In this paper,a new study concerning the usage of artificial neural networks in the control application is given.It is shown,that the data gathered during proper operation of a given control plant can be used in the l...In this paper,a new study concerning the usage of artificial neural networks in the control application is given.It is shown,that the data gathered during proper operation of a given control plant can be used in the learning process to fully embrace the control pattern.Interestingly,the instances driven by neural networks have the ability to outperform the original analytically driven scenarios.Three different control schemes,namely perfect,linear-quadratic,and generalized predictive controllers were used in the theoretical study.In addition,the nonlinear recurrent neural network-based generalized predictive controller with the radial basis function-originated predictor was obtained to exemplify the main results of the paper regarding the real-world application.展开更多
The precise measurement of the antineutrino spectra produced by isotope fission in reactors is of great significance for studying neutrino oscillations,refining nuclear databases,and addressing the reactor antineutrin...The precise measurement of the antineutrino spectra produced by isotope fission in reactors is of great significance for studying neutrino oscillations,refining nuclear databases,and addressing the reactor antineutrino anomaly.In this paper,we report a method that utilizes a feedforward neural network(FNN)model to decompose the prompt energy spectrum observed in a short-baseline reactor neutrino experiment and extract the antineutrino spectra produced by the fission of major isotopes such as^(235)U,^(238)U,^(239)Pu,and^(241)Pu in the nuclear reactor.We present two training strategies for the model and compare them with the traditional X^(2) minimization method by applying them to the same set of pseudo-data corresponding to a total exposure of(2.9×5×1800)GW_(th)·tons·days.The results show that the FNN model not only converges faster and better during the fitting process but also achieves relative errors of less than 1%in the 2−8 MeV range in the extracted spectra,outperforming the X^(2) minimization method.The feasibility and superiority of this method were validated in the study.展开更多
Enhancing the accuracy of real-time ship roll prediction is crucial for maritime safety and operational efficiency.To address the challenge of accurately predicting the ship roll status with nonlinear time-varying dyn...Enhancing the accuracy of real-time ship roll prediction is crucial for maritime safety and operational efficiency.To address the challenge of accurately predicting the ship roll status with nonlinear time-varying dynamic characteristics,a real-time ship roll prediction scheme is proposed on the basis of a data preprocessing strategy and a novel stochastic trainer-based feedforward neural network.The sliding data window serves as a ship time-varying dynamic observer to enhance model prediction stability.The variational mode decomposition method extracts effective information on ship roll motion and reduces the non-stationary characteristics of the series.The energy entropy method reconstructs the mode components into high-frequency,medium-frequency,and low-frequency series to reduce model complexity.An improved black widow optimization algorithm trainer-based feedforward neural network with enhanced local optimal avoidance predicts the high-frequency component,enabling accurate tracking of abrupt signals.Additionally,the deterministic algorithm trainer-based neural network,characterized by rapid processing speed,predicts the remaining two mode components.Thus,real-time ship roll forecasting can be achieved through the reconstruction of mode component prediction results.The feasibility and effectiveness of the proposed hybrid prediction scheme for ship roll motion are demonstrated through the measured data of a full-scale ship trial.The proposed prediction scheme achieves real-time ship roll prediction with superior prediction accuracy.展开更多
This paper studies the generalization capability of feedforward neural networks (FNN).The mechanism of FNNs for classification is investigated from the geometric and probabilistic viewpoints. It is pointed out that th...This paper studies the generalization capability of feedforward neural networks (FNN).The mechanism of FNNs for classification is investigated from the geometric and probabilistic viewpoints. It is pointed out that the outputs of the output layer in the FNNs for classification correspond to the estimates of posteriori probability of the input pattern samples with desired outputs 1 or 0. The theorem for the generalized kernel function in the radial basis function networks (RBFN) is given. For an 2-layer perceptron network (2-LPN). an idea of using extended samples to improve generalization capability is proposed. Finally. the experimental results of radar target classification are given to verify the generaliztion capability of the RBFNs.展开更多
As it is well known,it is difficult to identify a nonlinear time varying system using traditional identification approaches,especially under unknown nonlinear function.Neural networks have recently emerged as a succes...As it is well known,it is difficult to identify a nonlinear time varying system using traditional identification approaches,especially under unknown nonlinear function.Neural networks have recently emerged as a successful tool in the area of identification and control of time invariant nonlinear systems.However,it is still difficult to apply them to complicated time varying system identification.In this paper we present a learning algorithm for identification of the nonlinear time varying system using feedforward neural networks.The main idea of this approach is that we regard the weights of the network as a state of a time varying system,then use a Kalman filter to estimate the state.Thus the network implements nonlinear and time varying mapping.We derived both the global and local learning algorithms.Simulation results demonstrate the effectiveness of this approach.展开更多
