Soil macronutrients(i.e. nitrogen(N), phosphorus(P), and potassium(K)) are important soils components and knowing the spatial distribution of these parameters are necessary at precision agriculture. The purpose of thi...Soil macronutrients(i.e. nitrogen(N), phosphorus(P), and potassium(K)) are important soils components and knowing the spatial distribution of these parameters are necessary at precision agriculture. The purpose of this study was to evaluate the feasibility of different methods such as artificial neural networks(ANN) and two geostatistical methods(geographically weighted regression(GWR) and cokriging(CK)) to estimate N, P and K contents. For this purpose, soil samples were taken from topsoil(0–30 cm) at 106 points and analyzed for their chemical and physical parameters. These data were divided into calibration(n = 84) and validation(n = 22). Chemical and physical variables including clay, p H and organic carbon(OC) were used as auxiliary soil variables to estimate the N, P and K contents. Results showed that the ANN model(with coefficient of determination R^2 = 0.922 and root mean square error RMSE = 0.0079%) was more accurate compared to the CK model(with R^2 = 0.612 and RMSE = 0.0094%), and the GWR model(with R^2 = 0.872 and RMSE = 0.0089%) to estimate the N variable. The ANN model estimated the P with the RMSE of 3.630 ppm, which was respectively 28.93% and 20.00% less than the RMSE of 4.680 ppm and 4.357 ppm from the CK and GWR models. The estimated K by CK, GWR and ANN models have the RMSE of 76.794 ppm, 75.790 ppm and 52.484 ppm. Results indicated that the performance of the CK model for estimation of macro nutrients(N, P and K) was slightly lower than the GWR model. Also, the accuracy of the ANN model was higher than CK and GWR models, which proved to be more effective and reliable methods for estimating macro nutrients.展开更多
The features of the floating gate devices as analog memory have been investigatedexperimentally.Programming properties of the devices,compatibility and endurance of program-ming,and programming methods are presented i...The features of the floating gate devices as analog memory have been investigatedexperimentally.Programming properties of the devices,compatibility and endurance of program-ming,and programming methods are presented in this paper.The results illustrate that thedevice can be used to store the analog weights for the neural networks,and the method that thestored value is adjusted continuously to approach to a given analog values is a rather practicalmethod for storing weights of neural networks.展开更多
Randomized weights neural networks have fast learning speed and good generalization performance with one single hidden layer structure. Input weighs of the hidden layer are produced randomly. By employing certain acti...Randomized weights neural networks have fast learning speed and good generalization performance with one single hidden layer structure. Input weighs of the hidden layer are produced randomly. By employing certain activation function, outputs of the hidden layer are calculated with some randomization. Output weights are computed using pseudo inverse. Mutual information can be used to measure mutual dependence of two variables quantitatively based on the probability theory. In this paper, these hidden layer’s outputs that relate to prediction variable closely are selected with the simple mutual information based feature selection method. These hidden nodes with high mutual information values are maintained as a new hidden layer. Thus, the size of the hidden layer is reduced. The new hidden layer’s output weights are learned with the pseudo inverse method. The proposed method is compared with the original randomized algorithms using concrete compressive strength benchmark dataset.展开更多
This paper derives some sufficient conditions for exponential stability for the equilibrium point by dividing the state variables of the system according to the characters of the neural networks. The new conditions ar...This paper derives some sufficient conditions for exponential stability for the equilibrium point by dividing the state variables of the system according to the characters of the neural networks. The new conditions are described by some blocks of the interconnection matrix. An example is given to demonstrate the effectiveness of the proposed theory.展开更多
