检索结果-内蒙古大学图书馆

23rd COTA International Conference of Transportation Professionals: Emerging data-Driven Sustainable Technological Innovation in Transportation, CICTP 2023

作者： Wu, Pingping Lu, Guangquan Liu, Miaomiao Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control School of Transportation Science and Engineering Beihang Univ. Beijing China Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control School of Transportation Science and Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang Univ. Beijing China Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies Southeast Univ. Nanjing China

ISBN: (数字)9780784485040

ISBN: (纸本)9780784485040

With the development of information and sensing technologies, a wide variety of intersection traffic data is available. The purpose of this paper is to make full use of video and commercial vehicle trajectory data to deeply explore the intersection safety status. In this paper, based on different sample sizes, different sampling frequencies, and different accuracies of data, the safety analysis of intersections is carried out from micro and macro aspects based on post-encroachment time (PET) and vehicle deceleration behavior, respectively. On the one hand, we use the full-sample and high-precision trajectory data extracted from video to analyze the safety of each region of intersection based on PET. On the other hand, using the trajectory data with low penetration rate and low sampling frequency extracted from the positioning data of the online car-hailing, a distribution fit, and non-parametric test are conducted for the vehicle deceleration behavior, and then the overall safety state of the intersection is evaluated. The results can provide ideas for the identification of intersection risk points and the application of different kinds of data on intersection safety evaluation. © ASCE.

关键词： Commercial vehicles

来源：评论

学校读者我要写书评

暂无评论

Physics-inspired Machine Learning for Quantum Error Mitigation

arXiv

引用

arXiv 2025年

作者： Xu, Xiao-Yue Xue, Xin Chen, Tianyu Ding, Chen Li, Tian Zhou, Haoyi Huang, He-Liang Bao, Wan-Su Henan Key Laboratory of Quantum Information and Cryptography Zhengzhou Henan450000 China Department of Computer Science Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing100191 China Department of Software Beihang University Beijing100191 China

Noise is a major obstacle in current quantum computing, and Machine Learning for Quantum Error Mitigation (ML-QEM) promises to address this challenge, enhancing computational accuracy while reducing the sampling overheads of standard QEM methods. Yet, existing models lack physical interpretability and rely heavily on extensive datasets, hindering their scalability in large-scale quantum circuits. To tackle these issues, we introduce the Neural Noise Accumulation Surrogate (NNAS), a physics-inspired neural network for ML-QEM that incorporates the structural characteristics of quantum noise accumulation within multi-layer circuits, endowing the model with physical interpretability. Experimental results demonstrate that NNAS outperforms current methods across a spectrum of metrics, including error mitigation capability, quantum resource consumption, and training dataset size. Notably, for deeper circuits where QEM methods typically struggle, NNAS achieves a remarkable reduction of over half in errors. NNAS also demands substantially fewer training data, reducing dataset reliance by at least an order of magnitude, due to its ability to rapidly capture noise accumulation patterns across circuit layers. This work pioneers the integration of quantum process-derived structural characteristics into neural network architectures, broadly enhancing QEM's performance and applicability, and establishes an integrative paradigm that extends to various quantum-inspired neural network architectures. © 2025, CC BY.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

AutoST: towards the universal modeling of spatio-temporal sequences 22

AutoST: towards the universal modeling of spatio-temporal se...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Jianxin Li Shuai Zhang Hui Xiong Haoyi Zhou Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Hong Kong University of Science and Technology (Guangzhou) Guangzhou HKUST Fok Ying Tung Research Institute Guangzhou China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China

