检索结果-内蒙古大学图书馆

Transfer learning with a spatiotemporal graph convolution network for city flowprediction

Frontiers of information Technology & Electronic Engineering 2025年第1期26卷 79-92页

作者： Binkun LIU Yu KANG Yang CAO Yunbo ZHAO Zhenyi XU Department of Automation University of Science and Technology of ChinaHefei 230026China Key Laboratory of System Control and Information Processing Ministry of EducationShanghai 200240China Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China Institute of Advanced Technology University of Science and Technology of ChinaHefei 230088China

Recently,deep learning based city flow prediction has been extensively used in the establishment of *** methods are data-hungry,making them unscalable to areas lacking *** transfer learningcan use data-rich source domains to assist target domain cities in city flow prediction,the performance of existingmethods cannot meet the needs of actual use,because the long-distance road network connectivity is *** this problem,we propose a transfer learning method based on spatiotemporal graph convolution,in which weconstruct a co-occurrence space between the source and target domains,and then align the mapping of the sourceand target domains’data in this space,to achieve the transfer learning of the source city flow prediction modelon the target ***,a dynamic spatiotemporal graph convolution module along with a temporalencoder is devised to simultaneously capture the concurrent spatiotemporal features,which implies the inherentrelationship among the road network structures,human travel habits,and city bike ***,these concurrentfeatures are leveraged as cross-city invariant representations and nonlinearly spanned to a co-occurrence *** domain features are thereby aligned with the source domain features in the co-occurrence space by using aMahalanobis distance loss,to achieve cross-city bike flow *** proposed method is evaluated on the publicbike flow datasets in Chicago,New York,and Washington in 2015,and significantly outperforms state-of-the-arttechniques.

关键词： Transfer learning City flow prediction Spatiotemporal graph convolution

来源：评论

学校读者我要写书评

暂无评论

C2P-Net: Comprehensive Depth Map to Planar Depth Conversion for Room Layout Estimation

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 PP页

作者： Zhang, Weidong Zhou, Mengjie Cheng, Jiyu Liu, Ying Zhang, Wei Xi'an University of Posts & Telecommunications School of Communications and Information Engineering China Xi'an Key Laboratory of Image Processing Technology and Applications for Public Security China Shandong University School of Control Science and Engineering China Ministry of Education Key Laboratory of Machine Intelligence and System Control China

Room layout estimation seeks to infer the overall spatial configuration of indoor scenes using perspective or panoramic images. As the layout is determined by the dominant indoor planes, this problem inherently requires the reconstruction of these planes. Some studies reconstruct indoor planes from perspective images by learning pixel-level or instance-level plane parameters. However, directly learning these parameters has the problems of susceptibility to occlusions and position dependency. In this paper, we introduce the Comprehensive depth map to Planar depth (C2P) conversion, which reformulates planar depth reconstruction into the prediction of a comprehensive depth map and planar visibility confidence. Based on the parametric representation of planar depth we propose, the C2P conversion is applicable to both panoramic and perspective images. Accordingly, we present an effective framework for room layout estimation that jointly learns the comprehensive depth map and planar visibility confidence. Due to the differentiability of the C2P conversion, our network autonomously learns planar visibility confidence by constraining the estimated plane parameters and reconstructed planar depth map. We further propose a novel approach for 3D layout generation through sequential planar depth map integration. Experimental results demonstrate the superiority of our method across all evaluated panoramic and perspective datasets. © 1979-2012 IEEE.

关键词： Image-Text Matching Medical Report Generation Sample-graph Consistency Self-boosting framework

来源：评论

学校读者我要写书评

暂无评论

Non-Line-of-Sight Multipath Classification Method for BDS Using Convolutional Sparse Autoencoder with LSTM

引用

Tsinghua Science and Technology 2025年第1期30卷 68-86页

作者： Yahang Qin Zhenni Li Shengli Xie Bo Li Ming Liu Victor Kuzin School of Automation Guangdong University of Technologyand also with Guangdong-Hong Kong-Macao Joint Laboratory for Smart Discrete ManufacturingGuangzhou 510006China School of Automation Guangdong University of TechnologyGuangdong Key Laboratory of IoT Information TechnologyGuangzhou 510006China 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Key Laboratory of Intelligent Information Processing and System Integration of IoTMinistry of EducationGuangzhou 510006China Department of Electronic and Computer Engineering Hong Kong University of Science and TechnologHong Kong 999077China Academician of Russian Engineering Academy Moscow Moscow 125009Russia

