The off situ accurate reconstruction of the core neutron field is an important step in realizing real-time reactor monitoring.The existing off situ reconstruction method of the neutron field is only applicable to case...The off situ accurate reconstruction of the core neutron field is an important step in realizing real-time reactor monitoring.The existing off situ reconstruction method of the neutron field is only applicable to cases wherein a single region changes at a specified location of the core.However,when the neutron field changes are complex,the accurate identification of the individual changed regions becomes challenging,which seriously affects the accuracy and stability of the neutron field recon-struction.Therefore,this study proposed a dual-task hybrid network architecture(DTHNet)for off situ reconstruction of the core neutron field,which trained the outermost assembly reconstruction task and the core reconstruction task jointly such that the former could assist the latter in the reconstruction of the core neutron field under core complex changes.Furthermore,to exploit the characteristics of the ex-core detection signals,this study designed a global-local feature upsampling module that efficiently distributed the ex-core detection signals to each reconstruction unit to improve the accuracy and stability of reconstruction.Reconstruction experiments were performed on the simulation datasets of the CLEAR-I reactor to verify the accuracy and stability of the proposed method.The results showed that when the location uncertainty of a single region did not exceed nine and the number of multiple changed regions did not exceed five.Further,the reconstructed ARD was within 2%,RD_(max)was maintained within 17.5%,and the number of RD≥10%was maintained within 10.Furthermore,when the noise interference of the ex-core detection signals was within±2%,although the average number of RD≥10%increased to 16,the average ARD was still within in 2%,and the average RD_(max)was within 22%.Collectively,these results show that,theoretically,the DTHNet can accurately and stably reconstruct most of the neutron field under certain complex core changes.展开更多
This paper presents a new HMM/MLP hybrid network for speech recognition. By taking advantage of the discriminative training of MLP, the unreasonable model correctness assumption on the model correctness of the ML trai...This paper presents a new HMM/MLP hybrid network for speech recognition. By taking advantage of the discriminative training of MLP, the unreasonable model correctness assumption on the model correctness of the ML training in basic HMM can be overcome, and its discriminative ability and recognition performance can be improved. Experimental results demonstrate that the discriminative ability and recognition performance of HMM/MLP is apparently better than normal HMM.展开更多
The demand for wireless data has been driving network capacity to double about every two years for the past 50 years, if not 100 years, and this has come to be known as Cooper＇s Law. In recent years, this trend has a...The demand for wireless data has been driving network capacity to double about every two years for the past 50 years, if not 100 years, and this has come to be known as Cooper＇s Law. In recent years, this trend has accelerated as a greater proportion of the population adopts wireless devices with ever greater capabilities, including tablets that support HD video and other advanced capabilities.展开更多
The mobile ad hoc network (MANET) with infrastructure networks (hybrid networks) has several practical uses. The utility of hybrid network is increased in real time applications by providing some suitable quality of s...The mobile ad hoc network (MANET) with infrastructure networks (hybrid networks) has several practical uses. The utility of hybrid network is increased in real time applications by providing some suitable quality of service. The quality thresholds are imposed on parameters like end-to-end delay (EED), jitter, packet delivery ratio (PDR) and throughput. This paper utilizes the extended ad hoc on-demand distance vector (AODV) routing protocol for communication between ad hoc network and fixed wired network. This paper also uses the IEEE 802.11e medium access control (MAC) function HCF Controlled Channel Access (HCCA) to support quality of service (QoS) in hybrid network. In this paper two simulation scenarios are analyzed for hybrid networks. The nodes in wireless ad hoc networks are mobile in one scenario and static in the other scenario. Both simulation scenarios are used to compare the performance of extended AODV with HCCA (IEEE 802.11e) and without HCCA (IEEE802.11) for real time voice over IP (VoIP) traffic. The extensive set of simulations results show that the performance of extended AODV with HCCA (IEEE 802.11e) improves QoS in hybrid network and it is unaffected whether the nodes in wireless ad hoc networks are mobile or static.展开更多
The deepwater subsea wellhead(SW)system is the foundation for the construction of oil and gas wells and the crucial channel for operation.During riser connection operation,the SW system is subjected to cyclic dynamic ...The deepwater subsea wellhead(SW)system is the foundation for the construction of oil and gas wells and the crucial channel for operation.During riser connection operation,the SW system is subjected to cyclic dynamic loads which cause fatigue damage to the SW system,and continuously accumulated fatigue damage leads to fatigue failure of the SW system,rupture,and even blowout accidents.This paper proposes a hybrid Bayesian network(HBN)-based dynamic reliability assessment approach for deepwater SW systems during their service life.In the proposed approach,the relationship between the accumulation of fatigue damage and the fatigue failure probability of the SW system is predicted,only considering normal conditions.The HBN model,which includes the accumulation of fatigue damage under normal conditions and the other factors affecting the fatigue of the SW system,is subsequently developed.When predictive and diagnostic analysis techniques are adopted,the dynamic reliability of the SW system is achieved,and the most influential factors are determined.Finally,corresponding safety control measures are proposed to improve the reliability of the SW system effectively.The results illustrate that the fatigue failure speed increases rapidly when the accumulation fatigue damage is larger than 0.45 under normal conditions and that the reliability of the SW system is larger than 94%within the design life.展开更多
Satellite and terrestrial cellular networks can be integrated together to achieve extended broad-band coverage for,e.g.,maritime communication sce-narios,in the upcoming sixth-generation(6G)era.To counter spectrum sca...Satellite and terrestrial cellular networks can be integrated together to achieve extended broad-band coverage for,e.g.,maritime communication sce-narios,in the upcoming sixth-generation(6G)era.To counter spectrum scarcity,collaborative spectrum sharing is considered for hybrid satellite-terrestrial networks(HSTNs)in this paper.With only slowly-varying large-scale channel state information(CSI),joint power and channel allocation is implemented for terrestrial mobile terminals(MTs)which share the same frequency band with the satellite MTs oppor-tunistically.Specially,strict quality service assurance is adopted for terrestrial MTs under the constraint of leakage interference to satellite MTs.With the tar-get of maximizing both the number of served terres-trial MTs and the average sum transmission rate,a double-target spectrum sharing problem is formulated.To solve the complicated mixed integer programming(MIP)problem efficiently,user-centric channel pools are introduced.Simulations demonstrate that the proposed spectrum sharing scheme could achieve a significant performance gain for the HSTN.展开更多
