检索结果-内蒙古大学图书馆

A cloud-based framework for verifiable privacy-preserving spectrum auction

High-Confidence Computing 2022年第1期2卷 47-53页

作者： Ruinian Li Tianyi Song Bo Mei Chunqiang Hu Wei Li Maya Larson Xiuzhen Cheng Rongfang Bie Department of Computer Science Bowling Green State UniversityBowling GreenOhioUSA Department of Computer Science Texas Christian UniversityTexasUSA Department of Software Engineering Chongqing UniversityChongqingChina Department of Computer Science Georgia State UniveristyAtlantaUSA Department of Computer Science the George Washington UniversityWashington DCUSA School of Computer Science and Technology Shandong UniversityQingdaoChina School of Information Science and Technology Beijing Normal UniversityBeijingChina

Spectrum auction is one of the most effective ways to achieve dynamic spectrum allocation in cognitive radio net-works,and it provides one effective way to manage the spectrum demands of IoT devices with limited *** spectrum auctions focus on protecting bidder privacy and achieving excellent social efficiency,but few tackles the verification of auction results that are controlled by the *** this paper,we propose a cloud-based framework for verifiable privacy-preserving spectrum *** framework adopts a modified AFGH re-encryption algorithm that achieves both bid privacy protection and auction results verification at the same *** cloud server helps to compute auction results based on homomorphic encryption,and an auctioneer decrypts the encrypted data from the server to obtain auction ***,the property of re-encryption makes it possible for any bidder to verify the auction results without compromising other bidders’privacy.

关键词： Homomorphic encryption Re-encryption Spectrum auction Privacy-preservation auction

来源：评论

学校读者我要写书评

暂无评论

A Novel Redundant Service Caching and Task Offloading Method in Mobile Edge Computing 31st

A Novel Redundant Service Caching and Task Offloading Metho...

引用

31st International Conference on Web Services, ICWS 2024, Held as Part of the Services Conference Federation, SCF 2024

作者： Ouyang, Zhaobin Xia, Yunni Li, Jingpeng Feng, Jiafeng Yu, Yang Zhang, Ke Xu, Xifeng Ma, Yong Chen, Peng Li, Xiaobo School of Computer Chongqing University Chongqing400030 China China Huadian Corporation Guangdong Branch Guangdong China Nanjing Nanzi Huadun Digital Technology Co. Ltd. Nanjing China School of Computer Science and Technology Beijing Institute of Technology Beijing100083 China School of Computer and Information Engineering Jiangxi Normal University Nanchang330000 China School of Computer and Software Engineering Xihua University Chengdu China Chongqing Animal Husbandry Techniques Extension Center Chongqing China

ISBN: (纸本)9783031770715

Edge caching is a promising technologies, which enhances content delivery and reduces service latency by caching potentially interested content and services on edge nodes near users. Due to constraints such as limited edge server capacities and unstable communications in a highly dynamic MEC environment, caching and content delivery are prone to failures and inconsistencies. Consequently, redundant caching mechanisms are in high need as counter measures in this paper, we proposes a novel redundant service caching and task offloading Decision (FT-STD) method. Specifically, we utilize the primary backup (PB) approach for offloading fault tolerance and employ a learning-based algorithm for yielding redundant service caching schedules in MEC. Simulation results demonstrate thatclearly outperforms its peers across multiple performance metrics. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Authentication Scheme Based on Non-Interactive Zero-Knowledge Proof for Mobile Health 24

Authentication Scheme Based on Non-Interactive Zero-Knowledg...

