检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhai, Yunpeng Peng, Peixi Jia, Mengxi Li, Shiyong Chen, Weiqiang Gao, Xuesong Tian, Yonghong National Engineering Research Center of Visual Technology School of Computer Science Peking University China School of Electronic and Computer Engineering Peking University Shenzhen Graduate School China Peng Cheng Laboratory China AI Application Research Center Huawei Technologies Co. Ltd China State Key Laboratory of Digital Multimedia Technology Hisense Qingdao China

Unsupervised person re-identification has achieved great success through the self-improvement of individual neural networks. However, limited by the lack of diversity of discriminant information, a single network has difficulty learning sufficient discrimination ability by itself under unsupervised conditions. To address this limit, we develop a population-based evolutionary gaming (PEG) framework in which a population of diverse neural networks are trained concurrently through selection, reproduction, mutation, and population mutual learning iteratively. Specifically, the selection of networks to preserve is modeled as a cooperative game and solved by the best-response dynamics, then the reproduction and mutation are implemented by cloning and fluctuating hyper-parameters of networks to learn more diversity, and population mutual learning improves the discrimination of networks by knowledge distillation from each other within the population. In addition, we propose a cross-reference scatter (CRS) to approximately evaluate re-ID models without labeled samples and adopt it as the criterion of network selection in PEG. CRS measures a model's performance by indirectly estimating the accuracy of its predicted pseudo-labels according to the cohesion and separation of the feature space. Extensive experiments demonstrate that (1) CRS approximately measures the performance of models without labeled samples;(2) and PEG produces new state-of-the-art accuracy for person re-identification, indicating the great potential of population-based network cooperative training for unsupervised learning. © 2023, CC BY.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

An ADRC-Incorporated Stochastic Gradient Descent Algorithm for Latent Factor Analysis

arXiv

引用

arXiv 2024年

作者： Li, Jinli Yuan, Ye The School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China The Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China The College of Computer and Information Science Southwest University Chongqing400715 China

High-dimensional and incomplete (HDI) matrix contains many complex interactions between numerous nodes. A stochastic gradient descent (SGD)-based latent factor analysis (LFA) model is remarkably effective in extracting valuable information from an HDI matrix. However, such a model commonly encounters the problem of slow convergence because a standard SGD algorithm only considers the current learning error to compute the stochastic gradient without considering the historical and future state of the learning error. To address this critical issue, this paper innovatively proposes an ADRC-incorporated SGD (ADS) algorithm by refining the instance learning error by considering the historical and future state by following the principle of an ADRC controller. With it, an ADS-based LFA model is further achieved for fast and accurate latent factor analysis on an HDI matrix. Empirical studies on two HDI datasets demonstrate that the proposed model outperforms the state-of-the-art LFA models in terms of computational efficiency and accuracy for predicting the missing data of an HDI matrix. 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

A Method of Constructing and Automatically Labeling Radio Frequency Signal Training Dataset for UAV

A Method of Constructing and Automatically Labeling Radio Fr...

引用

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

作者： Chao Liu Ruipeng Ma Zheng Si Mingmin Chi School of Computer Science Shanghai Key Laboratory of Data Science Fudan University Zhengzhou Zhongke Institute of Integrated Circuit and System Application School of Cyber Science and Engineering Zhengzhou University Henan Institute of Advanced Technology Zhengzhou University

The problem of signal detection and classification of multiple UAVs can be solved using object detection techniques in computer vision. However, this requires collecting and labeling a large amount of reliable raw data. Since the UAV signal dataset cannot be directly applied to object detection, we propose a method using time-frequency domain filtering and automatic labeling to construct a large-scale time-frequency spectrogram dataset. Experimental results show that the average recognition accuracies of image transmission signals and remote control signals under interference conditions are 97% and 82%, respectively, while the average errors of signal parameters are 0.93% and 5.57%.

关键词： Training Time-frequency analysis Object detection Manuals Labeling Reliability Speech processing

来源：评论

学校读者我要写书评

暂无评论

Threat Capability of Stubborn Mining in Imperfect GHOST Bitcoin Blockchain

Threat Capability of Stubborn Mining in Imperfect GHOST Bitc...

