检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Ma, Jun Zhang, Yao Gu, Song Ge, Cheng Ma, Shihao Young, Adamo Zhu, Cheng Meng, Kangkang Yang, Xin Huang, Ziyan Zhang, Fan Liu, Wentao Pan, YuanKe Huang, Shoujin Wang, Jiacheng Sun, Mingze Xu, Weixin Jia, Dengqiang Choi, Jae Won Alves, Natália de Wilde, Bram Koehler, Gregor Wu, Yajun Wiesenfarth, Manuel Zhu, Qiongjie Dong, Guoqiang He, Jian Wang, Bo He, Junjun Yang, Hua Yang, Huihua Huang, Bingding Lyu, Mengye Ma, Yongkang Guo, Heng Zhang, Rongguo Maier-Hein, Klaus The Department of Laboratory Medicine and Pathobiology University of Toronto Peter Munk Cardiac Centre University Health Network Vector Institute Toronto Canada Shanghai AI Laboratory Shanghai200232 China The Department of Image Reconstruction Nanjing Anke Medical Technology Co. Ltd. Nanjing211113 China Ocean University of China Qingdao266100 China The Department of Computer Science University of Toronto Peter Munk Cardiac Centre University Health Network Vector Institute Toronto Canada Tinavi Medical Technologies Co. Ltd. Beijing100192 China University of Science and Technology Beijing Beijing100083 China The School of Biomedical Engineering Health Science Center Shenzhen University Shenzhen518055 China The Department of Radiological Algorithm Fosun Aitrox Information Technology Co. Ltd. Shanghai200033 China The School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China Shenzhen Technology University Shenzhen518000 China Xiamen University Xiamen361005 China Alibaba Beijing100084 China Infervision Medical Technology Co. Ltd. Beijing100025 China Hong Kong Centre for Cerebro-cardiovascular Health Engineering 000000 Hong Kong The Department of Radiology Armed Forces Yangju Hospital Yangju11429 Korea Republic of The Department of Radiology Radboudumc Nijmegen6525XZ Netherlands The Department of Medical Image Computing German Cancer Research Center Heidelberg69120 Germany ShenZhen Yorktal DMIT LLC Shenzhen518100 China Heidelberg69120 Germany The Department of Nuclear Medicine Nanjing Drum Tower Hospital Nanjing210008 China The College of Big Data and Internet Shenzhen Technology University Shenzhen518188 China The College of Health Science and Environmental Engineering Shenzhen Technology University Shenzhen China The Manteia Technologies Co. Ltd Xiamen China The Alibaba DAMO Academy Beijing China The Peter Munk Cardiac Centre University Health Network Department of Laboratory M

Quantitative organ assessment is an essential step in automated abdominal disease diagnosis and treatment planning. Artificial intelligence (AI) has shown great potential to automatize this process. However, most existing AI algorithms rely on many expert annotations and lack a comprehensive evaluation of accuracy and efficiency in real-world multinational settings. To overcome these limitations, we organized the FLARE 2022 Challenge, the largest abdominal organ analysis challenge to date, to benchmark fast, low-resource, accurate, annotation-efficient, and generalized AI algorithms. We constructed an intercontinental and multinational dataset from more than 50 medical groups, including Computed Tomography (CT) scans with different races, diseases, phases, and manufacturers. We independently validated that a set of AI algorithms achieved a median Dice Similarity Coefficient (DSC) of 90.0% by using 50 labeled scans and 2000 unlabeled scans, which can significantly reduce annotation requirements. The best-performing algorithms successfully generalized to holdout external validation sets, achieving a median DSC of 89.5%, 90.9%, and 88.3% on North American, European, and Asian cohorts, respectively. They also enabled automatic extraction of key organ biology features, which was labor-intensive with traditional manual measurements. This opens the potential to use unlabeled data to boost performance and alleviate annotation shortages for modern AI models. © 2023, CC BY-NC-ND.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Transferring knowledge distillation for multilingual social event detection

