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
The analysis of interwell connectivity plays an important role in the formulation of oilfield development plans and the description of residual oil distribution. In fact, sandstone reservoirs in China's onshore oi...The analysis of interwell connectivity plays an important role in the formulation of oilfield development plans and the description of residual oil distribution. In fact, sandstone reservoirs in China's onshore oilfields generally have the characteristics of thin and many layers, so multi-layer joint production is usually adopted. It remains a challenge to ensure the accuracy of splitting and dynamic connectivity in each layer of the injection-production wells with limited field data. The three-dimensional well pattern of multi-layer reservoir and the relationship between injection-production wells can be equivalent to a directional heterogeneous graph. In this paper, an improved graph neural network is proposed to construct an interacting process mimics the real interwell flow regularity. In detail, this method is used to split injection and production rates by combining permeability, porosity and effective thickness, and to invert the dynamic connectivity in each layer of the injection-production wells by attention mechanism.Based on the material balance and physical information, the overall connectivity from the injection wells,through the water injection layers to the production layers and the output of final production wells is established. Meanwhile, the change of well pattern caused by perforation, plugging and switching of wells at different times is achieved by updated graph structure in spatial and temporal ways. The effectiveness of the method is verified by a combination of reservoir numerical simulation examples and field example. The method corresponds to the actual situation of the reservoir, has wide adaptability and low cost, has good practical value, and provides a reference for adjusting the injection-production relationship of the reservoir and the development of the remaining oil.展开更多
This elucidation investigates the Hausdorff dimension of the output space of multi-layer neural networks. When the factor map from the covering space of the output space to the output space has a synchronizing word, t...This elucidation investigates the Hausdorff dimension of the output space of multi-layer neural networks. When the factor map from the covering space of the output space to the output space has a synchronizing word, the Hausdorff dimension of the output space relates to its topological entropy. This clarifies the geometrical structure of the output space in more details.展开更多
This paper presents a study on the improvement of MLNNs(multi-layer neural networks)performance by an activity function for multi logic training patterns.Our model network has L hidden layers of two inputs and three,f...This paper presents a study on the improvement of MLNNs(multi-layer neural networks)performance by an activity function for multi logic training patterns.Our model network has L hidden layers of two inputs and three,four to six output training using BP(backpropagation)neural network.We used logic functions of XOR(exclusive OR),OR,AND,NAND(not AND),NXOR(not exclusive OR)and NOR(not OR)as the multi logic teacher signals to evaluate the training performance of MLNNs by an activity function for information and data enlargement in signal processing(synaptic divergence state).We specifically used four activity functions from which we modified one and called it L&exp.function as it could give the highest training abilities compared to the original activity functions of Sigmoid,ReLU and Step during simulation and training in the network.And finally,we propose L&exp.function as being good for MLNNs and it may be applicable for signal processing of data and information enlargement because of its performance training characteristics with multiple training logic patterns hence can be adopted in machine deep learning.展开更多
The hybrid method composed of clustering and predicting stages is proposed to predict the endpoint phos- phorus content of molten steel in BOF （Basic Oxygen Furnace）. At the clustering stage, the weighted K-means is...The hybrid method composed of clustering and predicting stages is proposed to predict the endpoint phos- phorus content of molten steel in BOF （Basic Oxygen Furnace）. At the clustering stage, the weighted K-means is performed to generate some clusters with homogeneous data. The weights of factors influencing the target are calcu- lated using EWM （Entropy Weight Method）. At the predicting stage, one GMDH （Group Method of Data Handling） polynomial neural network is built for each cluster. And the predictive results from all the GMDH polynomial neural networks are integrated into a whole to be the result for the hybrid method. The hybrid method, GMDH polnomial neural network and BP neural network are employed for a comparison. The results show that the proposed hybrid method is effective in predicting the endpoint phosphorus content of molten steel in BOF. Furthermore, the hybrid method outperforms BP neural network and GMDH polynomial neural network.展开更多
A tightly coupled GPS （ global positioning system ）/SINS （ strap down inertial navigation system） based on a GMDH （ group method of data handling） neural network was presented to solve the problem of degraded ac...A tightly coupled GPS （ global positioning system ）/SINS （ strap down inertial navigation system） based on a GMDH （ group method of data handling） neural network was presented to solve the problem of degraded accuracy for less than four visible GPS satellites with poor signal quality. Positions and velocities of the satellites were predicted by a GMDH neural network, and the pseudo ranges and pseudo range rates received by the GPS receiver were simulated to ensure the regular op eration of the GPS/SINS Kalman filter during outages. In the mathematical simulation a tightly cou pled navigation system with a proposed approach has better navigation accuracy during GPS outages, and the anti jamming ability is strengthened for the tightly coupled navigation system.展开更多
