检索结果-内蒙古大学图书馆

One Size Fits All: A Unified Traffic Predictor for Capturing the Essential Spatial-Temporal Dependency

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING systems 2024年第8期35卷 11317-11331页

作者： Luo, Guiyang Zhang, Hui Yuan, Quan Li, Jinglin Wang, Wendong Wang, Fei-Yue Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing 100044 Peoples R China Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

Traffic prediction is a keystone for building smart cities in the new era and has found wide applications in traffic scheduling and management, environment policy making, public safety, and so on. Instead of creating a traffic predictor for each city, this article focuses on designing a unified network model that could be directly applied for traffic prediction in any city, by learning the essential spatial-temporal dependencies, i.e., the mutual relationship between traffic and the corresponding fine-grained road network. To achieve this goal, this article proposes a joint knowledge-and data-driven mechanism that novelly divides dependencies into three kinds of correlations, i.e., road segment, intra-intersection, and inter-intersection correlation, which capture the microcosmic, middle, and macroscopic dependencies between traffic and the road network, respectively. Specifically, we first construct traffic datasets that could cover all road segments from real-world trajectory datasets, which makes it possible to model the whole road network as a graph, with the help of fine-grained road topology. Then, we propose meta road segment learner, connection-aware spatial-temporal graph convolutional network (GCN), and multiscale residual networks for capturing the microcosmic, middle, and macroscopic dependencies, respectively. Our experiments on three real-world datasets demonstrate that our proposed method could: 1) achieve better prediction accuracy compared with several approaches and 2) capture the mutual relationship between traffic and the fine-grained road network since our model trained only using data from the source city achieves good performance when it is directly applied for traffic prediction in the target city, without any fine-tuning. The codes will be made publicly available.

关键词： Graph convolutional network (GCN) spatial-temporal dependencies (STDs) spatial-temporal GCN traffic prediction

来源：评论

学校读者我要写书评

暂无评论

ADMM-based joint rescheduling method for high-speed railway timetabling and platforming in case of uncertain perturbation✩

引用

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES 2023年第1期152卷

作者： Liu, Xuan Zhou, Min Dong, Hairong Wu, Xingtang Li, Yidong Wang, Fei-Yue Beijing Jiaotong Univ State Key Lab Rail Traff Control & Safety Beijing 100044 Peoples R China Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing 100044 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

The operation of high-speed trains is susceptible to perturbations such as strong winds and heavy snowfall, causing them to deviate from operating schedules. A joint mixed-integer linear programming (MILP) model based on the event-activity network is proposed to reschedule the train timetable and platform assignment jointly. Trains traveling in different directions are simultaneously considered in this model, and they can occupy the available reverse platforms in stations. Furthermore, to strengthen the robustness of the rescheduling scheme in case of uncertain perturbations, such as variable temporary speed restrictions caused by changing wind speed, the uncertainty is modeled using scenario-based chance constraints, which are then converted into deterministic constraints. Model predictive control (MPC) divides the entire time horizon into several stages. In each stage, the proposed model is decomposed according to directions. The constraints for trains traveling in different directions are dualized by the Alternating Direction Method of Multipliers (ADMM), which makes the sub-problems decoupled and solvable in parallel in each iteration of ADMM, promoting real-time performance. The real timetable and line data of Beijing-Shanghai HSR are utilized to investigate the effect of the proposed method. Compared to the commonly used strategies, it can significantly reduce delays and the number of affected events. The proposed method also shows relatively high robustness compared to the method in the case of predefined perturbations. It causes fewer conflicts and fewer needs for rescheduling when facing the changing perturbation and gets rescheduling results with higher quality.

