检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Cheng, Zihan Guo, Jintao Zhang, Jian Qi, Lei Zhou, Luping Shi, Yinghuan Gao, Yang Shanghai Jiao Tong University School of Medicine Shanghai200025 China National Institute of Healthcare Data Science Nanjing University Jiangsu Nanjing210093 China State Key Laboratory for Novel Software Technology the National Institute of Healthcare Data Science Nanjing University Jiangsu Nanjing210093 China School of Computer Science and Engineering Key Lab of Computer Network and Information Integration Southeast University Jiangsu Nanjing211189 China School of Electrical and Information Engineering The University of Sydney SydneyNSW2006 Australia

To segment medical images with distribution shifts, domain generalization (DG) has emerged as a promising setting to train models on source domains that can generalize to unseen target domains. Existing DG methods are mainly based on CNN or ViT architectures. Recently, advanced state space models, represented by Mamba, have shown promising results in various supervised medical image segmentation. The success of Mamba is primarily owing to its ability to capture long-range dependencies while keeping linear complexity with input sequence length, making it a promising alternative to CNNs and ViTs. Inspired by the success, in the paper, we explore the potential of the Mamba architecture to address distribution shifts in DG for medical image segmentation. Specifically, we propose a novel Mamba-based framework, Mamba-Sea, incorporating global-to-local sequence augmentation to improve the model’s generalizability under domain shift issues. Our Mamba-Sea introduces a global augmentation mechanism designed to simulate potential variations in appearance across different sites, aiming to suppress the model’s learning of domain-specific information. At the local level, we propose a sequence-wise augmentation along input sequences, which perturbs the style of tokens within random continuous sub-sequences by modeling and resampling style statistics associated with domain shifts. To our best knowledge, Mamba-Sea is the first work to explore the generalization of Mamba for medical image segmentation, providing an advanced and promising Mamba-based architecture with strong robustness to domain shifts. Remarkably, our proposed method is the first to surpass a Dice coefficient of 90% on the Prostate dataset, which exceeds previous SOTA of 88.61%. The code is available at https://***/orange-czh/Mamba-Sea. Copyright © 2025, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Mobility-Aware Multi-Task Migration and Offloading Scheme for Internet of Vehicles

引用

Chinese Journal of Electronics 2023年第6期32卷 1192-1202页

作者： LI Xujie TANG Jing XU Yuan SUN Ying College of Computer and Information Hohai University State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Key Lab for Wireless Sensor Network and Communication Shanghai Institute of Microsystem School of Information Engineering Jiangsu Open University

In Internet of vehicles, vehicular edge computing(VEC) as a new paradigm can effectively accomplish various tasks. Due to limited computing resources of the roadside units(RSUs), computing ability of vehicles can be a powerful supplement to computing resources. Then the task to be processed in data center can be offloaded to the vehicles by the RSUs. Due to mobility of the vehicles, the tasks will be migrated among the RSUs. How to effectively offload multiple tasks to the vehicles for processing is a challenging problem. A mobility-aware multi-task migration and offloading scheme for Internet of vehicles is presented and analyzed. Considering the coupling between migration and offloading, the joint migration and offloading optimization problem is formulated. The problem is a NP-hard problem and it is very hard to be solved by the conventional methods. To tackle the difficult problem, the idea of alternating optimization and divide and conquer is introduced. The problem can be decoupled into two sub-problems: computing resource allocation problem and vehicle node selection problem. If the vehicle node selection is given, the problem can be solved based on Lagrange function. And if the allocation of computing resource is given, the problem turns into a 0-1 integer programming problem, and the linear relaxation of branch bound algorithm is introduced to solve it. Then the optimization value is obtained through continuous iteration. Simulation results show that the proposed algorithm can effectively improve system performance.

关键词： Costs Computational modeling System performance Simulation Programming Multitasking Resource management

来源：评论

学校读者我要写书评

暂无评论

Theoretical research on temperature field of power cable joint with FEM

Theoretical research on temperature field of power cable joi...

引用

2012 International Conference on System Science and Engineering, ICSSE 2012

作者： Lin, Shanming Hu, Wanqing College of Computer and Information Hohai University Changzhou Jiangsu China Jiangsu Key Laboratory of Power Transmission and Distribution Equipment Technology Changzhou Jiangsu China

ISBN: (纸本)9781467309455

The temperature of the power cable joint is an important parameter reflecting the operating status of the cable. In order to detect the local temperature and temperature rise of the cable joint accurately and overcome the deficiencies of the traditional thermal circuit method, based on the principle of heat transfer theory and finite element method (FEM), a model of cable joint steady temperature field distribution is constructed by adopting the method of finite element divided automatically. The simulation analysis shows the relationship between core temperature and surface temperature of the power cable joint, which proves that the surface temperature can reflect the temperature of the cable joint accurately. With the consideration of the structure, the surface temperature provides a theoretical basis for the monitor of the operating status of power cable in engineering. © 2012 IEEE.

