82,respectively versus ranges of 0.40–0.64 and 0.20–0.51,for the two latter estimators.The neural network-based estimators RNN(Z_(DR),K_(DP))and RNN(ZH,K_(DP)),show KGE score characteristics comparable to those obtained from the best parametric relations,specifically optimized for the synthetic copula-based dataset.However,the neural network-based estimators were shown to be more robust when applied to a specific rainfall event.More specifically,neural network-based estimators trained on synthetic data are sensitive to the copulas’ability to capture the dependence between the variables of interest over the entire distribution of joint values.This leads to a near-cancellation of sensitivity to variability in the raindrop size distribution,as shown the coefficients of correlation near 1,especially for RNN(Z_(DR),K_(DP)),and for less extent RNN(Z_(H),K_(DP)).
文摘A brief review of color matching technology and its application of printing RGB images by CMY or CMYK ink jet printers is presented, followed by an explanation to the conventional approaches that are commonly used in color matching. Then, a four color matching method combining neural network with genetic algorithm is proposed. The initial weights and thresholds of the BP neural network for RGB to CMY color conversion are optimized by the new genetic algorithm based on evolutionarily stable strategy. The fourth component K is generated by using GCR (Gray Component Replacement) concept. Simulation experiments show that it is well behaved in both accuracy and generalization performance.
文摘As a most popular learning algorithm for the feedforward neural networks, the classic BP algorithm has its many shortages. To overcome some of the shortages, a modified learning algorithm is proposed in the article. And the simulation result illustrate the modified algorithm is more effective and practicable.
文摘. This paper proposes a novel remote sensing signal de-noising algorithm based on neural networks and tensor analysis. The defects exist in a constant deviation between the wavelet coeffi cients and that the wavelet coefficients of the noisy signal to estimate the discontinuity of hard threshold function and soft threshold function, limiting its further application in order to overcome this shortcoming, this paper proposes a new threshold function, compared with the original threshold function, a new threshold function is simple and easy to calculate, not only with the soft threshold function is continuous. To deal with this drawback, we integrate the NN to enhance the model. Neural network belongs to the basic unsupervised learning of neural networks, the principle of competition based on the mechanism of learning and biological and the memory capacity can be increased as the number of learning patterns increases, not only offi ine learning can also be carried out on-line ＂learning while learning＂ type. The integrated algorithm can host better performance.
文摘This paper presents a method of determining the friction coefficient in metal forming using multilayer artificial neural networks based on experimental data obtained from strip drawing test.The number of input variables of the artificial neural network has been optimized using genetic algorithm.This process is based on surface parameters of the sheet and dies,sheet material parameters and clamping force as input parameters to train the neural network.In addition to demonstrating the fact that regression statistics model using genetic selection and intelligent problem solver are better than models without preprocessing of input data,the sensitivity analysis of the input variables has been conducted.This avoids the time-consuming testing of neurons in finding the best network architecture.The obtained results from this study have also pointed out that genetic algorithm can successfully be applied to optimize the training set and the outputs agree with experimental results.This allows reduction or elimination of expensive experimental tests to determine friction coefficient value.
基金supported by the National Natural Science Foundation of China(Nos.61974164,62074166,62004219,62004220,and 62104256).
文摘Artificial neural networks(ANNs)have led to landmark changes in many fields,but they still differ significantly fromthemechanisms of real biological neural networks and face problems such as high computing costs,excessive computing power,and so on.Spiking neural networks(SNNs)provide a new approach combined with brain-like science to improve the computational energy efficiency,computational architecture,and biological credibility of current deep learning applications.In the early stage of development,its poor performance hindered the application of SNNs in real-world scenarios.In recent years,SNNs have made great progress in computational performance and practicability compared with the earlier research results,and are continuously producing significant results.Although there are already many pieces of literature on SNNs,there is still a lack of comprehensive review on SNNs from the perspective of improving performance and practicality as well as incorporating the latest research results.Starting from this issue,this paper elaborates on SNNs along the complete usage process of SNNs including network construction,data processing,model training,development,and deployment,aiming to provide more comprehensive and practical guidance to promote the development of SNNs.Therefore,the connotation and development status of SNNcomputing is reviewed systematically and comprehensively from four aspects:composition structure,data set,learning algorithm,software/hardware development platform.Then the development characteristics of SNNs in intelligent computing are summarized,the current challenges of SNNs are discussed and the future development directions are also prospected.Our research shows that in the fields of machine learning and intelligent computing,SNNs have comparable network scale and performance to ANNs and the ability to challenge large datasets and a variety of tasks.The advantages of SNNs over ANNs in terms of energy efficiency and spatial-temporal data processing have been more fully exploited.And the development of programming and deployment tools has lowered the threshold for the use of SNNs.SNNs show a broad development prospect for brain-like computing.
基金supported by the National Key Research and Development Program of China [grant number2017YFA0604500]
文摘Wind speed forecasting is of great importance for wind farm management and plays an important role in grid integration. Wind speed is volatile in nature and therefore it is difficult to predict with a single model. In this study, three hybrid multi-step wind speed forecasting models are developed and compared — with each other and with earlier proposed wind speed forecasting models. The three models are based on wavelet decomposition(WD), the Cuckoo search(CS) optimization algorithm, and a wavelet neural network(WNN). They are referred to as CS-WD-ANN(artificial neural network), CS-WNN, and CS-WD-WNN, respectively. Wind speed data from two wind farms located in Shandong, eastern China, are used in this study. The simulation result indicates that CS-WD-WNN outperforms the other two models, with minimum statistical errors. Comparison with earlier models shows that CS-WD-WNN still performs best, with the smallest statistical errors. The employment of the CS optimization algorithm in the models shows improvement compared with the earlier models.
