Implanted neural probes can detect weak discharges of neurons in the brain by piercing soft brain tissue,thus as important tools for brain science research,as well as diagnosis and treatment of brain diseases.However,...Implanted neural probes can detect weak discharges of neurons in the brain by piercing soft brain tissue,thus as important tools for brain science research,as well as diagnosis and treatment of brain diseases.However,the rigid neural probes,such as Utah arrays,Michigan probes,and metal microfilament electrodes,are mechanically unmatched with brain tissue and are prone to rejection and glial scarring after implantation,which leads to a significant degradation in the signal quality with the implantation time.In recent years,flexible neural electrodes are rapidly developed with less damage to biological tissues,excellent biocompatibility,and mechanical compliance to alleviate scarring.Among them,the mechanical modeling is important for the optimization of the structure and the implantation process.In this review,the theoretical calculation of the flexible neural probes is firstly summarized with the processes of buckling,insertion,and relative interaction with soft brain tissue for flexible probes from outside to inside.Then,the corresponding mechanical simulation methods are organized considering multiple impact factors to realize minimally invasive implantation.Finally,the technical difficulties and future trends of mechanical modeling are discussed for the next-generation flexible neural probes,which is critical to realize low-invasiveness and long-term coexistence in vivo.展开更多
The amount of oxygen blown into the converter is one of the key parameters for the control of the converter blowing process,which directly affects the tap-to-tap time of converter. In this study, a hybrid model based ...The amount of oxygen blown into the converter is one of the key parameters for the control of the converter blowing process,which directly affects the tap-to-tap time of converter. In this study, a hybrid model based on oxygen balance mechanism (OBM) and deep neural network (DNN) was established for predicting oxygen blowing time in converter. A three-step method was utilized in the hybrid model. First, the oxygen consumption volume was predicted by the OBM model and DNN model, respectively. Second, a more accurate oxygen consumption volume was obtained by integrating the OBM model and DNN model. Finally, the converter oxygen blowing time was calculated according to the oxygen consumption volume and the oxygen supply intensity of each heat. The proposed hybrid model was verified using the actual data collected from an integrated steel plant in China, and compared with multiple linear regression model, OBM model, and neural network model including extreme learning machine, back propagation neural network, and DNN. The test results indicate that the hybrid model with a network structure of 3 hidden layer layers, 32-16-8 neurons per hidden layer, and 0.1 learning rate has the best prediction accuracy and stronger generalization ability compared with other models. The predicted hit ratio of oxygen consumption volume within the error±300 m^(3)is 96.67%;determination coefficient (R^(2)) and root mean square error (RMSE) are0.6984 and 150.03 m^(3), respectively. The oxygen blow time prediction hit ratio within the error±0.6 min is 89.50%;R2and RMSE are0.9486 and 0.3592 min, respectively. As a result, the proposed model can effectively predict the oxygen consumption volume and oxygen blowing time in the converter.展开更多
Deep learning, especially through convolutional neural networks (CNN) such as the U-Net 3D model, has revolutionized fault identification from seismic data, representing a significant leap over traditional methods. Ou...Deep learning, especially through convolutional neural networks (CNN) such as the U-Net 3D model, has revolutionized fault identification from seismic data, representing a significant leap over traditional methods. Our review traces the evolution of CNN, emphasizing the adaptation and capabilities of the U-Net 3D model in automating seismic fault delineation with unprecedented accuracy. We find: 1) The transition from basic neural networks to sophisticated CNN has enabled remarkable advancements in image recognition, which are directly applicable to analyzing seismic data. The U-Net 3D model, with its innovative architecture, exemplifies this progress by providing a method for detailed and accurate fault detection with reduced manual interpretation bias. 2) The U-Net 3D model has demonstrated its superiority over traditional fault identification methods in several key areas: it has enhanced interpretation accuracy, increased operational efficiency, and reduced the subjectivity of manual methods. 3) Despite these achievements, challenges such as the need for effective data preprocessing, acquisition of high-quality annotated datasets, and achieving model generalization across different geological conditions remain. Future research should therefore focus on developing more complex network architectures and innovative training strategies to refine fault identification performance further. Our findings confirm the transformative potential of deep learning, particularly CNN like the U-Net 3D model, in geosciences, advocating for its broader integration to revolutionize geological exploration and seismic analysis.展开更多