关键词： Timetable rescheduling Platforming Uncertain perturbation Model predictive control Alternative direction method of multipliers

来源：评论

学校读者我要写书评

暂无评论

Blind Image Despeckling Using a Multiscale Attention-Guided Neural Network

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第1期5卷 205-216页

作者： Guo, Yu Lu, Yuxu Liu, Ryan Wen Zhu, Fenghua Wuhan University of Technology School of Navigation Wuhan430063 China Wuhan University of Technology Chongqing Research Institute Chongqing401151 China Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Beijing100190 China

Coherent imaging systems have been applied in the detection of target of interest, natural resource exploration, ailment diagnosis, etc. However, it is easy to generate speckle-degraded images due to the coherent interference of reflected echoes, restricting these practical applications. Speckle noise is a granular interference that affects the observed reflectivity. It is often modeled as multiplicative noise with a negative exponential distribution. This nonlinear property makes despeckling of imaging data an intractable problem. To enhance the despeckling performance, we propose to blindly remove speckle noise using an intelligent computing-enabled multiscale attention-guided neural network (termed MSANN). In particular, we first introduce the logarithmic transformation to convert the multiplicative speckle noise model to an additive version. Our MSANN, essentially a feature pyramid network, is then exploited to restore degraded images in the logarithmic domain. To enhance the generalization ability of the MSANN, a multiscale feature enhancement attention module is incorporated into the MSANN to extract multiscale features for improving the imaging quality. A multiscale mixed loss function is further presented to increase the network robustness during training. The final despeckled images are naturally equivalent to the exponential versions of the output of the MSANN. Experimental results have shown that the MSANN has the capacity of effectively removing the speckle noise while preserving essential structures. It can achieve superior despeckling results in terms of visual quality and quantitative measures. © 2020 IEEE.

关键词： Additives

来源：评论

学校读者我要写书评

暂无评论

Piecewise Compensation Model Predictive Governor Combined With Conditional Disturbance Negation for Underactuated AUV Tracking control

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2023年第6期70卷 6191-6200页

作者： Kong, Shihan Sun, Jinlin Wang, Jian Zhou, Ziye Shao, Jinyan Yu, Junzhi Peking Univ Coll Engn Dept Adv Mfg & Robot State Key Lab Turbulence & Complex Syst Beijing 100871 Peoples R China Jiangsu Univ Sch Elect & Informat Engn Zhenjiang 212013 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

With respect to the accurate tracking control for autonomous underwater vehicles (AUVs), this article proposes a novel control architecture consisting of piecewise compensation model predictive governor and conditional disturbance negation-based active disturbance rejection controller. The designed piecewise compensation mechanism is implemented to eliminate the steady tracking errors resulting from the underactuation problem of AUVs, and the model predictive governor aims to generate reference tracking velocities satisfying the constraints. Concurrently, a finite-time extended state observer is designed to improve the convergence performance of the estimation errors. In addition, the concept of conditional disturbance negation is employed to endow AUVs with the capability of taking advantage of disturbances rather than only rejecting disturbances. Finally, comprehensive analyses of the simulations and the experiments demonstrate the impressive control performance, verifying the feasibility of potential applications on real AUVs.

关键词： Underwater vehicles Predictive models Kinetic theory Trajectory Force Convergence Observers Autonomous underwater vehicle (AUV) conditional disturbance negation (CDN) finite-time extended state observer (ESO) piecewise compensation tracking control

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Monocular Depth Estimation With Geometric Prior and Pixel-Level Sensitivity

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2023年第3期8卷 2244-2256页

作者： Liu, Jierui Cao, Zhiqiang Liu, Xilong Wang, Shuo Yu, Junzhi Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Peking Univ Coll Engn Dept Adv Mfg & Robot State Key Lab Turbulence & Complex Syst Beijing Peoples R China

Self-supervised monocular depth estimation has gained popularity due to its convenience of training network without dense ground truth depth annotation. Specifically, the multi-frame monocular depth estimation achieves promising results in virtue of temporal information. However, existing multi-frame solutions ignore the different impacts of pixels of input frame on depth estimation and the geometric information is still insufficiently explored. In this paper, a self-supervised monocular depth estimation framework with geometric prior and pixel-level sensitivity is proposed. Geometric constraint is involved through a geometric pose estimator with prior depth predictor and optical flow predictor. Further, an alternative learning strategy is designed to improve the learning of prior depth predictor by decoupling it with the ego-motion from the geometric pose estimator. On this basis, prior feature consistency regularization is introduced into the depth encoder. By taking the dense prior cost volume based on optical flow map and ego-motion as the supervising signal for feature consistency learning, the cost volume is obtained with more reasonable feature matching. To deal with the pixel-level difference of sensitivity in input frame, a sensitivity-adaptive depth decoder is built by flexibly adding a shorter path from cost volume to the final depth prediction. In this way, the back propagation of gradient to cost volume is adaptively adjusted, and an accurate depth map is decoded. The effectiveness of the proposed method is verified on public datasets.