Blockchain platform swith the unique characteristics of anonymity,decentralization,and transparency of their transactions,which are faced with abnormal activities such as money laundering,phishing scams,and fraudulent...Blockchain platform swith the unique characteristics of anonymity,decentralization,and transparency of their transactions,which are faced with abnormal activities such as money laundering,phishing scams,and fraudulent behavior,posing a serious threat to account asset security.For these potential security risks,this paper proposes a hybrid neural network detection method(HNND)that learns multiple types of account features and enhances fusion information among them to effectively detect abnormal transaction behaviors in the blockchain.In HNND,the Temporal Transaction Graph Attention Network(T2GAT)is first designed to learn biased aggregation representation of multi-attribute transactions among nodes,which can capture key temporal information from node neighborhood transactions.Then,the Graph Convolutional Network(GCN)is adopted which captures abstract structural features of the transaction network.Further,the Stacked Denoising Autoencode(SDA)is developed to achieve adaptive fusion of thses features from different modules.Moreover,the SDA enhances robustness and generalization ability of node representation,leading to higher binary classification accuracy in detecting abnormal behaviors of blockchain accounts.Evaluations on a real-world abnormal transaction dataset demonstrate great advantages of the proposed HNND method over other compared methods.展开更多
A Reconfigurable Intelligent Surface(RIS)can relay signals from the transmitter to the receiver.In this regard,RISs operate similarly to traditional relays.We design a Multiple-Input-Multiple-Output(MIMO)system with a...A Reconfigurable Intelligent Surface(RIS)can relay signals from the transmitter to the receiver.In this regard,RISs operate similarly to traditional relays.We design a Multiple-Input-Multiple-Output(MIMO)system with a hybrid network of RIS and Half-Duplex(HD)Amplify-and-Forward(AF)relay.We model the system’s signal propagation and propose a new algorithm to get the system’s Achievable Rate(AR)value.We complete simulations to evaluate the performance of the RIS and HD-AF relay hybrid network system compared to the system assisted by either the RIS or HD-AF relay.The simulations indicate that many factors can considerably influence the system performance.Selecting an optimal placement for the RIS and relay can result in the best performance for the RIS and HD-AF relay hybrid network system in situations where the direct link between the receiver and transmitter is absent.展开更多
With the rapid development of related computer vision algorithms,the large-scale use of video surveillance systems has not only improved traffic safety,but also promoted the development of intelligent high-speed.Howev...With the rapid development of related computer vision algorithms,the large-scale use of video surveillance systems has not only improved traffic safety,but also promoted the development of intelligent high-speed.However,due to the complexity of the application scene,especially in the face of complex scene occlusion factors,the noise generated by the occlusion inevitably leads to the loss of the feature information of the identified person or object,which poses a great challenge to the existing pedestrian re-recognition algorithms.Therefore,this paper proposes a novel pedestrian re-recognition based on hybrid network.Feature extraction is carried out on four cooperative branches:local branch,global branch,global contrast pool branch and associated branch,and powerful diversity pedestrian feature expression ability is obtained.The network in this paper can be applied to different backbone networks.Through experimental comparison,the proposed algorithm has certain advantages compared with the latest methods,and the ablation experimental analysis further proves the effectiveness of the proposed network structure.展开更多
Vertically oriented carbon structures constructed from low-dimen-sional carbon materials are ideal frameworks for high-performance thermal inter-face materials(TIMs).However,improving the interfacial heat-transfer eff...Vertically oriented carbon structures constructed from low-dimen-sional carbon materials are ideal frameworks for high-performance thermal inter-face materials(TIMs).However,improving the interfacial heat-transfer efficiency of vertically oriented carbon structures is a challenging task.Herein,an orthotropic three-dimensional(3D)hybrid carbon network(VSCG)is fabricated by depositing vertically aligned carbon nanotubes(VACNTs)on the surface of a horizontally oriented graphene film(HOGF).The interfacial interaction between the VACNTs and HOGF is then optimized through an annealing strategy.After regulating the orientation structure of the VACNTs and filling the VSCG with polydimethylsi-loxane(PDMS),VSCG/PDMS composites with excellent 3D thermal conductive properties are obtained.The highest in-plane and through-plane thermal conduc-tivities of the composites are 113.61 and 24.37 W m^(-1)K^(-1),respectively.The high contact area of HOGF and good compressibility of VACNTs imbue the VSCG/PDMS composite with low thermal resistance.In addition,the interfacial heat-transfer efficiency of VSCG/PDMS composite in the TIM performance was improved by 71.3%compared to that of a state-of-the-art thermal pad.This new structural design can potentially realize high-performance TIMs that meet the need for high thermal conductivity and low contact thermal resistance in interfacial heat-transfer processes.展开更多
As the demands of massive connections and vast coverage rapidly grow in the next wireless communication networks, rate splitting multiple access(RSMA) is considered to be the new promising access scheme since it can p...As the demands of massive connections and vast coverage rapidly grow in the next wireless communication networks, rate splitting multiple access(RSMA) is considered to be the new promising access scheme since it can provide higher efficiency with limited spectrum resources. In this paper, combining spectrum splitting with rate splitting, we propose to allocate resources with traffic offloading in hybrid satellite terrestrial networks. A novel deep reinforcement learning method is adopted to solve this challenging non-convex problem. However, the neverending learning process could prohibit its practical implementation. Therefore, we introduce the switch mechanism to avoid unnecessary learning. Additionally, the QoS constraint in the scheme can rule out unsuccessful transmission. The simulation results validates the energy efficiency performance and the convergence speed of the proposed algorithm.展开更多