Interconnection of all things challenges the traditional communication methods,and Semantic Communication and Computing(SCC)will become new solutions.It is a challenging task to accurately detect,extract,and represent...Interconnection of all things challenges the traditional communication methods,and Semantic Communication and Computing(SCC)will become new solutions.It is a challenging task to accurately detect,extract,and represent semantic information in the research of SCC-based networks.In previous research,researchers usually use convolution to extract the feature information of a graph and perform the corresponding task of node classification.However,the content of semantic information is quite complex.Although graph convolutional neural networks provide an effective solution for node classification tasks,due to their limitations in representing multiple relational patterns and not recognizing and analyzing higher-order local structures,the extracted feature information is subject to varying degrees of loss.Therefore,this paper extends from a single-layer topology network to a multi-layer heterogeneous topology network.The Bidirectional Encoder Representations from Transformers(BERT)training word vector is introduced to extract the semantic features in the network,and the existing graph neural network is improved by combining the higher-order local feature module of the network model representation network.A multi-layer network embedding algorithm on SCC-based networks with motifs is proposed to complete the task of end-to-end node classification.We verify the effectiveness of the algorithm on a real multi-layer heterogeneous network.展开更多
Knowledge of pore-water pressure(PWP)variation is fundamental for slope stability.A precise prediction of PWP is difficult due to complex physical mechanisms and in situ natural variability.To explore the applicabilit...Knowledge of pore-water pressure(PWP)variation is fundamental for slope stability.A precise prediction of PWP is difficult due to complex physical mechanisms and in situ natural variability.To explore the applicability and advantages of recurrent neural networks(RNNs)on PWP prediction,three variants of RNNs,i.e.,standard RNN,long short-term memory(LSTM)and gated recurrent unit(GRU)are adopted and compared with a traditional static artificial neural network(ANN),i.e.,multi-layer perceptron(MLP).Measurements of rainfall and PWP of representative piezometers from a fully instrumented natural slope in Hong Kong are used to establish the prediction models.The coefficient of determination(R^2)and root mean square error(RMSE)are used for model evaluations.The influence of input time series length on the model performance is investigated.The results reveal that MLP can provide acceptable performance but is not robust.The uncertainty bounds of RMSE of the MLP model range from 0.24 kPa to 1.12 k Pa for the selected two piezometers.The standard RNN can perform better but the robustness is slightly affected when there are significant time lags between PWP changes and rainfall.The GRU and LSTM models can provide more precise and robust predictions than the standard RNN.The effects of the hidden layer structure and the dropout technique are investigated.The single-layer GRU is accurate enough for PWP prediction,whereas a double-layer GRU brings extra time cost with little accuracy improvement.The dropout technique is essential to overfitting prevention and improvement of accuracy.展开更多
A brain-computer interface(BCI)system is one of the most effective ways that translates brain signals into output commands.Different imagery activities can be classified based on the changes inμandβrhythms and their...A brain-computer interface(BCI)system is one of the most effective ways that translates brain signals into output commands.Different imagery activities can be classified based on the changes inμandβrhythms and their spatial distributions.Multi-layer perceptron neural networks(MLP-NNs)are commonly used for classification.Training such MLP-NNs has great importance in a way that has attracted many researchers to this field recently.Conventional methods for training NNs,such as gradient descent and recursive methods,have some disadvantages including low accuracy,slow convergence speed and trapping in local minimums.In this paper,in order to overcome these issues,the MLP-NN trained by a hybrid population-physics-based algorithm,the combination of particle swarm optimization and gravitational search algorithm(PSOGSA),is proposed for our classification problem.To show the advantages of using PSOGSA that trains NNs,this algorithm is compared with other meta-heuristic algorithms such as particle swarm optimization(PSO),gravitational search algorithm(GSA)and new versions of PSO.The metrics that are discussed in this paper are the speed of convergence and classification accuracy metrics.The results show that the proposed algorithm in most subjects of encephalography(EEG)dataset has very better or acceptable performance compared to others.展开更多
One of the most important problems in robot kinematics and control is, finding the solution of Inverse Kinematics. Inverse kinematics computation has been one of the main problems in robotics research. As the Complexi...One of the most important problems in robot kinematics and control is, finding the solution of Inverse Kinematics. Inverse kinematics computation has been one of the main problems in robotics research. As the Complexity of robot increases, obtaining the inverse kinematics is difficult and computationally expensive. Traditional methods such as geometric, iterative and algebraic are inadequate if the joint structure of the manipulator is more complex. As alternative approaches, neural networks and optimal search methods have been widely used for inverse kinematics modeling and control in robotics This paper proposes neural network architecture that consists of 6 sub-neural networks to solve the inverse kinematics problem for robotics manipulators with 2 or higher degrees of freedom. The neural networks utilized are multi-layered perceptron (MLP) with a back-propagation training algorithm. This approach will reduce the complexity of the algorithm and calculation (matrix inversion) faced when using the Inverse Geometric Models implementation (IGM) in robotics. The obtained results are presented and analyzed in order to prove the efficiency of the proposed approach.展开更多