Community-acquired pneumonia(CAP)is considered a sort of pneumonia developed outside hospitals and clinics.To diagnose community-acquired pneumonia(CAP)more efficiently,we proposed a novel neural network model.We intr...Community-acquired pneumonia(CAP)is considered a sort of pneumonia developed outside hospitals and clinics.To diagnose community-acquired pneumonia(CAP)more efficiently,we proposed a novel neural network model.We introduce the 2-dimensional wavelet entropy(2d-WE)layer and an adaptive chaotic particle swarm optimization(ACP)algorithm to train the feed-forward neural network.The ACP uses adaptive inertia weight factor(AIWF)and Rossler attractor(RA)to improve the performance of standard particle swarm optimization.The final combined model is named WE-layer ACP-based network(WACPN),which attains a sensitivity of 91.87±1.37%,a specificity of 90.70±1.19%,a precision of 91.01±1.12%,an accuracy of 91.29±1.09%,F1 score of 91.43±1.09%,an MCC of 82.59±2.19%,and an FMI of 91.44±1.09%.The AUC of this WACPN model is 0.9577.We find that the maximum deposition level chosen as four can obtain the best result.Experiments demonstrate the effectiveness of both AIWF and RA.Finally,this proposed WACPN is efficient in diagnosing CAP and superior to six state-of-the-art models.Our model will be distributed to the cloud computing environment.展开更多
This study was undertaken to determine the accuracy of using Ultrasound (US) estimation of twin fetuses by use of Artificial Neural Network. At First, as the training group, we performed US examinations on 186 healthy...This study was undertaken to determine the accuracy of using Ultrasound (US) estimation of twin fetuses by use of Artificial Neural Network. At First, as the training group, we performed US examinations on 186 healthy singleton fetuses within 3 days of delivery. Three input variables were used to construct the ANN model: abdominal circumference (AC), ab-dominal diameter (AD), biparietal diameter (BPD). Then, a total of 121 twin fetuses were assessed sub-sequently as the validation group. In validation group, the mean absolute error and the mean absolute per-cent error between estimated fetal weight and actual fetal weight was 261.77 g and 7.81%, respectively. Results show that, twin estimation of birth weight by ultrasound correlates fairly well with the actual weights of twin fetuses.展开更多
In this paper, we use the global search characteristics of genetic algorithms to help search the weight space of the neurons in the cascade-correlation architecture. The cascade-correlation learning architecture is a ...In this paper, we use the global search characteristics of genetic algorithms to help search the weight space of the neurons in the cascade-correlation architecture. The cascade-correlation learning architecture is a technique of training and building neural networks that starts with a simple network of neurons and adds additional neurons as they are needed to suit a particular problem. In our approach, instead ofmodifying the genetic algorithm to account for convergence problems, we search the weight-space using the genetic algorithm and then apply the gradient technique of Quickprop to optimize the weights. This hybrid algorithm which is a combination of genetic algorithms and cascade-correlation is applied to the two spirals problem. We also use our algorithm in the prediction of the cyclic oxidation resistance of Ni- and Co-base superalloys.展开更多
Artificial neural networks(ANNs)are one of the hottest topics in computer science and artificial intelligence due to their potential and advantages in analyzing real-world problems in various disciplines,including but...Artificial neural networks(ANNs)are one of the hottest topics in computer science and artificial intelligence due to their potential and advantages in analyzing real-world problems in various disciplines,including but not limited to physics,biology,chemistry,and engineering.However,ANNs lack several key characteristics of biological neural networks,such as sparsity,scale-freeness,and small-worldness.The concept of sparse and scale-free neural networks has been introduced to fill this gap.Network sparsity is implemented by removing weak weights between neurons during the learning process and replacing them with random weights.When the network is initialized,the neural network is fully connected,which means the number of weights is four times the number of neurons.In this study,considering that a biological neural network has some degree of initial sparsity,we design an ANN with a prescribed level of initial sparsity.The neural network is tested on handwritten digits,Arabic characters,CIFAR-10,and Reuters newswire topics.Simulations show that it is possible to reduce the number of weights by up to 50%without losing prediction accuracy.Moreover,in both cases,the testing time is dramatically reduced compared with fully connected ANNs.展开更多
This paper outlines the application of the multi-layer perceptron artificial neural network (ANN), ordinary kriging (OK), and inverse distance weighting (IDW) models in the estimation of local scour depth around bridg...This paper outlines the application of the multi-layer perceptron artificial neural network (ANN), ordinary kriging (OK), and inverse distance weighting (IDW) models in the estimation of local scour depth around bridge piers. As part of this study, bridge piers were installed with bed sills at the bed of an experimental flume. Experimental tests were conducted under different flow conditions and varying distances between bridge pier and bed sill. The ANN, OK and IDW models were applied to the experimental data and it was shown that the artificial neural network model predicts local scour depth more accurately than the kriging and inverse distance weighting models. It was found that the ANN with two hidden layers was the optimum model to predict local scour depth. The results from the sixth test case showed that the ANN with one hidden layer and 17 hidden nodes was the best model to predict local scour depth. Whereas the results from the fifth test case found that the ANN with three hidden layers was the best model to predict local scour depth.展开更多