引用

24th IEEE International Conference on High Performance Computing and Communications, 8th IEEE International Conference on Data science and Systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Acheampong, Edward Mensah Zhou, Shijie Liao, Yongjian Antwi-Boasiako, Emmanuel Obiri, Isaac Amankona School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China School of Computer Science University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9798350319934

Digital technologies, such as wireless body area networks (WBANs) for mobile health (mHealth) applications, are expected to enhance the quality of the public health care system. Although mHealth can improve patients' quality of health by offering outpatient real-time health monitoring systems instead of being stuck in the hospital all the time to monitor chronic diseases. The major challenge in adopting mHealth is data security and privacy. The health data routed on the internet from the patient monitoring device to the health center for remote monitoring is vulnerable to confidentiality attacks. To handle this issue, we present an authentication scheme based on non-interactive zero-knowledge proof (NIZKP), which issues certificates and authenticates monitoring devices each time performing transactions without revealing sensitive information. Our authentication scheme provides a high level of security with a low computational cost, which is lightweight for WBANs. © 2022 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

SMART: Towards Pre-trained Missing-Aware Model for Patient Health Status Prediction 38

SMART: Towards Pre-trained Missing-Aware Model for Patient H...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Yu, Zhihao Chu, Xu Jin, Yujie Wang, Yasha Zhao, Junfeng School of Computer Science Peking University China Center on Frontiers of Computing Studies Peking University Beijing China National Research and Engineering Center of Software Engineering Peking University China Key Laboratory of High Confidence Software Technologies Ministry of Education Beijing China China Nanhu Laboratory Jiaxing China

Electronic health record (EHR) data has emerged as a valuable resource for analyzing patient health status. However, the prevalence of missing data in EHR poses significant challenges to existing methods, leading to spurious correlations and suboptimal predictions. While various imputation techniques have been developed to address this issue, they often obsess difficult-to-interpolate details and may introduce additional noise when making clinical predictions. To tackle this problem, we propose SMART, a Self-Supervised Missing-Aware RepresenTation Learning approach for patient health status prediction, which encodes missing information via missing-aware temporal and variable attentions and learns to impute missing values through a novel self-supervised pre-training approach which reconstructs missing data representations in the latent space rather than in input space as usual. By adopting elaborated attentions and focusing on learning higher-order representations, SMART promotes better generalization and robustness to missing data. We validate the effectiveness of SMART through extensive experiments on six EHR tasks, demonstrating its superiority over state-of-the-art methods. Our code is available at https://***/yzhHoward/SMART. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New End-to-End Image Contrastive Clustering Based on Mining Latent Positive Samples

A New End-to-End Image Contrastive Clustering Based on Minin...

引用

Machine Learning and Natural Language Processing (MLNLP), International Conference on

作者： Bo Feng Xi Yan Li Yan Bing Luo Zheng Pei School of science Xihua University Chengdu China School of Computer Science and Software Engineering Xihua University Chengdu China

ISBN: (数字)9798350354973

ISBN: (纸本)9798350354980

The integration of the contrastive learning paradigm into deep clustering has led to enhanced performance in image clustering. However, in existing researches, the samples in the class of the target may be still treated as negative samples, this means that more semantic sample pairs cannot be constructed and the intra-class compactness may be compromised. In this paper, we propose a new contrastive clustering method based on mining latent positive samples (CCLPS), which utilizes the nearest neighbor relationship between samples to mine semantic positive samples in the same class. In more detail, by mining latent positive samples in both the feature and cluster spaces, CCLPS can obtain more cluster-friendly feature representation of samples to enhance clustering performance. Samples mined from the feature space fuel the cluster-level contrastive learning task, while samples mined from the cluster space fuel the instance-level task. Three image datasets CIFAR-10, CIFAR-100 and Tiny-ImageNet are employed to experimentally demonstrate usefulness and effectiveness of the proposed method in image clustering, and transfer learning based on mining latent positive samples is also discussed and comparisons are made with 19 representative clustering methods on the datasets. Experimental results indicate that the proposed method can serve as a pre-training model for transfer learning and exhibits commendable feature modeling capabilities.