This paper presents the development of an artificial neural network (ANN) model based on the multi-layer perceptron (MLP) for analyzing internet traffic data over IP networks. We applied the ANN to analyze a time seri...This paper presents the development of an artificial neural network (ANN) model based on the multi-layer perceptron (MLP) for analyzing internet traffic data over IP networks. We applied the ANN to analyze a time series of measured data for network response evaluation. For this reason, we used the input and output data of an internet traffic over IP networks to identify the ANN model, and we studied the performance of some training algorithms used to estimate the weights of the neuron. The comparison between some training algorithms demonstrates the efficiency and the accu-racy of the Levenberg-Marquardt (LM) and the Resilient back propagation (Rp) algorithms in term of statistical crite-ria. Consequently, the obtained results show that the developed models, using the LM and the Rp algorithms, can successfully be used for analyzing internet traffic over IP networks, and can be applied as an excellent and fundamental tool for the management of the internet traffic at different times.展开更多
High rigidity twenty-high Sendzimir mills （ZRMs） are widely used for rolling stainless steels, silicon sheets, etc. A ZRM uses a small diameter work roll to produce massive rolling forces. Since a work roll with a s...High rigidity twenty-high Sendzimir mills （ZRMs） are widely used for rolling stainless steels, silicon sheets, etc. A ZRM uses a small diameter work roll to produce massive rolling forces. Since a work roll with a small diameter can be bent easily, strips often have complex shapes with mixed quarter and deep edge waves in the shape of plates. In order to solve this problem, fuzzy neural network controls are generally used for shape： recognition in ZRM control systems. Among various neural network types, the multi-layer perceptron （MLP） is typically used in current ZRMs. However, an MLP causes the loss of a large amount of shape recognition data. To improve the shape recognition per- formance of ZRM control systems, echo state networks （ESNs） are proposed to be used. Through simulation re- sults, it is found that shape recognition performance could be improved using the proposed ESN method.展开更多
Simultaneous perturbation stochastic approximation （SPSA） belongs to the class of gradient-free optimization methods that extract gradient information from successive objective function evaluation. This paper descri...Simultaneous perturbation stochastic approximation （SPSA） belongs to the class of gradient-free optimization methods that extract gradient information from successive objective function evaluation. This paper describes an improved SPSA algorithm, which entails fuzzy adaptive gain sequences, gradient smoothing, and a step rejection procedure to enhance convergence and stability. The proposed fuzzy adaptive simultaneous perturbation approximation （FASPA） algorithm is particularly well suited to problems involving a large number of parameters such as those encountered in nonlinear system identification using neural networks （NNs）. Accordingly, a multilayer perceptron （MLP） network with popular training algorithms was used to predicate the system response. We found that an MLP trained by FASPSA had the desired accuracy that was comparable to results obtained by traditional system identification algorithms. Simulation results for typical nonlinear systems demonstrate that the proposed NN architecture trained with FASPSA yields improved system identification as measured by reduced time of convergence and a smaller identification error.展开更多
A hybrid GMDH neural network model has been developed in order to predict the partition coefficients of invertase from Baker's yeast. ATPS experiments were carried out changing the molar average mass of PEG(1500–...A hybrid GMDH neural network model has been developed in order to predict the partition coefficients of invertase from Baker's yeast. ATPS experiments were carried out changing the molar average mass of PEG(1500–6000 Da), p H(4.0–7.0), percentage of PEG(10.0–20.0 w/w), percentage of MgSO_4(8.0–16.0 w/w), percentage of the cell homogenate(10.0–20.0 w/w) and the percentage of MnSO_4(0–5.0 w/w) added as cosolute. The network evaluation was carried out comparing the partition coefficients obtained from the hybrid GMDH neural network with the experimental data using different statistical metrics. The hybrid GMDH neural network model showed better fitting(AARD = 32.752%) as well as good generalization capacity of the partition coefficients of the ATPS than the original GMDH network approach and a BPANN model. Therefore hybrid GMDH neural network model appears as a powerful tool for predicting partition coefficients during downstream processing of biomolecules.展开更多
In addition to the effect that the COVID-19 pandemic has had on the physical and mental health of individuals,it has also led to a change in the mental and emotional state of many employees.Especially among businesses...In addition to the effect that the COVID-19 pandemic has had on the physical and mental health of individuals,it has also led to a change in the mental and emotional state of many employees.Especially among businesses and private companies,which faced many restrictions due to the special conditions of the pandemic.Therefore,the present study aimed to design an artificial neural network with MLP technique to analyze the relationship between demographic variables,resilience,COVID-19 and burnout in start-ups in Iran.The research method was quantitative.Managers and employees of start-ups formed the statistical population of the study,based on the statistical sample size of the unlimited community,384 of them were tested.For data gathering,standard questionnaires include of MBI-GS and BRCS and researcher-made questionnaire of stress caused by COVID-19 were used.The validity of the questionnaires was confirmed by a panel of experts and their reliability was confirmed by Cronbach’s alpha coefficient.The number of neurons in the input layer was equal to 10,the number of neurons in the 1st hidden layer was equal to 7,the number of neurons in the output layer was equal to 1,and the number of epochs was equal to 500.70%of the data were used for training and 30%for testing.In the designed artificial neural network,all experiment data except one were correctly predicted and the obtained MAE error was less than 0.012%.Finally,he precision and correction of the presented model was confirmed by the obtained results.展开更多