The stock market, as one of the hotspots in the financial field, forms a data system with a huge volume of data and complex relationships between various factors, making stock price prediction an area of keen interest...The stock market, as one of the hotspots in the financial field, forms a data system with a huge volume of data and complex relationships between various factors, making stock price prediction an area of keen interest for further in-depth mining and research. Mathematical statistics methods struggle to deal with nonlinear relationships in practical applications, making it difficult to explore deep information about stocks. Meanwhile, machine learning methods, particularly neural network models and composite models, which have achieved outstanding results in other fields, are being applied to the stock market with significant results. However, researchers have found that these methods do not grasp the essential information of the data as well as expected. In response to these issues, researchers are exploring better neural network models and combining them with other methods to analyze stock data. Thus, this paper proposes the ABiGRU composite model, which combines the attention mechanism and bidirectional gated recurrent unit (GRU) that can effectively extract data features for stock price prediction research. Models such as LSTM, GRU, and Bi-LSTM are selected for comparative experiments. To ensure the credibility and representativeness of the research data, daily stock price indices of BYD are chosen for closing price prediction studies across different models. The results show that the ABiGRU model has a lower prediction error and better fitting effect on three index-based stock prices, enhancing the learning efficiency of the neural network model and demonstrating good prediction stability. This suggests that the ABiGRU model is highly adaptable for stock price prediction.展开更多
In recent years,with the great success of pre-trained language models,the pre-trained BERT model has been gradually applied to the field of source code understanding.However,the time cost of training a language model ...In recent years,with the great success of pre-trained language models,the pre-trained BERT model has been gradually applied to the field of source code understanding.However,the time cost of training a language model from zero is very high,and how to transfer the pre-trained language model to the field of smart contract vulnerability detection is a hot research direction at present.In this paper,we propose a hybrid model to detect common vulnerabilities in smart contracts based on a lightweight pre-trained languagemodel BERT and connected to a bidirectional gate recurrent unitmodel.The downstream neural network adopts the bidirectional gate recurrent unit neural network model with a hierarchical attention mechanism to mine more semantic features contained in the source code of smart contracts by using their characteristics.Our experiments show that our proposed hybrid neural network model SolBERT-BiGRU-Attention is fitted by a large number of data samples with smart contract vulnerabilities,and it is found that compared with the existing methods,the accuracy of our model can reach 93.85%,and the Micro-F1 Score is 94.02%.展开更多
A mapping function between the Reynolds-averaged Navier-Stokes mean flow variables and transition intermittency factor is constructed by fully connected artificial neural network(ANN),which replaces the governing equa...A mapping function between the Reynolds-averaged Navier-Stokes mean flow variables and transition intermittency factor is constructed by fully connected artificial neural network(ANN),which replaces the governing equation of the intermittency factor in transition-predictive Spalart-Allmaras(SA)-γmodel.By taking SA-γmodel as the benchmark,the present ANN model is trained at two airfoils with various angles of attack,Mach numbers and Reynolds numbers,and tested with unseen airfoils in different flow states.The a posteriori tests manifest that the mean pressure coefficient,skin friction coefficient,size of laminar separation bubble,mean streamwise velocity,Reynolds shear stress and lift/drag/moment coefficient from the present two-way coupling ANN model almost coincide with those from the benchmark SA-γmodel.Furthermore,the ANN model proves to exhibit a higher calculation efficiency and better convergence quality than traditional SA-γmodel.展开更多
