检索结果-内蒙古大学图书馆

MACCoM: A multiple attention and convolutional cross-mixer framework for detailed 2D biomedical image segmentation

computers in Biology and Medicine 2024年 179卷 108847-108847页

作者： Ejiyi, Chukwuebuka Joseph Qin, Zhen Ejiyi, Makuachukwu Bennedith Ukwuoma, Chiagoziem Ejiyi, Thomas Ugochukwu Muoka, Gladys Wavinya Gyarteng, Emmanuel S.A. Bamisile, Olusola O. Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Sichuan Chengdu China Pharmacy Department University of Nigeria Nsukka Enugu State Nsukka Nigeria Department of Pure and Industrial Chemistry University of Nigeria Nsukka Enugu State Nsukka Nigeria School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Sichuan Industrial Internet Intelligent Monitoring and Application Engineering Research Center Chengdu University of Technology Chengdu China

The UNet architecture, which is widely used for biomedical image segmentation, has limitations like blurred feature maps and over- or under-segmented regions. To overcome these limitations, we propose a novel network architecture called MACCoM (Multiple Attention and Convolutional Cross-Mixer) – an end-to-end depthwise encoder-decoder fully convolutional network designed for binary and multi-class biomedical image segmentation built upon deeperUNet. We proposed a multi-scope attention module (MSAM) that allows the model to attend to diverse scale features, preserving fine details and high-level semantic information thus useful at the encoder-decoder connection. As the depth increases, our proposed spatial multi-head attention (SMA) is added to facilitate inter-layer communication and information exchange, enabling the network to effectively capture long-range dependencies and global context. MACCoM is also equipped with a convolutional cross-mixer we proposed to enhance the feature extraction capability of the model. By incorporating these modules, we effectively combine semantically similar features and reduce artifacts during the early stages of training. Experimental results on 4 biomedical datasets crafted from 3 datasets of varying modalities consistently demonstrate that MACCoM outperforms or matches state-of-the-art baselines in the segmentation tasks. With Breast Ultrasound Image (BUSI), MACCoM recorded 99.06 % Jaccard, 77.58 % Dice, and 93.92 % Accuracy, while recording 99.50 %, 98.44 %, and 99.29 % respectively for Jaccard, Dice, and Accuracy on the Chest X-ray (CXR) images used. The Jaccard, Dice, and Accuracy for the High-Resolution Fundus (HRF) images are 95.77 %, 74.35 %, and 95.95 % respectively. The findings here highlight MACCoM's effectiveness in improving segmentation performance and its valuable potential in image analysis. © 2024 Elsevier Ltd

关键词： Mixers (machinery)

来源：评论

学校读者我要写书评

暂无评论

Auction Theory and Game Theory Based Pricing of Edge Computing Resources: A Survey

引用

IEEE Internet of Things Journal 2025年

作者： Yu, Jiguo Liu, Shun Zou, Yifei Wang, Guijuan Hu, Chunqiang University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu610054 China Qilu University of Technology Big Data Institute Jinan250353 China Qufu Normal University School of Computer Science Shandong Rizhao China Shandong University School of Computer Science and Technology Shandong Qingdao266237 China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan250353 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan250353 China Chongqing University School of Big Data and Software Engineering Chongqing400044 China

The proliferation of Internet of Things (IoT) devices and edge computing applications has heightened the demand for efficient resource allocation and pricing mechanisms. Effective pricing strategies play a crucial role in optimizing resource utilization, reducing latency, and ensuring fair resource distribution among users. Both auction theory and game theory have emerged as fundamental economic frameworks for designing pricing mechanisms in edge computing. This paper presents a comprehensive survey of pricing strategies that leverage both auction and game theory, systematically categorizing existing research based on auction mechanisms and game-theoretic models. Unlike previous surveys that focus solely on auction-based pricing, this work integrates game-theoretic perspectives, providing a holistic analysis of strategic interactions in edge computing resource allocation. Furthermore, we discuss key challenges, emerging trends, and future research directions aimed at enhancing efficiency, fairness, and privacy protection in cloud-edge collaborative computing environments. © 2014 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

