检索结果-内蒙古大学图书馆

Attention-Based Interaction Trajectory Prediction 9th

Attention-Based Interaction Trajectory Prediction

9th International Conference on Artificial Intelligence and Mobile Services, AIMS 2020, held as part of the Services Conference Federation, SCF 2020

作者： Liu, Zhe Zhang, Lizong Rao, Zhihong Liu, Guisong School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China China Electronic Technology Cyber Security Co. Ltd. Chengdu610000 China Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Chengdu611731 China School of Computer Science Zhongshan Institute University of Electronic Science and Technology of China Zhongshan528402 China

ISBN: (纸本)9783030596040

Trajectory prediction is a hot topic in the field of computer vision and has a wide range of applications. Trajectory prediction refers to predicting the future trajectory of a target based on its past trajectory. This paper proposes a method based on graph neural network and attention mechanism, in order to update trajectory characteristics by implement global pedestrian interaction. And, a direct relationship between history and future is introduced with the attention module for reducing error propagation. The method was evaluated on several real-world crowd datasets, the results demonstrate the effectiveness of our method. © 2020, Springer Nature Switzerland AG.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Correction to: Magnetic Particle Imaging-Guided Hyperthermia for Precise Treatment of Cancer: Review, Challenges, and Prospects

引用

Molecular imaging and biology 2023年第6期25卷 1151页

作者： Siao Lei Jie He Pengli Gao Yueqi Wang Hui Hui Yu An Jie Tian School of Engineering Medicine & School of Biological Science and Medical Engineering Beihang University Beijing 100191 China. Key Laboratory of Big Data-Based Precision Medicine (Beihang University) Ministry of Industry and Information Technology of the People's Republic of China Beijing 100191 People's Republic of China. CAS Key Laboratory of Molecular Imaging Institute of Automation Beijing 100190 China. School of Engineering Medicine & School of Biological Science and Medical Engineering Beihang University Beijing 100191 China. yuan1989@***. Key Laboratory of Big Data-Based Precision Medicine (Beihang University) Ministry of Industry and Information Technology of the People's Republic of China Beijing 100191 People's Republic of China. yuan1989@***. CAS Key Laboratory of Molecular Imaging Institute of Automation Beijing 100190 China. yuan1989@***. School of Engineering Medicine & School of Biological Science and Medical Engineering Beihang University Beijing 100191 China. tian@***. Key Laboratory of Big Data-Based Precision Medicine (Beihang University) Ministry of Industry and Information Technology of the People's Republic of China Beijing 100191 People's Republic of China. tian@***. CAS Key Laboratory of Molecular Imaging Institute of Automation Beijing 100190 China. tian@***. Zhuhai Precision Medical Center Zhuhai People's Hospital Affiliated With Jinan University Zhuhai 519000 China. tian@***.

来源：评论

学校读者我要写书评

暂无评论

A Novel High Performance Nanogenerator - Field Electrification Nanogenerator

SSRN

引用

SSRN 2023年

作者： Yin, Wuliang Chen, Liming Song, Xiuju Hu, Kui Xie, Yuedong Lu, Mingyang Yu, Zidong Guang, Haoze Luo, Jikui Li, Ruohao Soutis, Constantinos Liu, Xuqing Department of Electrical and Electronic Engineering The University of Manchester Sackville Street Building ManchesterM13 9PL United Kingdom Department of Chemistry The University of Manchester Sackville Street Building ManchesterM13 9PL United Kingdom Department of Materials The University of Manchester Sackville Street Building ManchesterM13 9PL United Kingdom School of Instrumentation and Optoelectronic Engineering Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data-based Precision Medicine Beihang University Beijing100191 China School of Engineering University of Bolton BoltonBL3 5AB United Kingdom Key Laboratory of Micro-nano Electronic Devices a Smart Systems of Zhejiang Province College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China School of Science Technology Engineering and Mathematics University of Washington BothellWA98011 United States

