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
Solutions of inverse problems are required in various fields of science and engineering. The concept of network inversion has been studied as a neural-network-based solution to inverse problems. In general, inverse pr...Solutions of inverse problems are required in various fields of science and engineering. The concept of network inversion has been studied as a neural-network-based solution to inverse problems. In general, inverse problems are not limited to a real-valued area. Recently, complex-valued neural networks have been actively studied in the field of neural networks. As an extension of network inversion to complex numbers, a complex-valued network inversion has been proposed. Moreover, inverse problems for estimating the parameters of distributed generation systems such as distributed energy plants or smart grids from observed electric circuit data have been studied in the field of natural energy. These emphasize the need to handle complex numbers in an alternating current （AC） circuit. In this paper, the authors propose an application of the complex-valued network inversion to the inverse estimation of a distributed generation. Further, the authors confirm the effectiveness of the complex-valued network inversion on the basis of simulation results.展开更多
Multi-link networks are universal in the real world such as relationship networks,transportation networks,and communication networks.It is significant to investigate the synchronization of the network with multi-link....Multi-link networks are universal in the real world such as relationship networks,transportation networks,and communication networks.It is significant to investigate the synchronization of the network with multi-link.In this paper,considering the complex network with uncertain parameters,new adaptive controller and update laws are proposed to ensure that complex-valued multilink network realizes finite-time complex projective synchronization(FTCPS).In addition,based on fractional-order Lyapunov functional method and finite-time stability theory,the criteria of FTCPS are derived and synchronization time is given which is associated with fractional order and control parameters.Meanwhile,numerical example is given to verify the validity of proposed finite-time complex projection strategy and analyze the relationship between synchronization time and fractional order and control parameters.Finally,the network is applied to image encryption,and the security analysis is carried out to verify the correctness of this method.展开更多
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
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
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
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
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
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
As an optical processor,a diffractive deep neural network(D2NN)utilizes engineered diffractive surfaces designed through machine learning to perform all-optical information processing,completing its tasks at the speed...As an optical processor,a diffractive deep neural network(D2NN)utilizes engineered diffractive surfaces designed through machine learning to perform all-optical information processing,completing its tasks at the speed of light propagation through thin optical layers.With sufficient degrees of freedom,D2NNs can perform arbitrary complex-valued linear transformations using spatially coherent light.Similarly,D2NNs can also perform arbitrary linear intensity transformations with spatially incoherent illumination;however,under spatially incoherent light,these transformations are nonnegative,acting on diffraction-limited optical intensity patterns at the input field of view.Here,we expand the use of spatially incoherent D2NNs to complex-valued information processing for executing arbitrary complex-valued linear transformations using spatially incoherent light.Through simulations,we show that as the number of optimized diffractive features increases beyond a threshold dictated by the multiplication of the input and output space-bandwidth products,a spatially incoherent diffractive visual processor can approximate any complex-valued linear transformation and be used for all-optical image encryption using incoherent illumination.The findings are important for the all-optical processing of information under natural light using various forms of diffractive surface-based optical processors.展开更多
Despite the superior advantages of specific emitter identification in extracting emitter features from in-phase and quadrature(I/Q)signals,challenges persist due to signal-type confusion and background noise interfere...Despite the superior advantages of specific emitter identification in extracting emitter features from in-phase and quadrature(I/Q)signals,challenges persist due to signal-type confusion and background noise interference.To address those limitations,this paper proposes a multi-channel contrast prediction coding and complex-valued residuals network(MCPC-MCVResNet)framework.This model employs contrast prediction techniques to directly extract discriminative features from electromagnetic signal sequences,effectively capturing both amplitude and phase information within I/Q data.A core innovation of this approach is the sphere space softmax(SS-softmax)loss,which optimizes intra-class clustering density of while establishing well-defined boundaries between distinct emitters.The SS-softmax mechanism significantly enhances the model's capacity to discern subtle variations among radiation emitters.Experimental results demonstrate superior identification accuracy,rapid convergence,and exceptional robustness in low signal-to-noise ratio environments.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