We redesign the parameterized quantum circuit in the quantum deep neural network, construct a three-layer structure as the hidden layer, and then use classical optimization algorithms to train the parameterized quantu...We redesign the parameterized quantum circuit in the quantum deep neural network, construct a three-layer structure as the hidden layer, and then use classical optimization algorithms to train the parameterized quantum circuit, thereby propose a novel hybrid quantum deep neural network(HQDNN) used for image classification. After bilinear interpolation reduces the original image to a suitable size, an improved novel enhanced quantum representation(INEQR) is used to encode it into quantum states as the input of the HQDNN. Multi-layer parameterized quantum circuits are used as the main structure to implement feature extraction and classification. The output results of parameterized quantum circuits are converted into classical data through quantum measurements and then optimized on a classical computer. To verify the performance of the HQDNN, we conduct binary classification and three classification experiments on the MNIST(Modified National Institute of Standards and Technology) data set. In the first binary classification, the accuracy of 0 and 4 exceeds98%. Then we compare the performance of three classification with other algorithms, the results on two datasets show that the classification accuracy is higher than that of quantum deep neural network and general quantum convolutional neural network.展开更多
With the wide application of drone technology,there is an increasing demand for the detection of radar return signals from drones.Existing detection methods mainly rely on time-frequency domain feature extraction and ...With the wide application of drone technology,there is an increasing demand for the detection of radar return signals from drones.Existing detection methods mainly rely on time-frequency domain feature extraction and classical machine learning algorithms for image recognition.This method suffers from the problem of large dimensionality of image features,which leads to large input data size and noise affecting learning.Therefore,this paper proposes to extract signal time-domain statistical features for radar return signals from drones and reduce the feature dimension from 512×4 to 16 dimensions.However,the downscaled feature data makes the accuracy of traditional machine learning algorithms decrease,so we propose a new hybrid quantum neural network with signal feature overlay projection(HQNN-SFOP),which reduces the dimensionality of the signal by extracting the statistical features in the time domain of the signal,introduces the signal feature overlay projection to enhance the expression ability of quantum computation on the signal features,and introduces the quantum circuits to improve the neural network’s ability to obtain the inline relationship of features,thus improving the accuracy and migration generalization ability of drone detection.In order to validate the effectiveness of the proposed method,we experimented with the method using the MM model that combines the real parameters of five commercial drones and random drones parameters to generate data to simulate a realistic environment.The results show that the method based on statistical features in the time domain of the signal is able to extract features at smaller scales and obtain higher accuracy on a dataset with an SNR of 10 dB.On the time-domain feature data set,HQNNSFOP obtains the highest accuracy compared to other conventional methods.In addition,HQNN-SFOP has good migration generalization ability on five commercial drones and random drones data at different SNR conditions.Our method verifies the feasibility and effectiveness of signal detection methods based on quantum computation and experimentally demonstrates that the advantages of quantum computation for information processing are still valid in the field of signal processing,it provides a highly efficient method for the drone detection using radar return signals.展开更多
We design a new hybrid quantum-classical convolutional neural network(HQCCNN)model based on parameter quantum circuits.In this model,we use parameterized quantum circuits(PQCs)to redesign the convolutional layer in cl...We design a new hybrid quantum-classical convolutional neural network(HQCCNN)model based on parameter quantum circuits.In this model,we use parameterized quantum circuits(PQCs)to redesign the convolutional layer in classical convolutional neural networks,forming a new quantum convolutional layer to achieve unitary transformation of quantum states,enabling the model to more accurately extract hidden information from images.At the same time,we combine the classical fully connected layer with PQCs to form a new hybrid quantum-classical fully connected layer to further improve the accuracy of classification.Finally,we use the MNIST dataset to test the potential of the HQCCNN.The results indicate that the HQCCNN has good performance in solving classification problems.In binary classification tasks,the classification accuracy of numbers 5 and 7 is as high as 99.71%.In multivariate classification,the accuracy rate also reaches 98.51%.Finally,we compare the performance of the HQCCNN with other models and find that the HQCCNN has better classification performance and convergence speed.展开更多
In recent years,wearable devices-based Human Activity Recognition(HAR)models have received significant attention.Previously developed HAR models use hand-crafted features to recognize human activities,leading to the e...In recent years,wearable devices-based Human Activity Recognition(HAR)models have received significant attention.Previously developed HAR models use hand-crafted features to recognize human activities,leading to the extraction of basic features.The images captured by wearable sensors contain advanced features,allowing them to be analyzed by deep learning algorithms to enhance the detection and recognition of human actions.Poor lighting and limited sensor capabilities can impact data quality,making the recognition of human actions a challenging task.The unimodal-based HAR approaches are not suitable in a real-time environment.Therefore,an updated HAR model is developed using multiple types of data and an advanced deep-learning approach.Firstly,the required signals and sensor data are accumulated from the standard databases.From these signals,the wave features are retrieved.Then the extracted wave features and sensor data are given as the input to recognize the human activity.An Adaptive Hybrid Deep Attentive Network(AHDAN)is developed by incorporating a“1D Convolutional Neural Network(1DCNN)”with a“Gated Recurrent Unit(GRU)”for the human activity recognition process.Additionally,the Enhanced Archerfish Hunting Optimizer(EAHO)is suggested to fine-tune the network parameters for enhancing the recognition process.An experimental evaluation is performed on various deep learning networks and heuristic algorithms to confirm the effectiveness of the proposed HAR model.The EAHO-based HAR model outperforms traditional deep learning networks with an accuracy of 95.36,95.25 for recall,95.48 for specificity,and 95.47 for precision,respectively.The result proved that the developed model is effective in recognizing human action by taking less time.Additionally,it reduces the computation complexity and overfitting issue through using an optimization approach.展开更多