关键词： Training Clustering methods Transfer learning Semantics Contrastive learning Benchmark testing Natural language processing Fuels Standards

来源：评论

学校读者我要写书评

暂无评论

LOPE: A Low-Overhead Payment Verification Method for Blockchains

引用

Chinese Journal of Electronics 2021年第2期30卷 349-358页

作者： ZHANG Ying HE Zhengyuan JIA Linpeng DING Donghui ZHANG Hanwen SUN Yi School of Software Engineering Tongji University Blockchain Lab Institute of Computing Technology Chinese Academy of Sciences School of Computer Science and Technology University of Chinese Academy of Sciences

With its characteristics of decentralization,security, data traceability, and tamper-resistance, the blockchain has been widely used in various *** the difference in the performance of the devices, the light client is proposed so that devices without the ability to store a full blockchain copy can also participate in the blockchain transactions. However,the light client has to communicate with full nodes and verify the authenticity of a transaction which brings in some extent of communication, computation, and storage overheads to the light client. These overheads cannot be ignored for some low-performance devices, such as embedded devices or Io T chips, and therefore the current light client scheme does not work in this situation. We propose LOPE(a Low-overhead payment v Erification method) for poor-capacity nodes in the blockchain *** LOPE, a grouping protocol is designed to partition full nodes into groups to serve the verification requests of the light client. In addition, Practical byzantine fault tolerance(PBFT) is used to ensure the light client to get a credible result in spite of a few dishonest nodes existing in the group. We conduct LOPE and evaluate it in a testbed. The experiment results show that LOPE reduces more than half of the communication overhead, degrades the computation overhead of the light client to a large extent, and avoids the storage overhead of the hash roots of block headers in the light client. We also conduct theoretical analysis to show the performance improvement and security issues of LOPE.

关键词： current light client scheme storage overhead blockchains Low-overhead payment vErification method peer-to-peer computing software fault tolerance electronic money data integrity LOPE low-performance devices cryptographic protocols fault tolerance blockchain transactions

来源：评论

学校读者我要写书评

暂无评论

Identification of Switched Gated Recurrent Neural Networks Using the EM Algorithm 5

Identification of Switched Gated Recurrent Neural Networks U...

引用

5th International Conference on Data-Driven Optimization of Complex Systems, DOCS 2023

作者： Bai, Wentao Gu, Suhang Yan, Chao Zhang, Haoyu Jiang, Chunli Guo, Fan School of Computer Science and Engineering Changshu Institute of Technology Changshu China School of Electrical Engineering and Automation Changshu Institute of Technology Changshu China School of Information Science and Technology Hangzhou Normal University Hangzhou China School of Software Engineering Chongqing University of Posts and Telecommunications Chongqing China School of Automation Nanjing Institute of Technology Nanjing China

ISBN: (纸本)9798350393521

In the domain of nonlinear hybrid dynamic system modeling, the effectiveness of switched autoregressive exogenous (SARX) systems may face certain restrictions. To address this issue, this paper presents an enhanced switched system framework. In this framework, all SARX subsystems are replaced with gated recurrent neural networks, aiming to overcome these limitations. Importantly, the proposed switched system does not rely on any prior assumptions about the knowledge of operating modes. Finally, a new identification method is proposed based on the expectation-maximization (EM) algorithm, and its effectiveness is validated through a simulation example. © 2023 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

TPMARL-MSS Thought-Perception Multi-Agent Reinforcement Learning Meeting Scheduling System 25

TPMARL-MSS Thought-Perception Multi-Agent Reinforcement Lear...

引用

25th IEEE International Conferences on High Performance Computing and Communications, 9th International Conference on Data science and Systems, 21st IEEE International Conference on Smart City and 9th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC/DSS/SmartCity/DependSys 2023

作者： Zhang, Jinsong Mao, Xiaoxuan Li, Lu Wu, Hanqian Joint Graduate School Southeast University Nanjing China College of Software Engineering Southeast University Nanjing China School of Cyber Science and Engineering Southeast University Nanjing China School of Cyber Science and Engineering Southeast University Key Laboratory of Computer Network and Information Integration of Ministry of Education Nanjing China

