检索结果-内蒙古大学图书馆

A multicenter single-arm objective performance criteria trial evaluating the efficacy and safety of a dedicated venous sinus thrombectomy device for severe cerebral venous sinus thrombosis

引用

Neuroprotection 2024年第4期2卷 318-328页

作者： Shadamu Yusuying Yan Wu Ming Li Jiangang Duan Jian Chen Yujiao Chen Chen Zhou Hetao Bian Chuanhui Li Chuanjie Wu Ran Meng Xunming Ji Department of Neurosurgery Xuanwu HospitalCapital Medical UniversityBeijingChina Department of China-America Institute of Neuroscience Xuanwu HospitalCapital Medical UniversityBeijingChina Emergency Department Xuanwu HospitalCapital Medical UniversityBeijingChina Department of Blood Transfusion Beijing Jishuitan HospitalBeijingChina Laboratory of Brain Disorders Ministry of Science and TechnologyCollaborative Innovation Center for Brain DisordersBeijing Institute of Brain DisordersBeijing Advanced Innovation Center for Big Data-based Precision MedicineCapital Medical UniversityBeijingChina Department of Neurology Stroke CenterXuanwu HospitalCapital Medical UniversityBeijingChina Department of Neurology Xuanwu HospitalCapital Medical UniversityBeijingChina

Aim:Approximately 21%of patients with cerebral venous sinus thrombosis(CVST)are refractory to anticoagulation treatment and face poor *** patients may benefit from endovascular *** numerous studies have reported promising results with endovascular therapy,it remains challenging to obtain convincing evidence of its efficacy and safety due to the unique challenges posed by CVST,such as larger vessel diameters,distinct pathophysiology,and substantial clot ***,dedicated endovascular therapy tools should be developed specifically for *** study aimed to evaluate the efficacy and safety of a dedicated venous sinus thrombectomy device in patients with acute or subacute ***:This prospective,multicenter,single-arm trial utilized an objective performance criterion *** patients received treatment with a dedicated venous sinus thrombectomy device to recanalize occluded sinuses or *** primary objective was to compare the immediate postoperative recanalization rate with a preset target value to determine whether the device met the clinical application *** trial plans to enroll 146 patients from 11 tertiary medical centers in ***:This trial is expected to fill a critical gap in endovascular treatments for CVST and support the development of reliable,dedicated thrombectomy devices for future studies.

关键词： anticoagulation cerebral venous sinus thrombosis endovascular treatment thrombectomy devices trial

来源：评论

学校读者我要写书评

暂无评论

Real-time bottleneck matching in spatial crowdsourcing

引用

Science China(Information Sciences) 2021年第8期64卷 233-234页

作者： Long LI Lingling WANG Weifeng LV State Key Laboratory of Software Development Environment (SKLSDE Lab) and Beijing Advanced Innovation Center for Big Data and Brain Computing (BDBC) Beihang University School of Management and Economics Beijing Institute of Technology

Dear editor,Spatial crowdsourcing(SC) services(e.g., Uber, DiDi, and Meituan) have become popular with smart-phone ***, the online matching problems in real-time spatial data are a key issue in SC [1–4]. Unlike the current one-sided online matching study in real-time spatial data [5], which focuses on minimizing the overall cost of the matching,

关键词： Real-time bottleneck matching in spatial crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Coupled Alternating Neural Networks for Solving Multi-Population High-Dimensional Mean-Field Games with Stochasticity

TechRxiv

引用

TechRxiv 2022年

作者： Wang, Guofang Yao, Wang Zhang, Xiao Niu, Zijia The School of Mathematical Sciences Beihang University Beijing100191 China Key Laboratory of Mathematics Informatics and Behavioral Semantics Ministry of Education Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Peng Cheng Laboratory Guangdong Shenzhen518055 China The Institute of Artificial Intelligence Beihang University Beijing100191 China Key Laboratory of Mathematics Informatics and Behavioral Semantics Ministry of Education Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

Multi-population mean-field game is a critical subclass of mean-field games (MFGs). It is a theoretically feasible multi-agent model for simulating and analyzing the game between multiple heterogeneous populations of interacting massive agents. Due to the factors of game complexity, dimensionality disaster and disturbances should be taken into account simultaneously, how to solve the multi-population high-dimensional stochastic MFG problem is faced with great challenges. We present CA-Net, a coupled alternating neural network approach for tractably solving multi-population high-dimensional MFGs in the stochastic case. First, we provide a universal modeling framework for large-scale heterogeneous multi-agent game systems, which is strictly expressed as a multi-population MFG problem. Next, we generalize the potential variational primal-dual structure that MFGs exhibit, then phrase the multi-population MFG problem as a convex-concave saddle-point problem. Last but not least, we design a generative adversarial network (GAN) with multiple generators and multiple discriminators—the solving network, which parameterizes the value functions and the density functions of multiple populations by two sets of neural networks, respectively. Moreover, numerical experiments demonstrate the feasibility and effectiveness of our approach. © 2022, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

I4R: Promoting deep reinforcement learning by the indicator for expressive representations 29

I4R: Promoting deep reinforcement learning by the indicator ...

