检索结果-内蒙古大学图书馆

A Simplified Variant for Graph Convolutional Network Based Knowledge Graph Completion Model

学校读者我要写书评

暂无评论

A Simplified Variant for Graph Convolutional Network Based K...

IEEE International Conference on Data science in Cyberspace (DSC)

作者： Yashen Wang Qiang Li Yi Zhang Xuecheng Zhang Zhuoya Ju Jian Sun National Engineering Laboratory for Risk Perception and Prevention (RPP) Key Laboratory of Cognition and Intelligence Technology (CIT) China Academy of Electronics and Information Technology Artificial Intelligence Institute of CETC Beijing China The State Key Laboratory for Management and Control of Complex Systems Scientific and Technological Innovation Center of ARI Institute of Automation Chinese Academy of Sciences Beijing China CETC Academy of Electronics and Information Technology Group Co. Ltd. Beijing China Khoury College of Computer Science Northeastern University U.S.A Scientific and Technological Innovation Center of ARI Beijing China Qi An Xin Technology Group Inc. Beijing China

Knowledge graphs (KGs) serve as useful resources for various applications including machine learning, data mining, and artificial intelligence. Knowledge Graph Completion (KGC) aims at reasoning over known (observed) facts and infer the missing (unobserved) relationships, to improve KG's coverage. Many recent works have laid stress on leveraging Graph Convolutional Networks (GCNs) for KGC task, which obtain good representation learning ability for graph-structured data, and have achieved satisfactory results. However, GCN-based researches continue to improve these lines of models by introducing an increasingly complex feature space. Especially, the hyper-parameter space of conventional GCN-based KGC model is too huge, resulting in low computational efficiency and excessive storage pressure. To overcome this problem, this paper investigates a simplified and generic variant for GCN-based KGC model, and shows that simple changes in the architecture of the underlying architecture (with a Subtraction Operator and an Addition Operator), can compte with state-of-the-art GCN-based models. Therefore, this paper proposes a easy-to-accomplish plug-in unit, which could be loaded into any current GCN-based KGC architectures, and help them maximize the maintenance of native model's original performance while significantly reducing parameter scale.

关键词：

Society 5.0: Metaverse Facilitated Human-centric “5H” Services Across Cyber-Physical-Social Spaces

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2024年第3期58卷 159-164页

作者： Xiao Wang Jun Huang QingHua Ni Zhe Wan HuaDan Xue Larry Stapleton Fei-Yue Wang Engineering Research Center of Autonomous Unmanned System Technology Ministry of Education Anhui University Hefei 230601 China Macau University of Science and Technology Macau 999078 China Beijing Normal University Beijing 100875 China Department of Radiology Peking Union Medical College Hospital Shuaifuyuan Beijing 100730 Dongcheng District China Brownsbarn Thomastown Co. Kilkenny Ireland R95D8P2 Qingdao Academy of Intelligent Industries Qingdao 266109 China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China

Cyber-Physical-Social systems bridge the gap between social resource organization and distribution, and give birth to Society 5.0, which represents a transformative vision aimed at realizing the human-centric paradigm for more efficient and effective sustainable development. In this paper, we discuss the decentralized paradigm in fostering human needs-driven smart services, in line with Maslow’s hierarchy of needs theory. Societies 5.0 is committed to optimizing the use of natural, artificial, and social resources by enhancing democratic participation and ensuring that decision-making processes are more transparent, reliable, and aligned with the needs of the populace in sustainable ways. Moreover, our discussion extends to how Society 5.0’s principles correlate with the United Nations Sustainable Development Goals (SDGs), providing a framework that supports health, education, and poverty reduction, among other targets. This approach also aligns with the Human Development Index (HDI), reinforcing the notion that technological progress in Society 5.0 does not overshadow but rather complements and enhances human values, paving a synergistic path towards sustainable development that is both advanced and fundamentally human-centric.