关键词： Nanogenerators

来源：评论

学校读者我要写书评

暂无评论

Minute-cadence Observations of the LAMOST Fields with the TMTS: III. Statistic Study of the Flare Stars from the First Two Years

arXiv

引用

arXiv 2023年

作者： Liu, Qichun Lin, Jie Wang, Xiaofeng Gu, Shenghong Shi, Jianrong Zhang, Liyun Xi, Gaobo Mo, Jun Cai, Yongzhi Chen, Liyang Chen, Zhihao Guo, Fangzhou Jiang, Xiaojun Li, Gaici Li, Wenxiong Lin, Han Lin, Weili Liu, Jialian Miao, Cheng Ma, Xiaoran Peng, Haowei Xiang, Danfeng Yan, Shengyu Zhang, Jicheng Zhang, Xinhan Physics Department Tsinghua Center for Astrophysics Tsinghua University Beijing100084 China Beijing Planetarium Beijing Academy of Science and Technology Beijing100044 China Yunnan Observatories Chinese Academy of Sciences Kunming650216 China Key Laboratory for the Structure and Evolution of Celestial Objects Chinese Academy of Sciences Kunming650216 China CAS Key Laboratory of Optical Astronomy National Astronomical Observatories Chinese Academy of Sciences Beijing100101 China School of Astronomy and Space Science University of Chinese Academy of Sciences Beijing100049 China College of Physics College of Big Data and Information Engineering Guizhou University Guiyang550025 China Center for Astronomical Mega-Science Chinese Academy of Sciences 20A Datun Road Chaoyang District Beijing100012 China The School of Physics and Astronomy Tel Aviv University Tel Aviv69978 Israel Department of Astronomy Beijing Normal University Beijing100875 China

Tsinghua University-Ma Huateng Telescopes for Survey (TMTS) aims to detect fast-evolving transients in the Universe, which has led to the discovery of thousands of short-period variables and eclipsing binaries since 2020. In this paper, we present the observed properties of 125 flare stars identified by TMTS within the first two years, with an attempt to constrain their eruption physics. As expected, most of these flares were recorded in late-type red stars with GBP − GRP > 2.0 mag;however, the flares associated with bluer stars tend to be on average more energetic and have broader profiles. The peak flux (Fpeak) of the flare is found to depend strongly on the equivalent duration (ED) of the energy release, i.e., Fpeak ∝ ED0.72±0.04, which is consistent with results derived from the Kepler and Evryscope samples. This relation is likely related to the magnetic loop emission, while, for the more popular non-thermal electron heating model, a specific time evolution may be required to generate this relation. We notice that flares produced by hotter stars have a flatter Fpeak ∝ ED relation compared to that from cooler stars. This is related to the statistical discrepancy in light-curve shape of flare events with different colors. In spectra from LAMOST, we find that flare stars have apparently stronger Hα emission than inactive stars, especially at the low temperature end, suggesting that chromospheric activity plays an important role in producing flares. On the other hand, the subclass with frequent flares is found to show Hα emission of similar strength in its spectra to that recorded with only a single flare but similar effective temperature, implying that the chromospheric activity may not be the only trigger for eruptions. Copyright © 2023, The Authors. All rights reserved.

关键词： Stars

来源：评论

学校读者我要写书评

暂无评论

Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation

Cross-domain Object Detection through Coarse-to-Fine Feature...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yangtao Zheng Di Huang Songtao Liu Yunhong Wang Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University State Key Laboratory of Software Development Environment Beihang University School of Computer Science and Engineering Beihang University Beijing China

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Recent years have witnessed great progress in deep learning based object detection. However, due to the domain shift problem, applying off-the-shelf detectors to an unseen domain leads to significant performance drop. To address such an issue, this paper proposes a novel coarse-to-fine feature adaptation approach to cross-domain object detection. At the coarse-grained stage, different from the rough image-level or instance-level feature alignment used in the literature, foreground regions are extracted by adopting the attention mechanism, and aligned according to their marginal distributions via multi-layer adversarial learning in the common feature space. At the fine-grained stage, we conduct conditional distribution alignment of foregrounds by minimizing the distance of global prototypes with the same category but from different domains. Thanks to this coarse-to-fine feature adaptation, domain knowledge in foreground regions can be effectively transferred. Extensive experiments are carried out in various cross-domain detection scenarios. The results are state-of-the-art, which demonstrate the broad applicability and effectiveness of the proposed approach.

关键词： Feature extraction Subspace constraints Object detection Detectors Task analysis Semantics Prototypes

来源：评论

学校读者我要写书评

暂无评论

Delay-Sensitive Goods Delivery and In-Situ Sensing Using A Multi-Task Drone

引用

IEEE Transactions on Mobile Computing 2025年

作者： Liu, Bin Ni, Wei Liu, Ren Ping Guo, Y. Jay Zhu, Hongbo Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Wireless Communications Nanjing210003 China Nanjing University of Posts and Telecommunications Engineering Research Center of Health Service System Based on Ubiquitous Wireless Networks Ministry of Education Nanjing210003 China University of Technology Sydney Global Big Data Technologies Centre UltimoNSW Australia Barkhausen Institut Technische Universität Dresden Dresden Germany DATA61 CSIRO MarsfieldNSW2122 Australia