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Luo, Xufang Meng, Qi He, Di Chen, Wei Wang, Yunhong Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Microsoft Research Beijing China School of EECS Peking University China

ISBN: (纸本)9780999241165

Learning expressive representations is always crucial for well-performed policies in deep reinforcement learning (DRL). Different from supervised learning, in DRL, accurate targets are not always available, and some inputs with different actions only have tiny differences, which stimulates the demand for learning expressive representations. In this paper, firstly, we empirically compare the representations of DRL models with different performances. We observe that the representations of a better state extractor (SE) are more scattered than a worse one when they are visualized. Thus, we investigate the singular values of representation matrix, and find that, better SEs always correspond to smaller differences among these singular values. Next, based on such observations, we define an indicator of the representations for DRL model, which is the Number of Significant Singular Values (NSSV) of a representation matrix. Then, we propose I4R algorithm, to improve DRL algorithms by adding the corresponding regularization term to enhance the NSSV. Finally, we apply I4R to both policy gradient and value based algorithms on Atari games, and the results show the superiority of our proposed method.1,. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Driving Behavior Model for Multi-Vehicle Interaction at Uncontrolled Intersections Based on Risk Field Considering Drivers' Visual Field Characteristics

SSRN

引用

SSRN 2022年

作者： Wang, Zhaojie Lu, Guangquan Tan, Haitian Beijing Key Laboratory for Cooperative Vehicle Infrastructure System and Safety Control Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Beihang University Beijing100191 China

At uncontrolled intersections, drivers face a more complex traffic environment. The interactions between vehicles forces drivers to make complex decisions to avoid vehicle collisions. In most existing studies on modeling driving behavior at uncontrolled intersections, multi-vehicle interaction scenarios are often categorized as moving-across scenario and merging scenario. Separate driving behavior models are constructed for each scenario. Few studies have been conducted to model drivers' driving behaviors at uncontrolled intersections uniformly. In this study, based on risk homeostasis theory (RHT) and preview-follower theory (PFT), a risk-field based driving behavior model is constructed to simulate multi-vehicle interactions at uncontrolled intersections. Taking into account the driver's visual field characteristics, this model uses risk field theory to quantify the risk vehicle endured during preview time and find the trajectory that conform to the driver's behavior while satisfying the risk threshold constraint. An exploratory algorithm was contained in this model to solve intersection deadlock scenarios. By adjusting the acceptable risk level, vehicles can restart the traffic flow by finding a suitable acceleration from feasible action space. The model is able to uniformly describe the driving behavior of drivers within uncontrolled intersections, including merging behavior and moving-across behavior. The simulation results show that the model can accurately reproduce the priority and trajectory of vehicles crossing the intersection and resolve multi-vehicle conflicts within a reasonable time. The application of our model to improve the traffic efficiency in mixed traffic environments with automated and manual vehicles is also discussed. The model can be used for traffic simulation at uncontrolled intersections and to provide test validation for automated driving systems. © 2022, The Authors. All rights reserved.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Event detection and evolution in multi-lingual social streams

引用

Frontiers of Computer Science 2020年第5期14卷 213-227页

作者： Yaopeng Liu Hao Peng Jianxin Li Yangqiu Song Xiong Li Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang UniversityBeijing100083China State Key Laboratory of Software Development Environment Beihang UniversityBeijing100083China Department of Computer Science and Engineering HKUSTHong Kong99907China National Computer Network Emergency Response Technical Team/Coordination Center of China Beijing100029China

Real-life events are emerging and evolving in social and news *** methods have succeeded in capturing designed features of monolingual events,but lack of interpretability and multi-lingual *** this end,we propose a multi-lingual event mining model,namely MLEM,to automatically detect events and generate evolution graph in multilingual hybrid-length text streams including English,Chinese,French,German,Russian and ***,we merge the same entities and similar phrases and present multiple similarity measures by incremental word2vec *** propose an 8-tuple to describe event for correlation analysis and evolution graph *** evaluate the MLEM model using a massive human-generated dataset containing real world *** results show that our new model MLEM outperforms the baseline method both in efficiency and effectiveness.

