检索结果-内蒙古大学图书馆

A New Collaborative Scheduling Mechanism Based on Grading Mapping for Resource Balance in Distributed Object Cloud Storage System 16th

A New Collaborative Scheduling Mechanism Based on Grading Ma...

引用

16th EAI International Conference on Collaborative Computing: networking, Applications, and Worksharing, CollaborateCom 2020

作者： Lu, Yu Chen, Ningjiang Pu, Wenjuan Wang, Ruifeng School of Computer and Electronic Information Guangxi University Nanning530004 China Guangxi Key Laboratory of Multimedia Communications and Network Technology Nanning530004 China

ISBN: (纸本)9783030675394

An algorithmic mapping of storage locations brings high storage efficiency to the storage system, but the loss of efficient scheduling makes systems prone to crashing at low usage. This paper uses the Ceph storage system as a research sample to analyze these issues and proposes a grading mapping adaptive storage resource collaborative optimization mechanism. This approach grading both the storage device and the storage content, and introduced random factors and influence factors as two-factors to quantify the grading mapping relationship between the two of them. This relation coordinates the storage systems’ performance and reliability. In addition, a collaborative storage algorithm is proposed to realize balanced storage efficiency and control data migration. The experimental results show that in comparison with the inherent mechanism in the traditional Ceph system, the proposed cooperative storage adaptation mechanism for data balancing has increased the average system usage by 17% and reduces data migration by 50% compared to the traditional research approach. © 2021, ICST Institute for computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Task allocation based on profit maximization for mobile crowdsourcing

引用

The Journal of China Universities of Posts and Telecommunications 2020年第1期27卷 26-37页

作者： Hou Yinglin Cheng Weiqing School of Computer Science Nanjing University of Posts and TelecommunicationsNanjing 210023China Key Laboratory of Computer Network and Information Integration Southeast UniversityNanjing 211189China

In recent years, with the development of smart devices, mobile users can use them to sense the environment. In order to improve the data quality and achieve maximum profits, incentive mechanism is needed to motivate users to participate. In this paper, reputation mechanism, participant selection, task allocation and joint pricing in mobile crowdsourcing system are studied. A user reputation evaluation method is proposed, and a participant selection algorithm(PSA) based on user reputation is proposed. Besides, a social welfare maximization algorithm(SWMA) is proposed, which achieves task pricing with maximizing the interests of all parties, including both task publishers and mobile users. The social welfare maximization problem is divided into local optimization sub-problems which can be solved by double decomposition. It is proved that the algorithm converges to the optimal solution. Results of simulations verify that algorithms PSA and SWMA are effective.

关键词： mobile crowdsourcing maximum profits reputation mechanism task allocation

来源：评论

学校读者我要写书评

暂无评论

SFTA: Spiking Neural networks Vulnerable to Spiking Feature Transferable Attack

SFTA: Spiking Neural Networks Vulnerable to Spiking Feature ...

引用

IEEE International Symposium on Parallel and Distributed Processing with Applications and IEEE International Conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Xuanwei Lin Chen Dong Ximeng Liu College of Computer and Data Science Fuzhou University Fujian Key Laboratory of Network Computing and Intelligent Information Processing (Fuzhou University) Key Lab of Information Security of Network Systems (Fuzhou University)

Many recent works have shown that spiking neural networks (SNNs) are vulnerable to well-crafted adversarial attacks in the white-box setting, which may lead to misclassification of the trained model. However, the information about the model is in a black-box setting and is usually unknown to the attacker, e.g., the parameters and structure of the model. So it is more challenging to counter the attack in the black-box setting, and there is still little research on this aspect in SNNs. Therefore, this work describes a transfer-based black box adversarial attack against spike feature space representations, providing insights for robust spike features in SNNs models. The attack is explicitly designed to be transferable, and more robust feature gradients are obtained by accumulating the feature gradients of the intermediate layers. Then we can successfully attack the black-box model by suppressing robust positive features and enhancing negative features. Extensive experimental evaluation demonstrates the proposed method’s effectiveness and superior performance on static and neuromorphic datasets. i.e., The attack success is 89.72% and 90% on the static MNIST and CIFAR10 datasets, and 85.97% and 69.09% on the neuromorphic N-MNIST and CIFARO-DVS datasets.

