Complex-valued neural networks(CVNNs)have shown their excellent efficiency compared to their real counterparts in speech enhancement,image and signal processing.Researchers throughout the years have made many efforts ...Complex-valued neural networks(CVNNs)have shown their excellent efficiency compared to their real counterparts in speech enhancement,image and signal processing.Researchers throughout the years have made many efforts to improve the learning algorithms and activation functions of CVNNs.Since CVNNs have proven to have better performance in handling the naturally complex-valued data and signals,this area of study will grow and expect the arrival of some effective improvements in the future.Therefore,there exists an obvious reason to provide a comprehensive survey paper that systematically collects and categorizes the advancement of CVNNs.In this paper,we discuss and summarize the recent advances based on their learning algorithms,activation functions,which is the most challenging part of building a CVNN,and applications.Besides,we outline the structure and applications of complex-valued convolutional,residual and recurrent neural networks.Finally,we also present some challenges and future research directions to facilitate the exploration of the ability of CVNNs.展开更多
In this paper, a novel design procedure is proposed for synthesizing high-capacity auto-associative memories based on complex-valued neural networks with real-imaginary-type activation functions and constant delays. S...In this paper, a novel design procedure is proposed for synthesizing high-capacity auto-associative memories based on complex-valued neural networks with real-imaginary-type activation functions and constant delays. Stability criteria dependent on external inputs of neural networks are derived. The designed networks can retrieve the stored patterns by external inputs rather than initial conditions. The derivation can memorize the desired patterns with lower-dimensional neural networks than real-valued neural networks, and eliminate spurious equilibria of complex-valued neural networks. One numerical example is provided to show the effectiveness and superiority of the presented results.展开更多
In this paper, the singularity and its effect on learning dynamics in the complex-valued neural network are elucidated. It has learned that the linear combination structure in the updating rule of the complex-valued n...In this paper, the singularity and its effect on learning dynamics in the complex-valued neural network are elucidated. It has learned that the linear combination structure in the updating rule of the complex-valued neural network increases the speed of moving away from the singular points, and the complex-valued neural network cannot be easily influenced by the singular points, whereas the learning of the usual real-valued neural network can be attracted in the neighborhood of singular points, which causes a standstill in learning. Simulation results on the learning dynamics of the three-layered real-valued and complex-valued neural networks in the neighborhood of singularities support the analytical results.展开更多
The problem of exponential module-phase synchronization of complex-valued neural networks(CVNNs)with time-varying delay and stochastic perturbations was investigated.The model of CVNNs with time-varying delay and stoc...The problem of exponential module-phase synchronization of complex-valued neural networks(CVNNs)with time-varying delay and stochastic perturbations was investigated.The model of CVNNs with time-varying delay and stochastic perturbations was considered.The error system was deduced and the module-phase synchronization was defined.Based on the principle of Lyapunov stability theory,the appropriate controller was designed to control the CVNNs.Finally,the effectiveness and reliability of the method were verified by the numerical simulations.展开更多
The thermal conductivity of nanofluids is an important property that influences the heat transfer capabilities of nanofluids.Researchers rely on experimental investigations to explore nanofluid properties,as it is a n...The thermal conductivity of nanofluids is an important property that influences the heat transfer capabilities of nanofluids.Researchers rely on experimental investigations to explore nanofluid properties,as it is a necessary step before their practical application.As these investigations are time and resource-consuming undertakings,an effective prediction model can significantly improve the efficiency of research operations.In this work,an Artificial Neural Network(ANN)model is developed to predict the thermal conductivity of metal oxide water-based nanofluid.For this,a comprehensive set of 691 data points was collected from the literature.This dataset is split into training(70%),validation(15%),and testing(15%)and used to train the ANN model.The developed model is a backpropagation artificial neural network with a 4–12–1 architecture.The performance of the developed model shows high accuracy with R values above 0.90 and rapid convergence.It shows that the developed ANN model accurately predicts the thermal conductivity of nanofluids.展开更多
With the rapid development of the Artificial Intelligence of Things(AIoT),convolutional neural networks(CNNs)have demonstrated potential and remarkable performance in AIoT applications due to their excellent performan...With the rapid development of the Artificial Intelligence of Things(AIoT),convolutional neural networks(CNNs)have demonstrated potential and remarkable performance in AIoT applications due to their excellent performance in various inference tasks.However,the users have concerns about privacy leakage for the use of AI and the performance and efficiency of computing on resource-constrained IoT edge devices.Therefore,this paper proposes an efficient privacy-preserving CNN framework(i.e.,EPPA)based on the Fully Homomorphic Encryption(FHE)scheme for AIoT application scenarios.In the plaintext domain,we verify schemes with different activation structures to determine the actual activation functions applicable to the corresponding ciphertext domain.Within the encryption domain,we integrate batch normalization(BN)into the convolutional layers to simplify the computation process.For nonlinear activation functions,we use composite polynomials for approximate calculation.Regarding the noise accumulation caused by homomorphic multiplication operations,we realize the refreshment of ciphertext noise through minimal“decryption-encryption”interactions,instead of adopting bootstrapping operations.Additionally,in practical implementation,we convert three-dimensional convolution into two-dimensional convolution to reduce the amount of computation in the encryption domain.Finally,we conduct extensive experiments on four IoT datasets,different CNN architectures,and two platforms with different resource configurations to evaluate the performance of EPPA in detail.展开更多