In this paper,a fast neural network model for the forecasting of effective points by DEA model is proposed,which is based on the SPDS training algorithm.The SPDS training algorithm overcomes the drawbacks of slow conv...In this paper,a fast neural network model for the forecasting of effective points by DEA model is proposed,which is based on the SPDS training algorithm.The SPDS training algorithm overcomes the drawbacks of slow convergent speed and partially minimum result for BP algorithm.Its training speed is much faster and its forecasting precision is much better than those of BP algorithm.By numeric examples,it is showed that adopting the neural network model in the forecasting of effective points by DEA model is valid.展开更多
The present study was conducted to present the comparative modeling, predictive and generalization abilities of response surface methodology (RSM) and artificial neural network (ANN) for the thermal structure of stabi...The present study was conducted to present the comparative modeling, predictive and generalization abilities of response surface methodology (RSM) and artificial neural network (ANN) for the thermal structure of stabilized confined jet diffusion flames in the presence of different geometries of bluff-body burners. Two stabilizer disc burners tapered at 30° and 60° and another frustum cone of 60°/30° inclination angle were employed all having the same diameter of 80 (mm) acting as flame holders. The measured radial mean temperature profiles of the developed stabilized flames at different normalized axial distances (x/dj) were considered as the model example of the physical process. The RSM and ANN methods analyze the effect of the two operating parameters namely (r), the radial distance from the center line of the flame, and (x/dj) on the measured temperature of the flames, to find the predicted maximum temperature and the corresponding process variables. A three-layered Feed Forward Neural Network in conjugation with the hyperbolic tangent sigmoid (tansig) as transfer function and the optimized topology of 2:10:1 (input neurons: hidden neurons: output neurons) was developed. Also the ANN method has been employed to illustrate such effects in the three and two dimensions and shows the location of the predicted maximum temperature. The results indicated the superiority of ANN in the prediction capability as the ranges of R2 and F Ratio are 0.868 - 0.947 and 231.7 - 864.1 for RSM method compared to 0.964 - 0.987 and 2878.8 7580.7 for ANN method beside lower values for error analysis terms.展开更多
Biometric techniques require critical operations of digital processing for identification of individuals. In this context, this paper aims to develop a system for automatic processing of fingerprint identification by ...Biometric techniques require critical operations of digital processing for identification of individuals. In this context, this paper aims to develop a system for automatic processing of fingerprint identification by their minutiae using Artificial Neural Networks （ANN）, which reveals to be highly effective. The ANN method implemented is a based on Multi-Layer Perceptron （MLP） model, which utilizes the algorithm of retro-propagation of gradient during the learning process. In such a process, the mean square error generated represents the specific parameter for the identification phase by comparing a fingerprint taken from a crime scene with those of a reference database.展开更多
In the context of new risks and threats associated to nuclear, biological and chemical （NBC） attacks, and given the shortcomings of certain analytical methods such as principal component analysis （PCA）, a neural n...In the context of new risks and threats associated to nuclear, biological and chemical （NBC） attacks, and given the shortcomings of certain analytical methods such as principal component analysis （PCA）, a neural network approach seems to be more accurate. PCA consists in projecting the spectrum of a gas collected from a remote sensing system in, firstly, a three-dimensional space, then in a two-dimensional one using a model of Multi-Layer Perceptron based neural network. It adopts during the learning process, the back propagation algorithm of the gradient, in which the mean square error output is continuously calculated and compared to the input until it reaches a minimal threshold value. This aims to correct the synaptic weights of the network. So, the Artificial Neural Network （ANN） tends to be more efficient in the classification process. This paper emphasizes the contribution of the ANN method in the spectral data processing, classification and identification and in addition, its fast convergence during the back propagation of the gradient.展开更多
With the emphasis on user privacy and communication security, encrypted traffic has increased dramatically, which brings great challenges to traffic classification. The classification method of encrypted traffic based...With the emphasis on user privacy and communication security, encrypted traffic has increased dramatically, which brings great challenges to traffic classification. The classification method of encrypted traffic based on GNN can deal with encrypted traffic well. However, existing GNN-based approaches ignore the relationship between client or server packets. In this paper, we design a network traffic topology based on GCN, called Flow Mapping Graph (FMG). FMG establishes sequential edges between vertexes by the arrival order of packets and establishes jump-order edges between vertexes by connecting packets in different bursts with the same direction. It not only reflects the time characteristics of the packet but also strengthens the relationship between the client or server packets. According to FMG, a Traffic Mapping Classification model (TMC-GCN) is designed, which can automatically capture and learn the characteristics and structure information of the top vertex in FMG. The TMC-GCN model is used to classify the encrypted traffic. The encryption stream classification problem is transformed into a graph classification problem, which can effectively deal with data from different data sources and application scenarios. By comparing the performance of TMC-GCN with other classical models in four public datasets, including CICIOT2023, ISCXVPN2016, CICAAGM2017, and GraphDapp, the effectiveness of the FMG algorithm is verified. The experimental results show that the accuracy rate of the TMC-GCN model is 96.13%, the recall rate is 95.04%, and the F1 rate is 94.54%.展开更多
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.