关键词： Cyber-Physical-Social systems Society 5.0 Human-Centric Services Socio-technical synergistic sustainable development

Development and initial experiments of an intelligent dual-arm mobile robot - Baymax-I

学校读者我要写书评

暂无评论

Development and initial experiments of an intelligent dual-a...

2021 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2021

作者： Liu, Wei Wang, Haitao Wang, Rui Wen, Dayong Lu, Tao Wang, Shuo Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China University of Chinese Academy of Sciences Beijing100049 China CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai200031 China

ISBN: (纸本)9781665436786

This paper addresses the design and control of an intelligent dual-arm mobile robot named Baymax-I. The mechanism design of Baymax-I is based on modular concepts, which is mainly composed of three parts, including main body, dual-arms and a mobile chassis. The main body is designed as human-like structure, carrying multiple sensors. UR3 manipulators are adopted as two arms. Each manipulator has six degrees of freedom. A two-finger grip pawl is mounted on the end of each manipulator. A MIR mobile chassis drives the Baymax-I motion with high maneuverability. As for software systems, the robot is designed based on hierarchical structure. The bottom driving layer is used to perform specific movements. The middle layer is responsible for processing sensor data. The top layer is algorithm execution layer. In the end, three experiments including SLAM, pressing the elevator and opening the fridge are presented to verify the feasibility and effectiveness of the proposed system design and control methods of the Baymax-I robot. © 2021 IEEE.

关键词： Mobile robots

Supramolecular systems Containing B-N Frustrated Lewis Pairs of Tris(pentafluorophenyl)borane and Triphenylamine Derivatives

学校读者我要写书评

暂无评论

Organic Materials

Organic Materials 2021年第2期3卷 174-183页

作者： Chidchob, P. Jansen, S.A.H. Meskers, S.C.J. Weyandt, E. Van Leest, N.P. De Bruin, B. Palmans, A.R.A. Vantomme, G. Meijer, E.W. Laboratory of Macromolecular and Organic Chemistry Eindhoven University of Technology P.O. Box 513 Eindhoven 5600 MB Netherlands Institute for Complex Molecular Systems (ICMS) Eindhoven University of Technology P.O. Box 513 Eindhoven 5600 MB Netherlands Homogeneous Supramolecular and Bio-Inspired Catalysis Group Van 'T Hoff Institute for Molecular Sciences University of Amsterdam Science Park 904 Amsterdam 1098 XH Netherlands

The introduction of a chemical additive to supramolecular polymers holds high potential in the development of new structures and functions. In this regard, various donor- and acceptor-based molecules have been applied in the design of these noncovalent polymers. However, the incorporation of boron nitrogen frustrated Lewis pairs in such architectures is still rare despite their many intriguing properties in catalysis and materials science. The limited choices of suitable boron derivatives represent one of the main limitations for the advancement in this direction. Here, we examine the use of the commercially available tris(pentafluorophenyl)borane with various triphenylamine derivatives to create supramolecular B-N charge transfer systems. Our results highlight the importance of a proper balance between the donor/acceptor strength and the driving force for supramolecular polymerization to achieve stable, long-range ordered B-N systems. Detailed analyses using electron paramagnetic resonance and optical spectroscopy suggest that tris(pentafluorophenyl)borane displays complex behavior with the amide-based triphenylamine supramolecular polymers and may interact in dimers or larger chiral aggregates, depending on the specific structure of the triphenylamines. © 2021. The Author(s).