关键词： event detection event evolution stream processing multi-lingual anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Self-organization Preserved Graph Structure Learning with Principle of Relevant Information

arXiv

引用

arXiv 2022年

作者： Sun, Qingyun Li, Jianxin Yang, Beining Fu, Xingcheng Peng, Hao Yu, Philip S. Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China School of Computer Science and Engineering Beihang University Beijing100191 China Department of Computer Science University of Illinois at Chicago Chicago United States

Most Graph Neural Networks follow the message-passing paradigm, assuming the observed structure depicts the ground-truth node relationships. However, this fundamental assumption cannot always be satisfied, as real-world graphs are always incomplete, noisy, or redundant. How to reveal the inherent graph structure in a unified way remains under-explored. We proposed PRI-GSL, a Graph Structure Learning framework guided by the Principle of Relevant Information, providing a simple and unified framework for identifying the self-organization and revealing the hidden structure. PRI-GSL learns a structure that contains the most relevant yet least redundant information quantified by von Neumann entropy and Quantum Jensen-Shannon divergence. PRI-GSL incorporates the evolution of quantum continuous walk with graph wavelets to encode node structural roles, showing in which way the nodes interplay and self-organize with the graph structure. Extensive experiments demonstrate the superior effectiveness and robustness of PRI-GSL. Copyright © 2022, The Authors. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

On the Chordality of Simple Decomposition in Top-Down Style 8th

On the Chordality of Simple Decomposition in Top-Down Style

引用

8th International Conference on Mathematical Aspects of Computer and Information Sciences, MACIS 2019

作者： Mou, Chenqi Lai, Jiahua LMIB–School of Mathematical Sciences Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

ISBN: (纸本)9783030431198

Simple decomposition of polynomial sets computes conditionally squarefree triangular sets or systems with certain zero or ideal relationships with the polynomial sets. In this paper we study the chordality of polynomial sets occurring in the process of simple decomposition in top-down style. We first reformulate Wang’s algorithm for simple decomposition in top-down style so that the decomposition process can be described in an inductive way. Then we prove that for a polynomial set whose associated graph is chordal, all the polynomial sets in the process of Wang’s algorithm for computing simple decomposition of this polynomial set have associated graphs which are subgraphs of the input chordal graph. © 2020, Springer Nature Switzerland AG.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

Quantum Graph Convolutional Neural Networks

Quantum Graph Convolutional Neural Networks

引用

第40届中国控制会议

作者： Jin Zheng Qing Gao Yanxuan Lü School of Automation Science and Electrical Engineering Beihang University Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University

At present, there are a large number of quantum neural network models to deal with Euclidean spatial data, while little research have been conducted on non-Euclidean spatial data. In this paper, we propose a novel quantum graph convolutional neural network（QGCN） model based on quantum parametric circuits and utilize the computing power of quantum systems to accomplish graph classification tasks in traditional machine learning. The proposed QGCN model has a similar architecture as the classical graph convolutional neural networks, which can illustrate the topology of the graph type data and efficiently learn the hidden layer representation of node features as well. Numerical simulation results on a graph dataset demonstrate that the proposed model can be effectively trained and has good performance in graph level classification tasks.

关键词： Quantum machine learning Quantum computing Quantum graph convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

CLDG: Contrastive Learning on Dynamic Graphs

CLDG: Contrastive Learning on Dynamic Graphs

引用

International Conference on data Engineering

作者： Yiming Xu Bin Shi Teng Ma Bo Dong Haoyi Zhou Qinghua Zheng Department of Computer Science and Technology Xi’an Jiaotong University China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University China Department of Distance Education Xi’an Jiaotong University China School of Software Beihang University China Advanced Innovation Center for Big Data and Brain Computing Beihang University China

The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It constructs self-supervised signals by maximizing the mutual information between the statistic graph’s augmentation views. However, the semantics and labels may change within the augmentation process, causing a significant performance drop in downstream tasks. This drawback becomes greatly magnified on dynamic graphs. To address this problem, we designed a simple yet effective framework named CLDG. Firstly, we elaborate that dynamic graphs have temporal translation invariance at different levels. Then, we proposed a sampling layer to extract the temporally-persistent signals. It will encourage the node to maintain consistent local and global representations, i.e., temporal translation invariance under the timespan views. The extensive experiments demonstrate the effectiveness and efficiency of the method on seven datasets by outperforming eight unsupervised state-of-the-art baselines and showing competitiveness against four semi-supervised methods. Compared with the existing dynamic graph method, the number of model parameters and training time is reduced by an average of 2,001.86 times and 130.31 times on seven datasets, respectively. The code and data are available at: https://***/yimingxu24/CLDG.

关键词：

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：