Optimizing routing and resource allocation in decentralized unmanned aerial vehicle(UAV)networks remains challenging due to interference and rapidly changing topologies.The authors introduce a novel framework combinin...Optimizing routing and resource allocation in decentralized unmanned aerial vehicle(UAV)networks remains challenging due to interference and rapidly changing topologies.The authors introduce a novel framework combining double deep Q-networks(DDQNs)and graph neural networks(GNNs)for joint routing and resource allocation.The framework uses GNNs to model the network topology and DDQNs to adaptively control routing and resource allocation,addressing interference and improving network performance.Simulation results show that the proposed approach outperforms traditional methods such as Closest-to-Destination(c2Dst),Max-SINR(mSINR),and Multi-Layer Perceptron(MLP)-based models,achieving approximately 23.5% improvement in throughput,50% increase in connection probability,and 17.6% reduction in number of hops,demonstrating its effectiveness in dynamic UAV networks.展开更多
To explore the material basis and mechanisms of the anti-inflammatory effects of Hibiscus mutabilis L..The active ingredients and potential targets of Hibiscus mutabilis L.were obtained through the literature review a...To explore the material basis and mechanisms of the anti-inflammatory effects of Hibiscus mutabilis L..The active ingredients and potential targets of Hibiscus mutabilis L.were obtained through the literature review and SwissADME platform.Genes related to the inflammation were collected using Genecards and OMIM databases,and the intersection genes were submitted on STRING and DAVID websites.Then,the protein interaction network(PPI),gene ontology(GO)and pathway(KEGG)were analyzed.Cytoscape 3.7.2 software was used to construct the“Hibiscus mutabilis L.-active ingredient-target-inflammation”network diagram,and AutoDockTools-1.5.6 software was used for the molecular docking verification.The antiinflammatory effect of Hibiscus mutabilis L.active ingredient was verified by the RAW264.7 inflammatory cell model.The results showed that 11 active components and 94 potential targets,1029 inflammatory targets and 24 intersection targets were obtained from Hibiscus mutabilis L..The key anti-inflammatory active ingredients of Hibiscus mutabilis L.are quercetin,apigenin and luteolin.Its action pathway is mainly related to NF-κB,cancer pathway and TNF signaling pathway.Cell experiments showed that total flavonoids of Hibiscus mutabilis L.could effectively inhibit the expression of tumor necrosis factor(TNF-α),interleukin 8(IL-8)and epidermal growth factor receptor(EGFR)in LPS-induced RAW 264.7 inflammatory cells.It also downregulates the phosphorylation of human nuclear factor ĸB inhibitory protein α(IĸBα)and NF-κB p65 subunit protein(p65).Overall,the anti-inflammatory effect of Hibiscus mutabilis L.is related to many active components,many signal pathways and targets,which provides a theoretical basis for its further development and application.展开更多
As the demand for high-quality services proliferates,an innovative network architecture,the fully-decoupled RAN(FD-RAN),has emerged for more flexible spectrum resource utilization and lower network costs.However,with ...As the demand for high-quality services proliferates,an innovative network architecture,the fully-decoupled RAN(FD-RAN),has emerged for more flexible spectrum resource utilization and lower network costs.However,with the decoupling of uplink base stations and downlink base stations in FDRAN,the traditional transmission mechanism,which relies on real-time channel feedback,is not suitable as the receiver is not able to feedback accurate and timely channel state information to the transmitter.This paper proposes a novel transmission scheme without relying on physical layer channel feedback.Specifically,we design a radio map based complex-valued precoding network(RMCPNet)model,which outputs the base station precoding based on user location.RMCPNet comprises multiple subnets,with each subnet responsible for extracting unique modal features from diverse input modalities.Furthermore,the multimodal embeddings derived from these distinct subnets are integrated within the information fusion layer,culminating in a unified representation.We also develop a specific RMCPNet training algorithm that employs the negative spectral efficiency as the loss function.We evaluate the performance of the proposed scheme on the public DeepMIMO dataset and show that RMCPNet can achieve 16%and 76%performance improvements over the conventional real-valued neural network and statistical codebook approach,respectively.展开更多
Distributed Denial of Service(DDoS)attacks are one of the severe threats to network infrastructure,sometimes bypassing traditional diagnosis algorithms because of their evolving complexity.PresentMachine Learning(ML)t...Distributed Denial of Service(DDoS)attacks are one of the severe threats to network infrastructure,sometimes bypassing traditional diagnosis algorithms because of their evolving complexity.PresentMachine Learning(ML)techniques for DDoS attack diagnosis normally apply network traffic statistical features such as packet sizes and inter-arrival times.However,such techniques sometimes fail to capture complicated relations among various traffic flows.In this paper,we present a new multi-scale ensemble strategy given the Graph Neural Networks(GNNs)for improving DDoS detection.Our technique divides traffic into macro-and micro-level elements,letting various GNN models to get the two corase-scale anomalies and subtle,stealthy attack models.Through modeling network traffic as graph-structured data,GNNs efficiently learn intricate relations among network entities.The proposed ensemble learning algorithm combines the results of several GNNs to improve generalization,robustness,and scalability.Extensive experiments on three benchmark datasets—UNSW-NB15,CICIDS2017,and CICDDoS2019—show that our approach outperforms traditional machine learning and deep learning models in detecting both high-rate and low-rate(stealthy)DDoS attacks,with significant improvements in accuracy and recall.These findings demonstrate the suggested method’s applicability and robustness for real-world implementation in contexts where several DDoS patterns coexist.展开更多