关键词： charge transfer supramolecular assembly triphenylamine tris(pentafluorophenyl)borane

Bayesian Optimization Framework for Efficient Fleet Design in Autonomous Multi-Robot Exploration

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Concha, David Molina Li, Jiping Yin, Haoran Park, Kyeonghyeon Lee, Hyun-Rok Lee, Taesik Sirohi, Dhruv Lee, Chi-Guhn The Dynamic Optimization and Reinforcement Learning Laboratory The Department of Mechanical & Industrial Engineering University of Toronto TorontoONM5S3G8 Canada The Department of Electrical & Computer Engineering University of Toronto TorontoONM5S3G8 Canada The Division of Engineering Science The Faculty of Applied Science and Engineering University of Toronto TorontoONM5S3G8 Canada The Complex System Design Laboratory The Department of Industrial and Systems Engineering Korea Advanced Institute of Science and Technology Daejeon34141 Korea Republic of The Department of Industrial Engineering Inha University Incheon22212 Korea Republic of

This study addresses the challenge of fleet design optimization in the context of heterogeneous multi-robot fleets, aiming to obtain feasible designs that balance performance and costs. In the domain of autonomous multi-robot exploration, reinforcement learning agents play a central role, offering adaptability to complex terrains and facilitating collaboration among robots. However, modifying the fleet composition results in changes in the learned behavior, and training multi-robot systems using multi-agent reinforcement learning is expensive. Therefore, an exhaustive evaluation of each potential fleet design is infeasible. To tackle these hurdles, we introduce Bayesian Optimization for Fleet Design (BOFD), a framework leveraging multiobjective Bayesian Optimization to explore fleets on the Pareto front of performance and cost while accounting for uncertainty in the design space. Moreover, we establish a sub-linear bound for cumulative regret, supporting BOFD’s robustness and efficacy. Extensive benchmark experiments in synthetic and simulated environments demonstrate the superiority of our framework over state-of-the-art methods, achieving efficient fleet designs with minimal fleet evaluations. Copyright © 2024, The Authors. All rights reserved.

关键词： Multipurpose robots

Global-Supervised Contrastive Loss and View-Aware-Based Post-Processing for Vehicle Re-Identification

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hu, Zhijun Xu, Yong Wen, Jie Cheng, Xianjing Zhang, Zaijun Sun, Lilei Wang, Yaowei School of Mathematics and Statistics Guangxi Normal University Guilin541004 China College of Computer Science and Technology Guizhou University Guiyang550025 China Shenzhen Key Laboratory of Visual Object Detection and Recognition Shenzhen China College of Computer Science and Technology Guizhou University Guiyang550025 China Key Laboratory of Complex Systems and Intelligent Computing School of Mathematics and Statistics Qiannan Normal University for Nationalities Duyun558000 China Peng Cheng Laboratory Shenzhen518055 China

In this paper, we propose a Global-Supervised Contrastive loss (LGSupCon) and a view-aware-based post-processing (VABPP) method for the field of vehicle re-identification. The traditional supervised contrastive loss (LSupCon) calculates the distances of features within the batch, so it has the local attribute. While the proposed LGSupCon has new properties and has good global attributes, the positive and negative features of each anchor in the training process come from the entire training set. The proposed VABPP method is the first time that the view-aware-based method is used as a post-processing method in the field of vehicle re-identification. The advantages of VABPP are that, first, it is only used during testing and does not affect the training process. Second, as a post-processing method, it can be easily integrated into other trained re-id models. We directly apply the view-pair distance scaling coefficient matrix calculated by the model trained in this paper to another trained re-id model, and the VABPP method greatly improves its performance, which verifies the feasibility of the VABPP method. © 2022, CC BY-NC-SA.

关键词： Vehicles

Feature refinement attention U-net for enhanced liver segmentation

学校读者我要写书评

暂无评论

Engineering Applications of Artificial Intelligence 2025年 157卷

作者： Wang, Hui Liu, Desheng Zhao, Zhilei Wu, Yue Cekderi, Anil Baris State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China College of Information Science & Electronic Technology Jiamusi University Jiamusi154007 China