TASS: Threshold Adaptor Signature Scheme for Holographic IoT Consumer Devices in Blockchain Enabled Federated Learning

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Wang, Zengxiang Qin, Zhen Kumari, Saru Feng, Chaosheng Alenazi, Mohammed J.F Wu, Deyan Chen, Chien-Ming Xiong, Hu University of Electronic Science and Technology of China Network and Data Security Key Laboratory of Sichuan Province Sichuan Chengdu610054 China Chaudhary Charan Singh University Department of Mathematics Uttar Pradesh Meerut India Sichuan Normal University School of Computer Science Sichuan Chengdu610101 China Department of Computer Engineering Riyadh11451 Saudi Arabia Sichuan Institute of Computer Sciences China Nanjing University of Information Science and Technology School of Artificial Intelligence Nanjing250004 China

The integration of virtual medical assistants utilizing holographic projections has transformed holographic IoT consumer devices, fostering advanced healthcare interactions and attracting significant interest from industry and academia. Most federated learning (FL) systems in holographic IoT consumer devices are centrally managed, which exposes them to risks such as medical data breaches and single points of failure. Although blockchain technology provides an effective solution by enabling decentralized model training, it faces inherent limitations in terms of computational efficiency and security. Adapter signatures (AS) offload some of the computation on the blockchain to mitigate these problems through means such as key revelation. Despite their advantages, existing AS schemes suffer from bilateral design constraints, which increase the risks of key loss, single points of failure, and lack support for multi-party transaction scenarios. This paper proposes a novel threshold adapter signature scheme (TASS) based on elliptic curve cryptography (ECC) to address these challenges. TASS allows a group of entities to collaboratively generate partial signatures in a distributed manner, reducing the risks associated with key loss and single points of failure. Each participant holds only a share of the private key, ensuring that no single entity has complete control. This distributed approach enhances the system’s resilience against attacks and operational failures. Unlike traditional AS schemes that primarily support one-to-one transactions, TASS is designed to facilitate one-to-many and many-to-many transactions. Experimental evaluations demonstrate the superior performance of ECC-driven TASS in large-scale participants, providing a secure, efficient, and scalable foundation for integrating holographic interactions and blockchain technology within holographic IoT consumer devices. © 1975-2011 IEEE.

关键词： Privacy by design

来源：评论

学校读者我要写书评

暂无评论

AsyncSC: An Asynchronous Sidechain for Multi-Domain Data Exchange in Internet of Things

arXiv

引用

arXiv 2024年

作者： Yang, Lingxiao Dong, Xuewen Wan, Zhiguo Gao, Sheng Tong, Wei Lu, Di Shen, Yulong Du, Xiaojiang The School of Computer Science and Technology Xidian University The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education China The Shaanxi Key Laboratory of Blockchain and Secure Computing Xi'An710071 China The Zhejiang Lab Hangzhou311121 China The School of Information Central University of Finance and Economics Beijing100081 China The School of Information Science and Engineering Zhejiang Sci-Tech University Hangzhou310018 China The School of Computer Science and Technology Xidian University China The Shaanxi Key Laboratory of Network and System Security Xi'An710071 China The School of Engineering and Science Stevens Institute of Technology Hoboken07030 United States

Sidechain techniques improve blockchain scalability and interoperability, providing decentralized exchange and cross-chain collaboration solutions for Internet of Things (IoT) data across various domains. However, current state-of-the-art (SOTA) schemes for IoT multi-domain data exchange are constrained by the need for synchronous networks, hindering efficient cross-chain interactions in discontinuous networks and leading to suboptimal data exchange. In this paper, we propose AsyncSC, a novel asynchronous sidechain construction. It employs a committee to provide Cross-Blockchain as a Service (C-BaaS) for data exchange in multi-domain IoT. To fulfill the need for asynchronous and efficient data exchange, we combine the ideas of aggregate signatures and verifiable delay functions to devise a novel cryptographic primitive called delayed aggregate signature (DAS), which constructs asynchronous cross-chain proofs (ACPs) that ensure the security of cross-chain interactions. To ensure the consistency of asynchronous transactions, we propose a multilevel buffered transaction pool that guarantees the transaction sequencing. We analyze and prove the security of AsyncSC, simulate an asynchronous communication environment, and conduct a comprehensive evaluation. The results show that AsyncSC outperforms SOTA schemes, improving throughput by an average of 1.21 to 3.96 times, reducing transaction latency by 59.76% to 83.61%, and maintaining comparable resource overhead. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Auto-Parallel Method for Deep Learning Models Based on Genetic Algorithm

