检索结果-南通市图书馆

A credible traffic prediction method based on self-supervised causal discovery

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第5期67卷 244-258页

作者： Dan WANG yingjie liu Bin SONG State Key Laboratory of Integrated Services Networks Xidian University

Next-generation wireless network aims to support low-latency, high-speed data transmission services by incorporating artificial intelligence(AI) technologies. To fulfill this promise, AI-based network traffic prediction is essential for pre-allocating resources, such as bandwidth and computing power. This can help reduce network congestion and improve the quality of service(QoS) for users. Most studies achieve future traffic prediction by exploiting deep learning and reinforcement learning, to mine spatio-temporal correlated variables. Nevertheless, the prediction results obtained only by the spatio-temporal correlated variables cannot reflect real traffic changes. This phenomenon prevents the true prediction variables from being inferred, making the prediction algorithm perform poorly. Inspired by causal science, we propose a novel network traffic prediction method based on self-supervised spatio-temporal causal discovery(SSTCD). We first introduce the Granger causal discovery algorithm to build a causal graph among prediction variables and obtain spatio-temporal causality in the observed data, which reflects the real reasons affecting traffic ***, a graph neural network(GNN) is adopted to incorporate causality for traffic prediction. Furthermore,we propose a self-supervised method to implement causal discovery to to address the challenge of lacking ground-truth causal graphs in the observed data. Experimental results demonstrate the effectiveness of the SSTCD method.

关键词： wireless network traffic prediction causal discovery self-supervised

Numerical study of corner separation in a linear compressor cascade using various turbulence models

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2016年第3期29卷 639-652页

作者： liu Yangwei Yan Hao liu yingjie Lu Lipeng Li Qiushi Collaborative Innovation Center of Advanced Aero-Engine Beihang UniversityBeijing 100083China National Key Laboratory of Science and Technology on Aero-Engine Aero-ThermodynamicsSchool of Energy and Power EngineeringBeihang University

Three-dimensional corner separation is a common phenomenon that significantly affects compressor performance. Turbulence model is still a weakness for RANS method on predicting corner separation flow accurately. In the present study, numerical study of corner separation in a linear highly loaded prescribed velocity distribution （PVD） compressor cascade has been investigated using seven frequently used turbulence models. The seven turbulence models include Spalart Allmaras model, standard k-e model, realizable k-e model, standard k-to model, shear stress transport k co model, v2-fmodel and Reynolds stress model. The results of these turbulence models have been compared and analyzed in detail with available experimental data. It is found the standard k-1： model, realizable k-e model, v2-f model and Reynolds stress model can provide reasonable results for predicting three dimensional corner separation in the compressor cascade. The Spalart-Allmaras model, standard k-to model and shear stress transport k-w model overesti- mate corner separation region at incidence of 0°. The turbulence characteristics are discussed and turbulence anisotropy is observed to be stronger in the corner separating region.

关键词： Compressor cascade Corner separation Turbomachinery CFD Turbulence anisotropy Turbulence models

Secure and reliable computation offloading in blockchain-assisted cyber-physical IoT systems

在线全文

学校读者我要写书评

暂无评论

Digital Communications and Networks 2022年第5期8卷 625-635页

作者： Dan Wang Bin Song yingjie liu Mingjun Wang The State Key Laboratory of Integrated Services Networks Xidian UniversityXi'an710071China

With the development of the Cyber-Physical Internet of Things System(CPIoTS),the number of Cyber-Physical System(CPS)applications accessed in networks has increased ***-sensitive resource orchestration in CPS applications is extraordinarily essential for maintaining the Quality of Experience(QoE)for *** edge-cloud computing performs effectively in achieving latency-aware resource allocation in CPIoTS,existing methods fail to jointly consider the security and reliability requirements,thereby increasing the process latency of tasks and degrading the QoE of *** paper aims to minimize the system latency of edge-cloud computing coupled with CPS while simultaneously considering the security and reliability *** first consider a time-varying channel model as a Finite-State Markov Channel(FSMC)and propose a distributed blockchain-assisted CPIoTS to realize secure consensus and reliable resource orchestration by offloading computation tasks in edge-cloud ***,we propose an efficient resource allocation algorithm,PPO-SRRA,that optimizes computing offloading and multi-dimension resource(e.g.,communication,computation,and consensus resource)allocation by using a policy-based Deep Reinforcement Learning(DRL)*** experimental results show that the proposed resource allocation scheme can reduce the system latency and ensure consensus security.