In modern wireless communication systems,the accurate acquisition of channel state information(CSI)is critical to the performance of beamforming,non-orthogonal multiple access(NOMA),etc.However,with the application of...In modern wireless communication systems,the accurate acquisition of channel state information(CSI)is critical to the performance of beamforming,non-orthogonal multiple access(NOMA),etc.However,with the application of massive MIMO in 5G,the number of antennas increases by hundreds or even thousands times,which leads to excessive feedback overhead and poses a huge challenge to the conventional channel state information feedback scheme.In this paper,by using deep learning technology,we develop a system framework for CSI feedback based on fully connected feedforward neural networks(FCFNN),named CF-FCFNN.Through learning the training set composed of CSI,CF-FCFNN is able to recover the original CSI from the compressed CSI more accurately compared with the existing method based on deep learning without increasing the algorithm complexity.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
Global navigation satellite system-reflection(GNSS-R)sea surface altimetry based on satellite constellation platforms has become a new research direction and inevitable trend,which can meet the altimetric precision at...Global navigation satellite system-reflection(GNSS-R)sea surface altimetry based on satellite constellation platforms has become a new research direction and inevitable trend,which can meet the altimetric precision at the global scale required for underwater navigation.At present,there are still research gaps for GNSS-R altimetry under this mode,and its altimetric capability cannot be specifically assessed.Therefore,GNSS-R satellite constellations that meet the global altimetry needs to be designed.Meanwhile,the matching precision prediction model needs to be established to quantitatively predict the GNSS-R constellation altimetric capability.Firstly,the GNSS-R constellations altimetric precision under different configuration parameters is calculated,and the mechanism of the influence of orbital altitude,orbital inclination,number of satellites and simulation period on the precision is analyzed,and a new multilayer feedforward neural network weighted joint prediction model is established.Secondly,the fit of the prediction model is verified and the performance capability of the model is tested by calculating the R2 value of the model as 0.9972 and the root mean square error(RMSE)as 0.0022,which indicates that the prediction capability of the model is excellent.Finally,using the novel multilayer feedforward neural network weighted joint prediction model,and considering the research results and realistic costs,it is proposed that when the constellation is set to an orbital altitude of 500 km,orbital inclination of 75and the number of satellites is 6,the altimetry precision can reach 0.0732 m within one year simulation period,which can meet the requirements of underwater navigation precision,and thus can provide a reference basis for subsequent research on spaceborne GNSS-R sea surface altimetry.展开更多
Freezing of gait is a significant and debilitating motor symptom often observed in individuals with Parkinson's disease.Resting-state functional magnetic resonance imaging,along with its multi-level feature indice...Freezing of gait is a significant and debilitating motor symptom often observed in individuals with Parkinson's disease.Resting-state functional magnetic resonance imaging,along with its multi-level feature indices,has provided a fresh perspective and valuable insight into the study of freezing of gait in Parkinson's disease.It has been revealed that Parkinson's disease is accompanied by widespread irregularities in inherent brain network activity.However,the effective integration of the multi-level indices of resting-state functional magnetic resonance imaging into clinical settings for the diagnosis of freezing of gait in Parkinson's disease remains a challenge.Although previous studies have demonstrated that radiomics can extract optimal features as biomarkers to identify or predict diseases,a knowledge gap still exists in the field of freezing of gait in Parkinson's disease.This cross-sectional study aimed to evaluate the ability of radiomics features based on multi-level indices of resting-state functional magnetic resonance imaging,along with clinical features,to distinguish between Parkinson's disease patients with and without freezing of gait.We recruited 28 patients with Parkinson's disease who had freezing of gait(15 men and 13 women,average age 63 years)and 30 patients with Parkinson's disease who had no freezing of gait(16 men and 14 women,average age 64 years).Magnetic resonance imaging scans were obtained using a 3.0T scanner to extract the mean amplitude of low-frequency fluctuations,mean regional homogeneity,and degree centrality.Neurological and clinical characteristics were also evaluated.We used the least absolute shrinkage and selection operator algorithm to extract features and established feedforward neural network models based solely on resting-state functional magnetic resonance imaging indicators.We then performed predictive analysis of three distinct groups based on resting-state functional magnetic resonance imaging indicators indicators combined with clinical features.Subsequently,we conducted 100 additional five-fold cross-validations to determine the most effective model for each classification task and evaluated the performance of the model using the area under the receiver operating characteristic curve.The results showed that when differentiating patients with Parkinson's disease who had freezing of gait from those who did not have freezing of gait,or from healthy controls,the models using only the mean regional homogeneity values achieved the highest area under the receiver operating characteristic curve values of 0.750(with