检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Yue, Tianai Xu, Rongtao Wu, Jingqian Yang, Wenjie Du, Shide Wang, Changwei Johns Hopkins University Baltimore21218 United States State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The University of Hong Kong Hong Kong999077 Hong Kong College of Computer and Big Data Fuzhou University Fuzhou350108 China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences Jinan250014 China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan250014 China

Semi-supervised techniques for medical image segmentation have demonstrated potential, effectively training models using scarce labeled data alongside a wealth of unlabeled data. Therefore, semi-supervised medical image segmentation is one of the key issues in engineering applications of medical artificial intelligence. Consistency constraints based on prototype alignment provide an intuitively sensible way to discover valuable insights from unlabeled data that can motivate segmentation performance. In this work, we propose a dual prototypes contrastive network (DPC-Net) to motivate semi-supervised medical segmentation accuracy by imposing image-level global prototype constraints and pixel-level local prototype constraints. First, we introduce a Background-Separation Global Prototype Contrastive Learning technique that utilizes the natural mutual exclusivity of foreground and background to separate the inter-class distances and encourage the segmentation network to obtain segmentation results that are more complete and do not contain background regions. Second, we design a Cross-Consistent Local Prototype Contrastive Learning techniques to extend the perturbation consistency of the two networks to the prototype's localized response to the feature map, thereby shaping a more stable intra-class prototype space and producing accurate and robust pixel-level predictions. Finally, we comprehensively evaluate our method on mainstream semi-supervised medical image segmentation benchmarks and settings, and experimental results show that our DPC-Net outperforms current state-of-the-art methods. © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Construction and Application of the SMART Model for Adaptive Industrial Data Collection Based on Knowledge Graphs

Construction and Application of the SMART Model for Adaptive...

引用

IEEE International Conference on Big Data

作者： Wendan Cheng Zhen Zhang Heng Qian Qiuyue Wang Guanqun Su Lingge Meng 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 China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China Shu Ju (Shandong) Intelligent Technology Co. Ltd. Jinan China Shandong Standard Institute of Emerging Technologies and Innovations Co. Ltd. Jinan China Shandong Qingniao IIoT Co. Ltd. Jinan China

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Industrial data collection is the foundation for implementing enterprise digitization, which is of great significance to the development of intelligent manufacturing. However, Industrial Data Collection Standards (IDCS) are primarily published in paper or PDF formats, which makes it challenging to associate and reuse knowledge. This brings difficulties to data collection and management of heterogeneous devices, thus affecting the adaptive collection of industrial data. For this reason, this paper introduces SMART into industrial data collection and proposes the construction and application of a knowledge graph-based SMART Model. First, ontology semantic reasoning and natural language processing techniques are utilized to develop an ontology model for industrial data collection and extract fine-grained IDCS knowledge. Then, the knowledge is integrated according to the standard primitive structure and conceptual reasoning rules by constructing a standard association model to form the Industrial Data Collection Standards Knowledge Graph (IDCS-KG). Finally, the SMART competence level is quantitatively assessed based on the completion degree of each operation within the SMART Model. An experimental case study demonstrates that the SMART Model can collect intelligent adaptive industrial data through the reasoning and analysis of equipment adaptation protocols and data quality management strategies.

关键词： Adaptation models Analytical models Protocols Knowledge graphs Data collection Ontologies Data models Cognition Natural language processing Standards

来源：评论

学校读者我要写书评

暂无评论

GrayINT – Detection and Localization of Gray Failures via Hybrid In-band network Telemetry

GrayINT – Detection and Localization of Gray Failures via H...

引用

Asia-Pacific network Operations and Management Symposium (APNOMS)

作者： Kuichao Zhang Wei Su Huiling Shi Kai Zhang Wei Zhang 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 China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China National Engineering Laboratory for Next Generation Internet Interconnection Devices (NGIID) School of Electronics and Information Engineering Beijing Jiaotong University Beijing China

As the underlying infrastructure, data center networks (DCNs) provide an important platform for cloud computing and next-generation networks. However, due to the influence of many factors, such as network, hardware, and software, various failures may occur during the operation of the DCN, which brings great challenges to its reliability. Particularly, a more insidious type of network failure, known as gray failure, presents a significant threat to system stability. In response to this challenge, in this work, we propose GrayINT, a gray failure detection and localization system that leverages In-band network Telemetry (INT) technology to monitor all paths within the data center network in real-time. To verify the feasibility of our design, we build a fat-tree data center network on a virtual network testbed. A large number of experimental results demonstrate that our system can monitor device and link status in real-time, achieving gray failure detection and localization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Merge Collision Prediction TDMA-MAC Protocol in Distributed VANET

A Merge Collision Prediction TDMA-MAC Protocol in Distribute...