针对车联网中高通信需求和高移动性造成的车对车链路(Vehicle to Vehicle,V2V)间的信道冲突及网络效用低下的问题,提出了一种基于并联门控循环单元(Gated Recurrent Unit,GRU)和长短期记忆网络(Long Short-Term Memory,LSTM)的组合模型...针对车联网中高通信需求和高移动性造成的车对车链路(Vehicle to Vehicle,V2V)间的信道冲突及网络效用低下的问题,提出了一种基于并联门控循环单元(Gated Recurrent Unit,GRU)和长短期记忆网络(Long Short-Term Memory,LSTM)的组合模型的车联网信道分配算法。算法以降低V2V链路信道碰撞率和空闲率为目标,将信道分配问题建模为分布式深度强化学习问题,使每条V2V链路作为单个智能体,并通过最大化每回合平均奖励的方式进行集中训练、分布式执行。在训练过程中借助GRU训练周期短和LSTM拟合精度高的组合优势去拟合深度双重Q学习中Q函数,使V2V链路能快速地学习优化信道分配策略,合理地复用车对基础设施(Vehicle to Infrastructure,V2I)链路的信道资源,实现网络效用最大化。仿真结果表明,与单纯使用GRU或者LSTM网络模型的分配算法相比,该算法在收敛速度方面加快了5个训练回合,V2V链路间的信道碰撞率和空闲率降低了约27%,平均成功率提升了约10%。展开更多
Fully connected neural networks(FCNNs)have been developed for the closure of subgrid-scale(SGS)stress and SGS heat flux in large-eddy simulations of compressible turbulent channel flow.The FCNNbased SGS model trained ...Fully connected neural networks(FCNNs)have been developed for the closure of subgrid-scale(SGS)stress and SGS heat flux in large-eddy simulations of compressible turbulent channel flow.The FCNNbased SGS model trained using data with Mach number Ma=3.0 and Reynolds number Re=3000 was applied to situations with different Mach numbers and Reynolds numbers.The input variables of the neural network model were the filtered velocity gradients and temperature gradients at a single spatial grid point.The a priori test showed that the FCNN model had a correlation coefficient larger than 0.91 and a relative error smaller than 0.43,with much better reconstructions of SGS unclosed terms than the dynamic Smagorinsky model(DSM).In a posteriori test,the behavior of the FCNN model was marginally better than that of the DSM in predicting the mean velocity profiles,mean temperature profiles,turbulent intensities,total Reynolds stress,total Reynolds heat flux,and mean SGS flux of kinetic energy,and outperformed the Smagorinsky model.展开更多
This works intends to provide numerical solutions based on the nonlinear fractional order derivatives of the classical White and Comiskey model(NFD-WCM).The fractional order derivatives have provided authentic and acc...This works intends to provide numerical solutions based on the nonlinear fractional order derivatives of the classical White and Comiskey model(NFD-WCM).The fractional order derivatives have provided authentic and accurate solutions for the NDF-WCM.The solutions of the fractional NFD-WCM are provided using the stochastic computing supervised algorithm named Levenberg-Marquard Backpropagation(LMB)based on neural networks(NNs).This regression approach combines gradient descent and Gauss-Newton iterative methods,which means finding a solution through the sequences of different calculations.WCM is used to demonstrate the heroin epidemics.Heroin has been on-growth world wide,mainly in Asia,Europe,and the USA.It is the fourth foremost cause of death due to taking an overdose in the USA.The nonlinear mathematical system NFD-WCM discusses the overall circumstance of different drug users,such as suspected groups,drug users without treatment,and drug users with treatment.The numerical results of NFD-WCM via LMB-NNs have been substantiated through training,testing,and validation measures.The stability and accuracy are then checked through the statistical tool,such asmean square error(MSE),error histogram,and fitness curves.The suggested methodology’s strength is demonstrated by the high convergence between the reference solutions and the solutions generated by adding the efficacy of a constructed solver LMB-NNs,with accuracy levels ranging from 10?9 to 10?10.展开更多
基金support received from the National Natural Science Foundation of China(GrantNos.62204204 and 52175148)Science and Technology Innovation 2030-Major Project(Grant No.2022ZD0208601)+1 种基金Shanghai Sailing Program(Grant No.21YF1451000)Presidential Foundation of CAEP(Grant No.YZJJZQ2022001).
文摘Implanted neural probes can detect weak discharges of neurons in the brain by piercing soft brain tissue,thus as important tools for brain science research,as well as diagnosis and treatment of brain diseases.However,the rigid neural probes,such as Utah arrays,Michigan probes,and metal microfilament electrodes,are mechanically unmatched with brain tissue and are prone to rejection and glial scarring after implantation,which leads to a significant degradation in the signal quality with the implantation time.In recent years,flexible neural electrodes are rapidly developed with less damage to biological tissues,excellent biocompatibility,and mechanical compliance to alleviate scarring.Among them,the mechanical modeling is important for the optimization of the structure and the implantation process.In this review,the theoretical calculation of the flexible neural probes is firstly summarized with the processes of buckling,insertion,and relative interaction with soft brain tissue for flexible probes from outside to inside.Then,the corresponding mechanical simulation methods are organized considering multiple impact factors to realize minimally invasive implantation.Finally,the technical difficulties and future trends of mechanical modeling are discussed for the next-generation flexible neural probes,which is critical to realize low-invasiveness and long-term coexistence in vivo.