an accuracy of 70.9%)and 0.759(with an accuracy of 65.3%),respectively.When classifying patients with Parkinson's disease who had freezing of gait from those who had no freezing of gait,the model using the mean amplitude of low-frequency fluctuation values combined with two clinical features achieved the highest area under the receiver operating characteristic curve of 0.847(with an accuracy of 74.3%).The most significant features for patients with Parkinson's disease who had freezing of gait were amplitude of low-frequency fluctuation alterations in the left parahippocampal gyrus and two clinical characteristics:Montreal Cognitive Assessment and Hamilton Depression Scale scores.Our findings suggest that radiomics features derived from resting-state functional magnetic resonance imaging indices and clinical information can serve as valuable indices for the identification of freezing of gait in Parkinson's disease.展开更多
The problem of effluent total nitrogen(TN)at most of the wastewater treatment plants(WWTPs)in China is important for meeting the related water quality standards,even under the condition of high energy consumption.To a...The problem of effluent total nitrogen(TN)at most of the wastewater treatment plants(WWTPs)in China is important for meeting the related water quality standards,even under the condition of high energy consumption.To achieve better prediction and control of effluent TN concentration,an efficient prediction model,based on controllable operation parameters,was constructed in a sequencing batch reactor process.Compared with previous models,this model has two main characteristics:①Superficial gas velocity and anoxic time are controllable operation parameters and are selected as the main input parameters instead of dissolved oxygen to improve the model controllability,and②the model prediction accuracy is improved on the basis of a feedforward neural network(FFNN)with algorithm optimization.The results demonstrated that the FFNN model was efficiently optimized by scaled conjugate gradient,and the performance was excellent compared with other models in terms of the correlation coefficient(R).The optimized FFNN model could provide an accurate prediction of effluent TN based on influent water parameters and key control parameters.This study revealed the possible application of the optimized FFNN model for the efficient removal of pollutants and lower energy consumption at most of the WWTPs.展开更多
Using numerical simulations, we explore the mechanism for propagation of rate signals through a 10-layer feed-forward network composed of Hodgkin-Huxley （HH） neurons with sparse connectivity. When white noise is aff...Using numerical simulations, we explore the mechanism for propagation of rate signals through a 10-layer feed-forward network composed of Hodgkin-Huxley （HH） neurons with sparse connectivity. When white noise is afferent to the input layer, neuronal firing becomes progressively more synchronous in successive layers and synchrony is well developed in deeper layers owing to the feedforward connections between neighboring layers. The synchrony ensures the successful propagation of rate signals through the network when the synaptic conductance is weak. As the synaptic time constant Tsyn varies, coherence resonance is observed in the network activity due to the intrinsic property of HH neurons. This makes the output firing rate single-peaked as a function of Tsyn, suggesting that the signal propagation can be modulated by the synaptic time constant. These results are consistent with experimental results and advance our understanding of how information is processed in feedforward networks.展开更多
Online gradient methods are widely used for training the weight of neural networks and for other engineering computations. In certain cases, the resulting weight may become very large, causing difficulties in the impl...Online gradient methods are widely used for training the weight of neural networks and for other engineering computations. In certain cases, the resulting weight may become very large, causing difficulties in the implementation of the network by electronic circuits. In this paper we introduce a punishing term into the error function of the training procedure to prevent this situation. The corresponding convergence of the iterative training procedure and the boundedness of the weight sequence are proved. A supporting numerical example is also provided.展开更多
A comparison of construction forms and base functions is made between feedforward neural network and wavelet network. The relations between them are studied from the constructions of wavelet functions or dilation func...A comparison of construction forms and base functions is made between feedforward neural network and wavelet network. The relations between them are studied from the constructions of wavelet functions or dilation functions in wavelet network by different activation functions in feedforward neural network. It is concluded that some wavelet function is equal to the linear combination of several neurons in feedforward neural network.展开更多
Artificial Neural Networks(ANNs)are used in numerous engineering and scientific disciplines as an automated approach to resolve a number of problems.However,to build an artificial neural network that is prudent enough...Artificial Neural Networks(ANNs)are used in numerous engineering and scientific disciplines as an automated approach to resolve a number of problems.However,to build an artificial neural network that is prudent enough to rely on,vast quantities of relevant data have to be fed.In this study,we analysed the scope of artificial neural networks in geothermal reservoir architecture.In particular,we attempted to solve joint inversion problem through Feedforward Neural Network(FNN)technique.In order to identify geothermal sweet spots in the subsurface,an extensive geophysical studies were conducted in Gandhar area of Gujarat,India.The data were acquired along six profile lines for gravity,magnetics and magnetotellurics.Initially low velocity zone was identified using refraction seismic technique in order to set a common datum level for other potential data.The depth of low velocity zone in Gandhar was identified at 11 m.The FNN backpropagation method was applied to gain the global minima of the data space and model space as desired.The input dataset fed to the inversion algorithm in the form of gravity,magnetic susceptibility and resistivity helped to predict the suitable model after network training in multiple steps.The joint inversion of data is conducive to understanding the subsurface geological and lithological features along with probable geothermal sweet spots.The results of this study show the geothermal sweet spots at depth ranging from 200 m to 300 m.The results from our study can be used for targeted zones for geothermal water exploitation.展开更多