In this paper, the global asymptotic stability is investigated for a class of Cohen-Grossberg neural networks with time-varying and distributed delays. By using the Lyapunov-Krasovskii functional and equivalent descri...In this paper, the global asymptotic stability is investigated for a class of Cohen-Grossberg neural networks with time-varying and distributed delays. By using the Lyapunov-Krasovskii functional and equivalent descriptor form of the considered system, several delay-dependent sufficient conditions are obtained to guarantee the asymptotic stability of the addressed systems. These conditions are dependent on both time-varying and distributed delays and presented in terms of LMIs and therefore, the stability criteria of such systems can be checked readily by resorting to the Matlab LMI toolbox. Finally, an example is given to show the effectiveness and less conservatism of the proposed methods.展开更多
This article investigates the potential impact of manufacturing uncertainty in composite structures here in the form of thickness variation in laminate plies, on the robustness of commonly used Artificial Neural Netwo...This article investigates the potential impact of manufacturing uncertainty in composite structures here in the form of thickness variation in laminate plies, on the robustness of commonly used Artificial Neural Networks (ANN) in Structural Health Monitoring (SHM). Namely, the robustness of an ANN SHM system is assessed through an airfoil case study based on the sensitivity of delamination location and size predictions, when the ANN is imposed to noisy input. In light of the observed poor performance of the original network, even when its architecture was carefully optimized, it had been proposed to weigh the input layer of the ANN by a set of signal-to-noise (SN) ratios and then trained the network. Both damage location and size predictions of the latter SHM approach were increased to above 90%. Practical aspects of the proposed robust SN-ANN SHM have also been discussed.展开更多
Nowadays,the most heterogeneous architectures were made up by the various IP modules of different hardware vendors,but this model is less efficiently.In order to solve this problem,AMD joint other hardware vendors pro...Nowadays,the most heterogeneous architectures were made up by the various IP modules of different hardware vendors,but this model is less efficiently.In order to solve this problem,AMD joint other hardware vendors proposed heterogeneous system architecture(HSA)specification.On the one hand,the HSA could help developers to accelerate the design process and programming.On the other hand,it improved the system performance and reduced the power.In this paper we presented the implementation of a framework for accelerating training and classification of arbitrary Convolutional Neural Networks(CNNs)on the HSA,on the basis of implementation,we presented tow accelerated methods that are Online update weights and letting CPU to participate in calculation.Experimental results showed that the implementation of CNNs on HSA 4 to 10 times faster than on the CPU.展开更多
As a useful alternative of Shewhart control chart, exponentially weighted moving average (EWMA) control chat has been applied widely to quality control, process monitoring, forecast, etc. In this paper, a method was i...As a useful alternative of Shewhart control chart, exponentially weighted moving average (EWMA) control chat has been applied widely to quality control, process monitoring, forecast, etc. In this paper, a method was introduced for optimal design of EWMA and multivariate EWMA (MEWMA) control charts, in which the optimal parameter pair ( λ ,k) or ( λ ,h) was searched by using the generalized regression neural network (GRNN). The results indicate that the optimal parameter pair can be obtained effectively by the proposed strategy for a given in-control average running length (ARL0) and shift to detect under any conditions, removing the drawback of incompleteness existing in the tables that had been reported.展开更多