arXiv

引用

arXiv 2021年

作者： Ren, Jiaqian Peng, Hao Jiang, Lei Wu, Jia Tong, Yongxin Wang, Lihong Bai, Xu Wang, Bo Yang, Qiang Institute of Information Engineering Chinese Academy of Sciences The School of Cyber Security University of Chinese Academy of Sciences Beijing100041 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100083 China The School of Cyber Science and Technology Beihang University Beijing100083 China Institute of Information Engineering Chinese Academy of Sciences Beijing100041 China The Department of Computing Macquarie University Sydney Australia The State Key Laboratory of Software Development Environment The School of Computer Science and Engineering Beihang University Beijing100083 China The National Computer Network Emergency Response Technical Team Coordination Center of China Beijing100029 China The Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong AI Group WeBank Co. Ltd. China

Recently published graph neural networks (GNNs) show promising performance at social event detection tasks. However, most studies are oriented toward monolingual data in languages with abundant training samples. This has left the more common multilingual settings and lesser-spoken languages relatively unexplored. Thus, we present a GNN that incorporates cross-lingual word embeddings for detecting events in multilingual data streams. The first exploit is to make the GNN work with multilingual data. For this, we outline a construction strategy that aligns messages in different languages at both the node and semantic levels. Relationships between messages are established by merging entities that are the same but are referred to in different languages. Non-English message representations are converted into English semantic space via the cross-lingual word embeddings. The resulting message graph is then uniformly encoded by a GNN model. In special cases where a lesser-spoken language needs to be detected, a novel cross-lingual knowledge distillation framework, called CLKD, exploits prior knowledge learned from similar threads in English to make up for the paucity of annotated data. Experiments on both synthetic and real-world datasets show the framework to be highly effective at detection in both multilingual data and in languages where training samples are scarce. © 2021, CC BY.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Enhancing Collaborative Inference on Heterogeneous Edge Devices via Adaptive Ensemble Knowledge Distillation

引用

IEEE Journal on Selected Areas in Communications 2025年

作者： Wu, Shangrui Li, Yupeng Wang, Wenhua Guo, Jianxiong Fan, Wentao Liu, Qin Jia, Weijia Yu, Shui Cao, Jiannong Wang, Tian Beijing Normal-Hong Kong Baptist University Guangdong Provincial/Zhuhai Key Laboratory of IRADS Department of Computer Science Zhuhai China Hong Kong Baptist University Hong Kong Hong Kong Hong Kong Baptist University Department of Interactive Media Hong Kong Hong Kong Beijing Normal University Institute of Artificial Intelligence and Future Networks Zhuhai China Xi'an University of Posts and Telecommunications Shaanxi Key Laboratory of Information Communication Network and Security Shaanxi Xi'an China Hunan University College of Computer Science and Electronic Engineering Changsha China University of Technology Sydney School of Computer Science Sydney Australia The Hong Kong Polytechnic University Department of Computing Hong Kong Hong Kong

The integration of edge computing with deep neural networks (DNNs) is crucial for intelligent industrial cyber-physical systems. Typically, deploying DNNs on heterogeneous edge devices relies on methods like model compression and partitioning. However, these approaches often result in homogeneous models across devices. This homogeneity limits the collective capability of edge computing systems, particularly in terms of generalization to diverse data distributions and adaptation to dynamic industrial environments. In this work, we propose to treat each DNN on an edge device as an independent model, aggregating their capabilities via ensemble learning to enhance generalization and dynamic adaptability. To realize this, we introduce the Adaptive Ensemble Knowledge Distillation Framework (AEKDF), combining cloud-based model training with edge computing based collaborative inference. In the cloud, AEKDF develops an enhanced Born Again network that generates diverse, lightweight models tailored to specific edge devices through knowledge distillation. This process ensures model diversity which is critical to effective ensemble learning. On the edge, AEKDF employs an adaptive ensemble technique that aggregates prediction logits across devices, enabling rapid adaptation to changing environments and maintaining inference efficiency. Our extensive evaluations conducted on a realistic prototype demonstrate the substantial boost in predictive performance achieved by our AEKDF, showcasing a 4% to 10% accuracy improvement on the CIFAR-100 compared to conventional single-model approaches, while maintaining low latency. © 1983-2012 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