Developing efficient and accurate automated liver segmentation methods is of far-reaching significance for the prevention, diagnosis, treatment, and prognostic assessment of liver diseases. Artificial intelligence (AI) technology has shown immense potential in various computer vision tasks and has been increasingly adopted in medical image segmentation in recent years. However, conventional neural networks often exhibit limitations in capturing global context capture, constraining their performance in medical image segmentation. To address this challenge, we propose a Feature Refinement Attention U-Net (FRAttU-Net). The architecture is designed with two key components: a High and Low Frequency Feature Fusion and Enhancement Module (HLF3EM) between the encoder and decoder to integrate the multilevel features and enhance the high-level feature representation using edge cues, and an Otsu Density Refinement Module in the output layer to strengthen density information representation and improve the prediction accuracy. Extensive experiments demonstrate that FRAttU-Net achieves state-of-the-art accuracy, outperforming existing methods on multiple datasets. This performance advancement holds considerable potential in improving clinical decision-making in liver disease diagnosis and treatment planning. The code is available at: https://***/HUI623/FRAttU-Net. © 2025 Elsevier Ltd

关键词： Image segmentation

X-ray magnetic circular dichroism and resonant inelastic X-ray scattering explained: role of many-body correlation and mixed-valence fluctuations

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Kim, Beom Hyun Lee, Sang-Jun Huang, H. Lu, D. Hong, S.S. Lee, S. Abbamonte, P. Joe, Y.I. Szypryt, P. Doriese, W.B. Swetz, D.S. Ullom, J.N. Kao, C.-C. Lee, J.-S. Kim, Bongjae Center for Theoretical Physics of Complex Systems Institute for Basic Science Daejeon34126 Korea Republic of Stanford Synchrotron Radiation Lightsource SLAC National Accelerator Laboratory Menlo ParkCA94025 United States Department of Materials Science Institute of Optoelectronics Fudan University Shanghai200433 China Department of Materials Science and Engineering University of California DavisCA95616 United States Department of Physics and Materials Research Laboratory University of Illinois UrbanaIL61801 United States National Institute of Standards and Technology BoulderCO80305 United States SLAC National Accelerator Laboratory Menlo ParkCA94025 United States Department of Physics Kyungpook National University Daegu41566 Korea Republic of

X-ray magnetic circular dichroism (XMCD) and resonant inelastic X-ray scattering with magnetic circular dichroism (RIXS-MCD) provide unparalleled insights into the electronic and magnetic dynamics of complex materials. Yet, their spectra remain challenging to interpret due to intricate many-body interactions. Here, we introduce a theoretical framework based on the Anderson impurity model, fully incorporating charge transfer (CT) and core-valence exchange correlation (CVEC) effects. Using epitaxial ferromagnetic La0.7Sr0.3MnO3 film as a model system, we capture elusive spectral features, demonstrating the necessity of CT inclusion for resolving XMCD subpeaks and revealing the profound impact of CVEC on RIXS-MCD spectra. Our approach not only successfully mirrors experimental results but also opens new avenues for exploring spin, orbital, and charge excitations in 3d transition metals and other correlated materials. © 2024, CC BY.

关键词： X ray scattering

Streaming Algorithms for the k-Submodular Cover Problem

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Wenqi Gutin, Gregory Mao, Yaping Du, Donglei Zhang, Xiaoyan School of Mathematical Science Institute of Mathematics Nanjing Normal University Key Laboratory of Ministry of Education Numerical Simulation of Large Scale Complex Systems Nanjing210023 China Royal Holloway University of London Egham SurreyTW20 0EX United Kingdom School of Mathematics and Statistics Academy of Plateau Science and Sustainability Qinghai Normal University Qinghai Xining810008 China Faculty of Management University of New Brunswick FrederictonNBE3B9Y2 Canada

Given a natural number k ≥ 2, we consider the k-submodular cover problem (k-SC). The objective is to find a minimum cost subset of a ground set X subject to the value of a k-submodular utility function being at least a certain predetermined value τ. For this problem, we design a bicriteria algorithm with a cost at most O(1/ǫ) times the optimal value, while the utility is at least (1 − ǫ)τ/r, where r depends on the monotonicity of g. © 2023, CC BY.

关键词： Approximation algorithms