Drones are evolving into highly capable and adaptable devices, prompting the development of advanced control frameworks. This paper introduces a novel online control framework tailored for a multi-task drone, explicitly addressing the simultaneous execution of in-situ sensing and goods delivery. To tackle this complex scenario, a finite-horizon Markov decision process (FH-MDP) is formulated to ensure not only the prompt delivery of goods but also the minimization of energy consumption and the maximization of the drone's reward for in-situ sensing. A significant contribution lies in establishing the monotonicity and subadditivity of the FH-MDP. This mathematical foundation provides evidence for the existence of an optimal, monotone, deterministic Markovian policy. The crux of the optimal policy revolves around flight distance- and time-related thresholds, determining the precise points at which the drone should switch its optimal action. This unique feature empowers the multi-task drone to make real-time decisions, such as adjusting flight speed or engaging in in-situ sensing, by comparing its current state with these predefined thresholds. This process can be accomplished with a linear complexity, ensuring efficiency in decision-making. The optimality of our approach is rigorously demonstrated through numerical validation, where it is compared against a computationally expensive, dynamic programming-based alternative. Under the considered simulation settings, our approach reduces drone energy consumption by a substantial 19.8% compared to existing benchmarks. This not only highlights the practical effectiveness of the proposed framework but also underscores its potential for significant advancements in the field of drone operations and energy efficiency. © 2002-2012 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

A laying hen breeding environment monitoring system based on internet of things

A laying hen breeding environment monitoring system based on...

引用

2019 International Conference on Civil engineering, Environment Resources and Energy Materials, CCESEM 2019

作者： Zhai, Zhifen Zhang, Jianhua Chai, Xin Kong, Fantao Wu, Jianzhai Zhang, Jing Han, Shuqing Chinese Academy of Agricultural Engineering Beijing100125 China Agricultural Information Institute Chinese Academy of Agricultural Sciences Key Laboratory of Agricultural Big Data Ministry of Agriculture and Rural Affairs Beijing100081 China

The breeding environment of laying hens has an important influence on the growth of laying hens, the prevention and control of diseases, and the yield and quality of eggs. Therefore, the real-time collection and utilization of the environment information of laying hens is the key point of breeding laying hens. In this study, the environmental information monitoring and control equipment and systems for egg-breeding laying hens were integrated and developed. The real-time monitoring of the environment information of the laying hens and the information query function on the webpage and mobile devices was realized. The stability and versatility testing of equipment and systems were completed through the pilot deployment of equipment and systems in a laying hen farm in Beijing. The design and development of the equipment and system can provide technical support for the modernization, mechanization and information management of laying hens. © Published under licence by IOP Publishing Ltd.

关键词： Disease control

来源：评论

学校读者我要写书评

暂无评论

Information Integration and Environmental Monitoring for Cage Pigeons

Information Integration and Environmental Monitoring for Cag...

引用

2019 International Conference on Civil engineering, Environment Resources and Energy Materials, CCESEM 2019

作者： Chai, Xin Zhai, Zhifen Zhang, Jianhua Kong, Fantao Wu, Jianzhai Sun, Wei Zhou, Xiangyang Han, Shuqing Agricultural Information Institute Chinese Academy of Agricultural Sciences Key Laboratory of Agricultural Big Data Ministry of Agriculture and Rural Affairs Beijing100081 China Chinese Academy of Agricultural Engineering Beijing100125 China

Environmental changes in the farm can have a significant impact on the healthy growth of cage pigeons, disease prevention and the quality of pigeon meat. The stability and adaptability testing of environmental monitoring equipment and systems was completed through the pilot deployment of IoT Ranch in a pigeon farm in Beijing. An integrated program for real-time monitoring of environmental parameters of cage pigeons is implemented. Moreover, a system for informatizing and researching environmental information and real-time querying information on a webpage or mobile terminal is developed. The information-integrated environmental monitoring equipment and system can provide technical support for the modernization, automation and digital management of cage pigeons. © Published under licence by IOP Publishing Ltd.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

A Novel Model and an Online Prediction Platform for Acute Gastrointestinal Injury in Patients Undergoing On-Pump Heart Valve Replacement