基金financially supported by the National Natural Science Foundation of China (Nos.51974023 and52374321)the funding of State Key Laboratory of Advanced Metallurgy,University of Science and Technology Beijing,China (No.41620007)。
文摘The amount of oxygen blown into the converter is one of the key parameters for the control of the converter blowing process,which directly affects the tap-to-tap time of converter. In this study, a hybrid model based on oxygen balance mechanism (OBM) and deep neural network (DNN) was established for predicting oxygen blowing time in converter. A three-step method was utilized in the hybrid model. First, the oxygen consumption volume was predicted by the OBM model and DNN model, respectively. Second, a more accurate oxygen consumption volume was obtained by integrating the OBM model and DNN model. Finally, the converter oxygen blowing time was calculated according to the oxygen consumption volume and the oxygen supply intensity of each heat. The proposed hybrid model was verified using the actual data collected from an integrated steel plant in China, and compared with multiple linear regression model, OBM model, and neural network model including extreme learning machine, back propagation neural network, and DNN. The test results indicate that the hybrid model with a network structure of 3 hidden layer layers, 32-16-8 neurons per hidden layer, and 0.1 learning rate has the best prediction accuracy and stronger generalization ability compared with other models. The predicted hit ratio of oxygen consumption volume within the error±300 m^(3)is 96.67%;determination coefficient (R^(2)) and root mean square error (RMSE) are0.6984 and 150.03 m^(3), respectively. The oxygen blow time prediction hit ratio within the error±0.6 min is 89.50%;R2and RMSE are0.9486 and 0.3592 min, respectively. As a result, the proposed model can effectively predict the oxygen consumption volume and oxygen blowing time in the converter.
文摘Deep learning, especially through convolutional neural networks (CNN) such as the U-Net 3D model, has revolutionized fault identification from seismic data, representing a significant leap over traditional methods. Our review traces the evolution of CNN, emphasizing the adaptation and capabilities of the U-Net 3D model in automating seismic fault delineation with unprecedented accuracy. We find: 1) The transition from basic neural networks to sophisticated CNN has enabled remarkable advancements in image recognition, which are directly applicable to analyzing seismic data. The U-Net 3D model, with its innovative architecture, exemplifies this progress by providing a method for detailed and accurate fault detection with reduced manual interpretation bias. 2) The U-Net 3D model has demonstrated its superiority over traditional fault identification methods in several key areas: it has enhanced interpretation accuracy, increased operational efficiency, and reduced the subjectivity of manual methods. 3) Despite these achievements, challenges such as the need for effective data preprocessing, acquisition of high-quality annotated datasets, and achieving model generalization across different geological conditions remain. Future research should therefore focus on developing more complex network architectures and innovative training strategies to refine fault identification performance further. Our findings confirm the transformative potential of deep learning, particularly CNN like the U-Net 3D model, in geosciences, advocating for its broader integration to revolutionize geological exploration and seismic analysis.
文摘The stock market, as one of the hotspots in the financial field, forms a data system with a huge volume of data and complex relationships between various factors, making stock price prediction an area of keen interest for further in-depth mining and research. Mathematical statistics methods struggle to deal with nonlinear relationships in practical applications, making it difficult to explore deep information about stocks. Meanwhile, machine learning methods, particularly neural network models and composite models, which have achieved outstanding results in other fields, are being applied to the stock market with significant results. However, researchers have found that these methods do not grasp the essential information of the data as well as expected. In response to these issues, researchers are exploring better neural network models and combining them with other methods to analyze stock data. Thus, this paper proposes the ABiGRU composite model, which combines the attention mechanism and bidirectional gated recurrent unit (GRU) that can effectively extract data features for stock price prediction research. Models such as LSTM, GRU, and Bi-LSTM are selected for comparative experiments. To ensure the credibility and representativeness of the research data, daily stock price indices of BYD are chosen for closing price prediction studies across different models. The results show that the ABiGRU model has a lower prediction error and better fitting effect on three index-based stock prices, enhancing the learning efficiency of the neural network model and demonstrating good prediction stability. This suggests that the ABiGRU model is highly adaptable for stock price prediction.
基金supported by the National Natural Science Foundation of China(Grant Nos.62272120,62106030,U20B2046,62272119,61972105)the Technology Innovation and Application Development Projects of Chongqing(Grant Nos.cstc2021jscx-gksbX0032,cstc2021jscxgksbX0029).
文摘In recent years,with the great success of pre-trained language models,the pre-trained BERT model has been gradually applied to the field of source code understanding.However,the time cost of training a language model from zero is very high,and how to transfer the pre-trained language model to the field of smart contract vulnerability detection is a hot research direction at present.In this paper,we propose a hybrid model to detect common vulnerabilities in smart contracts based on a lightweight pre-trained languagemodel BERT and connected to a bidirectional gate recurrent unitmodel.The downstream neural network adopts the bidirectional gate recurrent unit neural network model with a hierarchical attention mechanism to mine more semantic features contained in the source code of smart contracts by using their characteristics.Our experiments show that our proposed hybrid neural network model SolBERT-BiGRU-Attention is fitted by a large number of data samples with smart contract vulnerabilities,and it is found that compared with the existing methods,the accuracy of our model can reach 93.85%,and the Micro-F1 Score is 94.02%.