ISBN: (纸本)9798350330014

In today's evolving society, the increasing complexity and frequency of meetings necessitate advanced scheduling systems. Traditional methods are constrained by rigid prede-fined strategies, lack intelligent negotiation mechanisms, and often compromise user privacy. Addressing these challenges, we introduce the Thought-Perception Multi-Agent Reinforcement Learning Meeting Scheduling System (TPMARL-MSS). Unlike conventional systems, TPMARL-MSS autonomously learns and refines its strategies through continuous feedback. It features automated negotiation and adaptive decision-making, offering a more nuanced scheduling approach. Importantly, our Thought-Perception module protect privacy, allowing the agent to deduce preferences from participant behavior without revealing personal data. Evaluations on the real-world dataset shows that TPMARL-MSS surpasses traditional methods in efficiency and schedule quality, highlighting its practical applicability. © 2023 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Activation Space Selectable Kolmogorov-Arnold Networks

arXiv

引用

arXiv 2024年

作者： Yang, Zhuoqin Zhang, Jiansong Luo, Xiaoling Lu, Zheng Shen, Linlin School of Computer Science University of Nottingham Ningbo China Ningbo China School of Computer Science & Software Engineering Shenzhen University Shenzhen China

The multilayer perceptron (MLP), a fundamental paradigm in current artificial intelligence, is widely applied in fields such as computer vision and natural language processing. However, the recently proposed Kolmogorov-Arnold Network (KAN), based on nonlinear additive connections, has been proven to achieve performance comparable to MLPs with significantly fewer parameters. Despite this potential, the use of a single activation function space results in reduced performance of KAN and related works across different tasks. To address this issue, we propose an activation space Selectable KAN (S-KAN). S-KAN employs an adaptive strategy to choose the possible activation mode for data at each feedforward KAN node. Our approach outperforms baseline methods in seven representative function fitting tasks and significantly surpasses MLP methods with the same level of parameters. Furthermore, we extend the structure of S-KAN and propose an activation space selectable Convolutional KAN (S-ConvKAN), which achieves leading results on four general image classification datasets. Our method mitigates the performance variability of the original KAN across different tasks and demonstrates through extensive experiments that feedforward KANs with selectable activations can achieve or even exceed the performance of MLP-based methods. This work contributes to the understanding of the data-centric design of new AI paradigms and provides a foundational reference for innovations in KAN-based network architectures. Copyright © 2024, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Multi-hypergraph Neural Network with Fusion of Location Information for Session-based Recommendation

引用

IAENG International Journal of Applied Mathematics 2023年第4期53卷 1页

作者： Li, Ziang Wu, Jie Han, Guojing Ma, Chi Chen, Yuenai School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China Anshan Meteorological Service Anshan114001 China School of Computer Science and Engineering Huizhou University Huizhou516007 China School of Computer Science and Engineering Huizhou University Huizhou516007 China

Session recommendation is a technology that processes data referring to the user-anonymous session behavior analysis. This technique has a wide range of applications in e-commerce, videos, social networks, and other fields and it is a hot topic in current recommendation system research. Multi-hypergraph neural network with fusion of location information for session-based recommendation (MHGNN-LI) captures multi-dimensional interest features in the session through the multi-hypergraph representation and combines different contrastive learning methods to alleviate the problem of data sparsity. It also considers the dependence order of the recommended items to improve the recommendation effect. Concerning the methodology of work, the model first constructs a session hypergraph to obtain the interest features of multiple items in the session. Secondly, it decouples the interest features into global and local features within the session, and then it integrates the item features with location information into the local interest features. Finally, it introduces a line graph at the feature level between the different sessions and maximizes the mutual information between sessions and within them, through contrastive learning, to enhance the expression ability of session data. As for the validation, comparative experiments, with related models on two public datasets, Tmall and Diginetica, show that the MHGNN-LI model has improved on P@10 and MRR@10 by, at least, 15.47% and 20.51%, as well as 9.77% and 12.37% on the Tmall and Diginetica datasets, respectively. © (2023), (International Association of Engineers). All Rights Reserved.

关键词： Location

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：