In-situ data scheduling optimization based on rainbow DQN for IIoT

引用

Future Generation computer Systems 2026年 174卷

作者： Peiying Zhang Siyi Li Lizhuang Tan Neeraj Kumar Jian Wang Kai Liu Qingdao Institute of Software College of Computer Science and Technology China University of Petroleum (East China) Qingdao 266580 China Shandong Key Laboratory of Intelligent Oil & Gas Industrial Software Qingdao 266580 China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan 250014 China Department of Computer Science and Engineering Thapar Institute of Engineering and Technology Patiala 147004 India Department of Computer Science University of Economics and Human Sciences Warszawa 01-043 Poland Department of Networks and Communications College of Computer Science and Information Technology Imam Abdulrahman Bin Faisal University Dammam 31441 Saudi Arabia College of Science China University of Petroleum (East China) Qingdao 266580 China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing 100084 China State Key Laboratory of Space Network and Communications Tsinghua University Beijing 100084 China

In industrial systems, in-situ computing refers to a mode of local or proximate data processing within the cloud–edge-terminal architecture. In the Industrial internet of Things (IIoT) environment, servers are typically deployed near terminal devices to coordinate and manage the scheduling of in-situ data, forming a comprehensive in-situ server system. With the rapid growth of IIoT terminal devices, challenges such as high processing delays and severe demand congestion arise in the in-situ data scheduling process. To address this challenge, this paper proposes a scheduling optimization scheme based on Rainbow DQN. The scheme designs a scheduling buffer and classification strategy to distinguish in-situ data based on storage demand characteristics, thereby optimizing the scheduling process. At the same time, a multi-level storage structure is introduced to store in-situ data classified according to the scheduling strategy. Additionally, the Rainbow DQN algorithm is utilized to assist in the scheduling decision-making of in-situ data retrieval, effectively alleviating system congestion while ensuring certain throughput performance. Extensive simulation experiments show that the Rainbow DQN algorithm achieves a reduction of 60.82% in average waiting delay, 62.94% in average unprocessed demand, and a 58.27% reduction in average completion delay.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Edge computing-enabled energy efficiency prediction of immersion cooling system for supercomputing centers

Cleaner Engineering and Technology

引用

Cleaner engineering and Technology 2025年 27卷

作者： Shuaiyin Ma Yichun Cao Yang Liu School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi'an 710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and Telecommunications Xi'an 710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'an 710121 China Shaanxi Union Research Centre of University and Enterprise for 5G+ Industrial Internet Communication Terminal Technology Xi'an University of Posts and Telecommunications Xi'an 710121 China Department of Management and Engineering Linköping University SE-581 83 Linköping Sweden Industrial Engineering and Management University of Oulu 90570 Oulu Finland

Within the context of cleaner production, enhancing energy efficiency and sustainability has emerged as a central focus in supercomputing center development. To address the challenges in predicting energy consumption, this study proposes an architecture of edge computing-enabled energy efficiency prediction of immersion cooling system for supercomputing centers. This architecture combines time-series generative adversarial network (TimeGAN) for data augmentation with the neural basis expansion analysis for time series (N-BEATS) for prediction, providing a robust solution for accurate energy consumption prediction. TimeGAN enhances the training dataset by generating high-quality synthetic time-series data, effectively mitigating issues of data sparsity and imbalance. N-BEATS, with its modular architecture and strong adaptability to temporal data, ensures precise predictions by capturing both global trends and local variations in energy usage. Experimental results demonstrate the effectiveness of the proposed architecture, exhibiting superior performance across key metrics when compared to traditional models. Specifically, the RMSE of TimeGAN-N-BEATS reduced by more than 8 %, the MSE decreased by over 18 %, and the R 2 reached 97.31 %, outperforming baseline models such as long short-term memory and gated recurrent unit, and their attention-enhanced variants. This study highlights the potential of integrating generative and predictive models to optimize energy efficiency in liquid cooling systems, offering valuable insights for sustainable supercomputing operations.