An Auto-Parallel Method for Deep Learning Models Based on Ge...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Yan Zeng ChengChuang Huang YiJie Ni ChunBao Zhou JiLin Zhang Jue Wang MingYao Zhou MeiTing Xue YunQuan Zhang School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Key Laboratory for Modeling and Simulation of Complex Systems Ministry of Education Hangzhou China Data Security Governance Zhejiang Engineering Research Center Hangzhou China School of ITMO Joint Institute Hangzhou Dianzi University Hangzhou China Institute of Computer Network Information Center of the Chinese Academy of Sciences Beijing China HuaWei State Key Laboratory of Computer Architecture Institute of Computing Technology of the Chinese Academy of Sciences Beijing China

As the size of datasets and neural network models increases, automatic parallelization methods for models have become a research hotspot in recent years. The existing auto-parallel methods based on machine learning or graph algorithms still have issues with search efficiency and applicability. This paper proposes an automatic parallel method based on a dual-population genetic algorithm, TGA, which transforms model partitioning and placement into an integer linear programming problem and constructs a cost model to evaluate the solution. The solution space is built using the neural network’s dataflow graph and device cluster’s topology, and the dual-population genetic algorithm is used to search for the optimal model parallel strategy. Experiments with various models show that the proposed method can improve single-step execution time by up to 42% compared to the Baechi method and up to 37.7% compared to the Hierarchical method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mind the Gap: Towards Generalizable Autonomous Penetration Testing via Domain Randomization and Meta-Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Zhou, Shicheng Liu, Jingju Lu, Yuliang Yang, Jiahai Zhang, Yue Chen, Jie College of Electronic Engineering National University of Defense Technology Hefei230037 China Key Laboratory of Cyberspace Security Situation Awareness and Evaluation Anhui Province Hefei230037 China Institute for Network Sciences and Cyberspace The Beijing National Research Center for Information Science and Technology Tsinghua University Beijing10084 China College of Computer Science and Technology National University of Defense Technology Changsha410073 China

With increasing numbers of vulnerabilities exposed on the internet, autonomous penetration testing (pentesting) has emerged as a promising research area. Reinforcement learning (RL) is a natural fit for studying this topic. However, two key challenges limit the applicability of RL-based autonomous pentesting in real-world scenarios: (a) training environment dilemma – training agents in simulated environments is sample-efficient while ensuring their realism remains challenging;(b) poor generalization ability – agents’ policies often perform poorly when transferred to unseen scenarios, with even slight changes potentially causing significant generalization gap. To this end, we propose GAP, a generalizable autonomous pentesting framework that aims to realizes efficient policy training in realistic environments and train generalizable agents capable of drawing inferences about other cases from one instance. GAP introduces a Real-to-Simto-Real pipeline that (a) enables end-to-end policy learning in unknown real environments while constructing realistic simulations;(b) improves agents’ generalization ability by leveraging domain randomization and meta-RL learning. Specially, we are among the first to apply domain randomization in autonomous pentesting and propose a large language model-powered domain randomization method for synthetic environment generation. We further apply meta-RL to improve agents’ generalization ability in unseen environments by leveraging synthetic environments. The combination of two methods effectively bridges the generalization gap and improves agents’ policy adaptation performance. Experiments are conducted on various vulnerable virtual machines, with results showing that GAP can enable policy learning in various realistic environments, achieve zero-shot policy transfer in similar environments, and realize rapid policy adaptation in dissimilar environments. The source code is available at https://***/Joe-zsc/GAP. Copyright © 2024, The Auth

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Domestic Violence Crisis Recognition Method based on Bi-LSTM+Attention 8

Domestic Violence Crisis Recognition Method based on Bi-LSTM...