ISBN: (纸本)9781713871088

The analysis of spatio-temporal sequences plays an important role in many real-world applications, demanding a high model capacity to capture the interdependence among spatial and temporal dimensions. Previous studies provided separated network design in three categories: spatial first, temporal first, and spatio-temporal synchronous. However, the manually-designed heterogeneous models can hardly meet the spatio-temporal dependency capturing priority for various tasks. To address this, we proposed a universal modeling framework with three distinctive characteristics: (i) Attention-based network backbone, including S2T Layer (spatial first), T2S Layer (temporal first), and STS Layer (spatio-temporal synchronous). (ii) The universal modeling framework, named UniST, with a unified architecture that enables flexible modeling priorities with the proposed three different modules. (iii) An automatic search strategy, named AutoST, automatically searches the optimal spatio-temporal modeling priority by network architecture search. Extensive experiments on five real-world datasets demonstrate that UniST with any single type of our three proposed modules can achieve state-of-the-art performance. Furthermore, AutoST can achieve overwhelming performance with UniST.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Triplet-Aware Graph Neural Networks for Factorized Multi-Modal Knowledge Graph Entity Alignment

SSRN

引用

SSRN 2023年

作者： Li, Qian Li, Jianxin Wu, Jia Peng, Xutan Ji, Cheng Peng, Hao Wang, Lihong Yu, Philip S. Beijing Advanced Innovation Center for Big Data and Brain Computing China Beijing China School of Computing Macquarie University Sydney Australia The University of Sheffield South Yorkshire United Kingdom China University of Illinois Chicago Chicago United States

Multi-Modal Entity Alignment (MMEA), aiming to discover matching entity pairs on two multi-modal knowledge graphs (MMKGs), is an essential task in knowledge graph fusion. Through mining feature information of MMKGs, entities are aligned to tackle the issue that an MMKG is incapable of effective integration. The recent attempt at neighbors and attribute fusion mainly focuses on aggregating multi-modal attributes, neglecting the structure effect with multi-modal attributes for entity alignment. This paper proposes an innovative approach, namely TriFac, to exploit embedding refinement for factorizing the original multi-modal knowledge graphs through a two-stage MMKG factorization. Notably, we propose triplet-aware graph neural networks to aggregate multi-relational features. We propose multi-modal fusion for aggregating multiple features and design three novel metrics to measure knowledge graph factorization performance on the unified factorized latent space. Empirical results indicate the effectiveness of TriFac, surpassing previous state-of-the-art models on two MMEA datasets and a power system dataset. © 2023, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning with Collaborative Aggregation Networks for Multi-Site brain Disorder Diagnosis

Personalized Federated Learning with Collaborative Aggregati...

引用

Industrial Automation, Robotics and Control Engineering (IARCE), International Conference on

作者： Qian Si Yang Li School of Cyber Science and Technology Beihang University Beijing China Department of Automation Science and Electrical Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing State Key Laboratory of Virtual Reality Technology and Systems Advanced Institute of Information Technology Peking University Beihang University Beijing China

ISBN: (数字)9798350380323

ISBN: (纸本)9798350380330

In multi-site brain disease diagnosis studies, traditional centralized training methods necessitate sharing medical data, posing significant privacy risks. Federated learning (FL) offers a privacy-preserving solution by enabling global model training through aggregating locally trained models from multiple data centers without sharing raw data. However, current FL approaches rely on a server-based network topology, where central server failure disrupts training. Additionally, data heterogeneity across sites often slows convergence and reduces accuracy. To overcome these issues, we introduce a decentralized personalized federated learning collaborative aggregation network (pFedCAN). This framework has two core components: (1) separating local models into shared and personalized layers, and (2) forming a collaborative aggregation network via similarity detection in the shared layers. Specifically, each center trains its local model, then separates it into shared and personalized layers. The shared layer is exchanged with other centers, while the personalized layer remains local. data centers analyze similarities in received shared layers to build a collaborative network, where shared layers from similar centers are aggregated to refine the model. This approach flexibly adapts to varying levels of data heterogeneity, enhancing model training efficiency. Validation on public datasets, ABIDE I and ADHD, shows that the proposed method outperforms current leading techniques.