Parkinson’s disease(PD)is a debilitating neurological disorder affecting over 10 million people worldwide.PD classification models using voice signals as input are common in the literature.It is believed that using d...Parkinson’s disease(PD)is a debilitating neurological disorder affecting over 10 million people worldwide.PD classification models using voice signals as input are common in the literature.It is believed that using deep learning algorithms further enhances performance;nevertheless,it is challenging due to the nature of small-scale and imbalanced PD datasets.This paper proposed a convolutional neural network-based deep support vector machine(CNN-DSVM)to automate the feature extraction process using CNN and extend the conventional SVM to a DSVM for better classification performance in small-scale PD datasets.A customized kernel function reduces the impact of biased classification towards the majority class(healthy candidates in our consideration).An improved generative adversarial network(IGAN)was designed to generate additional training data to enhance the model’s performance.For performance evaluation,the proposed algorithm achieves a sensitivity of 97.6%and a specificity of 97.3%.The performance comparison is evaluated from five perspectives,including comparisons with different data generation algorithms,feature extraction techniques,kernel functions,and existing works.Results reveal the effectiveness of the IGAN algorithm,which improves the sensitivity and specificity by 4.05%–4.72%and 4.96%–5.86%,respectively;and the effectiveness of the CNN-DSVM algorithm,which improves the sensitivity by 1.24%–57.4%and specificity by 1.04%–163%and reduces biased detection towards the majority class.The ablation experiments confirm the effectiveness of individual components.Two future research directions have also been suggested.展开更多
A new real and complex-valued hybrid time-delay neural network(TDNN)is proposed for modeling and linearizing the broad-band power amplifier(BPA).The neural network includes the generalized memory effect of input signa...A new real and complex-valued hybrid time-delay neural network(TDNN)is proposed for modeling and linearizing the broad-band power amplifier(BPA).The neural network includes the generalized memory effect of input signals,complex-valued input signals and the fractional order of a complex-valued input signal module,and,thus,the modeling accuracy is improved significantly.A comparative study of the normalized mean square error(NMSE)of the real and complex-valued hybrid TDNN for different spread constants,memory depths,node numbers,and order numbers is studied so as to establish an optimal TDNN as an effective baseband model,suitable for modeling strong nonlinearity of the BPA.A 51-dBm BPA with a 25-MHz bandwidth mixed test signal is used to verify the effectiveness of the proposed model.Compared with the memory polynomial(MP)model and the real-valued TDNN,the real and complex-valued hybrid TDNN is highly effective,leading to an improvement of 5 dB in the NMSE.In addition,the real and complex-valued hybrid TDNN has an improvement of 0.6 dB over the generalized MP model in the NMSE.Also,it has better numerical stability.Moreover,the proposed TDNN presents a significant improvement over the real-valued TDNN and the MP models in suppressing out-of-band spectral regrowth.展开更多
Recently,deep learning has been used to establish the nonlinear and nonintuitive mapping between physical structures and electromagnetic responses of meta-atoms for higher computational efficiency.However,to obtain su...Recently,deep learning has been used to establish the nonlinear and nonintuitive mapping between physical structures and electromagnetic responses of meta-atoms for higher computational efficiency.However,to obtain sufficiently accurate predictions,the conventional deep-learning-based method consumes excessive time to collect the data set,thus hindering its wide application in this interdisciplinary field.We introduce a spectral transfer-learning-based metasurface design method to achieve excellent performance on a small data set with only 1000 samples in the target waveband by utilizing open-source data from another spectral range.We demonstrate three transfer strategies and experimentally quantify their performance,among which the“frozen-none”robustly improves the prediction accuracy by∼26%compared to direct learning.We propose to use a complex-valued deep neural network during the training process to further improve the spectral predicting precision by∼30%compared to its real-valued counterparts.We design several typical teraherz metadevices by employing a hybrid inverse model consolidating this trained target network and a global optimization algorithm.The simulated results successfully validate the capability of our approach.Our work provides a universal methodology for efficient and accurate metasurface design in arbitrary wavebands,which will pave the way toward the automated and mass production of metasurfaces.展开更多
In this paper, the multistability issue is discussed for delayed complex-valued recurrent neural networks with discontinuous real-imaginary-type activation functions. Based on a fixed theorem and stability definition,...In this paper, the multistability issue is discussed for delayed complex-valued recurrent neural networks with discontinuous real-imaginary-type activation functions. Based on a fixed theorem and stability definition, sufficient criteria are established for the existence and stability of multiple equilibria of complex-valued recurrent neural networks. The number of stable equilibria is larger than that of real-valued recurrent neural networks, which can be used to achieve high-capacity associative memories. One numerical example is provided to show the effectiveness and superiority of the presented results.展开更多
This paper is concerned with the adaptive synchronization of fractional-order complex-valued chaotic neural networks(FOCVCNNs)with time-delay.The chaotic behaviors of a class of fractional-order complex-valued neural ...This paper is concerned with the adaptive synchronization of fractional-order complex-valued chaotic neural networks(FOCVCNNs)with time-delay.The chaotic behaviors of a class of fractional-order complex-valued neural network are investigated.Meanwhile,based on the complex-valued inequalities of fractional-order derivatives and the stability theory of fractional-order complex-valued systems,a new adaptive controller and new complex-valued update laws are proposed to construct a synchronization control model for fractional-order complex-valued chaotic neural networks.Finally,the numerical simulation results are presented to illustrate the effectiveness of the developed synchronization scheme.展开更多