引用

International Conference on Informative and Cybernetics for Computational Social Systems (ICCSS)

作者： Chang-Yue Zhang Shi-Yuan Han Jin Zhou Bao-Zhu Li Xiao-Jie Yu Kang Yao Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan China Internet of Things and Smart City Innovation Platform Zhuhai Fudan Innovation Institute Zhuhai China Shandong Provincial Network Security and Infomationization Technology Center Jinan China

ISBN: (纸本)9781665402460

The communication between vehicles has attracted more and more attention in intelligent transportation system(ITS). Due to the rapid movement of vehicles, the topology of network nodes changes rapidly, resulting in collisions between vehicles. Therefore, the design of efficient and reliable media access control protocol is very necessary to solve the communication problem between vehicles. In this paper, a merge collision prediction TDMA-MAC in distributed VANET(MCPMAC) is proposed to solve the merging collision problem. In MCPMAC, when multiple vehicles occupying the same time slot meet within the two hop communication range, one vehicle continues to use the time slot by comparing the time stamp of the vehicle access time slot, and the other vehicles sequentially select the idle time slot to reduce the probability of merging collision between vehicles. Simulation results show MCPMAC protocol has higher reliability and lower number of collisions than the existing MAC protocols.

关键词： Protocols network topology Simulation Merging Vehicular ad hoc networks Transportation Media Access Protocol

来源：评论

学校读者我要写书评

暂无评论

SAMamba: Adaptive state space modeling with hierarchical vision for infrared small target detection

引用

Information Fusion 2025年 124卷

作者： Wenhao Xu Shuchen Zheng Changwei Wang Zherui Zhang Chuan Ren Rongtao Xu Shibiao Xu School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing 100876 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 The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing 100190 China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan 250014 China School of Software Microelectronics Peking University Beijing 100084 China

Infrared small target detection (ISTD) is vital for long-range surveillance systems, particularly in military defense, maritime monitoring, and early warning applications. Despite its strategic importance, ISTD remains challenging due to two fundamental limitations: targets typically occupy less than 0.15% of the image area and exhibit low distinguishability from complex backgrounds. While recent advances in deep learning have shown promise, existing methods struggle with information loss during downsampling and inefficient modeling of global context. This paper presents SAMamba, a novel framework that synergistically integrates SAM2’s hierarchical feature learning with Mamba’s selective sequence modeling to address these challenges. Our key innovations include: (1) Feature Selection Adapter (FS-Adapter) that enables efficient domain adaptation from natural to infrared imagery by employing a dual-stage selection mechanism, which includes token-level selection via a learnable task embedding and channel-wise refinement through adaptive transformations; (2) Cross-Channel State-Space Interaction (CSI) module that achieves efficient global context modeling through selective state space modeling with linear complexity; and (3) Detail-Preserving Contextual Fusion (DPCF) module that adaptively combines multi-scale features through learnable fusion strategies, utilizing a gating mechanism to balance contributions from high-resolution and low-resolution features. SAMamba effectively addresses the core challenges of ISTD by bridging the domain gap, maintaining fine-grained target details, and efficiently modeling long-range dependencies. Extensive experiments on NUAA-SIRST, IRSTD-1k and NUDT-SIRST datasets demonstrate that SAMamba significantly outperforms state-of-the-art methods, particularly in challenging scenarios with heterogeneous backgrounds and varying target scales. Code is available at https://***/zhengshuchen/SAMamba .

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybrid remote display protocol for mobile thin client computing

Hybrid remote display protocol for mobile thin client comput...

引用

IEEE International Conference on Computer Science and Automation Engineering (CSAE)

作者： Wei Tang Biao Song Myeong Seob Kim Nguyen Tien Dung Eui Nam Huh Internet Computing and Network Security Laboratory Department of Computer Engineering Kyung Hee University Suwon South Korea

In recent years, the rapid development of mobile network and device promotes the investigation of mobile thin client technology. Based on the surveys in this field, we found that the codec used in the thin client protocol should be able to provide efficient data compression (to reduce network bandwidth consumption), and operate with low computing complexity (to decrease response latency and thin client power consumption). In this paper, we proposed a hybrid remote display protocol for mobile thin client, together with the main results of performance study.

关键词： Protocols Image coding Mobile communication Graphics processing unit Servers Streaming media Transform coding

来源：评论

学校读者我要写书评

暂无评论

Towards the Development of Personal Cloud computing for Mobile Thin-Clients

Towards the Development of Personal Cloud Computing for Mobi...