关键词： Correlation Neuromorphics Neural networks Closed box Ubiquitous computing Optimization Glass box

来源：评论

学校读者我要写书评

暂无评论

A High-Dimensional Temporal Data Publishing Method Based on Dynamic Bayesian networks and Differential Privacy

A High-Dimensional Temporal Data Publishing Method Based on ...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Yaxin Wang Zhen Zhang Heng Qian Yongchao Gao Qiuyue Wang 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

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Massive high-dimensional data generated by the Internet typically contains sensitive privacy information. Protecting data privacy while maintaining utility has become a pressing challenge. We propose a novel high-dimensional temporal data publishing method leveraging dynamic Bayesian networks and differential privacy. Initially, a dynamic Bayesian network is constructed, utilizing mutual information filtering of data. Subsequently, we calculate the Coherent Neighborhood Propinquity for each node within the network to determine edge sensitivity and establish a privacy budget. Noise is then strategically added to attribute data in accordance with the sensitivity and privacy budget requirements, ensuring the dataset complies with ε-differential privacy standards. Experimental results demonstrate that the data availability performance of the SMAP dataset (Soil Moisture Active Passive) surpasses that of competing algorithms while providing an equivalent level of privacy protection. Hence, our method significantly enhances data availability without compromising differential privacy protection.

关键词： Differential privacy Privacy Sensitivity Publishing Time series analysis Dynamic scheduling Bayes methods

来源：评论

学校读者我要写书评

暂无评论

ESNet: evolution and succession network for high-resolution salient object detection 24

ESNet: evolution and succession network for high-resolution ...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Hongyu Liu Runmin Cong Hua Li Qianqian Xu Qingming Huang Wei Zhang Institute of Information Science Beijing Jiaotong University & Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing China School of Control Science and Engineering Shandong University & Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Computer Science and Technology Hainan University Hainan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Preserving details and avoiding high computational costs are the two main challenges for the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two-stage HRSOD model from the perspective of evolution and succession, including an evolution stage with Low-resolution Location Model (LrLM) and a succession stage with High-resolution Refinement Model (HrRM). The evolution stage achieves detail-preserving salient objects localization on the low-resolution image through the evolution mechanisms on supervision and feature; the succession stage utilizes the shallow high-resolution features to complement and enhance the features inherited from the first stage in a lightweight manner and generate the final high-resolution saliency prediction. Besides, a new metric named Boundary-Detail-aware Mean Absolute Error (MAEBD) is designed to evaluate the ability to detect details in high-resolution scenes. Extensive experiments on five datasets demonstrate that our network achieves superior performance at real-time speed (49 FPS) compared to state-of-the-art methods. Our code is publicly available at: https://***/rmcong/ESNet_ICML24.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DW-MLSR: Unsupervised Deformable Medical Image Registration Based on Dual-Window Attention and Multi-Latent Space

SSRN

引用

SSRN 2024年

作者： Huang, YuXuan Yin, MengXiao Zhong, Cheng Li, ZhiPan Yang, Feng School of Computer and Electronic Information Guangxi University Nanning530004 China Guangxi Key Laboratory of Multimedia Communications Network Technology Guangxi University Guangxi Nanning530004 China Key Laboratory of Parallel Distributed and Intelligent Computing of Guangxi Universities and Colleges Nanning530004 China

Thanks to the emergence of transformers and Vision Transformer (VIT), attention mechanisms have also been applied to medical image registration. However, the current attention mechanisms in medical image registration suffer from incomplete information interaction. Common unsupervised registration methods may be constrained by the imperfect medical image data with uncertainty and noise, leading to unstable registration results susceptible to *** address these evident drawbacks, this paper proposes a novel medical image registration method, namely, Registration Based on Dual-Window Attention and Multi-Latent Space(DW-MLSR). The Dual-Window attention mechanism introduced in this paper enables the model to comprehensively focus on crucial local regions in the image, thereby improving registration accuracy and robustness. Meanwhile, MLS, employed as a data augmentation method, enhances the model's generalization ability and robustness by learning latent image representations, providing richer image *** results demonstrate the superiority of the proposed medical image registration method over mainstream registration models. Comparative experiments indicate that our approach holds significant application potential in the field of medical image registration. © 2024, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Multi-Signal Fusion of Social Diffusion Graph with Bi-Directional Semantic Consistency

Multi-Signal Fusion of Social Diffusion Graph with Bi-Direct...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Huacheng Li Chunhe Xia Tianbo Wang Wanshuang Lin Changnan Jiang Chen Chen Yuan Zhao Key Laboratory of Beijing Network Technology Beihang University Guangxi Collaborative Innovation Center of Multi-Source Information Integration and Intelligent Processing Guangxi Normal University School of Cyber Science and Technology Beihang University Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai

Devising diffusion graph to learn user representations is a crucial step in studying information propagation prediction. However, previous works mainly focused on structural and temporal features. To better incorporate content features, we introduce the Backward Decomposition and Forward Preservation mechanisms. The former involves decomposing content features for initializing node signals in the diffusion graph, thus fusing user features with content features. The latter aims to maintain node features generated by graph encoder consistent with the original content features. A series of experiments demonstrate that our model outperforms state-of-the-art models, and both mechanisms significantly enhance the prediction performance. Furthermore, our methods enables the features generated by the diffusion graph to more effectively incorporate features from various semantic spaces, whether encoded by language models or generated by graph embedding algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition

arXiv

引用

arXiv 2024年

作者： Zhou, Zi-Hao Fang, Siyuan Zhou, Zi-Jing Wei, Tong Wan, Yuanyu Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China Xiaomi Inc. China School of Software Technology Zhejiang University Ningbo China

Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-art LTSSL approaches heavily rely on high-quality pseudo-labels for large-scale unlabeled data. However, these methods often neglect the impact of representations learned by the neural network and struggle with real-world unlabeled data, which typically follows a different distribution than labeled data. This paper introduces a novel probabilistic framework that unifies various recent proposals in long-tail learning. Our framework derives the class-balanced contrastive loss through Gaussian kernel density estimation. We introduce a continuous contrastive learning method, CCL, extending our framework to unlabeled data using reliable and smoothed pseudo-labels. By progressively estimating the underlying label distribution and optimizing its alignment with model predictions, we tackle the diverse distribution of unlabeled data in real-world scenarios. Extensive experiments across multiple datasets with varying unlabeled data distributions demonstrate that CCL consistently outperforms prior state-of-the-art methods, achieving over 4% improvement on the ImageNet-127 dataset. Our source code is available at https://***/zhouzihao11/CCL. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Establishing Multi-Party Trust Architecture for DRM by Using Game-Theoretic Analysis of Security Policies

引用

Chinese Journal of Electronics 2023年第3期18卷 519-524页

作者： Zhiyong Zhang Qingqi Pei Jianfeng Ma Lin Yang Ministry of Education Key Laboratory of Computer Network and Information Security Xidian University Xi'an China Electronic and Information Engineering College Henan University of Science and Technology Luoyang China The Research Institute China Electronic Equipment and Systems Engineering Corporation Beijing China

A successful transaction of digital contents is primarily dependent on security policies, trust mechanisms and benefits balances, as well as the simple adoption of the combination of enhanced security policies would not effectively establish a trust relationship among various stakeholders in the DRM (Digital rights management)-enabling contents value chain. With respect to a generic DRM ecosystem, the hierarchy analyses of the multi-participant trust architecture were proposed based on the game-theoretic adoptions of security policies. By using formalized definitions of security components and services' utilities, we presented the choice of policies with the external relativity, in the contents acquisition scenario, as a multi-player simultaneous-move game referred to contents provider, digital services/rights provider and consumer. Also, in term of security policies combinations' utilities and benefit effects on participants, we further gained the game's Nash Equilibrium, which is a stable profile of security policies achieving the optimal balance of the security and utilities, thus establishing and strengthening the multi-party trust. The analytic conclusions show that enhanced security policies profile does not necessarily achieve optimal benefits balance in the one-stage game, for a small quantity of digital contents transactions. Whereas, the profile could transform into Nash Equilibrium with the increase of transaction sessions, meanwhile being Pareto Optimality.

关键词： Ecosystems Games computer architecture Transforms Copyright protection Nash equilibrium Security

来源：评论

学校读者我要写书评

暂无评论

Symbiosis Rather Than Aggregation: Towards Generalized Federated Learning via Model Symbiosis

引用

IEEE Internet of Things Journal 2025年

作者： Liu, Yuange Liu, Yuru Zhang, Weishan Zheng, Chaoqun Jiang, Wei Luo, Daobin Qiao, Qiao Meng, Lingzhao Zhao, Hongwei Yang, Su College of Computer Science and Technology Qingdao266580 China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Jinan250014 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan250014 China Information Science Academy of China Electronics Technology Group Corporation Beijing100036 China Fudan University School of Computer Science Shanghai200433 China

Federated Learning (FL) faces significant challenges in scenarios with non-IID (non-independent and identically distributed) data distributions across participating clients. Traditional aggregation-based approaches often struggle with the inherent misalignment between local and global optimization objectives, leadingwhich leads to gradient divergence and suboptimal generalization performance. This paper proposes a novel FL framework that replaces conventional aggregation with a biologically inspired model symbiosis approach called FedSym, which employs a dual-level symbiotic mechanism. Ectosymbiosis performs coarse-grained hierarchical parameter recombinations through random layer-wise model combination, while endosymbiosis enables fine-grained intra-layer parameter fusion through weighted averaging, collectively steering model updates towards flatter loss landscapes. Our theoretical analysis demonstrates that FedSym's convergence rate is O(1T) under non-IID conditions, which matches the convergence properties of FedAvg. Extensive experimentsevaluations across multiple datasets and model architectures show that FedSym achieves substantial improvements over state-of-the-art FL methods, particularly in challenging scenarios with high data heterogeneity, and demonstrates robust performance across varying numbers of participating clients and federation scales. © 2014 IEEE.

关键词： Federated learning

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：