A hybrid algorithm to design the multi layer feedforward neural network was proposed. Evolutionary programming is used to design the network that makes the training process tending to global optima. Artificial immunol...A hybrid algorithm to design the multi layer feedforward neural network was proposed. Evolutionary programming is used to design the network that makes the training process tending to global optima. Artificial immunology combined with simulated annealing algorithm is used to specify the initial weight vectors, therefore improves the probabiligy of training algorithm to converge to global optima. The applications of the neural network in the modulation style recognition of analog modulated rader signals demonstrate the good performance of the network.展开更多
The increasing demand for sustainable construction practices has led to growing interest in recycled aggregate concrete(RAC)as an eco-friendly alternative to conventional concrete.However,predicting its compressive st...The increasing demand for sustainable construction practices has led to growing interest in recycled aggregate concrete(RAC)as an eco-friendly alternative to conventional concrete.However,predicting its compressive strength remains a challenge due to the variability in recycled materials and mix design parameters.This study presents a robust machine learning framework for predicting the compressive strength of recycled aggregate concrete using feedforward neural networks(FFNN),Random Forest(RF),and XGBoost.A literature-derived dataset of 502 samples was enriched via interpolation-based data augmentation and modeled using five distinct optimization techniques within MATLAB’s Neural Net Fitting module:Bayesian Regularization,Levenberg-Marquardt,and three conjugate gradient variants—Powell/Beale Restarts,Fletcher-Powell,and Polak-Ribiere.Hyperparameter tuning,dropout regularization,and early stopping were employed to enhance generalization.Comparative analysis revealed that FFNN outperformed RF and XGBoost,achieving an R2 of 0.9669.To ensure interpretability,accumulated local effects(ALE)along with partial dependence plots(PDP)were utilized.This revealed trends consistent with the pre-existent domain knowledge.This allows estimation of strength from the properties of the mix without extensive lab testing,permitting designers to track the performance and sustainability trends in concrete mix designs while promoting responsible construction and demolition waste utilization.展开更多
This paper investigates the motion control of the heavy-duty Bionic Caterpillar-like Robot(BCR)for the maintenance of the China Fusion Engineering Test Reactor(CFETR).Initially,a comprehensive nonlinear mathematical m...This paper investigates the motion control of the heavy-duty Bionic Caterpillar-like Robot(BCR)for the maintenance of the China Fusion Engineering Test Reactor(CFETR).Initially,a comprehensive nonlinear mathematical model for the BCR system is formulated using a physics-based approach.The nonlinear components of the model are compensated through nonlinear feedback linearization.Subsequently,a fuzzy-based regulator is employed to enhance the receding horizon opti-mization process for achieving optimal results.A Deep Neural Network(DNN)is trained to address disturbances.Conse-quently,a novel hybrid controller incorporating Nonlinear Model Predictive Control(NMPC),the Fuzzy Regulator(FR),and Deep Neural Network Feedforward(DNNF),named NMPC-FRDNNF is developed.Finally,the efficacy of the control system is validated through simulations and experiments.The results indicate that the Root Mean Square Error(RMSE)of the controller with FR and DNNF decreases by 33.2 and 48.9%,respectively,compared to the controller without these enhancements.This research provides a theoretical foundation and practical insights for ensuring the future highly stable,safe,and efficient maintenance of blankets.展开更多
In this study,a feedforward neural network(FNN)approach is employed to optimize three local mass models(GK,GKs,and GK+J).We find that adding physical quantities related to the pairing effect in the input layer can eff...In this study,a feedforward neural network(FNN)approach is employed to optimize three local mass models(GK,GKs,and GK+J).We find that adding physical quantities related to the pairing effect in the input layer can effectively improve the prediction accuracy of local models.For the known masses in AME2012,the FNN reduces the root-mean-square deviation between theory and experiment for the three mass models by 11 keV,32 keV,and 623 keV.Among them,the improvement effect of the light mass region with mass number between 16 and 60 is better than that of medium and heavy mass regions.The approach also has good optimization results when extrapolating AME2012 to AME2020 and the latest measured masses after AME2020.Based on the improved mass data,the separation energies for single-and two-proton(neutron)emissions andα-decay energies are obtained,which agree well with the experiment.展开更多
A discussion is given on the convergence of the on-line gradient methods for two-layer feedforward neural networks in general cases. The theories are applied to some usual activation functions and energy functions.