引用

International Conference on Information Science and Applications (ICISA)

作者： Yuan Tian Biao Song Eui-Nam Huh Department of Computer Engineering Internet Computing and Network Security Laboratory Kyung Hee University South Korea

ISBN: (纸本)9781424492220

The phenomenon of cloud computing has been driven largely these days. Personal Cloud, as the cloud computing for personal usage, has come to the forefront. Compare with traditional operating system, personal cloud shifts individual computing "from being device-centric to information-centric", which create a bridge between operating system-based computing and the more service-oriented approach to IT. Also, the mobile thin-client has brought mobility to cloud computing. In this paper, we provide a reference base for the development of methodologies tailored for personal cloud computing. Besides, we also provide a security architecture for personal cloud based on the security requirement analysis.

关键词： security Cloud computing Privacy Servers Software Computer architecture

来源：评论

学校读者我要写书评

暂无评论

A Novel Cloud Market Infrastructure for Trading Service

A Novel Cloud Market Infrastructure for Trading Service

引用

International Conference on Computational Science and its Applications (ICCSA)

作者： Biao Song Mohammad Mehedi Hassan Eui-Nam Huh Internet Computing and Network Security Laboratory Department of Computer Engineering Kyung Hee University South Korea

In this paper, we present a novel combinatorial auction (CA) based trading infrastructure to enable the supply and demand of Cloud services from different Cloud providers (CP). We propose a new auction policy that considers the relationship among CPs (mutual business relationship) in bidding mechanism. In our new auction-based market model, we allow the group of service providers to publish their bids collaboratively as a single bid to the auctioneer. It gives service providers a chance to autonomously find partners and make groups. Then they can use group strategy to increase their competitive power and compete for winning the bid (s). This will reduce conflicts, as well as collaboration cost and negotiation time, among participants as compare to existing CA-based market model. We implement our proposed market model of trading service in a simulated environment and study its economic efficiency with existing model.

关键词： Cloud computing Collaboration Resource management Computer networks Power generation economics Power system modeling Environmental economics Supply and demand Costs Application software

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Algorithm for Partner Selection in Market Oriented Cloud computing

A Hybrid Algorithm for Partner Selection in Market Oriented ...

引用

International Conference on Management and Service Science, MASS

作者： Biao Song M. M. Hassan Eui-Nam Huh Chang-Woo Yoon Hyun-Woo Lee Internet Computing and Network Security Laboratory Department of Computer Engineering Kyung Hee University South Korea Electronics and Telecommunications Research Institute South Korea

In our previous paper, we proposed a novel combinatorial auction (CA) based cloud market model for trading services that allows cloud providers (CPs) to make groups and submit their bids collaboratively as a single bid for winning the auction. But to find a good combination of CP partners and make groups is a NP-hard problem. Since each provider only has limited information about other providers, past collaborative task information (i.e. no. of times collaboratively win the auctions, failed to make groups, etc.) needs to be analyzed and utilized for partner selection. We call it multi-task and multi-objective optimization problem. To solve this problem, in this paper, we propose a hybrid algorithm that utilizes artificial neural network (ANN) for gathering and analyzing information about previous tasks and then uses multi-objective genetic algorithm (MOGA) to solve the partner selection problem. Simulation results show that our proposed algorithm is effective.

关键词： Cloud computing Artificial neural networks Collaboration Computer networks Information analysis Electronic mail Algorithm design and analysis Genetic algorithms Neural networks IP networks

来源：评论

学校读者我要写书评

暂无评论

Propagation Service Decision Method for Web Services Composition in u-Lifecare System

Propagation Service Decision Method for Web Services Composi...

引用

International Conference on Computational Science and its Applications (ICCSA)

作者： Ki-moon Choi Mohammad Mehedi Hassan Eui-Nam Huh Internet Computing and Network Security Laboratory Department of Computer Engineering Kyung Hee University Yongin si Gyeonggi South Korea

In Web environment, multiple Web service(WS)s may provide similar functionalities with different nonfunctional property values (e.g. different QoS metrics). Quality of service (QoS) metrics of WSs are critical factors to select appropriate WSs execution path in WSs composition as it requires expensive computation cost to find out appropriate execution path in Web environment, i.e O(MN) assuming that there will be M candidate services and N WSs in composition model. Thus, it is very important to decide which service execution path will be more suitable to users in execution time. Existing methods find execution path in design time which is inefficient as the QoS metrics of WSs are changed frequently in real time. Thus, in this paper, we propose a dynamic service execution path selection method called PSDM (propagation service decision method) in execution time for web service composition in u-Lifecare system. The proposed scheme is analyzed and experiment results are shown in terms of frequency of service execution path.

关键词： Web services Quality of service Computer networks Availability Computational efficiency Frequency Throughput Costs Application software IP networks

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：