A new method for power quality (PQ) disturbances identification is brought forward based on combining a neural network with least square (LS) weighted fusion algorithm. The characteristic components of PQ disturbances...A new method for power quality (PQ) disturbances identification is brought forward based on combining a neural network with least square (LS) weighted fusion algorithm. The characteristic components of PQ disturbances are distilled through an improved phase-located loop (PLL) system at first, and then five child BP ANNs with different structures are trained and adopted to identify the PQ disturbances respectively. The combining neural network fuses the identification results of these child ANNs with LS weighted fusion algorithm, and identifies PQ disturbances with the fused result finally. Compared with a single neural network, the combining one with LS weighted fusion algorithm can identify the PQ disturbances correctly when noise is strong. However, a single neural network may fail in this case. Furthermore, the combining neural network is more reliable than a single neural network. The simulation results prove the conclusions above.展开更多
This paper expounds a data-fitting algorithm for the double-weight neural network,and presents a new algorithm for the system's power management on the base of that.The double-weight neural network learns knowledg...This paper expounds a data-fitting algorithm for the double-weight neural network,and presents a new algorithm for the system's power management on the base of that.The double-weight neural network learns knowledge from the past idle periods of the system,and predicts the lengths of the coming idle periods.As a result of that,the system can switch its running states and re- duce the power dissipation according to the predictive values.The results of the experiments prove that this algorithm shows a better performance in increasing the right rate of shutting down and reducing the power consumption than other traditional ones.展开更多
A new method based on the combination of a neural network and a genetic algorithm was proposed to rank the order of exploitation priority of coalbed methane reservoirs. The neural network was used to acquire the weigh...A new method based on the combination of a neural network and a genetic algorithm was proposed to rank the order of exploitation priority of coalbed methane reservoirs. The neural network was used to acquire the weights of reservoir parameters through sample training and genetic algorithm was used to optimize the initial connection weights of nerve cells in case the neural network fell into a local minimum. Additionally, subordinate functions of each parameter were established to normalize the actual values of parameters of coalbed methane reservoirs in the range between zero and unity. Eventually, evaluation values of all coalbed methane reservoirs could be obtained by using the comprehensive evaluation method, which is the basis to rank the coalbed methane reservoirs in the order of exploitation priority. The greater the evaluation value, the higher the exploitation priority. The ranking method was verified in this paper by ten exploited coalbed methane reservoirs in China. The evaluation results are in agreement with the actual exploitation cases. The method can ensure the truthfulness and credibility of the weights of parameters and avoid the subjectivity caused by experts. Furthermore, the probability of falling into local minima is reduced, because genetic the algorithm is used to optimize the neural network system.展开更多
In order to overcome shortcomings of traditional BP neural network,such as low study efficiency, slow convergence speed,easily trapped into local optimal solution,we proposed an improved BP neural network model based ...In order to overcome shortcomings of traditional BP neural network,such as low study efficiency, slow convergence speed,easily trapped into local optimal solution,we proposed an improved BP neural network model based on adaptive particle swarm optimization( PSO) algorithm. This algorithm adjusted the inertia weight coefficients and learning factors adaptively and therefore could be used to optimize the weights in the BP network. After establishing the improved PSO-BP( IPSO-BP) model,it was applied to solve fault diagnosis of rolling bearing. Wavelet denoising was selected to reduce the noise of the original vibration signals,and based on these vibration signals a wide set of features were used as the inputs in the neural network models. We demonstrate the effectiveness of the proposed approach by comparing with the traditional BP,PSO-BP and linear PSO-BP( LPSO-BP) algorithms. The experimental results show that IPSO-BP network outperforms other algorithms with faster convergence speed,lower errors,higher diagnostic accuracy and learning ability.展开更多