The most reliable archive of atmospheric CO_(2) information comprises ice core records spanning the last 800 ka(thousand years ago).The connection between temperature and greenhouse gases,as deduced from ice core reco...The most reliable archive of atmospheric CO_(2) information comprises ice core records spanning the last 800 ka(thousand years ago).The connection between temperature and greenhouse gases,as deduced from ice core records,may help better simulate CO_(2) variations.This research aimed to explore the model methods to precisely predict the atmospheric CO_(2) concentrations and fill the CO_(2) data gaps with CH4 concentration and temperature proxies(δD andδ18O)from Antarctica ice cores,employing Artificial Neural Network(ANN)and Wavelet Transform(WT)techniques.This study was divided into three sections to examine various timescales and resolutions.First,coarse-resolution CO_(2) records from the Vostok and EPICA Dronning Maud Land cores from 70–120 ka were used.Second,the models were applied to the Dome Fuji core for 9–120 ka.Finally,a high-resolution West Antarctic Ice Sheet(WAIS)Divide ice core record,focusing on the 9–70 ka,was employed.The results showed that between 70–120 ka,the hybrid method surpasses the traditional ANN approach.The hybrid method maintained superior performance in the last phase by utilizing high-resolution WAIS record.The results indicated improved accuracy(r=0.98),reinforcing the notion that hybrid methods yield better outcomes than those relying solely on AI methods.展开更多
In this paper,Isogeometric analysis(IGA)is effectively integrated with machine learning(ML)to investigate the bearing capacity of strip footings in layered soil profiles,with a focus on a sand-over-clay configuration....In this paper,Isogeometric analysis(IGA)is effectively integrated with machine learning(ML)to investigate the bearing capacity of strip footings in layered soil profiles,with a focus on a sand-over-clay configuration.The study begins with the generation of a comprehensive dataset of 10,000 samples from IGA upper bound(UB)limit analyses,facilitating an in-depth examination of various material and geometric conditions.A hybrid deep neural network,specifically the Whale Optimization Algorithm-Deep Neural Network(WOA-DNN),is then employed to utilize these 10,000 outputs for precise bearing capacity predictions.Notably,the WOA-DNN model outperforms conventional ML techniques,offering a robust and accurate prediction tool.This innovative approach explores a broad range of design parameters,including sand layer depth,load-to-soil unit weight ratio,internal friction angle,cohesion,and footing roughness.A detailed analysis of the dataset reveals the significant influence of these parameters on bearing capacity,providing valuable insights for practical foundation design.This research demonstrates the usefulness of data-driven techniques in optimizing the design of shallow foundations within layered soil profiles,marking a significant stride in geotechnical engineering advancements.展开更多
With limited number of labeled samples,hyperspectral image(HSI)classification is a difficult Problem in current research.The graph neural network(GNN)has emerged as an approach to semi-supervised classification,and th...With limited number of labeled samples,hyperspectral image(HSI)classification is a difficult Problem in current research.The graph neural network(GNN)has emerged as an approach to semi-supervised classification,and the application of GNN to hyperspectral images has attracted much attention.However,in the existing GNN-based methods a single graph neural network or graph filter is mainly used to extract HSI features,which does not take full advantage of various graph neural networks(graph filters).Moreover,the traditional GNNs have the problem of oversmoothing.To alleviate these shortcomings,we introduce a deep hybrid multi-graph neural network(DHMG),where two different graph filters,i.e.,the spectral filter and the autoregressive moving average(ARMA)filter,are utilized in two branches.The former can well extract the spectral features of the nodes,and the latter has a good suppression effect on graph noise.The network realizes information interaction between the two branches and takes good advantage of different graph filters.In addition,to address the problem of oversmoothing,a dense network is proposed,where the local graph features are preserved.The dense structure satisfies the needs of different classification targets presenting different features.Finally,we introduce a GraphSAGEbased network to refine the graph features produced by the deep hybrid network.Extensive experiments on three public HSI datasets strongly demonstrate that the DHMG dramatically outperforms the state-ofthe-art models.展开更多
In this article, we present a new type of unified dynamic scaling property for synchronizability, which can describe the scaling relationship between dynamic synehronizability and four hybrid ratios under the unified ...In this article, we present a new type of unified dynamic scaling property for synchronizability, which can describe the scaling relationship between dynamic synehronizability and four hybrid ratios under the unified hybrid network theory framework （UHNTF）. Our theory results can not only be applied to judge and analyze dynamic synehronizability for most of complex networks associated with the UHNTF, but also we can flexibly adjust and design different hybrid ratios and sealing exponent to meet actual requirement for the dynanfic characteristics of the UHNTF.展开更多
Indoor wireless communication networking has received significant attention along with the growth of indoor data traffic.VLC(Visible Light Communication)as a novel wireless communication technology with the advantages...Indoor wireless communication networking has received significant attention along with the growth of indoor data traffic.VLC(Visible Light Communication)as a novel wireless communication technology with the advantages of a high data rate,license-free spectrum and safety provides a practical solution for the indoor high-speed transmission of large data traffic.However,limited coverage is an inherent feature of VLC.In this paper,we propose a novel hybrid VLC-Wi-Fi system that integrates multiple links to achieve an indoor high-speed wide-coverage network combined with multiple access,a multi-path transmission control protocol,mobility management and cell handover.Furthermore,we develop a hybrid network experiment platform,the experimental results of which show that the hybrid VLC-Wi-Fi network outperforms both single VLC and Wi-Fi networks with better coverage and greater network capacity.展开更多
基金supported by the National Natural Science Foundation of China(No.12305344)the 2023 Anhui university research project of China(No.2023AH052179).