基金the support of the National Nature Science Foundation of China(No.52074336)Emerging Big Data Projects of Sinopec Corporation(No.20210918084304712)。
文摘The analysis of interwell connectivity plays an important role in the formulation of oilfield development plans and the description of residual oil distribution. In fact, sandstone reservoirs in China's onshore oilfields generally have the characteristics of thin and many layers, so multi-layer joint production is usually adopted. It remains a challenge to ensure the accuracy of splitting and dynamic connectivity in each layer of the injection-production wells with limited field data. The three-dimensional well pattern of multi-layer reservoir and the relationship between injection-production wells can be equivalent to a directional heterogeneous graph. In this paper, an improved graph neural network is proposed to construct an interacting process mimics the real interwell flow regularity. In detail, this method is used to split injection and production rates by combining permeability, porosity and effective thickness, and to invert the dynamic connectivity in each layer of the injection-production wells by attention mechanism.Based on the material balance and physical information, the overall connectivity from the injection wells,through the water injection layers to the production layers and the output of final production wells is established. Meanwhile, the change of well pattern caused by perforation, plugging and switching of wells at different times is achieved by updated graph structure in spatial and temporal ways. The effectiveness of the method is verified by a combination of reservoir numerical simulation examples and field example. The method corresponds to the actual situation of the reservoir, has wide adaptability and low cost, has good practical value, and provides a reference for adjusting the injection-production relationship of the reservoir and the development of the remaining oil.
文摘This elucidation investigates the Hausdorff dimension of the output space of multi-layer neural networks. When the factor map from the covering space of the output space to the output space has a synchronizing word, the Hausdorff dimension of the output space relates to its topological entropy. This clarifies the geometrical structure of the output space in more details.
文摘This paper presents a study on the improvement of MLNNs(multi-layer neural networks)performance by an activity function for multi logic training patterns.Our model network has L hidden layers of two inputs and three,four to six output training using BP(backpropagation)neural network.We used logic functions of XOR(exclusive OR),OR,AND,NAND(not AND),NXOR(not exclusive OR)and NOR(not OR)as the multi logic teacher signals to evaluate the training performance of MLNNs by an activity function for information and data enlargement in signal processing(synaptic divergence state).We specifically used four activity functions from which we modified one and called it L&exp.function as it could give the highest training abilities compared to the original activity functions of Sigmoid,ReLU and Step during simulation and training in the network.And finally,we propose L&exp.function as being good for MLNNs and it may be applicable for signal processing of data and information enlargement because of its performance training characteristics with multiple training logic patterns hence can be adopted in machine deep learning.
基金Sponsored by National Key Technology Research and Development in 11th Five Years Plan of China(2006BAE03A07)Fundamental Research Funds for Central University of China(FRF-AS-09-006B)
文摘The hybrid method composed of clustering and predicting stages is proposed to predict the endpoint phos- phorus content of molten steel in BOF （Basic Oxygen Furnace）. At the clustering stage, the weighted K-means is performed to generate some clusters with homogeneous data. The weights of factors influencing the target are calcu- lated using EWM （Entropy Weight Method）. At the predicting stage, one GMDH （Group Method of Data Handling） polynomial neural network is built for each cluster. And the predictive results from all the GMDH polynomial neural networks are integrated into a whole to be the result for the hybrid method. The hybrid method, GMDH polnomial neural network and BP neural network are employed for a comparison. The results show that the proposed hybrid method is effective in predicting the endpoint phosphorus content of molten steel in BOF. Furthermore, the hybrid method outperforms BP neural network and GMDH polynomial neural network.
文摘A tightly coupled GPS （ global positioning system ）/SINS （ strap down inertial navigation system） based on a GMDH （ group method of data handling） neural network was presented to solve the problem of degraded accuracy for less than four visible GPS satellites with poor signal quality. Positions and velocities of the satellites were predicted by a GMDH neural network, and the pseudo ranges and pseudo range rates received by the GPS receiver were simulated to ensure the regular op eration of the GPS/SINS Kalman filter during outages. In the mathematical simulation a tightly cou pled navigation system with a proposed approach has better navigation accuracy during GPS outages, and the anti jamming ability is strengthened for the tightly coupled navigation system.
