Information plays a crucial role in guiding behavioral decisions during public health emergencies. Individuals communicate to acquire relevant knowledge about an epidemic, which influences their decisions to adopt pro...Information plays a crucial role in guiding behavioral decisions during public health emergencies. Individuals communicate to acquire relevant knowledge about an epidemic, which influences their decisions to adopt protective measures.However, whether to disseminate specific information is also a behavioral decision. In light of this understanding, we develop a coupled information–vaccination–epidemic model to depict these co-evolutionary dynamics in a three-layer network. Negative information dissemination and vaccination are treated as separate decision-making processes. We then examine the combined effects of herd and risk motives on information dissemination and vaccination decisions through the lens of game theory. The microscopic Markov chain approach(MMCA) is used to describe the dynamic process and to derive the epidemic threshold. Simulation results indicate that increasing the cost of negative information dissemination and providing timely clarification can effectively control the epidemic. Furthermore, a phenomenon of diminishing marginal utility is observed as the cost of dissemination increases, suggesting that authorities do not need to overinvest in suppressing negative information. Conversely, reducing the cost of vaccination and increasing vaccine efficacy emerge as more effective strategies for outbreak control. In addition, we find that the scale of the epidemic is greater when the herd motive dominates behavioral decision-making. In conclusion, this study provides a new perspective for understanding the complexity of epidemic spreading by starting with the construction of different behavioral decisions.展开更多
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 proposes a neural network-based intelligent feedforward gust alleviation framework,which includes a neural network identification model and a neural network controller.A neural network training dataset is f...This paper proposes a neural network-based intelligent feedforward gust alleviation framework,which includes a neural network identification model and a neural network controller.A neural network training dataset is formed by collecting flight data and the gust data encountered during the aircraft flight.A neural network identification model is first trained to accurately predict the aircraft’s output.Then,based on the output of the identification model and the collected flight data,the parameters of the time-delay neural network controller are obtained through a learning process.The simulation results show that the designed intelligent controller has good gust alleviation effects for both continuous turbulence excitation and discrete gust excitation.For example,when the aircraft is 40000 kg and the flight speed is 0.81Ma,the controller achieves a 67.82%reduction in wingtip acceleration and a 35.90%reduction in center of mass acceleration under continuous turbulence excitation.When considering the measurement uncertainties,such as noise existing in the collected data,the trained controller can still achieve an acceptable gust alleviation effect.Finally,considering a flight in which the aircraft mass is constantly changing,the intelligent controller,which continuously learns from new flight data,maintains a good gust alleviation effect throughout the flight.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
Next generation grid systems where the emphasis shifts to distributed global collaboration, a service-oriented approach and information layer issues exhibit a strong sense of automation. Requirements for these systems...Next generation grid systems where the emphasis shifts to distributed global collaboration, a service-oriented approach and information layer issues exhibit a strong sense of automation. Requirements for these systems resemble the self-organizing and the healing properties of natural ecosystems. Some key ecological concepts and mechanisms are introduced into the design for the third generation grid computing architectures by inspiration of this resemblance. Also, an Ecological Network-based Computing Environment (ENCE) platform is designed in this paper. Based on the ENCE platform, a grid-computing model of three-layered grid conceptual prototype that embeds the ENCE layers is presented from the viewpoint of implementation. The implementation model should be useful to the design of the third generation grid systems.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
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
Siegenthaler’s“Correlation Immunity”concept has been improved in this paper.From practical points of view,the new concept is more powerful than the original one in avoid-ing the trade-off between“the order of corr...Siegenthaler’s“Correlation Immunity”concept has been improved in this paper.From practical points of view,the new concept is more powerful than the original one in avoid-ing the trade-off between“the order of correlation immunity”and“the linear complexity”of keystreams in cipher system.Bent functions are also introduced into the studies of linear approxima-tion and entropy immunity for feedforward networks.New results and new methods are presentedalso.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
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
Online gradient algorithm has been widely used as a learning algorithm for feedforward neural network training. In this paper, we prove a weak convergence theorem of an online gradient algorithm with a penalty term, a...Online gradient algorithm has been widely used as a learning algorithm for feedforward neural network training. In this paper, we prove a weak convergence theorem of an online gradient algorithm with a penalty term, assuming that the training examples are input in a stochastic way. The monotonicity of the error function in the iteration and the boundedness of the weight are both guaranteed. We also present a numerical experiment to support our results.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