The estimated ultimate recovery(EUR)of shale gas wells is influenced by many factors,and the accurate prediction still faces certain challenges.As an artificial intelligence algorithm,deep learning yields notable adva...The estimated ultimate recovery(EUR)of shale gas wells is influenced by many factors,and the accurate prediction still faces certain challenges.As an artificial intelligence algorithm,deep learning yields notable advantages in nonlinear regression.Therefore,it is feasible to predict the EUR of shale gas wells based on a deep-learning algorithm.In this paper,according to geological evaluation data,hydraulic fracturing data,production data and EUR evaluation results of 282 wells in the WY shale gas field,a deep-learning-based algorithm for EUR evaluation of shale gas wells was designed and realized.First,the existing EUR evaluation methods of shale gas wells and the deep feedforward neural network algorithm was systematically analyzed.Second,the technical process of a deep-learning-based algorithm for EUR prediction of shale gas wells was designed.Finally,by means of real data obtained from the WY shale gas field,several different cases were applied to testify the validity and accuracy of the proposed approach.The results show that the EUR prediction with high accuracy.In addition,the results are affected by the variety and number of input parameters,the network structure and hyperparameters.The proposed approach can be extended to other shale fields using the similar technic process.展开更多
文摘In this paper,a new study concerning the usage of artificial neural networks in the control application is given.It is shown,that the data gathered during proper operation of a given control plant can be used in the learning process to fully embrace the control pattern.Interestingly,the instances driven by neural networks have the ability to outperform the original analytically driven scenarios.Three different control schemes,namely perfect,linear-quadratic,and generalized predictive controllers were used in the theoretical study.In addition,the nonlinear recurrent neural network-based generalized predictive controller with the radial basis function-originated predictor was obtained to exemplify the main results of the paper regarding the real-world application.
基金supported by the China Postdoctoral Science Foundation(No.2024M753715)Fundamental Research Funds for the Central Universities,Sun Yat-sen University(Nos.24qnpy125 and 22lglj11)Guangdong Basic and Applied Basic Research Foundation(No.2023B1515120030).
文摘The precise measurement of the antineutrino spectra produced by isotope fission in reactors is of great significance for studying neutrino oscillations,refining nuclear databases,and addressing the reactor antineutrino anomaly.In this paper,we report a method that utilizes a feedforward neural network(FNN)model to decompose the prompt energy spectrum observed in a short-baseline reactor neutrino experiment and extract the antineutrino spectra produced by the fission of major isotopes such as^(235)U,^(238)U,^(239)Pu,and^(241)Pu in the nuclear reactor.We present two training strategies for the model and compare them with the traditional X^(2) minimization method by applying them to the same set of pseudo-data corresponding to a total exposure of(2.9×5×1800)GW_(th)·tons·days.The results show that the FNN model not only converges faster and better during the fitting process but also achieves relative errors of less than 1%in the 2−8 MeV range in the extracted spectra,outperforming the X^(2) minimization method.The feasibility and superiority of this method were validated in the study.
基金supported by the National Natural Science Foundation of China(Grant Nos.52231014 and 52271361)the Natural Science Foundation of Guangdong Province of China(Grant No.2023A1515010684).
文摘Enhancing the accuracy of real-time ship roll prediction is crucial for maritime safety and operational efficiency.To address the challenge of accurately predicting the ship roll status with nonlinear time-varying dynamic characteristics,a real-time ship roll prediction scheme is proposed on the basis of a data preprocessing strategy and a novel stochastic trainer-based feedforward neural network.The sliding data window serves as a ship time-varying dynamic observer to enhance model prediction stability.The variational mode decomposition method extracts effective information on ship roll motion and reduces the non-stationary characteristics of the series.The energy entropy method reconstructs the mode components into high-frequency,medium-frequency,and low-frequency series to reduce model complexity.An improved black widow optimization algorithm trainer-based feedforward neural network with enhanced local optimal avoidance predicts the high-frequency component,enabling accurate tracking of abrupt signals.Additionally,the deterministic algorithm trainer-based neural network,characterized by rapid processing speed,predicts the remaining two mode components.Thus,real-time ship roll forecasting can be achieved through the reconstruction of mode component prediction results.The feasibility and effectiveness of the proposed hybrid prediction scheme for ship roll motion are demonstrated through the measured data of a full-scale ship trial.The proposed prediction scheme achieves real-time ship roll prediction with superior prediction accuracy.
文摘This paper studies the generalization capability of feedforward neural networks (FNN).The mechanism of FNNs for classification is investigated from the geometric and probabilistic viewpoints. It is pointed out that the outputs of the output layer in the FNNs for classification correspond to the estimates of posteriori probability of the input pattern samples with desired outputs 1 or 0. The theorem for the generalized kernel function in the radial basis function networks (RBFN) is given. For an 2-layer perceptron network (2-LPN). an idea of using extended samples to improve generalization capability is proposed. Finally. the experimental results of radar target classification are given to verify the generaliztion capability of the RBFNs.
基金National Natural Science Foundation of China!(No.6 97740 33)
文摘As it is well known,it is difficult to identify a nonlinear time varying system using traditional identification approaches,especially under unknown nonlinear function.Neural networks have recently emerged as a successful tool in the area of identification and control of time invariant nonlinear systems.However,it is still difficult to apply them to complicated time varying system identification.In this paper we present a learning algorithm for identification of the nonlinear time varying system using feedforward neural networks.The main idea of this approach is that we regard the weights of the network as a state of a time varying system,then use a Kalman filter to estimate the state.Thus the network implements nonlinear and time varying mapping.We derived both the global and local learning algorithms.Simulation results demonstrate the effectiveness of this approach.
基金This work was supported by the Key Research and Development Project of Shaanxi Province under Grant no.2019ZDLGY07-07.