文摘The off situ accurate reconstruction of the core neutron field is an important step in realizing real-time reactor monitoring.The existing off situ reconstruction method of the neutron field is only applicable to cases wherein a single region changes at a specified location of the core.However,when the neutron field changes are complex,the accurate identification of the individual changed regions becomes challenging,which seriously affects the accuracy and stability of the neutron field recon-struction.Therefore,this study proposed a dual-task hybrid network architecture(DTHNet)for off situ reconstruction of the core neutron field,which trained the outermost assembly reconstruction task and the core reconstruction task jointly such that the former could assist the latter in the reconstruction of the core neutron field under core complex changes.Furthermore,to exploit the characteristics of the ex-core detection signals,this study designed a global-local feature upsampling module that efficiently distributed the ex-core detection signals to each reconstruction unit to improve the accuracy and stability of reconstruction.Reconstruction experiments were performed on the simulation datasets of the CLEAR-I reactor to verify the accuracy and stability of the proposed method.The results showed that when the location uncertainty of a single region did not exceed nine and the number of multiple changed regions did not exceed five.Further,the reconstructed ARD was within 2%,RD_(max)was maintained within 17.5%,and the number of RD≥10%was maintained within 10.Furthermore,when the noise interference of the ex-core detection signals was within±2%,although the average number of RD≥10%increased to 16,the average ARD was still within in 2%,and the average RD_(max)was within 22%.Collectively,these results show that,theoretically,the DTHNet can accurately and stably reconstruct most of the neutron field under certain complex core changes.
文摘This paper presents a new HMM/MLP hybrid network for speech recognition. By taking advantage of the discriminative training of MLP, the unreasonable model correctness assumption on the model correctness of the ML training in basic HMM can be overcome, and its discriminative ability and recognition performance can be improved. Experimental results demonstrate that the discriminative ability and recognition performance of HMM/MLP is apparently better than normal HMM.
文摘The demand for wireless data has been driving network capacity to double about every two years for the past 50 years, if not 100 years, and this has come to be known as Cooper＇s Law. In recent years, this trend has accelerated as a greater proportion of the population adopts wireless devices with ever greater capabilities, including tablets that support HD video and other advanced capabilities.
文摘The mobile ad hoc network (MANET) with infrastructure networks (hybrid networks) has several practical uses. The utility of hybrid network is increased in real time applications by providing some suitable quality of service. The quality thresholds are imposed on parameters like end-to-end delay (EED), jitter, packet delivery ratio (PDR) and throughput. This paper utilizes the extended ad hoc on-demand distance vector (AODV) routing protocol for communication between ad hoc network and fixed wired network. This paper also uses the IEEE 802.11e medium access control (MAC) function HCF Controlled Channel Access (HCCA) to support quality of service (QoS) in hybrid network. In this paper two simulation scenarios are analyzed for hybrid networks. The nodes in wireless ad hoc networks are mobile in one scenario and static in the other scenario. Both simulation scenarios are used to compare the performance of extended AODV with HCCA (IEEE 802.11e) and without HCCA (IEEE802.11) for real time voice over IP (VoIP) traffic. The extensive set of simulations results show that the performance of extended AODV with HCCA (IEEE 802.11e) improves QoS in hybrid network and it is unaffected whether the nodes in wireless ad hoc networks are mobile or static.
基金financially supported by the National Natural Science Foundation of China(Grant No.52071337)the Research Initiation Funds of Zhejiang University of Science and Technology(Grant No.F701102N06)+2 种基金the High-tech Ship Research Projects Sponsored by MIIT(Grant No.CBG2N21-4-2-5)the National Key Research and Development Program of China(Grant No.2022YFC2806300)the Marine Economy Development(Six Marine Industries)Special Foundation of the Department of Natural Resources of Guangdong Province(Grant No.GDNRC[2023]50).
文摘The deepwater subsea wellhead(SW)system is the foundation for the construction of oil and gas wells and the crucial channel for operation.During riser connection operation,the SW system is subjected to cyclic dynamic loads which cause fatigue damage to the SW system,and continuously accumulated fatigue damage leads to fatigue failure of the SW system,rupture,and even blowout accidents.This paper proposes a hybrid Bayesian network(HBN)-based dynamic reliability assessment approach for deepwater SW systems during their service life.In the proposed approach,the relationship between the accumulation of fatigue damage and the fatigue failure probability of the SW system is predicted,only considering normal conditions.The HBN model,which includes the accumulation of fatigue damage under normal conditions and the other factors affecting the fatigue of the SW system,is subsequently developed.When predictive and diagnostic analysis techniques are adopted,the dynamic reliability of the SW system is achieved,and the most influential factors are determined.Finally,corresponding safety control measures are proposed to improve the reliability of the SW system effectively.The results illustrate that the fatigue failure speed increases rapidly when the accumulation fatigue damage is larger than 0.45 under normal conditions and that the reliability of the SW system is larger than 94%within the design life.