Without dividing the complex-valued systems into two real-valued ones, a class of fractional-order complex-valued memristive neural networks(FCVMNNs) with time delay is investigated. Firstly, based on the complex-valu...Without dividing the complex-valued systems into two real-valued ones, a class of fractional-order complex-valued memristive neural networks(FCVMNNs) with time delay is investigated. Firstly, based on the complex-valued sign function, a novel complex-valued feedback controller is devised to research such systems. Under the framework of Filippov solution, differential inclusion theory and Lyapunov stability theorem, the finite-time Mittag-Leffler synchronization(FTMLS) of FCVMNNs with time delay can be realized. Meanwhile, the upper bound of the synchronization settling time(SST) is less conservative than previous results. In addition, by adjusting controller parameters, the global asymptotic synchronization of FCVMNNs with time delay can also be realized, which improves and enrich some existing results. Lastly,some simulation examples are designed to verify the validity of conclusions.展开更多
For a tridiagonal two-layer real six-neuron model,the Hopf bifurcation was investigated by studying the eigenvalue equations of the related linear system in the literature.In the present paper,we extend this two-layer...For a tridiagonal two-layer real six-neuron model,the Hopf bifurcation was investigated by studying the eigenvalue equations of the related linear system in the literature.In the present paper,we extend this two-layer real six-neuron network model into a complex-valued delayed network model.Based on the mathematical analysis method,some sufficient conditions to guarantee the existence of periodic oscillatory solutions are established under the assumption that the activation function can be separated into its real and imaginary parts.Our sufficient conditions obtained by the mathematical analysis method in this paper are simpler than those obtained by the Hopf bifurcation method.Computer simulation is provided to illustrate the correctness of the theoretical results.展开更多
Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay di...Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay differential equations(DDEs)and delay integrodifferential equations(DIDEs)with constant delays,primarily due to their low regularity at delayinduced breaking points.In this paper,a DNN method that combines multi-task learning(MTL)which is proposed to solve both the forward and inverse problems of DIDEs.The core idea of this approach is to divide the original equation into multiple tasks based on the delay,using auxiliary outputs to represent the integral terms,followed by the use of MTL to seamlessly incorporate the properties at the breaking points into the loss function.Furthermore,given the increased training dificulty associated with multiple tasks and outputs,we employ a sequential training scheme to reduce training complexity and provide reference solutions for subsequent tasks.This approach significantly enhances the approximation accuracy of solving DIDEs with DNNs,as demonstrated by comparisons with traditional DNN methods.We validate the effectiveness of this method through several numerical experiments,test various parameter sharing structures in MTL and compare the testing results of these structures.Finally,this method is implemented to solve the inverse problem of nonlinear DIDE and the results show that the unknown parameters of DIDE can be discovered with sparse or noisy data.展开更多
Metabolomics covers a wide range of applications in life sciences,biomedicine,and phytology.Data acquisition(to achieve high coverage and efficiency)and analysis(to pursue good classification)are two key segments invo...Metabolomics covers a wide range of applications in life sciences,biomedicine,and phytology.Data acquisition(to achieve high coverage and efficiency)and analysis(to pursue good classification)are two key segments involved in metabolomics workflows.Various chemometric approaches utilizing either pattern recognition or machine learning have been employed to separate different groups.However,insufficient feature extraction,inappropriate feature selection,overfitting,or underfitting lead to an insufficient capacity to discriminate plants that are often easily confused.Using two ginseng varieties,namely Panax japonicus(PJ)and Panax japonicus var.major(PJvm),containing the similar ginsenosides,we integrated pseudo-targeted metabolomics and deep neural network(DNN)modeling to achieve accurate species differentiation.A pseudo-targeted metabolomics approach was optimized through data acquisition mode,ion pairs generation,comparison between multiple reaction monitoring(MRM)and scheduled MRM(sMRM),and chromatographic elution gradient.In total,1980 ion pairs were monitored within 23 min,allowing for the most comprehensive ginseng metabolome analysis.The established DNN model demonstrated excellent classification performance(in terms of accuracy,precision,recall,F1 score,area under the curve,and receiver operating characteristic(ROC))using the entire metabolome data and feature-selection dataset,exhibiting superior advantages over random forest(RF),support vector machine(SVM),extreme gradient boosting(XGBoost),and multilayer perceptron(MLP).Moreover,DNNs were advantageous for automated feature learning,nonlinear modeling,adaptability,and generalization.This study confirmed practicality of the established strategy for efficient metabolomics data analysis and reliable classification performance even when using small-volume samples.This established approach holds promise for plant metabolomics and is not limited to ginseng.展开更多
For the diagnostics and health management of lithium-ion batteries,numerous models have been developed to understand their degradation characteristics.These models typically fall into two categories:data-driven models...For the diagnostics and health management of lithium-ion batteries,numerous models have been developed to understand their degradation characteristics.These models typically fall into two categories:data-driven models and physical models,each offering unique advantages but also facing limitations.Physics-informed neural networks(PINNs)provide a robust framework to integrate data-driven models with physical principles,ensuring consistency with underlying physics while enabling generalization across diverse operational conditions.This study introduces a PINN-based approach to reconstruct open circuit voltage(OCV)curves and estimate key ageing parameters at both the cell and electrode levels.These parameters include available capacity,electrode capacities,and lithium inventory capacity.The proposed method integrates OCV reconstruction models as functional components into convolutional neural networks(CNNs)and is validated using a public dataset.The results reveal that the estimated ageing parameters closely align with those obtained through offline OCV tests,with errors in reconstructed OCV curves remaining within 15 mV.This demonstrates the ability of the method to deliver fast and accurate degradation diagnostics at the electrode level,advancing the potential for precise and efficient battery health management.展开更多