SSRN

引用

SSRN 2023年

作者： Yang, Xiaofang Li, Yuanmin Li, Shuyan Zhang, Xu Liu, Zhaoqing Lu, Ning Hu, Wenteng Gao, Long Zhang, Jinduo Fu, Wenkang Cui, Fenfen Zhou, Wenjun Hu, Yuan Dang, Guoqing Yang, Luxi Lin, Yanyan Leung, Joseph W. Song, Bing Yuan, Jinqiu Meng, Wenbo The First School of Clinical Medicne Lanzhou University Gansu Lanzhou730030 China Department of Cardiovascular Surgery The First Hospital of Lanzhou University Gansu Lanzhou730030 China The First Department of General Surgery The First Hospital of Lanzhou University Gansu Lanzhou730030 China Gansu Province Key Laboratory of Biological Therapy and Regenerative Medicine Transformation Gansu Lanzhou730030 China School of Medical Information and Engineering Xuzhou Medical University Jiangsu Xuzhou221004 China Clinical Research Center Big Data Center The Seventh Affifiliated Hospital Sun Yat-sen University Guangdong Shenzhen518107 China Division of Gastroenterology UC Davis Medical Center Sacramento VA Medical Center SacramentoCA95817 United States Department of Thoracic Surgery The First Hospital of Lanzhou University Gansu Lanzhou730030 China State Key Laboratory of Applied Organic Chemistry China The First Clinical Medical School

Background: Acute gastrointestinal injury (AGI) in patients after on-pump cardiac surgery has not been fully assessed and predicted. Hence, this study aimed to develop a clinical model tool to predict AGI after on-pump heart valve replacement (HVR) ***: Machine learning algorithms including Least absolute shrinkage and selection operator (LASSO) regression and random forest (RF) were used to select variables from clinical data, logistic regression analysis was used to reconfirm the features to build the clinical model. The predictive performance was assessed by performing the receiver operating characteristic (ROC) curve analysis as well as calibration, clinical decision and impact curves. A cohort of 131 patients was used to independently validate the ***: A total of 1,070 patients (297 patients with AGI, 27.76%) were enrolled in the study, including 50 variables. The integrated model identified 7 risk factors including age, cardiothoracic ratio, New York Heart Association (NYHA) class, duration of cardiopulmonary bypass, intraoperative infusion of red blood cells, left ventricular ejection fraction and creatinine serum levels on 1ST postoperative day. The area under the curve (AUC) of the model was 0.893 (95% CI 0.873-0.911), with a sensitivity of 79.1% and specificity of 87.2%. The calibration, clinical decision, and impact curves showed a good predictive accuracy and clinical benefit of the model. An AUC of 0.913 (95% CI, 0.851- 0.955) was obtained from the external validation set, with a sensitivity of 91.3% and a specificity of 85.2%. Interpretation: This study presented the first AGI prediction calculator using machine learning, and an online platform. This model can inform individualized perioperative treatment decision-making and help prevent adverse *** Registration: Registered with Clinical *** (NCT05498935). Funding: This work was supported by National Natural Science Foundation of China (82260729), Natural Scienc

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Poisoning attack against estimating from pairwise comparisons

arXiv

引用

arXiv 2021年

作者： Ma, Ke Xu, Qianqian Zeng, Jinshan Cao, Xiaochun Huang, Qingming The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China The Artificial Intelligence Research Center Peng Cheng Laboratory Shenzhen518055 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The School of Computer and Information Engineering Jiangxi Normal University Jiangxi Nanchang330022 China Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China The School of Cyber Security University of Chinese Academy of Sciences Beijing100049 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China The Key Laboratory of Big Data Mining and Knowledge Management The School of Economics and Management University of Chinese Academy of Sciences Beijing100049 China

As pairwise ranking becomes broadly employed for elections, sports competitions, recommendation, information retrieval and so on, attackers have strong motivation and incentives to manipulate or disrupt the ranking list. They could inject malicious comparisons into the training data to fool the target ranking algorithm. Such a technique is called "poisoning attack" in regression and classification tasks. In this paper, to the best of our knowledge, we initiate the first systematic investigation of data poisoning attack on the pairwise ranking algorithms, which can be generally formalized as the dynamic and static games between the ranker and the attacker, and can be modeled as certain kinds of integer programming problems mathematically. To break the computational hurdle of the underlying integer programming problems, we reformulate them into the distributionally robust optimization (DRO) problems, which are computational tractable. Based on such DRO formulations, we propose two efficient poisoning attack algorithms and establish the associated theoretical guarantees including the existence of Nash equilibrium and the generalization ability bounds. The effectiveness of the suggested poisoning attack strategies is demonstrated by a series of toy simulations and several real data experiments. These experimental results show that the proposed methods can significantly reduce the performance of the ranker in the sense that the correlation between the true ranking list and the aggregated results with toxic data can be decreased dramatically. © 2021, CC BY-NC-ND.

关键词： Toys

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：