基金the financial supports provided by the National Natural Science Foundation of China(Nos.91852112 and 11988102)。
文摘A mapping function between the Reynolds-averaged Navier-Stokes mean flow variables and transition intermittency factor is constructed by fully connected artificial neural network(ANN),which replaces the governing equation of the intermittency factor in transition-predictive Spalart-Allmaras(SA)-γmodel.By taking SA-γmodel as the benchmark,the present ANN model is trained at two airfoils with various angles of attack,Mach numbers and Reynolds numbers,and tested with unseen airfoils in different flow states.The a posteriori tests manifest that the mean pressure coefficient,skin friction coefficient,size of laminar separation bubble,mean streamwise velocity,Reynolds shear stress and lift/drag/moment coefficient from the present two-way coupling ANN model almost coincide with those from the benchmark SA-γmodel.Furthermore,the ANN model proves to exhibit a higher calculation efficiency and better convergence quality than traditional SA-γmodel.
文摘针对车联网中高通信需求和高移动性造成的车对车链路(Vehicle to Vehicle,V2V)间的信道冲突及网络效用低下的问题,提出了一种基于并联门控循环单元(Gated Recurrent Unit,GRU)和长短期记忆网络(Long Short-Term Memory,LSTM)的组合模型的车联网信道分配算法。算法以降低V2V链路信道碰撞率和空闲率为目标,将信道分配问题建模为分布式深度强化学习问题,使每条V2V链路作为单个智能体,并通过最大化每回合平均奖励的方式进行集中训练、分布式执行。在训练过程中借助GRU训练周期短和LSTM拟合精度高的组合优势去拟合深度双重Q学习中Q函数,使V2V链路能快速地学习优化信道分配策略,合理地复用车对基础设施(Vehicle to Infrastructure,V2I)链路的信道资源,实现网络效用最大化。仿真结果表明,与单纯使用GRU或者LSTM网络模型的分配算法相比,该算法在收敛速度方面加快了5个训练回合,V2V链路间的信道碰撞率和空闲率降低了约27%,平均成功率提升了约10%。
基金Financial support provided by the National Natural Science Foundation of China(Grant Nos.11702042 and 91952104)。
文摘Fully connected neural networks(FCNNs)have been developed for the closure of subgrid-scale(SGS)stress and SGS heat flux in large-eddy simulations of compressible turbulent channel flow.The FCNNbased SGS model trained using data with Mach number Ma=3.0 and Reynolds number Re=3000 was applied to situations with different Mach numbers and Reynolds numbers.The input variables of the neural network model were the filtered velocity gradients and temperature gradients at a single spatial grid point.The a priori test showed that the FCNN model had a correlation coefficient larger than 0.91 and a relative error smaller than 0.43,with much better reconstructions of SGS unclosed terms than the dynamic Smagorinsky model(DSM).In a posteriori test,the behavior of the FCNN model was marginally better than that of the DSM in predicting the mean velocity profiles,mean temperature profiles,turbulent intensities,total Reynolds stress,total Reynolds heat flux,and mean SGS flux of kinetic energy,and outperformed the Smagorinsky model.
基金National Research Council of Thailand(NRCT)and Khon Kaen University:N42A650291.
文摘This works intends to provide numerical solutions based on the nonlinear fractional order derivatives of the classical White and Comiskey model(NFD-WCM).The fractional order derivatives have provided authentic and accurate solutions for the NDF-WCM.The solutions of the fractional NFD-WCM are provided using the stochastic computing supervised algorithm named Levenberg-Marquard Backpropagation(LMB)based on neural networks(NNs).This regression approach combines gradient descent and Gauss-Newton iterative methods,which means finding a solution through the sequences of different calculations.WCM is used to demonstrate the heroin epidemics.Heroin has been on-growth world wide,mainly in Asia,Europe,and the USA.It is the fourth foremost cause of death due to taking an overdose in the USA.The nonlinear mathematical system NFD-WCM discusses the overall circumstance of different drug users,such as suspected groups,drug users without treatment,and drug users with treatment.The numerical results of NFD-WCM via LMB-NNs have been substantiated through training,testing,and validation measures.The stability and accuracy are then checked through the statistical tool,such asmean square error(MSE),error histogram,and fitness curves.The suggested methodology’s strength is demonstrated by the high convergence between the reference solutions and the solutions generated by adding the efficacy of a constructed solver LMB-NNs,with accuracy levels ranging from 10?9 to 10?10.