Multipath signal recognition is crucial to the ability to provide high-precision absolute-position services by the BeiDou Navigation Satellite system(BDS).However,most existing approaches to this issue involve supervised machine learning(ML)methods,and it is difficult to move to unsupervised multipath signal recognition because of the limitations in signal *** by an autoencoder with powerful unsupervised feature extraction,we propose a new deep learning(DL)model for BDS signal recognition that places a long short-term memory(LSTM)module in series with a convolutional sparse autoencoder to create a new autoencoder ***,we propose to capture the temporal correlations in long-duration BeiDou satellite time-series signals by using the LSTM module to mine the temporal change patterns in the time ***,we develop a convolutional sparse autoencoder method that learns a compressed representation of the input data,which then enables downscaled and unsupervised feature extraction from long-duration BeiDou satellite series ***,we add an l_(1/2) regularizer to the objective function of our DL model to remove redundant neurons from the neural network while ensuring recognition *** tested our proposed approach on a real urban canyon dataset,and the results demonstrated that our algorithm could achieve better classification performance than two ML-based methods(e.g.,11%better than a support vector machine)and two existing DL-based methods(e.g.,7.26%better than convolutional neural networks).

关键词： convolutional sparse autoencoder BeiDou Navigation Satellite system(BDS) long short-term memory(LSTM) multipath classification

来源：评论

学校读者我要写书评

暂无评论

Optimizing Fixed-Time Generalized Nash Equilibrium Seeking in Multi-Unmanned Aerial Vehicle Games

引用

IEEE Transactions on Aerospace and Electronic systems 2025年

作者： Hua, Menghu Yao, Xiang-Yu Liu, Wen-Jin Geng, Mei-Jie Lv, Maolong China University of Geosciences School of Mechanical Engineering and Electronic Information Wuhan430074 China Ministry of Education Key Laboratory of System Control and Information Processing Shanghai 200240 China Air Force Engineering University College of Air Traffic Control and Navigation Xi'an710038 China

This study addresses a fixed-time generalized noncooperative game involving multiple unmanned aerial vehicles (UAVs) that encounter challenges such as discontinuous communication and external disturbances. Each UAV, motivated by selfinterest, seeks to optimize its performance function by adjusting its actions within shared equality and inequality constraints. To facilitate this, a fixed-time generalized Nash equilibrium (GNE) seeking algorithm is proposed for games with shared equality constraints, incorporating an internal dynamic system to ensure compliance with these constraints. By employing penalty methods, an auxiliary performance function is developed to manage games with mixed constraints. Furthermore, an error decomposition method and a fixed-time observer are introduced to address the issues of discontinuous communication and external disturbances. The study establishes sufficient conditions for the convergence of the fixed-time GNE seeking algorithm and provides an explicit upper bound on the settling time based on Lyapunov stability theory. The effectiveness of the proposed algorithms is demonstrated through various simulation examples. © 1965-2011 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Resilient Distributed Quadrotor UAVs Game: Addressing FDI and Physical Attacks

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Geng, Mei-Jie Ding, Hua-Feng Yao, Xiang-Yu Lv, Maolong China University of Geosciences School of Mechanical Engineering and Electronic Information Wuhan430074 China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China Air Force Engineering University College of Air Traffic Control and Navigation Xi'an710038 China

Distributed quadrotor unmanned aerial vehicles (UAVs) are increasingly deployed in critical applications, including reconnaissance, disaster response, and transportation, where system resilience is paramount. However, their complex dynamics and reliance on cyber-physical systems make them highly vulnerable to adversities such as uncertain dynamics, time-varying input disturbances, false data injection (FDI), and physical attacks. This paper proposes a hierarchical framework consisting of a game layer and an execution layer to enhance the resilience of a noncooperative game involving distributed UAVs. In the game layer, a novel FDI observer mitigates communication and computational FDI attacks, facilitating convergence to infinitesimal ranges around the Nash equilibrium (NE) point. The execution layer addresses uncertain dynamics and physical attacks, ensuring that UAVs can track a narrow neighborhood of the NE even in the presence of actuator failures. Extensive simulations validate the algorithm's effectiveness and robustness against mixed attack scenarios, underscoring its potential for real-world UAV applications. © 1967-2012 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Secure Consensus of Multi-agent systems via Fully Distributed Dynamic Edge-based Event Triggered Under Denial-of-service Attacks

引用

International Journal of control, Automation and systems 2025年第5期23卷 1337-1355页

作者： Li, Lei Liu, Lei Yan, Dongmei Liang, Chengqing School of Mathematics Hohai University Nanjing China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai China School of Modern Posts Nanjing University of Posts and Telecommunications Nanjing China College of Artificial Intelligence and Automation Hohai University Changzhou China Key Laboratory of Maritime Intelligent Cyberspace Technology Hohai University Ministry of Education Nanjing China