引用

IEEE International Conference on Communications (ICC)

作者： Haoran Zhu Zhi Chen Jelena Mišić Vojislav B. Mišić Xiaolin Chang Jing Bai Beijing Key Laboratory of Security and Privacy in Intelligent Transportation Beijing Jiaotong University P. R. China Beijing Institute of Computer Technology and Application P. R. China Ryerson University Toronto ON Canada

Bitcoin is the largest PoW blockchain, which currently uses the longest-chain protocol for chain selection and is vulnerable to various attacks like stubborn mining attack. As a variant of selfish mining attack, stubborn mining attack usually has 7 types of strategies, each of which does damage to the blockchain system. GHOST is another chain-selection protocol, which has been demonstrated to make the blockchain system more secure than the longest-chain protocol under selfish mining attack. There were studies on stubborn mining in perfect GHOST blockchains and they only studied two types of stubborn mining strategies. But it is a fact of life that the blockchain is an imperfect network due to ubiquitous network congestion and/or attacks. This paper aims to explore a simulation-based approach to quantitatively evaluate the threat capability of all 7 stubborn mining strategies. We first develop all stubborn strategies in imperfect GHOST blockchains. Then we evaluate miner revenues and system throughput over different network conditions. The results show that the lead-fork-stubborn strategy is the dominant strategy for attackers when they have more than 33% total computing power. The stubborn attackers with less than 20% total computing power lose their revenue whichever stubborn mining strategy is used. The blockchain with high network quality still has the risk of significant throughput downgrade. Our work can help the stubborn mining attack detection and secure blockchain system design.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HSR-Diff: Hyperspectral Image Super-Resolution via Conditional Diffusion Models

HSR-Diff: Hyperspectral Image Super-Resolution via Condition...

引用

International Conference on computer Vision (ICCV)

作者： Chanyue Wu Dong Wang Yunpeng Bai Hanyu Mao Ying Li Qiang Shen National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Provincial Key Laboratory of Speech & Image Information Processing School of Computer Science Northwestern Polytechnical University China Department of Computer Science Faculty of Business and Physical Sciences Aberystwyth University U.K.

Despite the proven significance of hyperspectral images (HSIs) in performing various computer vision tasks, its potential is adversely affected by the low-resolution (LR) property in the spatial domain, resulting from multiple physical factors. Inspired by recent advancements in deep generative models, we propose an HSI Super-resolution (SR) approach with Conditional Diffusion Models (HSR-Diff) that merges a high-resolution (HR) multispectral image (MSI) with the corresponding LR-HSI. HSR-Diff generates an HR-HSI via repeated refinement, in which the HR-HSI is initialized with pure Gaussian noise and iteratively refined. At each iteration, the noise is removed with a Conditional Denoising Transformer (CDFormer) that is trained on denoising at different noise levels, conditioned on the hierarchical feature maps of HR-MSI and LR-HSI. In addition, a progressive learning strategy is employed to exploit the global information of full-resolution images. Systematic experiments have been conducted on four public datasets, demonstrating that HSR-Diff outperforms state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fracture Analysis of Fractured Sandstone Based on Multiple Parameters

SSRN

引用

SSRN 2024年

作者： Zhu, Xing He, Chunlei Zhu, Hao Fan, Jie State Key Laboratory of Geohazard Prevention and Geoenvironment Protection Chengdu University of Technology Chengdu610059 China College of Environment and Civil Engineering Chengdu University of Technology Chengdu610059 China College of Computer and Cyber Security Chengdu University of Technology Chengdu610059 China Sichuan Engineering Technology Research Center of Industrial Internet Intelligent Monitoring and Application Chengdu University of Technology Chengdu610059 China