基金supported by National Natural Science Foundation of China(62101088,61801076,61971336)Natural Science Foundation of Liaoning Province(2022-MS-157,2023-MS-108)+1 种基金Key Laboratory of Big Data Intelligent Computing Funds for Chongqing University of Posts and Telecommunications(BDIC-2023-A-003)Fundamental Research Funds for the Central Universities(3132022230).
文摘Interconnection of all things challenges the traditional communication methods,and Semantic Communication and Computing(SCC)will become new solutions.It is a challenging task to accurately detect,extract,and represent semantic information in the research of SCC-based networks.In previous research,researchers usually use convolution to extract the feature information of a graph and perform the corresponding task of node classification.However,the content of semantic information is quite complex.Although graph convolutional neural networks provide an effective solution for node classification tasks,due to their limitations in representing multiple relational patterns and not recognizing and analyzing higher-order local structures,the extracted feature information is subject to varying degrees of loss.Therefore,this paper extends from a single-layer topology network to a multi-layer heterogeneous topology network.The Bidirectional Encoder Representations from Transformers(BERT)training word vector is introduced to extract the semantic features in the network,and the existing graph neural network is improved by combining the higher-order local feature module of the network model representation network.A multi-layer network embedding algorithm on SCC-based networks with motifs is proposed to complete the task of end-to-end node classification.We verify the effectiveness of the algorithm on a real multi-layer heterogeneous network.
基金supported by the Natural Science Foundation of China(Grant Nos.51979158,51639008,51679135,and 51422905)the Program of Shanghai Academic Research Leader by Science and Technology Commission of Shanghai Municipality(Project No.19XD1421900)。
文摘Knowledge of pore-water pressure(PWP)variation is fundamental for slope stability.A precise prediction of PWP is difficult due to complex physical mechanisms and in situ natural variability.To explore the applicability and advantages of recurrent neural networks(RNNs)on PWP prediction,three variants of RNNs,i.e.,standard RNN,long short-term memory(LSTM)and gated recurrent unit(GRU)are adopted and compared with a traditional static artificial neural network(ANN),i.e.,multi-layer perceptron(MLP).Measurements of rainfall and PWP of representative piezometers from a fully instrumented natural slope in Hong Kong are used to establish the prediction models.The coefficient of determination(R^2)and root mean square error(RMSE)are used for model evaluations.The influence of input time series length on the model performance is investigated.The results reveal that MLP can provide acceptable performance but is not robust.The uncertainty bounds of RMSE of the MLP model range from 0.24 kPa to 1.12 k Pa for the selected two piezometers.The standard RNN can perform better but the robustness is slightly affected when there are significant time lags between PWP changes and rainfall.The GRU and LSTM models can provide more precise and robust predictions than the standard RNN.The effects of the hidden layer structure and the dropout technique are investigated.The single-layer GRU is accurate enough for PWP prediction,whereas a double-layer GRU brings extra time cost with little accuracy improvement.The dropout technique is essential to overfitting prevention and improvement of accuracy.
文摘A brain-computer interface(BCI)system is one of the most effective ways that translates brain signals into output commands.Different imagery activities can be classified based on the changes inμandβrhythms and their spatial distributions.Multi-layer perceptron neural networks(MLP-NNs)are commonly used for classification.Training such MLP-NNs has great importance in a way that has attracted many researchers to this field recently.Conventional methods for training NNs,such as gradient descent and recursive methods,have some disadvantages including low accuracy,slow convergence speed and trapping in local minimums.In this paper,in order to overcome these issues,the MLP-NN trained by a hybrid population-physics-based algorithm,the combination of particle swarm optimization and gravitational search algorithm(PSOGSA),is proposed for our classification problem.To show the advantages of using PSOGSA that trains NNs,this algorithm is compared with other meta-heuristic algorithms such as particle swarm optimization(PSO),gravitational search algorithm(GSA)and new versions of PSO.The metrics that are discussed in this paper are the speed of convergence and classification accuracy metrics.The results show that the proposed algorithm in most subjects of encephalography(EEG)dataset has very better or acceptable performance compared to others.
文摘One of the most important problems in robot kinematics and control is, finding the solution of Inverse Kinematics. Inverse kinematics computation has been one of the main problems in robotics research. As the Complexity of robot increases, obtaining the inverse kinematics is difficult and computationally expensive. Traditional methods such as geometric, iterative and algebraic are inadequate if the joint structure of the manipulator is more complex. As alternative approaches, neural networks and optimal search methods have been widely used for inverse kinematics modeling and control in robotics This paper proposes neural network architecture that consists of 6 sub-neural networks to solve the inverse kinematics problem for robotics manipulators with 2 or higher degrees of freedom. The neural networks utilized are multi-layered perceptron (MLP) with a back-propagation training algorithm. This approach will reduce the complexity of the algorithm and calculation (matrix inversion) faced when using the Inverse Geometric Models implementation (IGM) in robotics. The obtained results are presented and analyzed in order to prove the efficiency of the proposed approach.