基金supported in part by the National Natural Science Foundation of China under Grant 62425110 and Grant U22A2002in part by the National Key Research and Development Program of China under Grant 2020YFA0711301+2 种基金in part by the Leading Project of Minzu University of China under Grant 2023QNYL23in part by the Key Research and Development Project of Nantong(Special Project for Prospective Technology Innovation)under Grant GZ2024002in part by the Suzhou Science and Technology Project,and in part by the FAW Jiefang Automotive Co.,Ltd.
文摘Satellite and terrestrial cellular networks can be integrated together to achieve extended broad-band coverage for,e.g.,maritime communication sce-narios,in the upcoming sixth-generation(6G)era.To counter spectrum scarcity,collaborative spectrum sharing is considered for hybrid satellite-terrestrial networks(HSTNs)in this paper.With only slowly-varying large-scale channel state information(CSI),joint power and channel allocation is implemented for terrestrial mobile terminals(MTs)which share the same frequency band with the satellite MTs oppor-tunistically.Specially,strict quality service assurance is adopted for terrestrial MTs under the constraint of leakage interference to satellite MTs.With the tar-get of maximizing both the number of served terres-trial MTs and the average sum transmission rate,a double-target spectrum sharing problem is formulated.To solve the complicated mixed integer programming(MIP)problem efficiently,user-centric channel pools are introduced.Simulations demonstrate that the proposed spectrum sharing scheme could achieve a significant performance gain for the HSTN.
文摘Blockchain platform swith the unique characteristics of anonymity,decentralization,and transparency of their transactions,which are faced with abnormal activities such as money laundering,phishing scams,and fraudulent behavior,posing a serious threat to account asset security.For these potential security risks,this paper proposes a hybrid neural network detection method(HNND)that learns multiple types of account features and enhances fusion information among them to effectively detect abnormal transaction behaviors in the blockchain.In HNND,the Temporal Transaction Graph Attention Network(T2GAT)is first designed to learn biased aggregation representation of multi-attribute transactions among nodes,which can capture key temporal information from node neighborhood transactions.Then,the Graph Convolutional Network(GCN)is adopted which captures abstract structural features of the transaction network.Further,the Stacked Denoising Autoencode(SDA)is developed to achieve adaptive fusion of thses features from different modules.Moreover,the SDA enhances robustness and generalization ability of node representation,leading to higher binary classification accuracy in detecting abnormal behaviors of blockchain accounts.Evaluations on a real-world abnormal transaction dataset demonstrate great advantages of the proposed HNND method over other compared methods.
文摘A Reconfigurable Intelligent Surface(RIS)can relay signals from the transmitter to the receiver.In this regard,RISs operate similarly to traditional relays.We design a Multiple-Input-Multiple-Output(MIMO)system with a hybrid network of RIS and Half-Duplex(HD)Amplify-and-Forward(AF)relay.We model the system’s signal propagation and propose a new algorithm to get the system’s Achievable Rate(AR)value.We complete simulations to evaluate the performance of the RIS and HD-AF relay hybrid network system compared to the system assisted by either the RIS or HD-AF relay.The simulations indicate that many factors can considerably influence the system performance.Selecting an optimal placement for the RIS and relay can result in the best performance for the RIS and HD-AF relay hybrid network system in situations where the direct link between the receiver and transmitter is absent.
文摘With the rapid development of related computer vision algorithms,the large-scale use of video surveillance systems has not only improved traffic safety,but also promoted the development of intelligent high-speed.However,due to the complexity of the application scene,especially in the face of complex scene occlusion factors,the noise generated by the occlusion inevitably leads to the loss of the feature information of the identified person or object,which poses a great challenge to the existing pedestrian re-recognition algorithms.Therefore,this paper proposes a novel pedestrian re-recognition based on hybrid network.Feature extraction is carried out on four cooperative branches:local branch,global branch,global contrast pool branch and associated branch,and powerful diversity pedestrian feature expression ability is obtained.The network in this paper can be applied to different backbone networks.Through experimental comparison,the proposed algorithm has certain advantages compared with the latest methods,and the ablation experimental analysis further proves the effectiveness of the proposed network structure.
基金financially supported by the National Natural Science Foundation of China(Grant Nos.52130303,52327802,52303101,52173078,51973158)the China Postdoctoral Science Foundation(2023M732579)+2 种基金Young Elite Scientists Sponsorship Program by CAST(No.2022QNRC001)National Key R&D Program of China(No.2022YFB3805702)Joint Funds of Ministry of Education(8091B032218).
文摘Vertically oriented carbon structures constructed from low-dimen-sional carbon materials are ideal frameworks for high-performance thermal inter-face materials(TIMs).However,improving the interfacial heat-transfer efficiency of vertically oriented carbon structures is a challenging task.Herein,an orthotropic three-dimensional(3D)hybrid carbon network(VSCG)is fabricated by depositing vertically aligned carbon nanotubes(VACNTs)on the surface of a horizontally oriented graphene film(HOGF).The interfacial interaction between the VACNTs and HOGF is then optimized through an annealing strategy.After regulating the orientation structure of the VACNTs and filling the VSCG with polydimethylsi-loxane(PDMS),VSCG/PDMS composites with excellent 3D thermal conductive properties are obtained.The highest in-plane and through-plane thermal conduc-tivities of the composites are 113.61 and 24.37 W m^(-1)K^(-1),respectively.The high contact area of HOGF and good compressibility of VACNTs imbue the VSCG/PDMS composite with low thermal resistance.In addition,the interfacial heat-transfer efficiency of VSCG/PDMS composite in the TIM performance was improved by 71.3%compared to that of a state-of-the-art thermal pad.This new structural design can potentially realize high-performance TIMs that meet the need for high thermal conductivity and low contact thermal resistance in interfacial heat-transfer processes.