To understand the deformation and fracture characteristics of fractured rock masses, a systematic experimental study was carried out on sandstone samples with various prefabricated cracks. Acoustic emission and digital image correlation technology were employed to analyze the failure mechanism and instability precursor of the fractured rock masses. The results indicate that the sandstone samples with double fractures exhibit stress drop behavior prior to failure, with the timing and magnitude of these drops varying according to fracture angle. Analysis of acoustic emission count rate and energy indicates that acoustic emission activity begins to fluctuate before 70% of peak stress is reached, with the count rate being particularly sensitive to the internal changes within the fractured rock mass. Five types of crack development were observed: wing cracks, oblique secondary cracks, coplanar secondary cracks, out-of-plane shear cracks, and out-of-plane tensile cracks. An image coefficient of variation (GCV), based on image gray characteristics, was introduced using the characteristic parameter of the image gray histogram. The GCV curve demonstrates a sudden change prior to the instability of fractured sandstone. For sandstone samples with fracture dip angles of 30°, 45°, 60°, and 75°, the time differences between the abrupt change point of GCV curve and the final failure is 43s, 36s, 28s, and 4s, respectively. This characteristic behavior can be used for effective short-term prediction of rock fracture instability. © 2024, The Authors. All rights reserved.

关键词： Image correlation

来源：评论

学校读者我要写书评

暂无评论

Bfs2adv: Black-Box Adversarial Attack Towards Hard-to-Attack Short Texts

SSRN

引用

SSRN 2023年

作者： Han, Xu Li, Qiang Cao, Hongbo Han, Lei Wang, Bin Bao, Xuhua Han, Yufei Wang, Wei Beijing Key Laboratory of Security and Privacy of Intelligent Transportation Beijing Jiaotong University Beijing100044 China Beijing Institute of Computer Technology and Application Beijing100584 China Zhejiang Key Laboratory of Multi-dimensional Perception Technology Zhejiang University Hangzhou310027 China Sangfro Technologies Inc Shenzhen518055 China INRIA Bretagne Rennes35042 France

The advent of Machine Learning as a Service (MLaaS) and deep learning applications has increased the susceptiblility of models to adversarial textual attacks, particularly in black-box settings. Prior work on black-box adversarial textual attacks generally follows a stable strategy that involves leveraging char-level, world-level, and sentence-level perturbations, as well as using queries to the target model to find adversarial examples in the search space. However, existing approaches prioritize query efficiency by reducing the search space, thereby overlooking hard-to-attack textual instances. To address this issue, we propose \textit{BFS2Adv}, a brute force algorithm that generates adversarial examples for both easy-to-attack and hard-to-attack textual ***2Adv, starting with an original text, employs word-level perturbations and synonym substitution to construct a comprehensive search space, with each node representing a potential adversarial example. The algorithm systematically explores this space through a breadth-first search, combined with queries to the target model, to effectively identify qualified adversarial *** implemented and evaluated a prototype of BFS2Adv against renowned models such as ALBERT and BERT, utilizing the SNLI and MR datasetsOur results demonstrate that BFS2Adv outperforms state-of-the-art algorithms and effectively improves the success rate of short-text adversarial ***, we provide detailed insights into the robustness of BFS2Adv by analyzing those hard-to-attack examples. © 2023, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Blockchain Scheme for Tracing Manufacturing Processes and Trading Transactions

A Hybrid Blockchain Scheme for Tracing Manufacturing Process...

引用

International Symposium on Parallel and Distributed Processing with applications, ISPA

作者： Ye Yuan Mingxing Yang Ruoting Xiong Yani Sun Xianchao Zhang Wei Ren HuBei Land Resources Vocational College China Gemological Institute China University of Geosciences Wuhan China School of Computing Science University of East Anglia UK Yunnan Key Laboratory of Blockchain Application Technology Yunnan Innovation Institute of Beihang University Kunming China Key Laboratory of Medical Electronics and Digital Health of Zhejiang Province Jiaxing University Jiaxing China State Key Laboratory of Geo-Information Engineering and Key Laboratory of Surveying and Mapping Science and Geospatial Information Technology of MNR Beijing China Ministry of Education Key Laboratory of Data Protection and Intelligent Management (Sichuan University) China School of Computer Science China University of Geosciences Wuhan China