文摘In modern wireless communication systems,the accurate acquisition of channel state information(CSI)is critical to the performance of beamforming,non-orthogonal multiple access(NOMA),etc.However,with the application of massive MIMO in 5G,the number of antennas increases by hundreds or even thousands times,which leads to excessive feedback overhead and poses a huge challenge to the conventional channel state information feedback scheme.In this paper,by using deep learning technology,we develop a system framework for CSI feedback based on fully connected feedforward neural networks(FCFNN),named CF-FCFNN.Through learning the training set composed of CSI,CF-FCFNN is able to recover the original CSI from the compressed CSI more accurately compared with the existing method based on deep learning without increasing the algorithm complexity.
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.
基金the National Natural Science Foundation of China under Grant(42274119)the Liaoning Revitalization Talents Program under Grant(XLYC2002082)+1 种基金National Key Research and Development Plan Key Special Projects of Science and Technology Military Civil Integration(2022YFF1400500)the Key Project of Science and Technology Commission of the Central Military Commission.
文摘Global navigation satellite system-reflection(GNSS-R)sea surface altimetry based on satellite constellation platforms has become a new research direction and inevitable trend,which can meet the altimetric precision at the global scale required for underwater navigation.At present,there are still research gaps for GNSS-R altimetry under this mode,and its altimetric capability cannot be specifically assessed.Therefore,GNSS-R satellite constellations that meet the global altimetry needs to be designed.Meanwhile,the matching precision prediction model needs to be established to quantitatively predict the GNSS-R constellation altimetric capability.Firstly,the GNSS-R constellations altimetric precision under different configuration parameters is calculated,and the mechanism of the influence of orbital altitude,orbital inclination,number of satellites and simulation period on the precision is analyzed,and a new multilayer feedforward neural network weighted joint prediction model is established.Secondly,the fit of the prediction model is verified and the performance capability of the model is tested by calculating the R2 value of the model as 0.9972 and the root mean square error(RMSE)as 0.0022,which indicates that the prediction capability of the model is excellent.Finally,using the novel multilayer feedforward neural network weighted joint prediction model,and considering the research results and realistic costs,it is proposed that when the constellation is set to an orbital altitude of 500 km,orbital inclination of 75and the number of satellites is 6,the altimetry precision can reach 0.0732 m within one year simulation period,which can meet the requirements of underwater navigation precision,and thus can provide a reference basis for subsequent research on spaceborne GNSS-R sea surface altimetry.
基金supported by the National Natural Science Foundation of China,No.82071909(to GF)the Natural Science Foundation of Liaoning Province,No.2023-MS-07(to HL)。
文摘Freezing of gait is a significant and debilitating motor symptom often observed in individuals with Parkinson's disease.Resting-state functional magnetic resonance imaging,along with its multi-level feature indices,has provided a fresh perspective and valuable insight into the study of freezing of gait in Parkinson's disease.It has been revealed that Parkinson's disease is accompanied by widespread irregularities in inherent brain network activity.However,the effective integration of the multi-level indices of resting-state functional magnetic resonance imaging into clinical settings for the diagnosis of freezing of gait in Parkinson's disease remains a challenge.Although previous studies have demonstrated that radiomics can extract optimal features as biomarkers to identify or predict diseases,a knowledge gap still exists in the field of freezing of gait in Parkinson's disease.This cross-sectional study aimed to evaluate the ability of radiomics features based on multi-level indices of resting-state functional magnetic resonance imaging,along with clinical features,to distinguish between Parkinson's disease patients with and without freezing of gait.We recruited 28 patients with Parkinson's disease who had freezing of gait(15 men and 13 women,average age 63 years)and 30 patients with Parkinson's disease who had no freezing of gait(16 men and 14 women,average age 64 years).Magnetic resonance imaging scans were obtained using a 3.0T scanner to extract the mean amplitude of low-frequency fluctuations,mean regional homogeneity,and degree centrality.Neurological and clinical characteristics were also evaluated.We used the least absolute shrinkage and selection operator algorithm to extract features and established feedforward neural network models based solely on resting-state functional magnetic resonance imaging indicators.We then performed predictive analysis of three distinct groups based on resting-state functional magnetic resonance imaging indicators indicators combined with clinical features.Subsequently,we conducted 100 additional five-fold cross-validations to determine the most effective model for each classification task and evaluated the performance of the model using the area under the receiver operating characteristic curve.The results showed that when differentiating patients with Parkinson's disease who had freezing of gait from those who did not have freezing of gait,or from healthy controls,the models using only the mean regional homogeneity values achieved the highest area under the receiver operating characteristic curve values of 0.750(with an accuracy of 70.9%)and 0.759(with an accuracy of 65.3%),respectively.When classifying patients with Parkinson's disease who had freezing of gait from those who had no freezing of gait,the model using the mean amplitude of low-frequency fluctuation values combined with two clinical features achieved the highest area under the receiver operating characteristic curve of 0.847(with an accuracy of 74.3%).The most significant features for patients with Parkinson's disease who had freezing of gait were amplitude of low-frequency fluctuation alterations in the left parahippocampal gyrus and two clinical characteristics:Montreal Cognitive Assessment and Hamilton Depression Scale scores.Our findings suggest that radiomics features derived from resting-state functional magnetic resonance imaging indices and clinical information can serve as valuable indices for the identification of freezing of gait in Parkinson's disease.