文摘As the demands of massive connections and vast coverage rapidly grow in the next wireless communication networks, rate splitting multiple access(RSMA) is considered to be the new promising access scheme since it can provide higher efficiency with limited spectrum resources. In this paper, combining spectrum splitting with rate splitting, we propose to allocate resources with traffic offloading in hybrid satellite terrestrial networks. A novel deep reinforcement learning method is adopted to solve this challenging non-convex problem. However, the neverending learning process could prohibit its practical implementation. Therefore, we introduce the switch mechanism to avoid unnecessary learning. Additionally, the QoS constraint in the scheme can rule out unsuccessful transmission. The simulation results validates the energy efficiency performance and the convergence speed of the proposed algorithm.
基金Project supported by the Natural Science Foundation of Shandong Province,China (Grant No. ZR2021MF049)the Joint Fund of Natural Science Foundation of Shandong Province (Grant Nos. ZR2022LLZ012 and ZR2021LLZ001)。
文摘We redesign the parameterized quantum circuit in the quantum deep neural network, construct a three-layer structure as the hidden layer, and then use classical optimization algorithms to train the parameterized quantum circuit, thereby propose a novel hybrid quantum deep neural network(HQDNN) used for image classification. After bilinear interpolation reduces the original image to a suitable size, an improved novel enhanced quantum representation(INEQR) is used to encode it into quantum states as the input of the HQDNN. Multi-layer parameterized quantum circuits are used as the main structure to implement feature extraction and classification. The output results of parameterized quantum circuits are converted into classical data through quantum measurements and then optimized on a classical computer. To verify the performance of the HQDNN, we conduct binary classification and three classification experiments on the MNIST(Modified National Institute of Standards and Technology) data set. In the first binary classification, the accuracy of 0 and 4 exceeds98%. Then we compare the performance of three classification with other algorithms, the results on two datasets show that the classification accuracy is higher than that of quantum deep neural network and general quantum convolutional neural network.
基金supported by Major Science and Technology Projects in Henan Province,China,Grant No.221100210600.
文摘With the wide application of drone technology,there is an increasing demand for the detection of radar return signals from drones.Existing detection methods mainly rely on time-frequency domain feature extraction and classical machine learning algorithms for image recognition.This method suffers from the problem of large dimensionality of image features,which leads to large input data size and noise affecting learning.Therefore,this paper proposes to extract signal time-domain statistical features for radar return signals from drones and reduce the feature dimension from 512×4 to 16 dimensions.However,the downscaled feature data makes the accuracy of traditional machine learning algorithms decrease,so we propose a new hybrid quantum neural network with signal feature overlay projection(HQNN-SFOP),which reduces the dimensionality of the signal by extracting the statistical features in the time domain of the signal,introduces the signal feature overlay projection to enhance the expression ability of quantum computation on the signal features,and introduces the quantum circuits to improve the neural network’s ability to obtain the inline relationship of features,thus improving the accuracy and migration generalization ability of drone detection.In order to validate the effectiveness of the proposed method,we experimented with the method using the MM model that combines the real parameters of five commercial drones and random drones parameters to generate data to simulate a realistic environment.The results show that the method based on statistical features in the time domain of the signal is able to extract features at smaller scales and obtain higher accuracy on a dataset with an SNR of 10 dB.On the time-domain feature data set,HQNNSFOP obtains the highest accuracy compared to other conventional methods.In addition,HQNN-SFOP has good migration generalization ability on five commercial drones and random drones data at different SNR conditions.Our method verifies the feasibility and effectiveness of signal detection methods based on quantum computation and experimentally demonstrates that the advantages of quantum computation for information processing are still valid in the field of signal processing,it provides a highly efficient method for the drone detection using radar return signals.
基金Project supported by the Natural Science Foundation of Shandong Province,China (Grant No.ZR2021MF049)the Joint Fund of Natural Science Foundation of Shandong Province (Grant Nos.ZR2022LLZ012 and ZR2021LLZ001)。
文摘We design a new hybrid quantum-classical convolutional neural network(HQCCNN)model based on parameter quantum circuits.In this model,we use parameterized quantum circuits(PQCs)to redesign the convolutional layer in classical convolutional neural networks,forming a new quantum convolutional layer to achieve unitary transformation of quantum states,enabling the model to more accurately extract hidden information from images.At the same time,we combine the classical fully connected layer with PQCs to form a new hybrid quantum-classical fully connected layer to further improve the accuracy of classification.Finally,we use the MNIST dataset to test the potential of the HQCCNN.The results indicate that the HQCCNN has good performance in solving classification problems.In binary classification tasks,the classification accuracy of numbers 5 and 7 is as high as 99.71%.In multivariate classification,the accuracy rate also reaches 98.51%.Finally,we compare the performance of the HQCCNN with other models and find that the HQCCNN has better classification performance and convergence speed.
文摘In recent years,wearable devices-based Human Activity Recognition(HAR)models have received significant attention.Previously developed HAR models use hand-crafted features to recognize human activities,leading to the extraction of basic features.The images captured by wearable sensors contain advanced features,allowing them to be analyzed by deep learning algorithms to enhance the detection and recognition of human actions.Poor lighting and limited sensor capabilities can impact data quality,making the recognition of human actions a challenging task.The unimodal-based HAR approaches are not suitable in a real-time environment.Therefore,an updated HAR model is developed using multiple types of data and an advanced deep-learning approach.Firstly,the required signals and sensor data are accumulated from the standard databases.From these signals,the wave features are retrieved.Then the extracted wave features and sensor data are given as the input to recognize the human activity.An Adaptive Hybrid Deep Attentive Network(AHDAN)is developed by incorporating a“1D Convolutional Neural Network(1DCNN)”with a“Gated Recurrent Unit(GRU)”for the human activity recognition process.Additionally,the Enhanced Archerfish Hunting Optimizer(EAHO)is suggested to fine-tune the network parameters for enhancing the recognition process.An experimental evaluation is performed on various deep learning networks and heuristic algorithms to confirm the effectiveness of the proposed HAR model.The EAHO-based HAR model outperforms traditional deep learning networks with an accuracy of 95.36,95.25 for recall,95.48 for specificity,and 95.47 for precision,respectively.The result proved that the developed model is effective in recognizing human action by taking less time.Additionally,it reduces the computation complexity and overfitting issue through using an optimization approach.