文摘This paper presents the development of an artificial neural network (ANN) model based on the multi-layer perceptron (MLP) for analyzing internet traffic data over IP networks. We applied the ANN to analyze a time series of measured data for network response evaluation. For this reason, we used the input and output data of an internet traffic over IP networks to identify the ANN model, and we studied the performance of some training algorithms used to estimate the weights of the neuron. The comparison between some training algorithms demonstrates the efficiency and the accu-racy of the Levenberg-Marquardt (LM) and the Resilient back propagation (Rp) algorithms in term of statistical crite-ria. Consequently, the obtained results show that the developed models, using the LM and the Rp algorithms, can successfully be used for analyzing internet traffic over IP networks, and can be applied as an excellent and fundamental tool for the management of the internet traffic at different times.
基金Sponsored by Korea Science and Engineering Foundation(KOSEF)Funded by Korea Government(MEST)(2010-0022521)
文摘High rigidity twenty-high Sendzimir mills （ZRMs） are widely used for rolling stainless steels, silicon sheets, etc. A ZRM uses a small diameter work roll to produce massive rolling forces. Since a work roll with a small diameter can be bent easily, strips often have complex shapes with mixed quarter and deep edge waves in the shape of plates. In order to solve this problem, fuzzy neural network controls are generally used for shape： recognition in ZRM control systems. Among various neural network types, the multi-layer perceptron （MLP） is typically used in current ZRMs. However, an MLP causes the loss of a large amount of shape recognition data. To improve the shape recognition per- formance of ZRM control systems, echo state networks （ESNs） are proposed to be used. Through simulation re- sults, it is found that shape recognition performance could be improved using the proposed ESN method.
文摘Simultaneous perturbation stochastic approximation （SPSA） belongs to the class of gradient-free optimization methods that extract gradient information from successive objective function evaluation. This paper describes an improved SPSA algorithm, which entails fuzzy adaptive gain sequences, gradient smoothing, and a step rejection procedure to enhance convergence and stability. The proposed fuzzy adaptive simultaneous perturbation approximation （FASPA） algorithm is particularly well suited to problems involving a large number of parameters such as those encountered in nonlinear system identification using neural networks （NNs）. Accordingly, a multilayer perceptron （MLP） network with popular training algorithms was used to predicate the system response. We found that an MLP trained by FASPSA had the desired accuracy that was comparable to results obtained by traditional system identification algorithms. Simulation results for typical nonlinear systems demonstrate that the proposed NN architecture trained with FASPSA yields improved system identification as measured by reduced time of convergence and a smaller identification error.
基金CAPES and Brazilian National Council of Research (CNPq) (Grant 407684/2013-1) for the financial support
文摘A hybrid GMDH neural network model has been developed in order to predict the partition coefficients of invertase from Baker's yeast. ATPS experiments were carried out changing the molar average mass of PEG(1500–6000 Da), p H(4.0–7.0), percentage of PEG(10.0–20.0 w/w), percentage of MgSO_4(8.0–16.0 w/w), percentage of the cell homogenate(10.0–20.0 w/w) and the percentage of MnSO_4(0–5.0 w/w) added as cosolute. The network evaluation was carried out comparing the partition coefficients obtained from the hybrid GMDH neural network with the experimental data using different statistical metrics. The hybrid GMDH neural network model showed better fitting(AARD = 32.752%) as well as good generalization capacity of the partition coefficients of the ATPS than the original GMDH network approach and a BPANN model. Therefore hybrid GMDH neural network model appears as a powerful tool for predicting partition coefficients during downstream processing of biomolecules.
文摘In addition to the effect that the COVID-19 pandemic has had on the physical and mental health of individuals,it has also led to a change in the mental and emotional state of many employees.Especially among businesses and private companies,which faced many restrictions due to the special conditions of the pandemic.Therefore,the present study aimed to design an artificial neural network with MLP technique to analyze the relationship between demographic variables,resilience,COVID-19 and burnout in start-ups in Iran.The research method was quantitative.Managers and employees of start-ups formed the statistical population of the study,based on the statistical sample size of the unlimited community,384 of them were tested.For data gathering,standard questionnaires include of MBI-GS and BRCS and researcher-made questionnaire of stress caused by COVID-19 were used.The validity of the questionnaires was confirmed by a panel of experts and their reliability was confirmed by Cronbach’s alpha coefficient.The number of neurons in the input layer was equal to 10,the number of neurons in the 1st hidden layer was equal to 7,the number of neurons in the output layer was equal to 1,and the number of epochs was equal to 500.70%of the data were used for training and 30%for testing.In the designed artificial neural network,all experiment data except one were correctly predicted and the obtained MAE error was less than 0.012%.Finally,he precision and correction of the presented model was confirmed by the obtained results.