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

Blockchain can be envisioned as an enabling framework in terms of cryptography and distributed computing to construct trusted data records among un-trusted users. It can be applied in two typical scenarios - historical process provenance and transaction tracing, by immutably sequentialized blocks. In the former there exists no tokens; but in the latter token handover among accounts should be cryptographically guaranteed. In some situations, above two applications may be both required. E.g., in the manufacture of a jewel, processing flow by different operators should be recorded for quality guaranteeing, and in its trading stage, the ownership handover should be recorded for value confirmation. To tackle above two requirements, two chains are usually thus demanded. In this paper, we propose a single chain solution to avoid cross-chain burden, by a hybrid block structure. The process data can be imported from the legacy (non-anonymous) information processing system, and transaction data stems from anonymous payment demand for ownership handover. We formally describe and prove token handover model with cryptographical authenticity. We also propose several security enhancements in the design for shortening the length of the chain, and protecting the data confidentiality in the chain. Our design is general and not limited to single application. The experimental results and extensive analysis justified that the performance and security of our proposed scheme is efficient.

关键词： Distributed processing Data privacy Manufacturing processes Information processing Handover Throughput Data structures Blockchains Delays Periodic structures

来源：评论

学校读者我要写书评

暂无评论

EAPDS: Efficient Auditable and Privacy-preservation Data Sharing Scheme Based on Attribute-Based Encryption for IoMT

引用

IEEE Internet of Things Journal 2025年

作者： Wang, Hui Xie, Yong Luo, Min Liu, Yining Shirazi, Syed Hamad Qinghai University Department of Information Technology Xining810016 China Qinghai Institute of Technology School of Computer and Information Science Xining810016 China Qinghai Provincial Key Laboratory of Big Data in Finance and Artificial Intelligence Application Technology Xining810016 China Wuhan University School of Cyber Science and Engineering Wuhan430072 China Wenzhou University of Technology School of Data Science and Artificial Intelligence Wenzhou325000 China Hazara University Department of Information Technology Mansehra21300 Pakistan

Data sharing schemes based on the Internet of Medical Things (IoMT) have emerged as a more convenient way to monitor and manage individuals’ health. However, this scenario faces challenges such as privacy preservation, effectiveness, and practicality, which hinder its further development. To the best of our knowledge, there is no agreed-upon data-sharing method that addresses all of these problems. In this paper, we make a step ahead by designing an Efficient and Auditable Privacy-preservation Data Sharing scheme (EAPDS) based on multi-authority attribute-based encryption. EAPDS designs an auditable anonymous authentication mechanism to realize identity privacy protection, as well as an efficient multi-authority attribute-based encryption mechanism to achieve the efficiency and practicability of data-sharing. Formal security analysis demonstrates EAPDS can resist replayable chosen-ciphertext attack. Many performance evaluation experiments and functional analyses show that EAPDS not only performs better than existing medical data-sharing schemes in terms of efficiency, but also in terms of privacy protection and feasibility. Consequently, our EAPDS scheme holds promising application prospects. © 2014 IEEE.

关键词： Data consistency

来源：评论

学校读者我要写书评

暂无评论

Research on Two-stage Conveying Bar Counting and Dividing System Based on Vision

Research on Two-stage Conveying Bar Counting and Dividing Sy...

引用

International Symposium on Distributed Computing and applications to Business, Engineering and Science (DCABES)

作者： Guojun Chen Yang Wu Jiangsu Key Laboratory of IoT Application Technology Wuxi Taihu University Wuxi China College of Computer Internet of Tings Engineering Wuxi Taihu University Wuxi China

ISBN: (纸本)9781665454636

A vision-based automatic bar counting system for two-stage conveying bars is proposed. The system solves the counting problems of sticking and relative sliding of a large number of rebar stacks through image processing algorithms. Through the improvement of the splitting end splitting machine, the design of two-step splitting and visual verification is adopted to achieve accurate splitting of stacked rebars. The system obviously reduces the requirements for installation space, and can make more effective use of the space in the rebar workshop. The system has fast running speed, high accuracy, small changes to the production line, and easy maintenance. It can not only meet the needs of production, but also greatly improve the efficiency of the existing counting system. It is suitable for rebar workshops with limited installation space. The experimental results show that the system can accurately count the bars and can accurately realize the steel separation. For bars with a diameter of 8-12mm, the counting accuracy is over 99.85%, and for bars with a diameter greater than 12mm, the counting accuracy is over 99.96%.

关键词： Visualization Conferences Machine vision Production Maintenance engineering Steel Distributed computing

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：