With the growing complexity and decentralization of network systems,the attack surface has expanded,which has led to greater concerns over network threats.In this context,artificial intelligence(AI)-based network intr...With the growing complexity and decentralization of network systems,the attack surface has expanded,which has led to greater concerns over network threats.In this context,artificial intelligence(AI)-based network intrusion detection systems(NIDS)have been extensively studied,and recent efforts have shifted toward integrating distributed learning to enable intelligent and scalable detection mechanisms.However,most existing works focus on individual distributed learning frameworks,and there is a lack of systematic evaluations that compare different algorithms under consistent conditions.In this paper,we present a comprehensive evaluation of representative distributed learning frameworks—Federated Learning(FL),Split Learning(SL),hybrid collaborative learning(SFL),and fully distributed learning—in the context of AI-driven NIDS.Using recent benchmark intrusion detection datasets,a unified model backbone,and controlled distributed scenarios,we assess these frameworks across multiple criteria,including detection performance,communication cost,computational efficiency,and convergence behavior.Our findings highlight distinct trade-offs among the distributed learning frameworks,demonstrating that the optimal choice depends strongly on systemconstraints such as bandwidth availability,node resources,and data distribution.This work provides the first holistic analysis of distributed learning approaches for AI-driven NIDS and offers practical guidelines for designing secure and efficient intrusion detection systems in decentralized environments.展开更多
Identifying the community structure of complex networks is crucial to extracting insights and understanding network properties.Although several community detection methods have been proposed,many are unsuitable for so...Identifying the community structure of complex networks is crucial to extracting insights and understanding network properties.Although several community detection methods have been proposed,many are unsuitable for social networks due to significant limitations.Specifically,most approaches depend mainly on user-user structural links while overlooking service-centric,semantic,and multi-attribute drivers of community formation,and they also lack flexible filtering mechanisms for large-scale,service-oriented settings.Our proposed approach,called community discovery-based service(CDBS),leverages user profiles and their interactions with consulted web services.The method introduces a novel similarity measure,global similarity interaction profile(GSIP),which goes beyond typical similarity measures by unifying user and service profiles for all attributes types into a coherent representation,thereby clarifying its novelty and contribution.It applies multiple filtering criteria related to user attributes,accessed services,and interaction patterns.Experimental comparisons against Louvain,Hierarchical Agglomerative Clustering,Label Propagation and Infomap show that CDBS reveals the higher performance as it achieves 0.74 modularity,0.13 conductance,0.77 coverage,and significantly fast response time of 9.8 s,even with 10,000 users and 400 services.Moreover,community discoverybased service consistently detects a larger number of communities with distinct topics of interest,underscoring its capacity to generate detailed and efficient structures in complex networks.These results confirm both the efficiency and effectiveness of the proposed method.Beyond controlled evaluation,communities discovery based service is applicable to targeted recommendations,group-oriented marketing,access control,and service personalization,where communities are shaped not only by user links but also by service engagement.展开更多
With network attack technology continuing to develop,traditional anomaly traffic detection methods that rely on feature engineering are increasingly insufficient in efficiency and accuracy.Graph Neural Network(GNN),a ...With network attack technology continuing to develop,traditional anomaly traffic detection methods that rely on feature engineering are increasingly insufficient in efficiency and accuracy.Graph Neural Network(GNN),a promising Deep Learning(DL)approach,has proven to be highly effective in identifying intricate patterns in graph⁃structured data and has already found wide applications in the field of network security.In this paper,we propose a hybrid Graph Convolutional Network(GCN)⁃GraphSAGE model for Anomaly Traffic Detection,namely HGS⁃ATD,which aims to improve the accuracy of anomaly traffic detection by leveraging edge feature learning to better capture the relationships between network entities.We validate the HGS⁃ATD model on four publicly available datasets,including NF⁃UNSW⁃NB15⁃v2.The experimental results show that the enhanced hybrid model is 5.71%to 10.25%higher than the baseline model in terms of accuracy,and the F1⁃score is 5.53%to 11.63%higher than the baseline model,proving that the model can effectively distinguish normal traffic from attack traffic and accurately classify various types of attacks.展开更多
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Solutions of inverse problems are required in various fields of science and engineering. The concept of network inversion has been studied as a neural-network-based solution to inverse problems. In general, inverse problems are not limited to a real-valued area. Recently, complex-valued neural networks have been actively studied in the field of neural networks. As an extension of network inversion to complex numbers, a complex-valued network inversion has been proposed. Moreover, inverse problems for estimating the parameters of distributed generation systems such as distributed energy plants or smart grids from observed electric circuit data have been studied in the field of natural energy. These emphasize the need to handle complex numbers in an alternating current （AC） circuit. In this paper, the authors propose an application of the complex-valued network inversion to the inverse estimation of a distributed generation. Further, the authors confirm the effectiveness of the complex-valued network inversion on the basis of simulation results.