关键词： Cyber-physical internet of things system Blockchain Reinforcement learning(RL) Edge-cloud computing

Underwater Image Transmission Method and Realization Based on Inductively Coupled Mooring Chain

在线全文

学校读者我要写书评

暂无评论

Journal of Ocean University of China 2024年第6期23卷 1503-1514页

作者： ZHENG Yu liu yingjie SONG Rujuan LI Hongzhi School of Life Sciences Tiangong UniversityTianjin 300387China National Ocean Technology Center Tianjin 300112China

Inductively coupled mooring chain transmission technology plays a crucial role in the long-distance online monitoring of marine hydrographic ***,the impedance characteristics of the seawater medium pose a limitation on its capability to achieve high-speed real-time transmission of underwater *** this paper,based on the principle of inductively coupled transmission for marine applications,the selected 1920×1080 pixel images are segmented,packaged,and then transmitted to the sending node using the user datagram protocol(UDP),and the modulation and demodulation of the transmitted images are realized using the orthogonal frequency division multiplexing(OFDM)algorithm of least squares(LS)estimation,and eight combinations with different mapping modes and coding rates are tested in the bandwidth of 200-800 k Hz and the quality of the transmitted images is evaluated using three criteria:mean squared error(MSE),peak signal to noise ratio(PSNR),and structural similarity index(SSIM).The results indicate that the image transmission quality is optimal when the mapping method is 16-quadrature amplitude modulation(16QAM),the coding rate is 1/2,and the center frequency is 800 k *** these conditions,the maximum transmission rate is 0.84 Mbit s^(-1),the SSIM criterion exceeds 0.91690 d B,and the learned perceptual image patch similarity(LPIPS)is less than *** paper provides a solution for the underwater image transmission of inductively coupled mooring chains for marine applications.

关键词： ocean inductively coupled mooring chain underwater image OFDM data communication

New development of cognitive diagnosis models

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2023年第1期17卷 157-169页

作者： yingjie liu Tiancheng ZHANG Xuecen WANG Ge YU Tao LI School of Computer Science and Engineering Northeastern UniversityShenyang 110169China

Cognitive diagnosis is the judgment of the student’s cognitive ability, is a wide-spread concern in educational science. The cognitive diagnosis model (CDM) is an essential method to realize cognitive diagnosis measurement. This paper presents new research on the cognitive diagnosis model and introduces four individual aspects of probability-based CDM and deep learning-based CDM. These four aspects are higher-order latent trait, polytomous responses, polytomous attributes, and multilevel latent traits. The paper also sorts on the contained ideas, model structures and respective characteristics, and provides direction for developing cognitive diagnosis in the future.

关键词： higher-order latent traits polytomous responses polytomous attributes multilevel latent traits cognitive diagnosis

Neural Networks with Local Converging Inputs(NNLCI)for Solving Conservation Laws,Part II:2D Problems

在线全文

学校读者我要写书评

暂无评论

Communications in Computational Physics 2023年第7期34卷 907-933页

作者： Haoxiang Huang Vigor Yang yingjie liu Woodruff School of Mechanical Engineering Georgia Institute of TechnologyAtlantaGA 30332USA Daniel Guggenheim School of Aerospace Engineering Georgia Institute of TechnologyAtlantaGA 30332USA School of Mathematics Georgia Institute of TechnologyAtlantaGA 30332USA

In our prior work[10],neural networks with local converging inputs(NNLCI)were introduced for solving one-dimensional conservation *** solutions of a conservation law in a converging sequence,computed from low-cost numerical schemes,and in a local domain of dependence of the space-time location,were used as the input to a neural network in order to predict a high-fidelity solution at a given space-time *** the present work,we extend the method to twodimensional conservation systems and introduce different solution *** results demonstrate the validity and effectiveness of the NNLCI method for application to multi-dimensional *** spite of low-cost smeared input data,the NNLCI method is capable of accurately predicting shocks,contact discontinuities,and the smooth region of the entire *** NNLCI method is relatively easy to train because of the use of local *** computing time saving is between one and two orders of magnitude compared with the corresponding high-fidelity schemes for two-dimensional Riemann *** relative efficiency of the NNLCI method is expected to be substantially greater for problems with higher spatial dimensions or smooth solutions.