This paper addresses the issue of ensuring secure consensus in linear multi-agent systems under Denial-of-Service attacks. At the outset, to address the issue of partially observable agent states, a state observer is engineered to offer state estimations for the agents. Using the capabilities of this observer, a novel fully distributed dynamic adaptive edge-based event triggered control mechanism is introduced, and a timing variable is utilized to ensure that the inter-event intervals for all communication links in the network are strictly positive, thereby excluding Zeno behavior. Following that, by leveraging the piecewise Lyapunov function approach, the necessary conditions are meticulously crafted to ensure that the system reaches a secure consensus, thereby establishing a quantitative link between control gains, the duration of attacks, and their frequencies. Ultimately, the effectiveness of the developed event-triggered control strategy is validated through a simulation example.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural-LAFC: A Neural Learning Adaptive Flight controller for Tailless Flapping-Wing Robots Under Uncertain Wind Disturbance Conditions

引用

IEEE Transactions on Aerospace and Electronic systems 2025年

作者： Guo, Qingcheng Zhang, Yichen Mou, Jiawang Liu, Wu Wu, Xiaosheng Lu, Jun-Guo Shanghai Jiao Tong University Department of Automation China Key Laboratory of System Control and Information Processing Ministry of Education of China China National Key Laboratory of Advanced Micro and Nano Manufacture Technology Shanghai200240 China Shanghai Jiao Tong University National Key Laboratory of Advanced Micro and Nano Manufacture Technology China Shanghai Jiao Tong University Department of Micro/Nano Electronics School of Electronic Information and Electrical Engineering Shanghai200240 China Designing Institute of Hubei Space Technology Academy Wuhan China Ministry of Education of China Key Laboratory of System Control and Information Processing Shanghai200240 China

Enabling bio-inspired flapping-wing robots (FWRs) to maintain stable flight in windy environments, similar to real flying creatures, is of significant importance. In this work, a neural learning-based adaptive flight controller (Neural-LAFC) is proposed for the attitude and position control of a tailless FWR under uncertain wind conditions. The key approach involves employing a deep neural network (DNN) that incorporates not only attitude information but also instantaneous flapping angles of the wings to learn the aerodynamic torques that cannot be accurately modeled. The training data are obtained from flight experiments conducted with the FWR in a wind tunnel environment. Subsequently, a composite adaptive law is presented to update a set of linear coefficients. These linear coefficients are utilized to blend the pre-trained basis functions to represent the aerodynamic torques. The tracking errors are shown to exponentially converge to a bounded region, as guaranteed by a Lyapunov function. Based on the learning-based attitude controller, we also develop an adaptive controller for position control. Notably, apart from the training phase, the FWR operates without prior knowledge of wind speed. Experimental results demonstrate that the Neural-LAFC successfully achieves the desired attitude stabilization, target point tracking, and path tracking of the FWR in windy conditions. The proposed control scheme also outperforms baseline controllers in wind disturbance suppression, reducing the root mean square position errors by more than 40% when the FWR is subjected to a horizontal wind within the speed of 180 {cm s{-1}}. © 1965-2011 IEEE.

关键词： Wind tunnels

来源：评论

学校读者我要写书评

暂无评论

Edge-Assisted Flexible Platooning of Connected and Automated Vehicles Under Traffic Anomaly

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Gao, Fengkun Yang, Bo Chen, Cailian Guan, Xinping Shanghai Jiao Tong University Department of Automation Shanghai200240 China Ministry of Education of China Key Laboratory of System Control and Information Processing Shanghai200240 China Shanghai Engineering Research Center of Industrial Intelligent Control and Management Shanghai200240 China

The platooning of connected and automated vehicles (CAVs) has the great potential to significantly improve travel experience in terms of safety, comfortableness, and energy efficiency. However, constrained by sensing range and prediction accuracy, the performance of CAV platoon can not be guaranteed in the scenario of mixed traffic consisting of CAVs and human-driven vehicles (HDVs). This is not only due to the uncertainty of HDVs but also related to the occurrence of various traffic anomalies, such as emergency braking and accidents. In this paper, we aim to investigate an efficient control strategy to guarantee the operation of the platoon in mixed traffic, especially in the case of traffic anomalies. To tackle the problem, an edge-assisted platoon control strategy, called E-CACC, is proposed. First, an error-aware flexible tracking policy is designed to adapt to HDV uncertainties and speed prediction errors. Based on the tracking policy, a zone model predictive control (ZMPC) method is then designed to guarantee travel safety and avoid undesired acceleration. Further, a coordination strategy of CAV platoon and roadside unit (RSU) is proposed to prevent the platoon from potential collision in the case of traffic anomalies, where an event-based communication trigger is designed to determine whether and when the platoon establishes communication links with RSU to acquire exogenous sensing data of anomaly segment. Finally, the evaluation results illustrate the effectiveness of the proposed method in improving travel safety and comfortableness. © 1967-2012 IEEE.