关键词： Edge computing Liquid cooling system N-BEATS Supercomputing centers TimeGAN

来源：评论

学校读者我要写书评

暂无评论

Front Cover: International Journal of Intelligent Systems, Volume 37 Issue 11 November 2022

引用

International Journal of Intelligent Systems 2022年第11期37卷

作者： Xianjia Meng Yong Yang Ximeng Liu Nan Jiang School of Information Science and Technology Northwest University Xi'an People's Republic of China Fujian Province Key Laboratory of Information Security of Network System and College of Computer and Data Science Fuzhou University Fuzhou People's Republic of China Cyberspace Security Research Center Peng Cheng Laboratory Shenzhen People's Republic of China Department of Internet of Things School of Information Engineering East China Jiao Tong University Nanchang People's Republic of China

来源：评论

学校读者我要写书评

暂无评论

Prototype Framework of Low-Latency Collection of Multi-Point Video Stream over Multi-Hop Multi-Channel Wireless network

Prototype Framework of Low-Latency Collection of Multi-Point...

引用

作者： Aung Myo Htut Juseong Kim JongWon Kim Chaodit Aswakul Wireless Network and Future Internet Research Unit Department of Electrical Engineering Faculty of Engineering Chulalongkorn University Networked Computing Systems (NetCS) Laboratory School of Electrical Engineering and Computer Science Gwangju Institute of Science and Technology

Big cities are facing heavy road traffic congestion. The main reason is the increasing number of vehicles beyond the road network capacity, which forces traffic police at times to be incapable of controlling the inevitable traffic jams. To resolve those traffic jams, traffic police need the near real-time information of the road network e.g. from traffic cameras. In this paper, a prototype framework of low-latency collection of multi-point video streams over a multi-hop multi-channel wireless network is proposed. Video frames are captured by Raspberry Pi cameras and sent by the wireless link to the herein-called IoT Concentrators. IoTCloud Hub then pulls and stores those video frames from the IoT Concentrators. Users（traffic police） can watch traffic videos from the display screen of the IoT-Cloud Hub. As a proof-of-concept implementation, two Pi Cameras have been set up with Apache Kafka Producers and two additional Raspberry Pi's have been set up as the IoT Concentrators, which run the leader and follower Apache Kafka Brokers. To complete our system, an Intel NUC as IoT-Cloud Hub and another Intel NUC as Orchestration-Hub have been also set up. We assume the available wired communication linkage between the Orchestration-Hub and the other devices. However, the links between the Pi Cameras, IoT Concentrators and IoT-Cloud Hub are wireless with Wi-Fi. To achieve a high performance, multiple Wi-Fi channels can be dynamically configured by the Orchestration-Hub to steer the VDO traffic（based on TCP） away from the congested channels. Based on the implementation prototype, the average TCP throughputs over all the wireless links have been improved by 56.046% on average, compared with the case without the dynamic Wi-Fi channel selection.

关键词： Apache Kafka Raspberry Pi video streaming wireless

来源：评论

学校读者我要写书评

暂无评论

A Hole Repairing Method Based on Edge-Preserving Projection 12th

A Hole Repairing Method Based on Edge-Preserving Projection

引用

12th International Conference on e-Learning and Games, Edutainment 2018

作者： Wang, Yinghui Zhao, Yanni Wang, Ningna Ning, Xiaojuan Shi, Zhenghao Zhao, Minghua Lv, Ke Huang, Liangyi Institute of Computer Science and Engineering Xi’an University of Technology Xi’an China Shaanxi Key Laboratory of Network Computing and Security Technology Xi’an China Department of Computer Science Shannxi Vocational and Technical College Xi’an China Booking B.V. Herengracht 597 Amsterdam1017 CE Netherlands Institute of Automation Chinese Academy of Sciences Beijing China School of Engineering and Applied Science George Washington University Washington D.C. United States