关键词： Surface temperature

来源：评论

学校读者我要写书评

暂无评论

Mining area security warning based on AHP and evidential reasoning

Mining area security warning based on AHP and evidential rea...

引用

第25届中国控制与决策会议

作者： Bingyi Kang Yong Deng Jiangsu Key Laboratory of Resources and Environmental Information Engineering China University of Mining and Technology School of Computer and Information Science Southwest University

ISBN: (纸本)9781467355339

With social and economic development, China's mining area security has taken a lot of attention. Mining area security involves many uncertain factors. In order to get the mining area security status comprehensively, a methodology base on Analystic Hierarchy process (AHP) and evidential reasoning is proposed to evaluate risk in mining area. In the method, the uncertain information were used to generate the basic probability assignment, and the attribute weights are got based on AHP. And then, the final results were obtained based on D/S combination rule. A numerical example is used to illustrate the effectiveness of the proposed method.

关键词： Mining area security, D/S theory, AHP, Data fusion

来源：评论

学校读者我要写书评

暂无评论

A content-based classified hierarchical vector quantization algorithm for volume compression

Journal of Software

引用

Journal of Software 2011年第2期6卷 322-330页

作者： Zhao, Li-Ping Yue, Guang-Xue Xiao, De-Gui Zhou, Xu Yu, Xiang Yu, Fei School of Mathematics and Information Engineering Jiaxing University Jiaxing Zhejiang China School of Computer and Communication Engineering Hunan University Changsha Hunan China Department of Computer Science and Technology Huaihua University Huaihua China Jiangsu Provincial Key Laboratory for Computer Information Processing Technology Soochow University Soochow China

An improved volumetric compression algorithm is presented in this paper. Histogram technique is used for analyzing the trait of volume data. The volume data is then partitioned into volume bricks which will be classified into two groups, the blocks with meaningless information as one group (also called empty blocks), and those with meaningful information as the other group (also called object blocks). An efficient hierarchical VQ is applied to compress object blocks while for empty blocks, nothing is saved. Compare with analogous Volume Compression algorithm, experimental results demonstrate the proposed algorithm not only can improve the compression rate significantly on the premise of the good quality of reconstruction image, but also can obtain fast decoding speed. © 2011 ACADEMY PUBLISHER.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Median Filtering Detection Based on Quaternion Convolutional Neural Network

引用

computers, Materials & Continua 2020年第10期65卷 929-943页

作者： Jinwei Wang Qiye Ni Yang Zhang Xiangyang Luo Yunqing Shi Jiangtao Zhai Sunil Kr Jha Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science&TechnologyNanjing210044China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450001China Department of Computer and Software Nanjing University of Information Science&TechnologyNanjing210044China State Key Laboratory of Information Security Institute of Information EngineeringChinese Academy of SciencesBeijing100093China Department of Electrical Computer Engineering New Jersey Institute of TechnologyNew JerseyNJ07102USA

Median filtering is a nonlinear signal processing technique and has an advantage in the field of image ***,more attention has been paid to the forensics research of median *** this paper,a median filtering forensics method based on quaternion convolutional neural network(QCNN)is *** median filtering residuals(MFR)are used to preprocess the *** the output of MFR is expanded to four channels and used as the input of *** QCNN,quaternion convolution is designed that can better mix the information of different channels than traditional *** quaternion pooling layer is designed to evaluate the result of quaternion *** is proposed to features well combine the three-channel information of color image and fully extract forensics *** show that the proposed method has higher accuracy and shorter training time than the traditional convolutional neural network with the same convolution depth.

关键词： Median filtering forensics quaternion convolution layer quaternion pooling layer color image

来源：评论

学校读者我要写书评

暂无评论

An Improved Incentive Ratio of the Resource Sharing on Cycles

引用

Journal of the Operations Research Society of China 2019年第3期7卷 409-427页

作者： Yu-Kun Cheng Zi-Xin Zhou Suzhou Key Laboratory for Big Data and Information Service School of BusinessSuzhou University of Science and TechnologySuzhou 215009JiangsuChina Department of Computer Science and Technology Peking UniversityBeijing 100871China

Consider a resource sharing system in peer-to-peer(P2P)networks where peers act as both suppliers and customers of *** participant obtains the utility by exchanging its resources with its neighbors according to the preset rules.A series of recent work considered a market equilibrium mechanism and studied the robustness of such a protocol against the Sybil attack strategy,which is a kind of grave threat in P2P *** concept of incentive ratio is applied to measure how much a participant could gain from the Sybil attack by splitting its identity and reconstructing its communication connections with *** Chen et al.(Incentive ratios of a proportional sharing mechanism in resource ***:23rd Annual International Computing and Combinatorics Conference,2017)proved the incentive ratio on cycle networks is bounded by 2 and 4,an open problem is left that is how to narrow the gap *** this paper,we improve the upper bound of incentive ratio on cycle networks to *** improvement comes from a better understanding of the market equilibrium mechanism and a novel analysis technique for the improvement in utility.

关键词： Game theory Resource sharing Market equilibrium mechanism Incentive ratio Sybil attac

来源：评论

学校读者我要写书评

暂无评论

Gas concentration detection using ultrasonic based on wireless sensor networks

Gas concentration detection using ultrasonic based on wirele...