基金supported by the Brain Pool Program through the National Research Foundation of Korea(NRF)and funded by the Ministry of Science and ICT[Grant numbers:2020H1D3A1A04081353,2020M1A5A1110607,2018R1A5A1024958,and RS-2023-00291696].
文摘The most reliable archive of atmospheric CO_(2) information comprises ice core records spanning the last 800 ka(thousand years ago).The connection between temperature and greenhouse gases,as deduced from ice core records,may help better simulate CO_(2) variations.This research aimed to explore the model methods to precisely predict the atmospheric CO_(2) concentrations and fill the CO_(2) data gaps with CH4 concentration and temperature proxies(δD andδ18O)from Antarctica ice cores,employing Artificial Neural Network(ANN)and Wavelet Transform(WT)techniques.This study was divided into three sections to examine various timescales and resolutions.First,coarse-resolution CO_(2) records from the Vostok and EPICA Dronning Maud Land cores from 70–120 ka were used.Second,the models were applied to the Dome Fuji core for 9–120 ka.Finally,a high-resolution West Antarctic Ice Sheet(WAIS)Divide ice core record,focusing on the 9–70 ka,was employed.The results showed that between 70–120 ka,the hybrid method surpasses the traditional ANN approach.The hybrid method maintained superior performance in the last phase by utilizing high-resolution WAIS record.The results indicated improved accuracy(r=0.98),reinforcing the notion that hybrid methods yield better outcomes than those relying solely on AI methods.
文摘In this paper,Isogeometric analysis(IGA)is effectively integrated with machine learning(ML)to investigate the bearing capacity of strip footings in layered soil profiles,with a focus on a sand-over-clay configuration.The study begins with the generation of a comprehensive dataset of 10,000 samples from IGA upper bound(UB)limit analyses,facilitating an in-depth examination of various material and geometric conditions.A hybrid deep neural network,specifically the Whale Optimization Algorithm-Deep Neural Network(WOA-DNN),is then employed to utilize these 10,000 outputs for precise bearing capacity predictions.Notably,the WOA-DNN model outperforms conventional ML techniques,offering a robust and accurate prediction tool.This innovative approach explores a broad range of design parameters,including sand layer depth,load-to-soil unit weight ratio,internal friction angle,cohesion,and footing roughness.A detailed analysis of the dataset reveals the significant influence of these parameters on bearing capacity,providing valuable insights for practical foundation design.This research demonstrates the usefulness of data-driven techniques in optimizing the design of shallow foundations within layered soil profiles,marking a significant stride in geotechnical engineering advancements.
文摘With limited number of labeled samples,hyperspectral image(HSI)classification is a difficult Problem in current research.The graph neural network(GNN)has emerged as an approach to semi-supervised classification,and the application of GNN to hyperspectral images has attracted much attention.However,in the existing GNN-based methods a single graph neural network or graph filter is mainly used to extract HSI features,which does not take full advantage of various graph neural networks(graph filters).Moreover,the traditional GNNs have the problem of oversmoothing.To alleviate these shortcomings,we introduce a deep hybrid multi-graph neural network(DHMG),where two different graph filters,i.e.,the spectral filter and the autoregressive moving average(ARMA)filter,are utilized in two branches.The former can well extract the spectral features of the nodes,and the latter has a good suppression effect on graph noise.The network realizes information interaction between the two branches and takes good advantage of different graph filters.In addition,to address the problem of oversmoothing,a dense network is proposed,where the local graph features are preserved.The dense structure satisfies the needs of different classification targets presenting different features.Finally,we introduce a GraphSAGEbased network to refine the graph features produced by the deep hybrid network.Extensive experiments on three public HSI datasets strongly demonstrate that the DHMG dramatically outperforms the state-ofthe-art models.
基金The work was supported by the National Natural Science Foundation of China （Grant Nos. 60874087 and 61174151）.
文摘In this article, we present a new type of unified dynamic scaling property for synchronizability, which can describe the scaling relationship between dynamic synehronizability and four hybrid ratios under the unified hybrid network theory framework （UHNTF）. Our theory results can not only be applied to judge and analyze dynamic synehronizability for most of complex networks associated with the UHNTF, but also we can flexibly adjust and design different hybrid ratios and sealing exponent to meet actual requirement for the dynanfic characteristics of the UHNTF.
基金supported by National Program on Key Basic Research Project of China(No.2013CB329205)National Natural Science Foundation of China(No.61601432)and Fundamental Research Funds for the Central Universities.
文摘Indoor wireless communication networking has received significant attention along with the growth of indoor data traffic.VLC(Visible Light Communication)as a novel wireless communication technology with the advantages of a high data rate,license-free spectrum and safety provides a practical solution for the indoor high-speed transmission of large data traffic.However,limited coverage is an inherent feature of VLC.In this paper,we propose a novel hybrid VLC-Wi-Fi system that integrates multiple links to achieve an indoor high-speed wide-coverage network combined with multiple access,a multi-path transmission control protocol,mobility management and cell handover.Furthermore,we develop a hybrid network experiment platform,the experimental results of which show that the hybrid VLC-Wi-Fi network outperforms both single VLC and Wi-Fi networks with better coverage and greater network capacity.