Bayesian regularized BP neural network(BRBPNN) technique was applied in the chlorophyll-α prediction of Nanzui water area in Dongting Lake. Through BP network interpolation method, the input and output samples of t...Bayesian regularized BP neural network(BRBPNN) technique was applied in the chlorophyll-α prediction of Nanzui water area in Dongting Lake. Through BP network interpolation method, the input and output samples of the network were obtained. After the selection of input variables using stepwise/multiple linear regression method in SPSS i1.0 software, the BRBPNN model was established between chlorophyll-α and environmental parameters, biological parameters. The achieved optimal network structure was 3-11-1 with the correlation coefficients and the mean square errors for the training set and the test set as 0.999 and 0.000?8426, 0.981 and 0.0216 respectively. The sum of square weights between each input neuron and the hidden layer of optimal BRBPNN models of different structures indicated that the effect of individual input parameter on chlorophyll- α declined in the order of alga amount 〉 secchi disc depth(SD) 〉 electrical conductivity (EC). Additionally, it also demonstrated that the contributions of these three factors were the maximal for the change of chlorophyll-α concentration, total phosphorus(TP) and total nitrogen(TN) were the minimal. All the results showed that BRBPNN model was capable of automated regularization parameter selection and thus it may ensure the excellent generation ability and robustness. Thus, this study laid the foundation for the application of BRBPNN model in the analysis of aquatic ecological data(chlorophyll-α prediction) and the explanation about the effective eutrophication treatment measures for Nanzui water area in Dongting Lake.展开更多
基金Foundation item:Under the auspices of Shahrood University of Technology,Iran(No.348517)
文摘Soil macronutrients(i.e. nitrogen(N), phosphorus(P), and potassium(K)) are important soils components and knowing the spatial distribution of these parameters are necessary at precision agriculture. The purpose of this study was to evaluate the feasibility of different methods such as artificial neural networks(ANN) and two geostatistical methods(geographically weighted regression(GWR) and cokriging(CK)) to estimate N, P and K contents. For this purpose, soil samples were taken from topsoil(0–30 cm) at 106 points and analyzed for their chemical and physical parameters. These data were divided into calibration(n = 84) and validation(n = 22). Chemical and physical variables including clay, p H and organic carbon(OC) were used as auxiliary soil variables to estimate the N, P and K contents. Results showed that the ANN model(with coefficient of determination R^2 = 0.922 and root mean square error RMSE = 0.0079%) was more accurate compared to the CK model(with R^2 = 0.612 and RMSE = 0.0094%), and the GWR model(with R^2 = 0.872 and RMSE = 0.0089%) to estimate the N variable. The ANN model estimated the P with the RMSE of 3.630 ppm, which was respectively 28.93% and 20.00% less than the RMSE of 4.680 ppm and 4.357 ppm from the CK and GWR models. The estimated K by CK, GWR and ANN models have the RMSE of 76.794 ppm, 75.790 ppm and 52.484 ppm. Results indicated that the performance of the CK model for estimation of macro nutrients(N, P and K) was slightly lower than the GWR model. Also, the accuracy of the ANN model was higher than CK and GWR models, which proved to be more effective and reliable methods for estimating macro nutrients.
文摘The features of the floating gate devices as analog memory have been investigatedexperimentally.Programming properties of the devices,compatibility and endurance of program-ming,and programming methods are presented in this paper.The results illustrate that thedevice can be used to store the analog weights for the neural networks,and the method that thestored value is adjusted continuously to approach to a given analog values is a rather practicalmethod for storing weights of neural networks.
文摘Randomized weights neural networks have fast learning speed and good generalization performance with one single hidden layer structure. Input weighs of the hidden layer are produced randomly. By employing certain activation function, outputs of the hidden layer are calculated with some randomization. Output weights are computed using pseudo inverse. Mutual information can be used to measure mutual dependence of two variables quantitatively based on the probability theory. In this paper, these hidden layer’s outputs that relate to prediction variable closely are selected with the simple mutual information based feature selection method. These hidden nodes with high mutual information values are maintained as a new hidden layer. Thus, the size of the hidden layer is reduced. The new hidden layer’s output weights are learned with the pseudo inverse method. The proposed method is compared with the original randomized algorithms using concrete compressive strength benchmark dataset.
文摘This paper derives some sufficient conditions for exponential stability for the equilibrium point by dividing the state variables of the system according to the characters of the neural networks. The new conditions are described by some blocks of the interconnection matrix. An example is given to demonstrate the effectiveness of the proposed theory.