关键词： Estimation Costs Training Sensitivity Cameras Optical flow Semantics Monocular depth estimation self-supervised learning prior feature consistency sensitivity adaptation

来源：评论

学校读者我要写书评

暂无评论

Point Cloud Classification Using Content-Based Transformer via Clustering in Feature Space

引用

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 231-239页

作者： Yahui Liu Bin Tian Yisheng Lv Lingxi Li Fei-Yue Wang the State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 the School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100190 IEEE the Transportation and Autonomous Systems Institute(TASI)and the Department of Electrical and Computer Engineering Purdue School of Engineering and TechnologyIndiana University-Purdue University Indianapolis(IUPUI)Indianapolis 46202 USA

Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to establish relationships between distant but relevant points. To overcome the limitation of local spatial attention, we propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space(content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class, thus enabling an effective trade-off between capturing long-range dependencies and computational complexity. We further introduce an inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately. Extensive experiments show that our PointConT model achieves a remarkable performance on point cloud shape classification. Especially, our method exhibits 90.3% Top-1 accuracy on the hardest setting of ScanObjectN N. Source code of this paper is available at https://***/yahuiliu99/PointC onT.

关键词： Content-based Transformer deep learning feature aggregator local attention point cloud classification

来源：评论

学校读者我要写书评

暂无评论

A Novel DAO-Based Parallel Enterprise management Framework in Web3 Era

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL systems 2024年第1期11卷 839-848页

作者： Wang, Ge Qin, Rui Li, Juanjuan Wang, Fei-Yue Gan, Yu Yan, Lihua Macau Univ Sci & Technol Macao Inst Syst Engn Macau 999078 Peoples R China Chinese Acad Sci State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Multimodal Artificial Intelligence S Beijing 100190 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Qingdao Huituo Waytous Intelligent Robot Co Ltd Qingdao 266114 Peoples R China

This article proposes a novel parallel management mode based on decentralized autonomous organizations (DAOs) for enterprises by utilizing the artificial systems, computational experiments, parallel execution (ACP) approach, parallel intelligence theory, and blockchain technologies, to realize the distributed management of an enterprise. The artificial enterprise DAO (EnDAO) corresponding to the actual enterprise is constructed, and they constitute a parallel system via virtual-real interaction and parallel execution. Through the non-fungible token (NFT)-based incentive mechanism, metaverse-based virtual learning and training, as well as DAO-based distributed management and decision-making, the management and control of the actual enterprise as well as its employees can be carried out. By virtue of the virtual-real interactions of three types of employees, as well as the virtual-real feedback of three closed loops in the parallel systems, DAO-based parallel management for enterprises can realize descriptive intelligence, predictive intelligence, and prescriptive intelligence. On this basis, this article takes the recruitment-oriented key performance indicator (KPI) management of a startup technology enterprise as the case to introduce the operation processes and illustrate the superiorities of the proposed DAO-based enterprise parallel management mode.

关键词： Blockchain decentralized autonomous organizations (DAOs) metaverse parallel intelligence parallel management

来源：评论

学校读者我要写书评

暂无评论

Trustworthy Intelligent Vehicle systems Based on TRUE Autonomous Organizations and Operations: A New Perspective

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2024年第2期9卷 3195-3204页

作者： Liang, Xiaolong Li, Juanjuan Qin, Rui Wang, Fei-Yue Macau Univ Sci & Technol Fac Innovat Engn Macau 999078 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Multimodal Artificial Intelligence S Beijing 100190 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 266109 Peoples R China