基金This work was funded by the Major Science and Technology Program for Water Pollution Control and Treatment(2017ZX07201003)the National Natural Science Foundation of China(51961125101)the Science and Technology Project of Zhejiang Province(2018C03003).
文摘The problem of effluent total nitrogen(TN)at most of the wastewater treatment plants(WWTPs)in China is important for meeting the related water quality standards,even under the condition of high energy consumption.To achieve better prediction and control of effluent TN concentration,an efficient prediction model,based on controllable operation parameters,was constructed in a sequencing batch reactor process.Compared with previous models,this model has two main characteristics:①Superficial gas velocity and anoxic time are controllable operation parameters and are selected as the main input parameters instead of dissolved oxygen to improve the model controllability,and②the model prediction accuracy is improved on the basis of a feedforward neural network(FFNN)with algorithm optimization.The results demonstrated that the FFNN model was efficiently optimized by scaled conjugate gradient,and the performance was excellent compared with other models in terms of the correlation coefficient(R).The optimized FFNN model could provide an accurate prediction of effluent TN based on influent water parameters and key control parameters.This study revealed the possible application of the optimized FFNN model for the efficient removal of pollutants and lower energy consumption at most of the WWTPs.
基金Project supported by the National Natural Science Foundation of China (Grant No 10614028)the National Key Basic Research Program of China (Grant No 2007CB814806)Program for New Century Excellent Talents in University of the Ministry of Education of China (Grant No NCET-08-0269)
文摘Using numerical simulations, we explore the mechanism for propagation of rate signals through a 10-layer feed-forward network composed of Hodgkin-Huxley （HH） neurons with sparse connectivity. When white noise is afferent to the input layer, neuronal firing becomes progressively more synchronous in successive layers and synchrony is well developed in deeper layers owing to the feedforward connections between neighboring layers. The synchrony ensures the successful propagation of rate signals through the network when the synaptic conductance is weak. As the synaptic time constant Tsyn varies, coherence resonance is observed in the network activity due to the intrinsic property of HH neurons. This makes the output firing rate single-peaked as a function of Tsyn, suggesting that the signal propagation can be modulated by the synaptic time constant. These results are consistent with experimental results and advance our understanding of how information is processed in feedforward networks.
文摘Online gradient methods are widely used for training the weight of neural networks and for other engineering computations. In certain cases, the resulting weight may become very large, causing difficulties in the implementation of the network by electronic circuits. In this paper we introduce a punishing term into the error function of the training procedure to prevent this situation. The corresponding convergence of the iterative training procedure and the boundedness of the weight sequence are proved. A supporting numerical example is also provided.
基金Supported by the National Natural Science Foundatipn of China (No. 59977019).
文摘A comparison of construction forms and base functions is made between feedforward neural network and wavelet network. The relations between them are studied from the constructions of wavelet functions or dilation functions in wavelet network by different activation functions in feedforward neural network. It is concluded that some wavelet function is equal to the linear combination of several neurons in feedforward neural network.
文摘Artificial Neural Networks(ANNs)are used in numerous engineering and scientific disciplines as an automated approach to resolve a number of problems.However,to build an artificial neural network that is prudent enough to rely on,vast quantities of relevant data have to be fed.In this study,we analysed the scope of artificial neural networks in geothermal reservoir architecture.In particular,we attempted to solve joint inversion problem through Feedforward Neural Network(FNN)technique.In order to identify geothermal sweet spots in the subsurface,an extensive geophysical studies were conducted in Gandhar area of Gujarat,India.The data were acquired along six profile lines for gravity,magnetics and magnetotellurics.Initially low velocity zone was identified using refraction seismic technique in order to set a common datum level for other potential data.The depth of low velocity zone in Gandhar was identified at 11 m.The FNN backpropagation method was applied to gain the global minima of the data space and model space as desired.The input dataset fed to the inversion algorithm in the form of gravity,magnetic susceptibility and resistivity helped to predict the suitable model after network training in multiple steps.The joint inversion of data is conducive to understanding the subsurface geological and lithological features along with probable geothermal sweet spots.The results of this study show the geothermal sweet spots at depth ranging from 200 m to 300 m.The results from our study can be used for targeted zones for geothermal water exploitation.
文摘A hybrid algorithm to design the multi layer feedforward neural network was proposed. Evolutionary programming is used to design the network that makes the training process tending to global optima. Artificial immunology combined with simulated annealing algorithm is used to specify the initial weight vectors, therefore improves the probabiligy of training algorithm to converge to global optima. The applications of the neural network in the modulation style recognition of analog modulated rader signals demonstrate the good performance of the network.