文摘Multi-link networks are universal in the real world such as relationship networks,transportation networks,and communication networks.It is significant to investigate the synchronization of the network with multi-link.In this paper,considering the complex network with uncertain parameters,new adaptive controller and update laws are proposed to ensure that complex-valued multilink network realizes finite-time complex projective synchronization(FTCPS).In addition,based on fractional-order Lyapunov functional method and finite-time stability theory,the criteria of FTCPS are derived and synchronization time is given which is associated with fractional order and control parameters.Meanwhile,numerical example is given to verify the validity of proposed finite-time complex projection strategy and analyze the relationship between synchronization time and fractional order and control parameters.Finally,the network is applied to image encryption,and the security analysis is carried out to verify the correctness of this method.
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.
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 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.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 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.
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 of the U.S.Department of Energy (DOE),Office of Basic Energy Sciences,Division of Materials Sciences and Engineering under Award#DE-SC0023088.
文摘As an optical processor,a diffractive deep neural network(D2NN)utilizes engineered diffractive surfaces designed through machine learning to perform all-optical information processing,completing its tasks at the speed of light propagation through thin optical layers.With sufficient degrees of freedom,D2NNs can perform arbitrary complex-valued linear transformations using spatially coherent light.Similarly,D2NNs can also perform arbitrary linear intensity transformations with spatially incoherent illumination;however,under spatially incoherent light,these transformations are nonnegative,acting on diffraction-limited optical intensity patterns at the input field of view.Here,we expand the use of spatially incoherent D2NNs to complex-valued information processing for executing arbitrary complex-valued linear transformations using spatially incoherent light.Through simulations,we show that as the number of optimized diffractive features increases beyond a threshold dictated by the multiplication of the input and output space-bandwidth products,a spatially incoherent diffractive visual processor can approximate any complex-valued linear transformation and be used for all-optical image encryption using incoherent illumination.The findings are important for the all-optical processing of information under natural light using various forms of diffractive surface-based optical processors.
基金supported by the National Natural Science Foundation of China(62201602)。
文摘Despite the superior advantages of specific emitter identification in extracting emitter features from in-phase and quadrature(I/Q)signals,challenges persist due to signal-type confusion and background noise interference.To address those limitations,this paper proposes a multi-channel contrast prediction coding and complex-valued residuals network(MCPC-MCVResNet)framework.This model employs contrast prediction techniques to directly extract discriminative features from electromagnetic signal sequences,effectively capturing both amplitude and phase information within I/Q data.A core innovation of this approach is the sphere space softmax(SS-softmax)loss,which optimizes intra-class clustering density of while establishing well-defined boundaries between distinct emitters.The SS-softmax mechanism significantly enhances the model's capacity to discern subtle variations among radiation emitters.Experimental results demonstrate superior identification accuracy,rapid convergence,and exceptional robustness in low signal-to-noise ratio environments.
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.