引用

8th Annual International Conference on network and Information Systems for computers, ICNISC 2022

作者： Wang, Zhixiao Yan, Wenyao Li, Zhuochun Huang, Min Fan, Qinyuan Wang, Xin Xi'an University of Technology Xi'an China Shaanxi Key Laboratory of Network Computing and Security Xi'an China College of Xi'an Innovation Yan'an University Xi'an710100 China University of Pittsburgh PittsburghPA15260 United States Art and Design Xi'an University of Technology Xi'an710048 China Fakultät Verkehrs- und Maschinensysteme Technische Universität Berlin Berlin13353 Germany Xi'an University of Technology Computer Science and Engineering Xi'an710048 China

ISBN: (纸本)9781665453516

Domestic violence (DV) is getting more and more attention due to the critical trouble and danger that pose great challenge to human rights and health. The popularity of various social medias can help these victims to share their experiences and obtain more possible support from numerous open communities. However, it is not only inefficient but also laborious and time-consuming to manually access and browse through a great deal of available posts on the Internet and social media space. Therefore, considering the advantages of Deep Learning (DL) technology in Natural Language Processing, adopting DL as an efficient strategy for automatic recognition and evaluation of DV victims is in the urgent requirements. This paper takes social media Facebook posts about domestic violence as the research object and uses Word2Vec to build word vector model. The paper uses Bi-LSTM+self-Attention deep learning models to accomplish DV crisis recognition task and compares it with CNN, RNN and LSTM. The assessment of experimental results show that the accuracy of CNN and LSTM are both above 90% which is better than RNN;And the accuracy of Bi-LSTM is the highest after using the Attention mechanism. The research results of this article will provide reference and help for public DVCS to rescue DV victims. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Robust Dynamic Broadcasting for Multi-Hop Wireless networks Under Time-Varying Connectivity and Dynamic SINR

引用

IEEE Transactions on Mobile Computing 2025年

作者： Tian, Xiang Yu, Jiguo Luo, Chuanwen Yu, Dongxiao Wang, Guijuan Feng, Bin Jinan250353 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Industrial Network and Information System Security Jinan250353 China University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu610054 China Qilu University of Technology Big Data Institute Jinan250353 China Beijing Forestry University School of Information Science and Technology Beijing100083 China Shandong University School of Computer Science and Technology Shandong Qingdao266237 China Taishan University School of Information Science and Technology 271000 China

Throughput-optimal dynamic broadcasting is an essential cornerstone for the efficient operation of Multi-hop Wireless networks (MWNs). Most existing algorithms for this problem were developed assuming static interference environments and network connectivity. However, wireless interference environments and network connectivity are inherently time-varying in real-world scenarios, primarily due to uncontrollable interference sources and unreliable links. Such time-varying characteristics make these existing algorithms less robust. In this paper, we study the robust throughput-optimal dynamic broadcasting for MWNs with multi-dimensional time-varying characteristics in terms of interference environments, network connectivity, and data arrival. We model the time-varying link existence states using a random process and characterize the time-varying interference environments through a dynamic variant of the classical Signal-to-Interference-plus-Noise-Ratio (SINR) model. In this variant, the SINR model parameters are dynamically adjusted over time by an adversary. Based on this, we first design a Robust Throughput-optimal Dynamic Broadcast (RTDB) algorithm which makes efficient slot-based max-weight link scheduling, power allocation, and data forwarding decisions in each time slot. We then prove its throughput-optimality in time-varying acyclic directed MWNs under the dynamic SINR model. The effectiveness of RTDB is validated via numerous simulations. © 2002-2012 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural networks

arXiv

引用

arXiv 2025年

作者： Dong, Xuewen Li, Jiachen Li, Shujun You, Zhichao Qu, Qiang Kholodov, Yaroslav Shen, Yulong School of Computer Science and Technology Xidian University The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education China The Shaanxi Key Laboratory of Blockchain and Secure Computing Xi’an710071 China University of Kent CanterburyCT2 7NP United Kingdom Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Intelligent Transportation Systems Lab Innopolis University Innopolis Russia School of Computer Science and Technology Xidian University China The Shaanxi Key Laboratory of Network and System Security Xi’an710071 China