基金This paper is partially supported by Medical Research Council Confidence in Concept Award,UK(MC_PC_17171)Royal Society International Exchanges Cost Share Award,UK(RP202G0230)+5 种基金British Heart Foundation Accelerator Award,UK(AA/18/3/34220)Hope Foundation for Cancer Research,UK(RM60G0680)Global Challenges Research Fund(GCRF),UK(P202PF11)Sino-UK Industrial Fund,UK(RP202G0289)LIAS Pioneering Partnerships award,UK(P202ED10)Data Science Enhancement Fund,UK(P202RE237).
文摘Community-acquired pneumonia(CAP)is considered a sort of pneumonia developed outside hospitals and clinics.To diagnose community-acquired pneumonia(CAP)more efficiently,we proposed a novel neural network model.We introduce the 2-dimensional wavelet entropy(2d-WE)layer and an adaptive chaotic particle swarm optimization(ACP)algorithm to train the feed-forward neural network.The ACP uses adaptive inertia weight factor(AIWF)and Rossler attractor(RA)to improve the performance of standard particle swarm optimization.The final combined model is named WE-layer ACP-based network(WACPN),which attains a sensitivity of 91.87±1.37%,a specificity of 90.70±1.19%,a precision of 91.01±1.12%,an accuracy of 91.29±1.09%,F1 score of 91.43±1.09%,an MCC of 82.59±2.19%,and an FMI of 91.44±1.09%.The AUC of this WACPN model is 0.9577.We find that the maximum deposition level chosen as four can obtain the best result.Experiments demonstrate the effectiveness of both AIWF and RA.Finally,this proposed WACPN is efficient in diagnosing CAP and superior to six state-of-the-art models.Our model will be distributed to the cloud computing environment.
文摘This study was undertaken to determine the accuracy of using Ultrasound (US) estimation of twin fetuses by use of Artificial Neural Network. At First, as the training group, we performed US examinations on 186 healthy singleton fetuses within 3 days of delivery. Three input variables were used to construct the ANN model: abdominal circumference (AC), ab-dominal diameter (AD), biparietal diameter (BPD). Then, a total of 121 twin fetuses were assessed sub-sequently as the validation group. In validation group, the mean absolute error and the mean absolute per-cent error between estimated fetal weight and actual fetal weight was 261.77 g and 7.81%, respectively. Results show that, twin estimation of birth weight by ultrasound correlates fairly well with the actual weights of twin fetuses.
文摘In this paper, we use the global search characteristics of genetic algorithms to help search the weight space of the neurons in the cascade-correlation architecture. The cascade-correlation learning architecture is a technique of training and building neural networks that starts with a simple network of neurons and adds additional neurons as they are needed to suit a particular problem. In our approach, instead ofmodifying the genetic algorithm to account for convergence problems, we search the weight-space using the genetic algorithm and then apply the gradient technique of Quickprop to optimize the weights. This hybrid algorithm which is a combination of genetic algorithms and cascade-correlation is applied to the two spirals problem. We also use our algorithm in the prediction of the cyclic oxidation resistance of Ni- and Co-base superalloys.
文摘Artificial neural networks(ANNs)are one of the hottest topics in computer science and artificial intelligence due to their potential and advantages in analyzing real-world problems in various disciplines,including but not limited to physics,biology,chemistry,and engineering.However,ANNs lack several key characteristics of biological neural networks,such as sparsity,scale-freeness,and small-worldness.The concept of sparse and scale-free neural networks has been introduced to fill this gap.Network sparsity is implemented by removing weak weights between neurons during the learning process and replacing them with random weights.When the network is initialized,the neural network is fully connected,which means the number of weights is four times the number of neurons.In this study,considering that a biological neural network has some degree of initial sparsity,we design an ANN with a prescribed level of initial sparsity.The neural network is tested on handwritten digits,Arabic characters,CIFAR-10,and Reuters newswire topics.Simulations show that it is possible to reduce the number of weights by up to 50%without losing prediction accuracy.Moreover,in both cases,the testing time is dramatically reduced compared with fully connected ANNs.