文摘Optimizing routing and resource allocation in decentralized unmanned aerial vehicle(UAV)networks remains challenging due to interference and rapidly changing topologies.The authors introduce a novel framework combining double deep Q-networks(DDQNs)and graph neural networks(GNNs)for joint routing and resource allocation.The framework uses GNNs to model the network topology and DDQNs to adaptively control routing and resource allocation,addressing interference and improving network performance.Simulation results show that the proposed approach outperforms traditional methods such as Closest-to-Destination(c2Dst),Max-SINR(mSINR),and Multi-Layer Perceptron(MLP)-based models,achieving approximately 23.5% improvement in throughput,50% increase in connection probability,and 17.6% reduction in number of hops,demonstrating its effectiveness in dynamic UAV networks.
文摘To explore the material basis and mechanisms of the anti-inflammatory effects of Hibiscus mutabilis L..The active ingredients and potential targets of Hibiscus mutabilis L.were obtained through the literature review and SwissADME platform.Genes related to the inflammation were collected using Genecards and OMIM databases,and the intersection genes were submitted on STRING and DAVID websites.Then,the protein interaction network(PPI),gene ontology(GO)and pathway(KEGG)were analyzed.Cytoscape 3.7.2 software was used to construct the“Hibiscus mutabilis L.-active ingredient-target-inflammation”network diagram,and AutoDockTools-1.5.6 software was used for the molecular docking verification.The antiinflammatory effect of Hibiscus mutabilis L.active ingredient was verified by the RAW264.7 inflammatory cell model.The results showed that 11 active components and 94 potential targets,1029 inflammatory targets and 24 intersection targets were obtained from Hibiscus mutabilis L..The key anti-inflammatory active ingredients of Hibiscus mutabilis L.are quercetin,apigenin and luteolin.Its action pathway is mainly related to NF-κB,cancer pathway and TNF signaling pathway.Cell experiments showed that total flavonoids of Hibiscus mutabilis L.could effectively inhibit the expression of tumor necrosis factor(TNF-α),interleukin 8(IL-8)and epidermal growth factor receptor(EGFR)in LPS-induced RAW 264.7 inflammatory cells.It also downregulates the phosphorylation of human nuclear factor ĸB inhibitory protein α(IĸBα)and NF-κB p65 subunit protein(p65).Overall,the anti-inflammatory effect of Hibiscus mutabilis L.is related to many active components,many signal pathways and targets,which provides a theoretical basis for its further development and application.
基金supported in part by the National Natural Science Foundation Original Exploration Project of China under Grant 62250004the National Natural Science Foundation of China under Grant 62271244+1 种基金the Natural Science Fund for Distinguished Young Scholars of Jiangsu Province under Grant BK20220067the Natural Sciences and Engineering Research Council of Canada (NSERC)
文摘As the demand for high-quality services proliferates,an innovative network architecture,the fully-decoupled RAN(FD-RAN),has emerged for more flexible spectrum resource utilization and lower network costs.However,with the decoupling of uplink base stations and downlink base stations in FDRAN,the traditional transmission mechanism,which relies on real-time channel feedback,is not suitable as the receiver is not able to feedback accurate and timely channel state information to the transmitter.This paper proposes a novel transmission scheme without relying on physical layer channel feedback.Specifically,we design a radio map based complex-valued precoding network(RMCPNet)model,which outputs the base station precoding based on user location.RMCPNet comprises multiple subnets,with each subnet responsible for extracting unique modal features from diverse input modalities.Furthermore,the multimodal embeddings derived from these distinct subnets are integrated within the information fusion layer,culminating in a unified representation.We also develop a specific RMCPNet training algorithm that employs the negative spectral efficiency as the loss function.We evaluate the performance of the proposed scheme on the public DeepMIMO dataset and show that RMCPNet can achieve 16%and 76%performance improvements over the conventional real-valued neural network and statistical codebook approach,respectively.
文摘Distributed Denial of Service(DDoS)attacks are one of the severe threats to network infrastructure,sometimes bypassing traditional diagnosis algorithms because of their evolving complexity.PresentMachine Learning(ML)techniques for DDoS attack diagnosis normally apply network traffic statistical features such as packet sizes and inter-arrival times.However,such techniques sometimes fail to capture complicated relations among various traffic flows.In this paper,we present a new multi-scale ensemble strategy given the Graph Neural Networks(GNNs)for improving DDoS detection.Our technique divides traffic into macro-and micro-level elements,letting various GNN models to get the two corase-scale anomalies and subtle,stealthy attack models.Through modeling network traffic as graph-structured data,GNNs efficiently learn intricate relations among network entities.The proposed ensemble learning algorithm combines the results of several GNNs to improve generalization,robustness,and scalability.Extensive experiments on three benchmark datasets—UNSW-NB15,CICIDS2017,and CICDDoS2019—show that our approach outperforms traditional machine learning and deep learning models in detecting both high-rate and low-rate(stealthy)DDoS attacks,with significant improvements in accuracy and recall.These findings demonstrate the suggested method’s applicability and robustness for real-world implementation in contexts where several DDoS patterns coexist.