Recent studies show that graph neural networks (GNNs) are vulnerable to backdoor attacks. Existing backdoor attacks against GNNs use fixed-pattern triggers and lack reasonable trigger constraints, overlooking individual graph characteristics and rendering insufficient evasiveness. To tackle the above issues, we propose ABARC, the first Adaptive Backdoor Attack with Reasonable Constraints, applying to both graph-level and node-level tasks in GNNs. For graph-level tasks, we propose a subgraph backdoor attack independent of the graph’s topology. It dynamically selects trigger nodes for each target graph and modifies node features with constraints based on graph similarity, feature range, and feature type. For node-level tasks, our attack begins with an analysis of node features, followed by selecting and modifying trigger features, which are then constrained by node similarity, feature range, and feature type. Furthermore, an adaptive edge-pruning mechanism is designed to reduce the impact of neighbors on target nodes, ensuring a high attack success rate (ASR). Experimental results show that even with reasonable constraints for attack evasiveness, our attack achieves a high ASR while incurring a marginal clean accuracy drop (CAD). When combined with the state-of-the-art defense randomized smoothing (RS) method, our attack maintains an ASR over 94%, surpassing existing attacks by more than 7%. Copyright © 2025, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Stochastic-Robust Planning of networked Hydrogen-Electrical Microgrids: A Study on Induced Refueling Demand

arXiv

引用

arXiv 2024年

作者： Sun, Xunhang Cao, Xiaoyu Zeng, Bo Zhai, Qiaozhu Başar, Tamer Guan, Xiaohong School of Automation Science and Engineering The Ministry of Education Key Laboratory for Intelligent Networks and Network Security Xi’an Jiaotong University Shaanxi Xi’an710049 China Coordinated Science Laboratory University of Illinois Urbana-Champaign UrbanaIL61801 United States Smart Integrated Energy Department Sichuan Digital Economy Industry Development Research Institute Sichuan Chengdu610037 China Department of Industrial Engineering The Department of Electrical and Computer Engineering University of Pittsburgh PittsburghPA15106 United States Center for Intelligent and Networked Systems Department of Automation Tsinghua University Beijing100084 China

Hydrogen-electrical microgrids are increasingly assuming an important role on the pathway toward decarbonization of energy and transportation systems. This paper studies networked hydrogen-electrical microgrids planning (NHEMP), considering a critical but often-overlooked issue, i.e., the demand-inducing effect (DIE) associated with infrastructure development decisions. Specifically, higher refueling capacities will attract more refueling demand of hydrogen-powered vehicles (HVs). To capture such interactions between investment decisions and induced refueling demand, we introduce a decision-dependent uncertainty (DDU) set and build a trilevel stochastic-robust formulation. The upper-level determines optimal investment strategies for hydrogen-electrical microgrids, the lower-level optimizes the risk-aware operation schedules across a series of stochastic scenarios, and, for each scenario, the middle-level identifies the "worst" situation of refueling demand within an individual DDU set to ensure economic feasibility. Then, an adaptive and exact decomposition algorithm, based on Parametric Column-and-Constraint Generation (PC&CG), is customized and developed to address the computational challenge and to quantitatively analyze the impact of DIE. Case studies on an IEEE exemplary system validate the effectiveness of the proposed NHEMP model and the PC&CG algorithm. It is worth highlighting that DIE can make an important contribution to the economic benefits of NHEMP, yet its significance will gradually decrease when the main bottleneck transits to other system restrictions. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

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：