The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to u...The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to understand complex mobility patterns.Deep learning techniques,such as graph neural networks(GNNs),are popular for their ability to capture spatio-temporal dependencies.However,these models often become overly complex due to the large number of hyper-parameters involved.In this study,we introduce Dynamic Multi-Graph Spatial-Temporal Graph Neural Ordinary Differential Equation Networks(DMST-GNODE),a framework based on ordinary differential equations(ODEs)that autonomously discovers effective spatial-temporal graph neural network(STGNN)architectures for traffic prediction tasks.The comparative analysis of DMST-GNODE and baseline models indicates that DMST-GNODE model demonstrates superior performance across multiple datasets,consistently achieving the lowest Root Mean Square Error(RMSE)and Mean Absolute Error(MAE)values,alongside the highest accuracy.On the BKK(Bangkok)dataset,it outperformed other models with an RMSE of 3.3165 and an accuracy of 0.9367 for a 20-min interval,maintaining this trend across 40 and 60 min.Similarly,on the PeMS08 dataset,DMST-GNODE achieved the best performance with an RMSE of 19.4863 and an accuracy of 0.9377 at 20 min,demonstrating its effectiveness over longer periods.The Los_Loop dataset results further emphasise this model’s advantage,with an RMSE of 3.3422 and an accuracy of 0.7643 at 20 min,consistently maintaining superiority across all time intervals.These numerical highlights indicate that DMST-GNODE not only outperforms baseline models but also achieves higher accuracy and lower errors across different time intervals and datasets.展开更多
The increasing popularity of the Internet and the widespread use of information technology have led to a rise in the number and sophistication of network attacks and security threats.Intrusion detection systems are cr...The increasing popularity of the Internet and the widespread use of information technology have led to a rise in the number and sophistication of network attacks and security threats.Intrusion detection systems are crucial to network security,playing a pivotal role in safeguarding networks from potential threats.However,in the context of an evolving landscape of sophisticated and elusive attacks,existing intrusion detection methodologies often overlook critical aspects such as changes in network topology over time and interactions between hosts.To address these issues,this paper proposes a real-time network intrusion detection method based on graph neural networks.The proposedmethod leverages the advantages of graph neural networks and employs a straightforward graph construction method to represent network traffic as dynamic graph-structured data.Additionally,a graph convolution operation with a multi-head attention mechanism is utilized to enhance the model’s ability to capture the intricate relationships within the graph structure comprehensively.Furthermore,it uses an integrated graph neural network to address dynamic graphs’structural and topological changes at different time points and the challenges of edge embedding in intrusion detection data.The edge classification problem is effectively transformed into node classification by employing a line graph data representation,which facilitates fine-grained intrusion detection tasks on dynamic graph node feature representations.The efficacy of the proposed method is evaluated using two commonly used intrusion detection datasets,UNSW-NB15 and NF-ToN-IoT-v2,and results are compared with previous studies in this field.The experimental results demonstrate that our proposed method achieves 99.3%and 99.96%accuracy on the two datasets,respectively,and outperforms the benchmark model in several evaluation metrics.展开更多
This study investigates photonuclear reaction(γ,n)cross-sections using Bayesian neural network(BNN)analysis.After determining the optimal network architecture,which features two hidden layers,each with 50 hidden node...This study investigates photonuclear reaction(γ,n)cross-sections using Bayesian neural network(BNN)analysis.After determining the optimal network architecture,which features two hidden layers,each with 50 hidden nodes,training was conducted for 30,000 iterations to ensure comprehensive data capture.By analyzing the distribution of absolute errors positively correlated with the cross-section for the isotope 159Tb,as well as the relative errors unrelated to the cross-section,we confirmed that the network effectively captured the data features without overfitting.Comparison with the TENDL-2021 Database demonstrated the BNN's reliability in fitting photonuclear cross-sections with lower average errors.The predictions for nuclei with single and double giant dipole resonance peak cross-sections,the accurate determination of the photoneutron reaction threshold in the low-energy region,and the precise description of trends in the high-energy cross-sections further demonstrate the network's generalization ability on the validation set.This can be attributed to the consistency of the training data.By using consistent training sets from different laboratories,Bayesian neural networks can predict nearby unknown cross-sections based on existing laboratory data,thereby estimating the potential differences between other laboratories'existing data and their own measurement results.Experimental measurements of photonuclear reactions on the newly constructed SLEGS beamline will contribute to clarifying the differences in cross-sections within the existing data.展开更多
Spectrum-based fault localization (SBFL) generates a ranked list of suspicious elements by using the program execution spectrum, but the excessive number of elements ranked in parallel results in low localization accu...Spectrum-based fault localization (SBFL) generates a ranked list of suspicious elements by using the program execution spectrum, but the excessive number of elements ranked in parallel results in low localization accuracy. Most researchers consider intra-class dependencies to improve localization accuracy. However, some studies show that inter-class method call type faults account for more than 20%, which means such methods still have certain limitations. To solve the above problems, this paper proposes a two-phase software fault localization based on relational graph convolutional neural networks (Two-RGCNFL). Firstly, in Phase 1, the method call dependence graph (MCDG) of the program is constructed, the intra-class and inter-class dependencies in MCDG are extracted by using the relational graph convolutional neural network, and the classifier is used to identify the faulty methods. Then, the GraphSMOTE algorithm is improved to alleviate the impact of class imbalance on classification accuracy. Aiming at the problem of parallel ranking of element suspicious values in traditional SBFL technology, in Phase 2, Doc2Vec is used to learn static features, while spectrum information serves as dynamic features. A RankNet model based on siamese multi-layer perceptron is constructed to score and rank statements in the faulty method. This work conducts experiments on 5 real projects of Defects4J benchmark. Experimental results show that, compared with the traditional SBFL technique and two baseline methods, our approach improves the Top-1 accuracy by 262.86%, 29.59% and 53.01%, respectively, which verifies the effectiveness of Two-RGCNFL. Furthermore, this work verifies the importance of inter-class dependencies through ablation experiments.展开更多