基金supported by the Research year project of the KongjuNational University in 2025 and the Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(No.RS-2024-00444170,Research and International Collaboration on Trust Model-Based Intelligent Incident Response Technologies in 6G Open Network Environment).
文摘With the growing complexity and decentralization of network systems,the attack surface has expanded,which has led to greater concerns over network threats.In this context,artificial intelligence(AI)-based network intrusion detection systems(NIDS)have been extensively studied,and recent efforts have shifted toward integrating distributed learning to enable intelligent and scalable detection mechanisms.However,most existing works focus on individual distributed learning frameworks,and there is a lack of systematic evaluations that compare different algorithms under consistent conditions.In this paper,we present a comprehensive evaluation of representative distributed learning frameworks—Federated Learning(FL),Split Learning(SL),hybrid collaborative learning(SFL),and fully distributed learning—in the context of AI-driven NIDS.Using recent benchmark intrusion detection datasets,a unified model backbone,and controlled distributed scenarios,we assess these frameworks across multiple criteria,including detection performance,communication cost,computational efficiency,and convergence behavior.Our findings highlight distinct trade-offs among the distributed learning frameworks,demonstrating that the optimal choice depends strongly on systemconstraints such as bandwidth availability,node resources,and data distribution.This work provides the first holistic analysis of distributed learning approaches for AI-driven NIDS and offers practical guidelines for designing secure and efficient intrusion detection systems in decentralized environments.
文摘Identifying the community structure of complex networks is crucial to extracting insights and understanding network properties.Although several community detection methods have been proposed,many are unsuitable for social networks due to significant limitations.Specifically,most approaches depend mainly on user-user structural links while overlooking service-centric,semantic,and multi-attribute drivers of community formation,and they also lack flexible filtering mechanisms for large-scale,service-oriented settings.Our proposed approach,called community discovery-based service(CDBS),leverages user profiles and their interactions with consulted web services.The method introduces a novel similarity measure,global similarity interaction profile(GSIP),which goes beyond typical similarity measures by unifying user and service profiles for all attributes types into a coherent representation,thereby clarifying its novelty and contribution.It applies multiple filtering criteria related to user attributes,accessed services,and interaction patterns.Experimental comparisons against Louvain,Hierarchical Agglomerative Clustering,Label Propagation and Infomap show that CDBS reveals the higher performance as it achieves 0.74 modularity,0.13 conductance,0.77 coverage,and significantly fast response time of 9.8 s,even with 10,000 users and 400 services.Moreover,community discoverybased service consistently detects a larger number of communities with distinct topics of interest,underscoring its capacity to generate detailed and efficient structures in complex networks.These results confirm both the efficiency and effectiveness of the proposed method.Beyond controlled evaluation,communities discovery based service is applicable to targeted recommendations,group-oriented marketing,access control,and service personalization,where communities are shaped not only by user links but also by service engagement.
基金National Natural Science Foundation of China(Grant No.62103434)National Science Fund for Distinguished Young Scholars(Grant No.62176263).
文摘With network attack technology continuing to develop,traditional anomaly traffic detection methods that rely on feature engineering are increasingly insufficient in efficiency and accuracy.Graph Neural Network(GNN),a promising Deep Learning(DL)approach,has proven to be highly effective in identifying intricate patterns in graph⁃structured data and has already found wide applications in the field of network security.In this paper,we propose a hybrid Graph Convolutional Network(GCN)⁃GraphSAGE model for Anomaly Traffic Detection,namely HGS⁃ATD,which aims to improve the accuracy of anomaly traffic detection by leveraging edge feature learning to better capture the relationships between network entities.We validate the HGS⁃ATD model on four publicly available datasets,including NF⁃UNSW⁃NB15⁃v2.The experimental results show that the enhanced hybrid model is 5.71%to 10.25%higher than the baseline model in terms of accuracy,and the F1⁃score is 5.53%to 11.63%higher than the baseline model,proving that the model can effectively distinguish normal traffic from attack traffic and accurately classify various types of attacks.