ISBN: (纸本)9783030237110

A point cloud hole repairing method based on edge-preserving projection is proposed in order to maintain sharp features of holes. First, the hole boundary points are acquired by quadrants and angles, then connections among 3D hole boundary points are projected onto the two-dimensional plane using the edge-preserving projection. Secondly, the two-dimensional region obtained from projection is subjected to point collectivization for obtaining filling points, at the same time, the radial-basis interpolation mapping technique is used to construct the hole surface according to the 3D hole boundary point. Finally, the two-dimensional filling points are reflected onto the surface of the constructed hole to complete hole repairing. Experimental results show that our method can effectively repair the hole of the point cloud and restore the sharp features of the hole. © 2019, Springer Nature Switzerland AG.

关键词： Repair

来源：评论

学校读者我要写书评

暂无评论

A Hole Repairing Method Based on Slicing 12th

A Hole Repairing Method Based on Slicing

引用

12th International Conference on e-Learning and Games, Edutainment 2018

作者： Zhao, Yanni Wang, Yinghui Wang, Ningna Ning, Xiaojuan Shi, Zhenghao Zhao, Minghua Lv, Ke Huang, Liangyi Institute of Computer Science and Engineering Xi’an University of Technology Xi’an China Shaanxi Key Laboratory of Network Computing and Security Technology Xi’an China Department of Computer Science Shannxi Vocational and Technical College Xi’an China Booking B.V. Herengracht 597 Amsterdam1017 CE Netherlands Institute of Automation Chinese Academy of Sciences Beijing China School of Engineering and Applied Science George Washington University Washington D.C. United States

ISBN: (纸本)9783030237110

The repairing of 3D point cloud holes has an important meaning to ensure the integrity of cloud data. We present a slice-based repairing method for 3D point cloud in this paper. Firstly, the model is horizontal sliced and each slice is projected on a two-dimensional plane, then the band-shaped points obtained during projection are clustered to select boundary points of the hole. Combined with optimal fitting points, the hole repairing point sets in the projection layer are re-sampled based on the cubic B-spline curve to fit boundary points. Finally, all hole repairing point sets in the projection layer are combined in 3D space to finish the entire hole recovery. The experimental results show that the proposed method can effectively repair complex holes for various point cloud models. © 2019, Springer Nature Switzerland AG.

关键词： Curve fitting

来源：评论

学校读者我要写书评

暂无评论

Correlation-Aware Virtual Machine Placement in Data Center networks 7th

Correlation-Aware Virtual Machine Placement in Data Center N...

引用

7th EAI International Conference on Cloud computing, CloudComp 2016 and 1st EAI International Conference on security and Privacy in New computing Environments, SPNCE 2016

作者： Chen, Tao Zhu, Yaoming Gao, Xiaofeng Kong, Linghe Chen, Guihai Wang, Yongjian Shanghai Key Laboratory of Scalable Computing and Systems Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of Information Network Security of Ministry of Public Security The Third Research Institute of Ministry of Public Security Shanghai China

ISBN: (纸本)9783319696041

The resource utilization (CPU, memory) is a key performance metric in data center networks. The goal of the cloud platform supported by data center networks is achieving high average resource utilization while guaranteeing the quality of cloud services. Previous work focus on increasing the time-average resource utilization and decreasing the overload ratio of servers by designing various efficient virtual machine placement schemes. Unfortunately, most of virtual machine placement schemes did not involve the service level agreements and statistical methods. In this paper, we propose a correlation-aware virtual machine placement scheme that effectively places virtual machines on physical machines. First, we employ Neural networks model to forecast the resource utilization trend according to the historical resource utilization data. Second, we design correlation-aware placement algorithms to enhance resource utilization while meeting the user-defined service level agreements. The results show that the efficiency of our virtual machine placement algorithms outperform the previous work by about 15%. © 2018, ICST Institute for computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Virtual machine

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：