基金partially supported by the JSPS KAKENHI(JP22H03643,JP19K22891)。
文摘Complex-valued neural networks(CVNNs)have shown their excellent efficiency compared to their real counterparts in speech enhancement,image and signal processing.Researchers throughout the years have made many efforts to improve the learning algorithms and activation functions of CVNNs.Since CVNNs have proven to have better performance in handling the naturally complex-valued data and signals,this area of study will grow and expect the arrival of some effective improvements in the future.Therefore,there exists an obvious reason to provide a comprehensive survey paper that systematically collects and categorizes the advancement of CVNNs.In this paper,we discuss and summarize the recent advances based on their learning algorithms,activation functions,which is the most challenging part of building a CVNN,and applications.Besides,we outline the structure and applications of complex-valued convolutional,residual and recurrent neural networks.Finally,we also present some challenges and future research directions to facilitate the exploration of the ability of CVNNs.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.61503338,61573316,61374152,and 11302195)the Natural Science Foundation of Zhejiang Province,China(Grant No.LQ15F030005)
文摘In this paper, a novel design procedure is proposed for synthesizing high-capacity auto-associative memories based on complex-valued neural networks with real-imaginary-type activation functions and constant delays. Stability criteria dependent on external inputs of neural networks are derived. The designed networks can retrieve the stored patterns by external inputs rather than initial conditions. The derivation can memorize the desired patterns with lower-dimensional neural networks than real-valued neural networks, and eliminate spurious equilibria of complex-valued neural networks. One numerical example is provided to show the effectiveness and superiority of the presented results.
文摘In this paper, the singularity and its effect on learning dynamics in the complex-valued neural network are elucidated. It has learned that the linear combination structure in the updating rule of the complex-valued neural network increases the speed of moving away from the singular points, and the complex-valued neural network cannot be easily influenced by the singular points, whereas the learning of the usual real-valued neural network can be attracted in the neighborhood of singular points, which causes a standstill in learning. Simulation results on the learning dynamics of the three-layered real-valued and complex-valued neural networks in the neighborhood of singularities support the analytical results.
基金supported by the National Natural Science Foundation of China under Grant No.61863025International S&T Cooperation Projects of Gansu province under Grant No.144WCGA166Longyuan Young Innovation Talents and the Doctoral Foundation of LUT。
文摘The problem of exponential module-phase synchronization of complex-valued neural networks(CVNNs)with time-varying delay and stochastic perturbations was investigated.The model of CVNNs with time-varying delay and stochastic perturbations was considered.The error system was deduced and the module-phase synchronization was defined.Based on the principle of Lyapunov stability theory,the appropriate controller was designed to control the CVNNs.Finally,the effectiveness and reliability of the method were verified by the numerical simulations.
基金supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(2021R1A6A1A10044950).
文摘The thermal conductivity of nanofluids is an important property that influences the heat transfer capabilities of nanofluids.Researchers rely on experimental investigations to explore nanofluid properties,as it is a necessary step before their practical application.As these investigations are time and resource-consuming undertakings,an effective prediction model can significantly improve the efficiency of research operations.In this work,an Artificial Neural Network(ANN)model is developed to predict the thermal conductivity of metal oxide water-based nanofluid.For this,a comprehensive set of 691 data points was collected from the literature.This dataset is split into training(70%),validation(15%),and testing(15%)and used to train the ANN model.The developed model is a backpropagation artificial neural network with a 4–12–1 architecture.The performance of the developed model shows high accuracy with R values above 0.90 and rapid convergence.It shows that the developed ANN model accurately predicts the thermal conductivity of nanofluids.
基金supported by the Natural Science Foundation of China No.62362008the Major Scientific and Technological Special Project of Guizhou Province([2024]014).
文摘With the rapid development of the Artificial Intelligence of Things(AIoT),convolutional neural networks(CNNs)have demonstrated potential and remarkable performance in AIoT applications due to their excellent performance in various inference tasks.However,the users have concerns about privacy leakage for the use of AI and the performance and efficiency of computing on resource-constrained IoT edge devices.Therefore,this paper proposes an efficient privacy-preserving CNN framework(i.e.,EPPA)based on the Fully Homomorphic Encryption(FHE)scheme for AIoT application scenarios.In the plaintext domain,we verify schemes with different activation structures to determine the actual activation functions applicable to the corresponding ciphertext domain.Within the encryption domain,we integrate batch normalization(BN)into the convolutional layers to simplify the computation process.For nonlinear activation functions,we use composite polynomials for approximate calculation.Regarding the noise accumulation caused by homomorphic multiplication operations,we realize the refreshment of ciphertext noise through minimal“decryption-encryption”interactions,instead of adopting bootstrapping operations.Additionally,in practical implementation,we convert three-dimensional convolution into two-dimensional convolution to reduce the amount of computation in the encryption domain.Finally,we conduct extensive experiments on four IoT datasets,different CNN architectures,and two platforms with different resource configurations to evaluate the performance of EPPA in detail.
基金The work described in this paper was fully supported by a grant from Hong Kong Metropolitan University(RIF/2021/05).