关键词： Braking performance

来源：评论

学校读者我要写书评

暂无评论

Analysis of the SEIR mean-field model in dynamic networks under intervention

引用

Infectious Disease Modelling 2025年第3期10卷 850-874页

作者： Li, Jiangmin Jin, Zhen Tang, Ming Complex System Research Center Shanxi University Shanxi Taiyuan 030006 China Key Laboratory of Complex Systems and Data Science of Ministry of Education Shanxi University Shanxi Taiyuan 030006 China Shanxi Key Laboratory for Mathematical Technology in Complex Systems Shanxi University Shanxi Taiyuan 030006 China School of Physics and Electronic Science East China Normal University Shanghai 200241 China Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai 200241 China

For emerging respiratory infectious diseases like COVID-19, non-pharmaceutical interventions such as isolation are crucial for controlling the spread. From the perspective of network transmission, non-pharmaceutical interventions like isolation alter the degree distribution and other topological structures of the network, thereby controlling the spread of the infectious disease. In this paper, we establish a SEIR mean-field propagation dynamics model for the synchronous evolution of dynamic networks caused by propagation and tracing isolation. We employ the reducing-dimension method to convert the mean-field model in networks into an equivalent and simpler low-dimension model, and then calculate the exact expression of the final size. In addition, we get the differential equations of the degree distribution over time in dynamic networks under tracing isolation and the relationships between the first and second moment of the dynamic network. While the degree of a node remains constant regardless of its state in many previous studies, this paper takes into account that the degree of each node changes over time whatever its state under the disease spread and intervention measures. © 2025 The Authors

关键词： Degree distribution Dynamic network The final size Tracing isolation

来源：评论

学校读者我要写书评

暂无评论

Experimental demonstration of 8190-km long-haul semiconductor-laser chaos synchronization induced by digital optical communication signal

引用

光：科学与应用（英文版） 2025年第2期14卷 333-343页

作者： Anbang Wang Junli Wang Lin Jiang Longsheng Wang Yuncai Wang Lianshan Yan Yuwen Qin Key Laboratory of Photonic Technology for Integrated Sensing and Communication Ministry of Education of ChinaGuangdong University of TechnologyGuangzhou 510006China Key Laboratory of Advanced Transducers and Intelligent Control System Ministry of Education and Shanxi ProvinceTaiyuan 030024China Institute of Advanced Photonics Technology School of Information EngineeringGuangdong University of TechnologyGuangzhou 510006China Guangdong Provincial Key Laboratory of Information Photonics Technology Guangdong University of TechnologyGuangzhou 510006China Key Laboratory of Advanced Transducers and Intelligent Control System Ministry of Education and Shanxi ProvinceTaiyuan 030024China College of Physics and Optoelectronics Taiyuan University of TechnologyTaiyuan 030024China Center for Information Photonics and Communications Southwest Jiaotong UniversityChengdu 610031China Key Laboratory of Photonic Technology for Integrated Sensing and Communication Ministry of Education of ChinaGuangdong University of TechnologyGuangzhou 510006China Institute of Advanced Photonics Technology School of Information EngineeringGuangdong University of TechnologyGuangzhou 510006China Guangdong Provincial Key Laboratory of Information Photonics Technology Guangdong University of TechnologyGuangzhou 510006China

Common-signal-induced synchronization of semiconductor lasers have promising applications in physical-layer secure transmission with high speed and compatibility with the current fiber ***,we propose an ultra-long-distance laser synchronization scheme by utilizing random digital optical communication signal as the common drive *** utilizing the long-haul optical coherent communication techniques,high-fidelity fiber transmission of the digital drive can be achieved and thus ultra-long-distance synchronization is *** were implemented with distributed feedback lasers injected by a random-digital phase-modulated drive *** show that high-quality synchronization can be achieved as the drive signal rate is larger than the laser relaxation frequency and the transmission bit error ratio is below a critical *** synchronization over 8191-km fiber transmission was experimentally *** to traditional common-signal-induced synchronization using analog drive signal such as chaos,the distance is increased by 8 times,and complicated hardware devices for channel impairment compensation are no longer *** addition,the proposed method does not sacrifice communication capacity like traditional methods which need a channel to transmit analog drive *** is therefore believed that this common-digital-signal induced laser synchronization paves a way for secure backbone and submarine transmission.

关键词： communication semiconductor synchronization signal digital chaos laser demonstration experimental induced

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：