引用

International Conference on information Science and Engineering

作者： Shan, Minglei Li, Xiang Zhu, Changping Zhang, Jiahua Department of Computer and Information Jiangsu Key Laboratory of Power Transmission and Distribution Equipment Technology Hohai University Changzhou China

ISBN: (纸本)9781424480968

In this article, a low power consumption wireless sensor for binary gas mixtures real-time quantitative analysis is presented. This small size wireless gas sensor, which is developed based on an improved time-of-flight (TOF) method, can evaluate target gas in gas mixtures with high resolution. And the wireless sensor network system reduce power consumption using a power control IEEE802.15.4 standard, which can provide an effective mechanism for improving energy efficiency by decreasing the transmitting power directly. In contrast with some other gas analysis techniques, it avoids the problem of the secondary pollution and the short sensor life of using chemic sensor, and the high power consumption problem of traditional TOF methods, makes ultrasonic wireless gas sensor available. Currently, this gas quantitative analysis system consists of several Wireless Ultrasonic Gas Sensor nodes (WUGS) and a master node. The WUGS hardware consists of a microcontroller for obtaining measuring data from the ultrasonic channel, and a Zigbee transceiver for transmitting the data sets to a master sensor node. Furthermore, an environmental monitoring chamber was designed for testing this WUGS using sulfur hexafluoride (SF6) and hydrogen (H2) mixed with air respectively. The resolutions of the tests were within 30μV/V and 500μV/V, respectively. The power cost of the WUGS during the detection period is lower than 90mW. The main advantages of this gas concentration measurement are high accuracy to the gas of which molecular weight is different largely from air, low power consumption and ease of network setup. The sensors have shown good stability for more than three months in a high-voltage substation, for an SF6 leak alarm system test. © 2010 IEEE.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

A novel bandpass filter using asymmetric open stub-loaded sirs

A novel bandpass filter using asymmetric open stub-loaded si...

引用

2012 International Applied Mechanics, MechatronicsAutomation and System Simulation Meeting, AMMASS 2012

作者： Liu, Guogao Tian, Li College of Computer and Information Hohai University China Jiangsu Key Laboratory of Power Transmission and Distribution Equipment Technology China

A novel microstrip bandpass filter using stepped impedance resonators (SIRs) with asymmetric open stub-loaded is proposed in this paper. The filter uses asymmetric open stubs as capacitive loads, resulting in higher-order spurious frequencies suppression and wider upper stopband. Compared with the traditional filter based on stepped impedance resonators at the same design frequency of 2.4 GHz, the proposed filter can significantly reduce the circuit size of 45 %. By changing the geometric dimensions of the asymmetric open stub-loaded SIRs, which can achieve single-band bandpass filter at the centre frequency of 3.5 GHz and dual-band bandpass filter at the centre frequency of 2.4/3.5 GHz.

关键词： Bandpass filters

来源：评论

学校读者我要写书评

暂无评论

CADEC: A Combinatorial Auction for Dynamic Distributed DNN Inference Scheduling in Edge-Cloud Networks

引用

IEEE Transactions on Mobile Computing 2025年

作者： Xu, Xiaolong Hu, Yuhao Cui, Guangming Qi, Lianyong Dou, Wanchun Nanjing University of Information Science and Technology School of Software Nanjing 210044 China Nanjing University of Information Science and Technology Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services School of Software China Nanjing University State Key Laboratory for Novel Software Technology China China University of Petroleum (East China) College of Computer science and technology Qingdao China Georgia State University Department of Computer Science United States

Deep Neural Network (DNN) Inference, as a key enabler of intelligent applications, is often computation-intensive and latency-sensitive. Combining the advantages of cloud computing (abundant computing resources) and edge computing (fast transmission), edge-cloud collaborative DNN inference is a powerful solution to these problems. However, in edge-cloud networks with heterogeneous resources, how to obtain reasonable decisions on server selection, model partition and resource allocation for efficient distributed DNN inference is a hard challenge. Furthermore, it is non-trivial to design suitable resource prices to maximize the social welfare. These challenges even escalate in dynamic edge-cloud networks where decisions should be generated as soon as each user arrives without future information. Therefore, we design a combinatorial auction for dynamic distributed DNN inference scheduling, named CADEC. CADEC first constructs a bid set for each user based on convex optimization theory for optimal solution searching. Next, prices of resources in the edge-cloud network are adjusted according to changes in supply-demand relationship, and whether to admit the request of each user is decided. Finally, the dynamic distributed inference scheduling decisions are generated through the primal-dual algorithm to maximize the social welfare. Theoretical analysis shows the good competitive ratio and polynomial time complexity of CADEC. Results of simulation experiments present that CADEC improves social welfare by up to 46% compared with state-of-the-art distributed DNN inference schemes. © 2002-2012 IEEE.

关键词： Combinatorial auction distributed DNN inference dynamic scheduling edge-cloud networks resource pricing

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：