文摘Parkinson’s disease(PD)is a debilitating neurological disorder affecting over 10 million people worldwide.PD classification models using voice signals as input are common in the literature.It is believed that using deep learning algorithms further enhances performance;nevertheless,it is challenging due to the nature of small-scale and imbalanced PD datasets.This paper proposed a convolutional neural network-based deep support vector machine(CNN-DSVM)to automate the feature extraction process using CNN and extend the conventional SVM to a DSVM for better classification performance in small-scale PD datasets.A customized kernel function reduces the impact of biased classification towards the majority class(healthy candidates in our consideration).An improved generative adversarial network(IGAN)was designed to generate additional training data to enhance the model’s performance.For performance evaluation,the proposed algorithm achieves a sensitivity of 97.6%and a specificity of 97.3%.The performance comparison is evaluated from five perspectives,including comparisons with different data generation algorithms,feature extraction techniques,kernel functions,and existing works.Results reveal the effectiveness of the IGAN algorithm,which improves the sensitivity and specificity by 4.05%–4.72%and 4.96%–5.86%,respectively;and the effectiveness of the CNN-DSVM algorithm,which improves the sensitivity by 1.24%–57.4%and specificity by 1.04%–163%and reduces biased detection towards the majority class.The ablation experiments confirm the effectiveness of individual components.Two future research directions have also been suggested.
基金The National Natural Science Foundation of China(No.61561052,61701262)the Science and Technology Foundation of Henan Province(No.182102410062,182102210114)the Science and Technology Foundation of Henan Educational Committee(No.17A510018)
文摘A new real and complex-valued hybrid time-delay neural network(TDNN)is proposed for modeling and linearizing the broad-band power amplifier(BPA).The neural network includes the generalized memory effect of input signals,complex-valued input signals and the fractional order of a complex-valued input signal module,and,thus,the modeling accuracy is improved significantly.A comparative study of the normalized mean square error(NMSE)of the real and complex-valued hybrid TDNN for different spread constants,memory depths,node numbers,and order numbers is studied so as to establish an optimal TDNN as an effective baseband model,suitable for modeling strong nonlinearity of the BPA.A 51-dBm BPA with a 25-MHz bandwidth mixed test signal is used to verify the effectiveness of the proposed model.Compared with the memory polynomial(MP)model and the real-valued TDNN,the real and complex-valued hybrid TDNN is highly effective,leading to an improvement of 5 dB in the NMSE.In addition,the real and complex-valued hybrid TDNN has an improvement of 0.6 dB over the generalized MP model in the NMSE.Also,it has better numerical stability.Moreover,the proposed TDNN presents a significant improvement over the real-valued TDNN and the MP models in suppressing out-of-band spectral regrowth.
基金support from the National Natural Science Foundation of China (Grant Nos.62027820,61975143,61735012,and 62205380).
文摘Recently,deep learning has been used to establish the nonlinear and nonintuitive mapping between physical structures and electromagnetic responses of meta-atoms for higher computational efficiency.However,to obtain sufficiently accurate predictions,the conventional deep-learning-based method consumes excessive time to collect the data set,thus hindering its wide application in this interdisciplinary field.We introduce a spectral transfer-learning-based metasurface design method to achieve excellent performance on a small data set with only 1000 samples in the target waveband by utilizing open-source data from another spectral range.We demonstrate three transfer strategies and experimentally quantify their performance,among which the“frozen-none”robustly improves the prediction accuracy by∼26%compared to direct learning.We propose to use a complex-valued deep neural network during the training process to further improve the spectral predicting precision by∼30%compared to its real-valued counterparts.We design several typical teraherz metadevices by employing a hybrid inverse model consolidating this trained target network and a global optimization algorithm.The simulated results successfully validate the capability of our approach.Our work provides a universal methodology for efficient and accurate metasurface design in arbitrary wavebands,which will pave the way toward the automated and mass production of metasurfaces.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.61374094 and 61503338)the Natural Science Foundation of Zhejiang Province,China(Grant No.LQ15F030005)
文摘In this paper, the multistability issue is discussed for delayed complex-valued recurrent neural networks with discontinuous real-imaginary-type activation functions. Based on a fixed theorem and stability definition, sufficient criteria are established for the existence and stability of multiple equilibria of complex-valued recurrent neural networks. The number of stable equilibria is larger than that of real-valued recurrent neural networks, which can be used to achieve high-capacity associative memories. One numerical example is provided to show the effectiveness and superiority of the presented results.
基金Project supported by the Science and Technology Support Program of Xingtai,China(Grant No.2019ZC054)。
文摘This paper is concerned with the adaptive synchronization of fractional-order complex-valued chaotic neural networks(FOCVCNNs)with time-delay.The chaotic behaviors of a class of fractional-order complex-valued neural network are investigated.Meanwhile,based on the complex-valued inequalities of fractional-order derivatives and the stability theory of fractional-order complex-valued systems,a new adaptive controller and new complex-valued update laws are proposed to construct a synchronization control model for fractional-order complex-valued chaotic neural networks.Finally,the numerical simulation results are presented to illustrate the effectiveness of the developed synchronization scheme.