Intelligent Vehicles (IVs), integrating sensing, communication, and computing technologies, have immense potential to elevate efficiency, reduce traffic accidents, and diminish emissions. However, since faulty decisions made by IVs may endanger the safety of people's lives and property, improper trust in these automated systems could potentially lead to significant risks and problems. The trust issues in IVs stems not only from technological immaturity but also from the inability of automation systems to handle complex social relationships. TRUE Autonomous Organizations and Operations (TAOs), underpinned by blockchain and smart contracts, propose a code-governed, trustworthy human-machine collaboration model, offering a promising approach to tackle those challenges. This paper introduces TAOs into IVs to propose an innovative human-machine collaboration system namely IV-TAOs, aiming to enhance the trustworthiness between humans and IVs. The architecture of IV-TAOs is formulated, with an exploration of both their characteristics and associated risk issues. This work provides a new perspective on addressing the trust issues encompassing but not confined solely within the context of intelligent vehicles.

关键词： Ethics Collaboration Organizations Intelligent vehicles Decision making Artificial intelligence Smart contracts Decentralized autonomous organizations TRUE autonomous organizations and operations intelligent vehicles blockchain

来源：评论

学校读者我要写书评

暂无评论

Approximate Dynamic Programming for Event-Driven H8 Constrained control

引用

IEEE TRANSACTIONS ON systems MAN CYBERNETICS-systems 2023年第9期53卷 5922-5932页

作者： Yang, Xiong Xu, Mengmeng Wei, Qinglai Tianjin Univ Sch Elect & Informat Engn Tianjin Key Lab Intelligent Unmanned Swarm Technol Tianjin 300072 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

We study the dynamic event-driven Hop constrained control problem through approximate dynamic programming (ADP). Differing from the existing literature considering systems with either symmetric constraints or asymmetric constraints, we consider the two different constraints simultaneously. Initially, by constructing a generalized nonquadratic value function, we trans -form the H-8 constrained control problem into an unconstrained two-player zero-sum game. Then, we present an event-driven Hamilton-Jacobi-Isaacs equation (ED-HJIE) corresponding to the zero-sum game for lowering down the computational load. To solve the ED-HJIE, we propose a dynamic triggering mech-anism together with a sole critic neural network (CNN) being built under the ADP framework. The CNN's weights are tuned via the gradient descent approach. After that, we prove uniform ultimate boundedness of the closed-loop system and the CNN's weight estimation error via Lyapunov's method. Finally, we sepa-rately use an F16 aircraft plant and an inverted pendulum system to validate the present theoretical claims.

关键词： Approximate dynamic programming (ADP) event-driven control H(8)control input constraint optimal control

来源：评论

学校读者我要写书评

暂无评论

Learning Transferable Conceptual Prototypes for Interpretable Unsupervised Domain Adaptation

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2024年 33卷 5284-5297页

作者： Gao, Junyu Ma, Xinhong Xu, Changsheng Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst MA Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 101408 Peoples R China Peng Cheng Lab Shenzhen Peoples R China

Despite the great progress of unsupervised domain adaptation (UDA) with the deep neural networks, current UDA models are opaque and cannot provide promising explanations, limiting their applications in the scenarios that require safe and controllable model decisions. At present, a surge of work focuses on designing deep interpretable methods with adequate data annotations and only a few methods consider the distributional shift problem. Most existing interpretable UDA methods are post-hoc ones, which cannot facilitate the model learning process for performance enhancement. In this paper, we propose an inherently interpretable method, named Transferable Conceptual Prototype Learning (TCPL), which could simultaneously interpret and improve the processes of knowledge transfer and decision-making in UDA. To achieve this goal, we design a hierarchically prototypical module that transfers categorical basic concepts from the source domain to the target domain and learns domain-shared prototypes for explaining the underlying reasoning process. With the learned transferable prototypes, a self-predictive consistent pseudo-label strategy that fuses confidence, predictions, and prototype information, is designed for selecting suitable target samples for pseudo annotations and gradually narrowing down the domain gap. Comprehensive experiments show that the proposed method can not only provide effective and intuitive explanations but also outperform previous state-of-the-arts. Code is available at https://***/file/d/1b1EHFghiF1ExD-Cn1HYg75VutfkXWp60/view?usp=sharing.

关键词： Prototypes Adaptation models Motorcycles Image recognition Decision making Cognition Target recognition Explainable AI transfer learning image classification deep learning

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

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

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：