The multilayer feedforward network is used for image segmentation. This paper deals with the procedure of achieving the learning patterns and the method of improving the learning rate. The experiment shows that the im...The multilayer feedforward network is used for image segmentation. This paper deals with the procedure of achieving the learning patterns and the method of improving the learning rate. The experiment shows that the image segmentation can get better result from using the multilayer feedforward network.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
基金Project supported by the National Natural Science Foundation of China (Grant No. 72174121)the Program for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning, and the Soft Science Research Project of Shanghai (Grant No. 22692112600)。
文摘Information plays a crucial role in guiding behavioral decisions during public health emergencies. Individuals communicate to acquire relevant knowledge about an epidemic, which influences their decisions to adopt protective measures.However, whether to disseminate specific information is also a behavioral decision. In light of this understanding, we develop a coupled information–vaccination–epidemic model to depict these co-evolutionary dynamics in a three-layer network. Negative information dissemination and vaccination are treated as separate decision-making processes. We then examine the combined effects of herd and risk motives on information dissemination and vaccination decisions through the lens of game theory. The microscopic Markov chain approach(MMCA) is used to describe the dynamic process and to derive the epidemic threshold. Simulation results indicate that increasing the cost of negative information dissemination and providing timely clarification can effectively control the epidemic. Furthermore, a phenomenon of diminishing marginal utility is observed as the cost of dissemination increases, suggesting that authorities do not need to overinvest in suppressing negative information. Conversely, reducing the cost of vaccination and increasing vaccine efficacy emerge as more effective strategies for outbreak control. In addition, we find that the scale of the epidemic is greater when the herd motive dominates behavioral decision-making. In conclusion, this study provides a new perspective for understanding the complexity of epidemic spreading by starting with the construction of different behavioral decisions.
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 proposes a neural network-based intelligent feedforward gust alleviation framework,which includes a neural network identification model and a neural network controller.A neural network training dataset is formed by collecting flight data and the gust data encountered during the aircraft flight.A neural network identification model is first trained to accurately predict the aircraft’s output.Then,based on the output of the identification model and the collected flight data,the parameters of the time-delay neural network controller are obtained through a learning process.The simulation results show that the designed intelligent controller has good gust alleviation effects for both continuous turbulence excitation and discrete gust excitation.For example,when the aircraft is 40000 kg and the flight speed is 0.81Ma,the controller achieves a 67.82%reduction in wingtip acceleration and a 35.90%reduction in center of mass acceleration under continuous turbulence excitation.When considering the measurement uncertainties,such as noise existing in the collected data,the trained controller can still achieve an acceptable gust alleviation effect.Finally,considering a flight in which the aircraft mass is constantly changing,the intelligent controller,which continuously learns from new flight data,maintains a good gust alleviation effect throughout the flight.
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 in part by the National Nature Science Foundation of China (No. 60474037 and 60004006) and Specialized Research Fund for the Doctoral Program of Higher Education from Educational Committee of China (No. 20030255009)
文摘Next generation grid systems where the emphasis shifts to distributed global collaboration, a service-oriented approach and information layer issues exhibit a strong sense of automation. Requirements for these systems resemble the self-organizing and the healing properties of natural ecosystems. Some key ecological concepts and mechanisms are introduced into the design for the third generation grid computing architectures by inspiration of this resemblance. Also, an Ecological Network-based Computing Environment (ENCE) platform is designed in this paper. Based on the ENCE platform, a grid-computing model of three-layered grid conceptual prototype that embeds the ENCE layers is presented from the viewpoint of implementation. The implementation model should be useful to the design of the third generation grid systems.
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 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.
基金Project supported by the Fund of National Natural Science for Yourth.
文摘Siegenthaler’s“Correlation Immunity”concept has been improved in this paper.From practical points of view,the new concept is more powerful than the original one in avoid-ing the trade-off between“the order of correlation immunity”and“the linear complexity”of keystreams in cipher system.Bent functions are also introduced into the studies of linear approxima-tion and entropy immunity for feedforward networks.New results and new methods are presentedalso.
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.
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.
基金Partly supported by the National Natural Science Foundation of China,and the Basic Research Program of the Committee of ScienceTechnology and Industry of National Defense of China.
文摘Online gradient algorithm has been widely used as a learning algorithm for feedforward neural network training. In this paper, we prove a weak convergence theorem of an online gradient algorithm with a penalty term, assuming that the training examples are input in a stochastic way. The monotonicity of the error function in the iteration and the boundedness of the weight are both guaranteed. We also present a numerical experiment to support our results.
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The multilayer feedforward network is used for image segmentation. This paper deals with the procedure of achieving the learning patterns and the method of improving the learning rate. The experiment shows that the image segmentation can get better result from using the multilayer feedforward network.
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.