基金Project supported by the National Natural Science Foundation of China (Grant Nos. 62176189 and 62106181)the Hubei Province Key Laboratory of Systems Science in Metallurgical Process (Wuhan University of Science and Technology) (Grant No. Y202002)。
文摘Without dividing the complex-valued systems into two real-valued ones, a class of fractional-order complex-valued memristive neural networks(FCVMNNs) with time delay is investigated. Firstly, based on the complex-valued sign function, a novel complex-valued feedback controller is devised to research such systems. Under the framework of Filippov solution, differential inclusion theory and Lyapunov stability theorem, the finite-time Mittag-Leffler synchronization(FTMLS) of FCVMNNs with time delay can be realized. Meanwhile, the upper bound of the synchronization settling time(SST) is less conservative than previous results. In addition, by adjusting controller parameters, the global asymptotic synchronization of FCVMNNs with time delay can also be realized, which improves and enrich some existing results. Lastly,some simulation examples are designed to verify the validity of conclusions.
文摘For a tridiagonal two-layer real six-neuron model,the Hopf bifurcation was investigated by studying the eigenvalue equations of the related linear system in the literature.In the present paper,we extend this two-layer real six-neuron network model into a complex-valued delayed network model.Based on the mathematical analysis method,some sufficient conditions to guarantee the existence of periodic oscillatory solutions are established under the assumption that the activation function can be separated into its real and imaginary parts.Our sufficient conditions obtained by the mathematical analysis method in this paper are simpler than those obtained by the Hopf bifurcation method.Computer simulation is provided to illustrate the correctness of the theoretical results.
文摘Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay differential equations(DDEs)and delay integrodifferential equations(DIDEs)with constant delays,primarily due to their low regularity at delayinduced breaking points.In this paper,a DNN method that combines multi-task learning(MTL)which is proposed to solve both the forward and inverse problems of DIDEs.The core idea of this approach is to divide the original equation into multiple tasks based on the delay,using auxiliary outputs to represent the integral terms,followed by the use of MTL to seamlessly incorporate the properties at the breaking points into the loss function.Furthermore,given the increased training dificulty associated with multiple tasks and outputs,we employ a sequential training scheme to reduce training complexity and provide reference solutions for subsequent tasks.This approach significantly enhances the approximation accuracy of solving DIDEs with DNNs,as demonstrated by comparisons with traditional DNN methods.We validate the effectiveness of this method through several numerical experiments,test various parameter sharing structures in MTL and compare the testing results of these structures.Finally,this method is implemented to solve the inverse problem of nonlinear DIDE and the results show that the unknown parameters of DIDE can be discovered with sparse or noisy data.
基金supported by the National Key R&D Program of China(Grant No.:2022YFC3501805)the National Natural Science Foundation of China(Grant No.:82374030)+2 种基金the Science and Technology Program of Tianjin in China(Grant No.:23ZYJDSS00030)the Tianjin Outstanding Youth Fund,China(Grant No.:23JCJQJC00030)the China Postdoctoral Science Foundation-Tianjin Joint Support Program(Grant No.:2023T030TJ).
文摘Metabolomics covers a wide range of applications in life sciences,biomedicine,and phytology.Data acquisition(to achieve high coverage and efficiency)and analysis(to pursue good classification)are two key segments involved in metabolomics workflows.Various chemometric approaches utilizing either pattern recognition or machine learning have been employed to separate different groups.However,insufficient feature extraction,inappropriate feature selection,overfitting,or underfitting lead to an insufficient capacity to discriminate plants that are often easily confused.Using two ginseng varieties,namely Panax japonicus(PJ)and Panax japonicus var.major(PJvm),containing the similar ginsenosides,we integrated pseudo-targeted metabolomics and deep neural network(DNN)modeling to achieve accurate species differentiation.A pseudo-targeted metabolomics approach was optimized through data acquisition mode,ion pairs generation,comparison between multiple reaction monitoring(MRM)and scheduled MRM(sMRM),and chromatographic elution gradient.In total,1980 ion pairs were monitored within 23 min,allowing for the most comprehensive ginseng metabolome analysis.The established DNN model demonstrated excellent classification performance(in terms of accuracy,precision,recall,F1 score,area under the curve,and receiver operating characteristic(ROC))using the entire metabolome data and feature-selection dataset,exhibiting superior advantages over random forest(RF),support vector machine(SVM),extreme gradient boosting(XGBoost),and multilayer perceptron(MLP).Moreover,DNNs were advantageous for automated feature learning,nonlinear modeling,adaptability,and generalization.This study confirmed practicality of the established strategy for efficient metabolomics data analysis and reliable classification performance even when using small-volume samples.This established approach holds promise for plant metabolomics and is not limited to ginseng.
基金supported by the Beijing Natural Science Foundation(Grant No.L223013)。
文摘For the diagnostics and health management of lithium-ion batteries,numerous models have been developed to understand their degradation characteristics.These models typically fall into two categories:data-driven models and physical models,each offering unique advantages but also facing limitations.Physics-informed neural networks(PINNs)provide a robust framework to integrate data-driven models with physical principles,ensuring consistency with underlying physics while enabling generalization across diverse operational conditions.This study introduces a PINN-based approach to reconstruct open circuit voltage(OCV)curves and estimate key ageing parameters at both the cell and electrode levels.These parameters include available capacity,electrode capacities,and lithium inventory capacity.The proposed method integrates OCV reconstruction models as functional components into convolutional neural networks(CNNs)and is validated using a public dataset.The results reveal that the estimated ageing parameters closely align with those obtained through offline OCV tests,with errors in reconstructed OCV curves remaining within 15 mV.This demonstrates the ability of the method to deliver fast and accurate degradation diagnostics at the electrode level,advancing the potential for precise and efficient battery health management.