基金supported and funded by the Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University(IMSIU)(grant number IMSIU-DDRSP2503)。
文摘The increasing demand for sustainable construction practices has led to growing interest in recycled aggregate concrete(RAC)as an eco-friendly alternative to conventional concrete.However,predicting its compressive strength remains a challenge due to the variability in recycled materials and mix design parameters.This study presents a robust machine learning framework for predicting the compressive strength of recycled aggregate concrete using feedforward neural networks(FFNN),Random Forest(RF),and XGBoost.A literature-derived dataset of 502 samples was enriched via interpolation-based data augmentation and modeled using five distinct optimization techniques within MATLAB’s Neural Net Fitting module:Bayesian Regularization,Levenberg-Marquardt,and three conjugate gradient variants—Powell/Beale Restarts,Fletcher-Powell,and Polak-Ribiere.Hyperparameter tuning,dropout regularization,and early stopping were employed to enhance generalization.Comparative analysis revealed that FFNN outperformed RF and XGBoost,achieving an R2 of 0.9669.To ensure interpretability,accumulated local effects(ALE)along with partial dependence plots(PDP)were utilized.This revealed trends consistent with the pre-existent domain knowledge.This allows estimation of strength from the properties of the mix without extensive lab testing,permitting designers to track the performance and sustainability trends in concrete mix designs while promoting responsible construction and demolition waste utilization.
基金supported by Comprehensive Research Facility for Fusion Technology Program of China under Contract No.2018-000052-73-01-001228the China Scholarship Council with No.202206340050National Natural Science Foundation of China with Grant No.11905147.
文摘This paper investigates the motion control of the heavy-duty Bionic Caterpillar-like Robot(BCR)for the maintenance of the China Fusion Engineering Test Reactor(CFETR).Initially,a comprehensive nonlinear mathematical model for the BCR system is formulated using a physics-based approach.The nonlinear components of the model are compensated through nonlinear feedback linearization.Subsequently,a fuzzy-based regulator is employed to enhance the receding horizon opti-mization process for achieving optimal results.A Deep Neural Network(DNN)is trained to address disturbances.Conse-quently,a novel hybrid controller incorporating Nonlinear Model Predictive Control(NMPC),the Fuzzy Regulator(FR),and Deep Neural Network Feedforward(DNNF),named NMPC-FRDNNF is developed.Finally,the efficacy of the control system is validated through simulations and experiments.The results indicate that the Root Mean Square Error(RMSE)of the controller with FR and DNNF decreases by 33.2 and 48.9%,respectively,compared to the controller without these enhancements.This research provides a theoretical foundation and practical insights for ensuring the future highly stable,safe,and efficient maintenance of blankets.
基金Supported by National Natural Science Foundation of China(11875188)China Scholarship Council(202409390020)。
文摘In this study,a feedforward neural network(FNN)approach is employed to optimize three local mass models(GK,GKs,and GK+J).We find that adding physical quantities related to the pairing effect in the input layer can effectively improve the prediction accuracy of local models.For the known masses in AME2012,the FNN reduces the root-mean-square deviation between theory and experiment for the three mass models by 11 keV,32 keV,and 623 keV.Among them,the improvement effect of the light mass region with mass number between 16 and 60 is better than that of medium and heavy mass regions.The approach also has good optimization results when extrapolating AME2012 to AME2020 and the latest measured masses after AME2020.Based on the improved mass data,the separation energies for single-and two-proton(neutron)emissions andα-decay energies are obtained,which agree well with the experiment.
基金Supported by the Natural Science Foundation of China
文摘A discussion is given on the convergence of the on-line gradient methods for two-layer feedforward neural networks in general cases. The theories are applied to some usual activation functions and energy functions.
基金supported by the funding of National Science and Technology Major Projects of China(2016ZX05037-006-005,2016ZX05037-006,2016ZX05035-004)。
文摘The estimated ultimate recovery(EUR)of shale gas wells is influenced by many factors,and the accurate prediction still faces certain challenges.As an artificial intelligence algorithm,deep learning yields notable advantages in nonlinear regression.Therefore,it is feasible to predict the EUR of shale gas wells based on a deep-learning algorithm.In this paper,according to geological evaluation data,hydraulic fracturing data,production data and EUR evaluation results of 282 wells in the WY shale gas field,a deep-learning-based algorithm for EUR evaluation of shale gas wells was designed and realized.First,the existing EUR evaluation methods of shale gas wells and the deep feedforward neural network algorithm was systematically analyzed.Second,the technical process of a deep-learning-based algorithm for EUR prediction of shale gas wells was designed.Finally,by means of real data obtained from the WY shale gas field,several different cases were applied to testify the validity and accuracy of the proposed approach.The results show that the EUR prediction with high accuracy.In addition,the results are affected by the variety and number of input parameters,the network structure and hyperparameters.The proposed approach can be extended to other shale fields using the similar technic process.