文摘This paper outlines the application of the multi-layer perceptron artificial neural network (ANN), ordinary kriging (OK), and inverse distance weighting (IDW) models in the estimation of local scour depth around bridge piers. As part of this study, bridge piers were installed with bed sills at the bed of an experimental flume. Experimental tests were conducted under different flow conditions and varying distances between bridge pier and bed sill. The ANN, OK and IDW models were applied to the experimental data and it was shown that the artificial neural network model predicts local scour depth more accurately than the kriging and inverse distance weighting models. It was found that the ANN with two hidden layers was the optimum model to predict local scour depth. The results from the sixth test case showed that the ANN with one hidden layer and 17 hidden nodes was the best model to predict local scour depth. Whereas the results from the fifth test case found that the ANN with three hidden layers was the best model to predict local scour depth.
基金the National Natural Science Foundation of China (No.60574006).
文摘In this paper, the global asymptotic stability is investigated for a class of Cohen-Grossberg neural networks with time-varying and distributed delays. By using the Lyapunov-Krasovskii functional and equivalent descriptor form of the considered system, several delay-dependent sufficient conditions are obtained to guarantee the asymptotic stability of the addressed systems. These conditions are dependent on both time-varying and distributed delays and presented in terms of LMIs and therefore, the stability criteria of such systems can be checked readily by resorting to the Matlab LMI toolbox. Finally, an example is given to show the effectiveness and less conservatism of the proposed methods.
文摘This article investigates the potential impact of manufacturing uncertainty in composite structures here in the form of thickness variation in laminate plies, on the robustness of commonly used Artificial Neural Networks (ANN) in Structural Health Monitoring (SHM). Namely, the robustness of an ANN SHM system is assessed through an airfoil case study based on the sensitivity of delamination location and size predictions, when the ANN is imposed to noisy input. In light of the observed poor performance of the original network, even when its architecture was carefully optimized, it had been proposed to weigh the input layer of the ANN by a set of signal-to-noise (SN) ratios and then trained the network. Both damage location and size predictions of the latter SHM approach were increased to above 90%. Practical aspects of the proposed robust SN-ANN SHM have also been discussed.
文摘Nowadays,the most heterogeneous architectures were made up by the various IP modules of different hardware vendors,but this model is less efficiently.In order to solve this problem,AMD joint other hardware vendors proposed heterogeneous system architecture(HSA)specification.On the one hand,the HSA could help developers to accelerate the design process and programming.On the other hand,it improved the system performance and reduced the power.In this paper we presented the implementation of a framework for accelerating training and classification of arbitrary Convolutional Neural Networks(CNNs)on the HSA,on the basis of implementation,we presented tow accelerated methods that are Online update weights and letting CPU to participate in calculation.Experimental results showed that the implementation of CNNs on HSA 4 to 10 times faster than on the CPU.
基金Funded by the National Key Technologies R&D Programs of China (No.2002BA105C)
文摘As a useful alternative of Shewhart control chart, exponentially weighted moving average (EWMA) control chat has been applied widely to quality control, process monitoring, forecast, etc. In this paper, a method was introduced for optimal design of EWMA and multivariate EWMA (MEWMA) control charts, in which the optimal parameter pair ( λ ,k) or ( λ ,h) was searched by using the generalized regression neural network (GRNN). The results indicate that the optimal parameter pair can be obtained effectively by the proposed strategy for a given in-control average running length (ARL0) and shift to detect under any conditions, removing the drawback of incompleteness existing in the tables that had been reported.
基金Sponsored by the Teaching and Research Award Programfor Outstanding Young Teachers in High Education Institutions of MOE China(Grant No.ZDXM03006).
文摘A new method for power quality (PQ) disturbances identification is brought forward based on combining a neural network with least square (LS) weighted fusion algorithm. The characteristic components of PQ disturbances are distilled through an improved phase-located loop (PLL) system at first, and then five child BP ANNs with different structures are trained and adopted to identify the PQ disturbances respectively. The combining neural network fuses the identification results of these child ANNs with LS weighted fusion algorithm, and identifies PQ disturbances with the fused result finally. Compared with a single neural network, the combining one with LS weighted fusion algorithm can identify the PQ disturbances correctly when noise is strong. However, a single neural network may fail in this case. Furthermore, the combining neural network is more reliable than a single neural network. The simulation results prove the conclusions above.