文摘The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to understand complex mobility patterns.Deep learning techniques,such as graph neural networks(GNNs),are popular for their ability to capture spatio-temporal dependencies.However,these models often become overly complex due to the large number of hyper-parameters involved.In this study,we introduce Dynamic Multi-Graph Spatial-Temporal Graph Neural Ordinary Differential Equation Networks(DMST-GNODE),a framework based on ordinary differential equations(ODEs)that autonomously discovers effective spatial-temporal graph neural network(STGNN)architectures for traffic prediction tasks.The comparative analysis of DMST-GNODE and baseline models indicates that DMST-GNODE model demonstrates superior performance across multiple datasets,consistently achieving the lowest Root Mean Square Error(RMSE)and Mean Absolute Error(MAE)values,alongside the highest accuracy.On the BKK(Bangkok)dataset,it outperformed other models with an RMSE of 3.3165 and an accuracy of 0.9367 for a 20-min interval,maintaining this trend across 40 and 60 min.Similarly,on the PeMS08 dataset,DMST-GNODE achieved the best performance with an RMSE of 19.4863 and an accuracy of 0.9377 at 20 min,demonstrating its effectiveness over longer periods.The Los_Loop dataset results further emphasise this model’s advantage,with an RMSE of 3.3422 and an accuracy of 0.7643 at 20 min,consistently maintaining superiority across all time intervals.These numerical highlights indicate that DMST-GNODE not only outperforms baseline models but also achieves higher accuracy and lower errors across different time intervals and datasets.
文摘The increasing popularity of the Internet and the widespread use of information technology have led to a rise in the number and sophistication of network attacks and security threats.Intrusion detection systems are crucial to network security,playing a pivotal role in safeguarding networks from potential threats.However,in the context of an evolving landscape of sophisticated and elusive attacks,existing intrusion detection methodologies often overlook critical aspects such as changes in network topology over time and interactions between hosts.To address these issues,this paper proposes a real-time network intrusion detection method based on graph neural networks.The proposedmethod leverages the advantages of graph neural networks and employs a straightforward graph construction method to represent network traffic as dynamic graph-structured data.Additionally,a graph convolution operation with a multi-head attention mechanism is utilized to enhance the model’s ability to capture the intricate relationships within the graph structure comprehensively.Furthermore,it uses an integrated graph neural network to address dynamic graphs’structural and topological changes at different time points and the challenges of edge embedding in intrusion detection data.The edge classification problem is effectively transformed into node classification by employing a line graph data representation,which facilitates fine-grained intrusion detection tasks on dynamic graph node feature representations.The efficacy of the proposed method is evaluated using two commonly used intrusion detection datasets,UNSW-NB15 and NF-ToN-IoT-v2,and results are compared with previous studies in this field.The experimental results demonstrate that our proposed method achieves 99.3%and 99.96%accuracy on the two datasets,respectively,and outperforms the benchmark model in several evaluation metrics.
基金supported by National key research and development program(No.2022YFA1602404)the National Natural Science Foundation of China(Nos.12388102,12275338,12005280)the Key Laboratory of Nuclear Data foundation(No.JCKY2022201C152)。
文摘This study investigates photonuclear reaction(γ,n)cross-sections using Bayesian neural network(BNN)analysis.After determining the optimal network architecture,which features two hidden layers,each with 50 hidden nodes,training was conducted for 30,000 iterations to ensure comprehensive data capture.By analyzing the distribution of absolute errors positively correlated with the cross-section for the isotope 159Tb,as well as the relative errors unrelated to the cross-section,we confirmed that the network effectively captured the data features without overfitting.Comparison with the TENDL-2021 Database demonstrated the BNN's reliability in fitting photonuclear cross-sections with lower average errors.The predictions for nuclei with single and double giant dipole resonance peak cross-sections,the accurate determination of the photoneutron reaction threshold in the low-energy region,and the precise description of trends in the high-energy cross-sections further demonstrate the network's generalization ability on the validation set.This can be attributed to the consistency of the training data.By using consistent training sets from different laboratories,Bayesian neural networks can predict nearby unknown cross-sections based on existing laboratory data,thereby estimating the potential differences between other laboratories'existing data and their own measurement results.Experimental measurements of photonuclear reactions on the newly constructed SLEGS beamline will contribute to clarifying the differences in cross-sections within the existing data.
基金funded by the Youth Fund of the National Natural Science Foundation of China(Grant No.42261070).
文摘Spectrum-based fault localization (SBFL) generates a ranked list of suspicious elements by using the program execution spectrum, but the excessive number of elements ranked in parallel results in low localization accuracy. Most researchers consider intra-class dependencies to improve localization accuracy. However, some studies show that inter-class method call type faults account for more than 20%, which means such methods still have certain limitations. To solve the above problems, this paper proposes a two-phase software fault localization based on relational graph convolutional neural networks (Two-RGCNFL). Firstly, in Phase 1, the method call dependence graph (MCDG) of the program is constructed, the intra-class and inter-class dependencies in MCDG are extracted by using the relational graph convolutional neural network, and the classifier is used to identify the faulty methods. Then, the GraphSMOTE algorithm is improved to alleviate the impact of class imbalance on classification accuracy. Aiming at the problem of parallel ranking of element suspicious values in traditional SBFL technology, in Phase 2, Doc2Vec is used to learn static features, while spectrum information serves as dynamic features. A RankNet model based on siamese multi-layer perceptron is constructed to score and rank statements in the faulty method. This work conducts experiments on 5 real projects of Defects4J benchmark. Experimental results show that, compared with the traditional SBFL technique and two baseline methods, our approach improves the Top-1 accuracy by 262.86%, 29.59% and 53.01%, respectively, which verifies the effectiveness of Two-RGCNFL. Furthermore, this work verifies the importance of inter-class dependencies through ablation experiments.