基金Sponsored by the Natural Scientific Research Foundation of Heilongjiang Province(Grant No.40000045-6-07259)the Natural Scientific Research Inno-vation Foundation of Harbin Institute of Technology(Grant No.HIT.NSRIF.2008.59)+1 种基金the Scientific and Technology Critical Project of Harbin,Hei-longjiang Province(2004)the National Soft Science Key Foundation(Grant No.2008GXS5D113)
文摘In this paper,a fast neural network model for the forecasting of effective points by DEA model is proposed,which is based on the SPDS training algorithm.The SPDS training algorithm overcomes the drawbacks of slow convergent speed and partially minimum result for BP algorithm.Its training speed is much faster and its forecasting precision is much better than those of BP algorithm.By numeric examples,it is showed that adopting the neural network model in the forecasting of effective points by DEA model is valid.
文摘The present study was conducted to present the comparative modeling, predictive and generalization abilities of response surface methodology (RSM) and artificial neural network (ANN) for the thermal structure of stabilized confined jet diffusion flames in the presence of different geometries of bluff-body burners. Two stabilizer disc burners tapered at 30° and 60° and another frustum cone of 60°/30° inclination angle were employed all having the same diameter of 80 (mm) acting as flame holders. The measured radial mean temperature profiles of the developed stabilized flames at different normalized axial distances (x/dj) were considered as the model example of the physical process. The RSM and ANN methods analyze the effect of the two operating parameters namely (r), the radial distance from the center line of the flame, and (x/dj) on the measured temperature of the flames, to find the predicted maximum temperature and the corresponding process variables. A three-layered Feed Forward Neural Network in conjugation with the hyperbolic tangent sigmoid (tansig) as transfer function and the optimized topology of 2:10:1 (input neurons: hidden neurons: output neurons) was developed. Also the ANN method has been employed to illustrate such effects in the three and two dimensions and shows the location of the predicted maximum temperature. The results indicated the superiority of ANN in the prediction capability as the ranges of R2 and F Ratio are 0.868 - 0.947 and 231.7 - 864.1 for RSM method compared to 0.964 - 0.987 and 2878.8 7580.7 for ANN method beside lower values for error analysis terms.
文摘Biometric techniques require critical operations of digital processing for identification of individuals. In this context, this paper aims to develop a system for automatic processing of fingerprint identification by their minutiae using Artificial Neural Networks （ANN）, which reveals to be highly effective. The ANN method implemented is a based on Multi-Layer Perceptron （MLP） model, which utilizes the algorithm of retro-propagation of gradient during the learning process. In such a process, the mean square error generated represents the specific parameter for the identification phase by comparing a fingerprint taken from a crime scene with those of a reference database.
文摘In the context of new risks and threats associated to nuclear, biological and chemical （NBC） attacks, and given the shortcomings of certain analytical methods such as principal component analysis （PCA）, a neural network approach seems to be more accurate. PCA consists in projecting the spectrum of a gas collected from a remote sensing system in, firstly, a three-dimensional space, then in a two-dimensional one using a model of Multi-Layer Perceptron based neural network. It adopts during the learning process, the back propagation algorithm of the gradient, in which the mean square error output is continuously calculated and compared to the input until it reaches a minimal threshold value. This aims to correct the synaptic weights of the network. So, the Artificial Neural Network （ANN） tends to be more efficient in the classification process. This paper emphasizes the contribution of the ANN method in the spectral data processing, classification and identification and in addition, its fast convergence during the back propagation of the gradient.
基金supported by the National Key Research and Development Program of China No.2023YFA1009500.
文摘With the emphasis on user privacy and communication security, encrypted traffic has increased dramatically, which brings great challenges to traffic classification. The classification method of encrypted traffic based on GNN can deal with encrypted traffic well. However, existing GNN-based approaches ignore the relationship between client or server packets. In this paper, we design a network traffic topology based on GCN, called Flow Mapping Graph (FMG). FMG establishes sequential edges between vertexes by the arrival order of packets and establishes jump-order edges between vertexes by connecting packets in different bursts with the same direction. It not only reflects the time characteristics of the packet but also strengthens the relationship between the client or server packets. According to FMG, a Traffic Mapping Classification model (TMC-GCN) is designed, which can automatically capture and learn the characteristics and structure information of the top vertex in FMG. The TMC-GCN model is used to classify the encrypted traffic. The encryption stream classification problem is transformed into a graph classification problem, which can effectively deal with data from different data sources and application scenarios. By comparing the performance of TMC-GCN with other classical models in four public datasets, including CICIOT2023, ISCXVPN2016, CICAAGM2017, and GraphDapp, the effectiveness of the FMG algorithm is verified. The experimental results show that the accuracy rate of the TMC-GCN model is 96.13%, the recall rate is 95.04%, and the F1 rate is 94.54%.