文摘This paper expounds a data-fitting algorithm for the double-weight neural network,and presents a new algorithm for the system's power management on the base of that.The double-weight neural network learns knowledge from the past idle periods of the system,and predicts the lengths of the coming idle periods.As a result of that,the system can switch its running states and re- duce the power dissipation according to the predictive values.The results of the experiments prove that this algorithm shows a better performance in increasing the right rate of shutting down and reducing the power consumption than other traditional ones.
基金EU-China Energy and Environment Programme(Europe Aid/120723/D/SV/CN)Research Fund for the Doctoral Program of Higher Education of China(20030425001)
文摘A new method based on the combination of a neural network and a genetic algorithm was proposed to rank the order of exploitation priority of coalbed methane reservoirs. The neural network was used to acquire the weights of reservoir parameters through sample training and genetic algorithm was used to optimize the initial connection weights of nerve cells in case the neural network fell into a local minimum. Additionally, subordinate functions of each parameter were established to normalize the actual values of parameters of coalbed methane reservoirs in the range between zero and unity. Eventually, evaluation values of all coalbed methane reservoirs could be obtained by using the comprehensive evaluation method, which is the basis to rank the coalbed methane reservoirs in the order of exploitation priority. The greater the evaluation value, the higher the exploitation priority. The ranking method was verified in this paper by ten exploited coalbed methane reservoirs in China. The evaluation results are in agreement with the actual exploitation cases. The method can ensure the truthfulness and credibility of the weights of parameters and avoid the subjectivity caused by experts. Furthermore, the probability of falling into local minima is reduced, because genetic the algorithm is used to optimize the neural network system.
基金Sponsored by the National Natural Science Foundation of China(Grant No.61174115 and 51104044)
文摘In order to overcome shortcomings of traditional BP neural network,such as low study efficiency, slow convergence speed,easily trapped into local optimal solution,we proposed an improved BP neural network model based on adaptive particle swarm optimization( PSO) algorithm. This algorithm adjusted the inertia weight coefficients and learning factors adaptively and therefore could be used to optimize the weights in the BP network. After establishing the improved PSO-BP( IPSO-BP) model,it was applied to solve fault diagnosis of rolling bearing. Wavelet denoising was selected to reduce the noise of the original vibration signals,and based on these vibration signals a wide set of features were used as the inputs in the neural network models. We demonstrate the effectiveness of the proposed approach by comparing with the traditional BP,PSO-BP and linear PSO-BP( LPSO-BP) algorithms. The experimental results show that IPSO-BP network outperforms other algorithms with faster convergence speed,lower errors,higher diagnostic accuracy and learning ability.
文摘Bayesian regularized BP neural network(BRBPNN) technique was applied in the chlorophyll-α prediction of Nanzui water area in Dongting Lake. Through BP network interpolation method, the input and output samples of the network were obtained. After the selection of input variables using stepwise/multiple linear regression method in SPSS i1.0 software, the BRBPNN model was established between chlorophyll-α and environmental parameters, biological parameters. The achieved optimal network structure was 3-11-1 with the correlation coefficients and the mean square errors for the training set and the test set as 0.999 and 0.000?8426, 0.981 and 0.0216 respectively. The sum of square weights between each input neuron and the hidden layer of optimal BRBPNN models of different structures indicated that the effect of individual input parameter on chlorophyll- α declined in the order of alga amount 〉 secchi disc depth(SD) 〉 electrical conductivity (EC). Additionally, it also demonstrated that the contributions of these three factors were the maximal for the change of chlorophyll-α concentration, total phosphorus(TP) and total nitrogen(TN) were the minimal. All the results showed that BRBPNN model was capable of automated regularization parameter selection and thus it may ensure the excellent generation ability and robustness. Thus, this study laid the foundation for the application of BRBPNN model in the analysis of aquatic ecological data(chlorophyll-α prediction) and the explanation about the effective eutrophication treatment measures for Nanzui water area in Dongting Lake.