关键词： Training Adaptation models data centers Federated learning Service robots Collaboration brain modeling data models Servers Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Machine-learning-assisted intelligent synthesis of UiO-66(Ce):Balancing the trade-off between structural defects and thermal stability for e hydrogenation of Dicyclopentadiene

引用

Materials Genome Engineering Advances 2024年第3期2卷 96-106页

作者： Jing Lin Tao Ban Tian Li Ye Sun Shenglan Zhou Rushuo Li Yanjing Su Jitti Kasemchainan Hongyi Gao Lei Shi Ge Wang Beijing Key Laboratory of Function Materials for Molecule&Structure Construction Beijing Advanced Innovation Center for Materials Genome EngineeringSchool of Materials Science and EngineeringUniversity of Science and Technology BeijingBeijingChina Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and EngineeringBeihang UniversityBeijingChina Beijing Advanced Innovation Center for Materials Genome Engineering Institute for Advanced Materials and TechnologySchool of Materials Science and EngineeringUniversity of Science and Technology BeijingBeijingChina Department of Chemical Technology Chulalongkorn UniversityBangkokThailand

Metal-organic frameworks(MOFs),renowned for structural diversity and design flexibility,exhibit potential in ***,the pursuit of higher catalytic activity through defects often compromises stability,requiring a delicate *** trial-and-error method for optimizing synthesis parameters within the complex chemical space is ***,taking the typical MOF UiO-66(Ce)as an illustrative example,a closed loop workflow is built,which integrates ma-chine learning(ML)-assissted prediction,multi-objective optimization(MOO)and experimental preparation to synergistically optimize the defect content and thermal stability of UiO-66(Ce)for efficient hydrogenation of dicyclopentadiene(DCPD).An automatic data extraction program ensures data accuracy,establishing a high-quality *** is employed to explore the intricate synthesis-structure-property correlations,enabling precise delineation of pure-phase subspace and accurate predictions of *** two iterations,MOO model identifies optimal protocols for high defect content(>40%)and thermal stability(>300℃).The optimized UiO-66(Ce)exhibits superior catalytic performance in hydroge-nation of DCPD,validating the precision and reliability of our *** ML-assisted approach offers a valuable paradigm for solving the trade-off riddle in materials field.

关键词： defect content machine learning metal-organic frameworks multi-objective optimization thermal stability

来源：评论

学校读者我要写书评

暂无评论

Motion Forecasting for Autonomous Vehicles: A Survey

arXiv

引用

arXiv 2025年

作者： Shi, Jianxin Chen, Jinhao Wang, Yuandong Sun, Li Liu, Chunyang Xiong, Wei Wo, Tianyu Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Information Engineering College Capital Normal University Beijing100048 China School of Control and Computer Engineering North China Electric Power University Beijing102206 China Didi Chuxing Beijing100094 China

In recent years, the field of autonomous driving has attracted increasingly significant public interest. Accurately forecasting the future behavior of various traffic participants is essential for the decision-making of Autonomous Vehicles (AVs). In this paper, we focus on both scenario-based and perception-based motion forecasting for AVs. We propose a formal problem formulation for motion forecasting and summarize the main challenges confronting this area of research. We also detail representative datasets and evaluation metrics pertinent to this field. Furthermore, this study classifies recent research into two main categories: supervised learning and self-supervised learning, reflecting the evolving paradigms in both scenario-based and perception-based motion forecasting. In the context of supervised learning, we thoroughly examine and analyze each key element of the methodology. For self-supervised learning, we summarize commonly adopted techniques. The paper concludes and discusses potential research directions, aiming to propel progress in this vital area of AV technology. © 2025, CC BY.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Find truth in the hands of the few:acquiring specific knowledge with crowdsourcing

引用

Frontiers of Computer Science 2021年第4期15卷 5-16页

作者： Tao HAN Hailong SUN Yangqiu SONG Yili FANG Xudong LIU SKLSDE Lab School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang UniversityBeijing 100191China Department of Computer Science and Engineering Hong Kong University of Science and TechnologyClearwater BayHong Kong 999077China School of Computer and Information Engineering Zhejiang Gongshang UniversityHangzhou 310018China