关键词： Neural network neural networks with local converging inputs physics informed machine learning conservation laws differential equation multi-fidelity optimization

LC-NPLA: Label and Community Information-Based Network Presentation Learning Algorithm

在线全文

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第12期38卷 203-223页

作者： Shihu liu Chunsheng Yang yingjie liu School of Mathematics and Computer Science Yunnan Minzu UniversityKunming650504China

Many network presentation learning algorithms(NPLA)have originated from the process of the random walk between nodes in recent *** these algorithms can obtain great embedding results,there may be also some *** instance,only the structural information of nodes is considered when these kinds of algorithms are *** at this issue,a label and community information-based network presentation learning algorithm(LC-NPLA)is proposed in this *** of all,by using the community information and the label information of nodes,the first-order neighbors of nodes are *** the next,the random walk strategy is improved by integrating the degree information and label information of ***,the node sequence obtained from random walk sampling is transformed into the node representation vector by the Skip-Gram *** last,the experimental results on ten real-world networks demonstrate that the proposed algorithm has great advantages in the label classification,network reconstruction and link prediction tasks,compared with three benchmark algorithms.

关键词： Label information community information network representation learning algorithm random walk

Numerical Identification of Nonlocal Potentials in Aggregation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Communications in Computational Physics 2022年第8期32卷 638-670页

作者： Yuchen He Sung Ha Kang Wenjing Liao Hao liu yingjie liu Institute of Natural Sciences Shanghai Jiao Tong UniversityShanghaiChina School of Mathematics Georgia Institute of TechnologyAtlantaGeorgiaGA 30332-0160USA Department of Mathematics Hong Kong Baptist UniversityHong Kong SAR

Aggregation equations are broadly used tomodel population dynamicswith nonlocal interactions,characterized by a potential in the *** paper considers the inverse problem of identifying the potential from a single noisy spatialtemporal *** identification is challenging in the presence of noise due to the instability of numerical *** propose a robust model-based technique to identify the potential by minimizing a regularized data fidelity term,and regularization is taken as the total variation and the squared Laplacian.A split Bregman method is used to solve the regularized optimization *** method is robust to noise by utilizing a Successively Denoised Differentiation *** consider additional constraints such as compact support and symmetry constraints to enhance the performance *** also apply thismethod to identify time-varying potentials and identify the interaction kernel in an agent-based *** numerical examples in one and two dimensions are included to verify the effectiveness and robustness of the proposed method.

关键词： Aggregation equation nonlocal potential PDE identification Bregman iteration operator splitting

Non-Oscillatory Hierarchical Reconstruction for Central and Finite Volume Schemes

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Communications in Computational Physics 2007年第5期2卷 933-963页

作者： yingjie liu Chi-Wang Shu Eitan Tadmor Mengping Zhang School of Mathematics Georgia Institute of TechnologyAtlantaGA 30332-0160USA. Division of Applied Mathematics Brown UniversityProvidenceRI 02912USA Department of Mathematics Institute for Physical Science and Technologyand Center of Scientific Computation and Mathematical Modeling(CSCAMM)University of MarylandCollege ParkMD 20742USA Department of Mathematics University of Science and Technology of ChinaHefeiAnhui 230026China

This is the continuation of the paper”Central discontinuous Galerkin methods on overlapping cells with a non-oscillatory hierarchical reconstruction”by the same *** hierarchical reconstruction introduced therein is applied to central schemes on overlapping cells and to finite volume schemes on non-staggered *** takes a new finite volume approach for approximating non-smooth solutions.A critical step for high-order finite volume schemes is to reconstruct a non-oscillatory high degree polynomial approximation in each cell out of nearby cell *** the paper this procedure is accomplished in two steps:first to reconstruct a high degree polynomial in each cell by using e.g.,a central reconstruction,which is easy to do despite the fact that the reconstructed polynomial could be oscillatory;then to apply the hierarchical reconstruction to remove the spurious oscillations while maintaining the high *** numerical computations for systems of conservation laws are performed without characteristic *** particular,we demonstrate that this new approach can generate essentially non-oscillatory solutions even for 5th-order schemes without characteristic decomposition.

关键词： Central scheme discontinuous Galerkin method ENO scheme finite volume scheme MUSCL scheme TVD scheme.