Crowdsourcing has been a helpful mechanism to leverage human intelligence to acquire useful ***,when we aggregate the crowd knowledge based on the currently developed voting algorithms,it often results in common knowledge that may not be *** this paper,we consider the problem of collecting specific knowledge via *** the help of using external knowledge base such as WordNet,we incorporate the semantic relations between the alternative answers into a probabilisticmodel to determine which answer is more *** formulate the probabilistic model considering both worker’s ability and task’s difficulty from the basic assumption,and solve it by the expectation-maximization(EM)*** increase algorithm compatibility,we also refine our method into semi-supervised *** results show that our approach is robust with hyper-parameters and achieves better improvement thanmajority voting and other algorithms when more specific answers are expected,especially for sparse data.

关键词： crowdsourcing knowledge acquisition EM algorithm label aggregation

来源：评论

学校读者我要写书评

暂无评论

Domain-Invariant Feature Progressive Distillation with Adversarial Adaptive Augmentation for Low-Resource Cross-Domain NER

Domain-Invariant Feature Progressive Distillation with Adver...

引用

作者： Zhang, Tao Xia, Congying Liu, Zhiwei Zhao, Shu Peng, Hao Yu, Philip Department of Computer Science University of Illinois at Chicago 851 South Morgan Street ChicagoIL60607-7053 United States School of Computer Science and Technology Anhui University No. 111 Jiulong Road Hefei Anhui230601 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University No. 37 Xue Yuan Road Haidian District Beijing100191 China

Considering the expensive annotation in Named Entity Recognition (NER), Cross-domain NER enables NER in low-resource target domains with few or without labeled data, by transferring the knowledge of high-resource domains. However, the discrepancy between different domains causes the domain shift problem and hampers the performance of cross-domain NER in low-resource scenarios. In this article, we first propose an adversarial adaptive augmentation, where we integrate the adversarial strategy into a multi-task learner to augment and qualify domain adaptive data. We extract domain-invariant features of the adaptive data to bridge the cross-domain gap and alleviate the label-sparsity problem simultaneously. Therefore, another important component in this article is the progressive domain-invariant feature distillation framework. A multi-grained MMD (Maximum Mean Discrepancy) approach in the framework to extract the multi-level domain invariant features and enable knowledge transfer across domains through the adversarial adaptive data. advanced Knowledge Distillation (KD) schema processes progressively domain adaptation through the powerful pre-trained language models and multi-level domain invariant features. Extensive comparative experiments over four English and two Chinese benchmarks show the importance of adversarial augmentation and effective adaptation from high-resource domains to low-resource target domains. Comparison with two vanilla and four latest baselines indicates the state-of-the-art performance and superiority confronted with both zero-resource and minimal-resource scenarios. © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Knowledge Graph Transformer Framework for Multi-Modal Entity Alignment

arXiv

引用

arXiv 2023年

作者： Li, Qian Ji, Cheng Guo, Shu Liang, Zhaoji Wang, Lihong Li, Jianxin School of Computer Science and Engineering Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing China National Computer Network Emergency Response Technical Team Coordination Center of China China

Multi-Modal Entity Alignment (MMEA) is a critical task that aims to identify equivalent entity pairs across multi-modal knowledge graphs (MMKGs). However, this task faces challenges due to the presence of different types of information, including neighboring entities, multimodal attributes, and entity types. Directly incorporating the above information (e.g., concatenation or attention) can lead to an unaligned information space. To address these challenges, we propose a novel MMEA transformer, called MoAlign, that hierarchically introduces neighbor features, multi-modal attributes, and entity types to enhance the alignment task. Taking advantage of the transformer's ability to better integrate multiple information, we design a hierarchical modifiable self-attention block in a transformer encoder to preserve the unique semantics of different information. Furthermore, we design two entity-type prefix injection methods to integrate entity-type information using type prefixes, which help to restrict the global information of entities not present in the MMKGs. Our extensive experiments on benchmark datasets demonstrate that our approach outperforms strong competitors and achieves excellent entity alignment performance. Copyright © 2023, The Authors. All rights reserved.

关键词： Knowledge graph

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：