检索结果-内蒙古大学图书馆

Multi-granularity ensemble sample selection and label correction for classification with noisy labels

Applied Soft computing 2025年 180卷

作者： Kecan Cai Hongyun Zhang Witold Pedrycz Duoqian Miao Chaofan Chen Department of Computer Science and Technology Tongji University Shanghai 201804 PR China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 201804 PR China Department of Electrical and Computer Engineering University of Alberta Edmonton AB T6G 2R3 Canada Systems Research Institute Polish Academy of Sciences 00-901 Warsaw Poland Istinye University Faculty of Engineering and Natural Sciences Department of Computer Engineering Sariyer/Istanbul Turkiye

Sample selection is crucial in classification tasks with noisy labels, yet most existing sample selection methods rely on a single criterion. These approaches often face challenges, including low purity of selected clean samples, and underfitting due to an insufficient number of selected clean training samples. To address these challenges, this paper proposes GNet-SSLC, a novel multi-granularity network framework that integrates multiple criteria ensemble sample selection (SS) and multiple views label correction (LC). In the SS phase, this paper proposes a metric learning-based dual k-Nearest Neighbor (k-NN) sample selection method. This method first uses corrected soft labels from the initial k-NN round to guide the selection of clean samples in the subsequent k-NN round. To further enhance selection accuracy, we combine this dual k-NN approach with a small loss sample selection technique through a voting mechanism. This multiple criteria ensemble method addresses the issues of low purity and instability inherent in single criterion approaches. In the LC phase, this paper designs a multiple views label correction framework that generates high-quality pseudo-labels for selected noisy samples. A key innovation of the framework is the design of a regularized contrastive learning loss, which optimizes the semi-supervised learning process by leveraging multiple views of training samples. The additional inclusion of training samples with high-quality pseudo-labels can effectively mitigate underfitting caused by a limited number of clean training samples. Experimental results on both synthetic and real-world noisy datasets indicate that GNet-SSLC enhances the purity and stability of the selected clean samples, and significantly improves classification performance. The enhancement is particularly notable with high noise rate dataset, such as CIFAR-100 dataset with 80% noise rate, achieving a 19.3% increase in classification accuracy compared to the baseline method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep neural network discrimination of multiplexed superconducting qubit states

arXiv

引用

arXiv 2021年

作者： Lienhard, Benjamin Vepsäläinen, Antti Govia, Luke C.G. Hoffer, Cole R. Qiu, Jack Y. Ristè, Diego Ware, Matthew Kim, David Winik, Roni Melville, Alexander Niedzielski, Bethany Yoder, Jonilyn Ribeill, Guilhem J. Ohki, Thomas A. Krovi, Hari K. Orlando, Terry P. Gustavsson, Simon Oliver, William D. Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02139 United States Research Laboratory of Electronics Massachusetts Institute of Technology CambridgeMA02139 United States Quantum Engineering and Computing Group Raytheon BBN Technologies CambridgeMA02138 United States MIT Lincoln Laboratory LexingtonMA02421 United States

Demonstrating a quantum computational advantage will require high-fidelity control and readout of multi-qubit systems. As system size increases, multiplexed qubit readout becomes a practical necessity to limit the growth of resource overhead. Many contemporary qubit-state discriminators presume single-qubit operating conditions or require considerable computational effort, limiting their potential extensibility. Here, we present multi-qubit readout using neural networks as state discriminators. We compare our approach to contemporary methods employed on a quantum device with five superconducting qubits and frequency-multiplexed readout. We find that fully-connected feedforward neural networks increase the qubit-state-assignment fidelity for our system. Relative to contemporary discriminators, the assignment error rate is reduced by up to 25 % due to the compensation of system-dependent nonidealities such as readout crosstalk which is reduced by up to one order of magnitude. Our work demonstrates a potentially extensible building block for high-fidelity readout relevant to both near-term devices and future fault-tolerant systems. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Skeleton-Based Pre-Training With Discrete Labels for Emotion Recognition in IoT Environments

引用

IEEE Internet of Things Journal 2025年

作者： Zhang, Zhen Liang, Feng Wang, Wei Zeng, Runhao Leung, Victor C.M Hu, Xiping Shenzhen MSU-BIT University Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing Shenzhen China Shenzhen MSU-BIT University Artificial Intelligence Research Institute China Lanzhou University Gansu Provincial Key Laboratory of Wearable Computing School of Information Science and Engineering Gansu China Beijing Institute of Technology School of Medical Technology China University of British Columbia Department of Electrical and Computer Engineering Canada

Self-supervised emotion recognition leveraging skeleton-based data offers a promising approach for classifying emotional expressions within the extensive amount of unlabeled data gathered by sensors in the Internet of Things (IoT). Recent advancements in this field have been driven by contrastive learning-based or generative learning-based self-supervised methods, which effectively tackle the issue of sparsely labeled data. In emotion recognition tasks, the emotional high-level semantics embedded in the skeleton data are more important than the subtle joint movements. Compared to existing methods, discrete label prediction can encourage SSL models to abstract high-level semantics in a manner similar to human perception. However, it is challenging to comprehensively capture emotional expressed in skeleton data solely from joint-based features. Moreover, emotional information conveyed through body movements may include redundant details that hinder the understanding of emotional expression. To overcome these challenges, we propose a novel discrete-label-based emotion recognition framework named the Appendage-Informed Redundancy-ignoring (AIR) discrete label framework. First, we introduce the Appendage-Skeleton Partitioning (ASP) module, which leverages limb movement data from the original skeleton to explore emotional expression. Next, we propose the Appendage-refined Multi-scale Discrete Label (AMDL) module, which transforms traditional self-supervised tasks into classification tasks. This design continuously extracts emotional semantics from skeleton data during pre-training, functioning similarly to predicting categories and subsequently classifying samples. To further reduce the nonessential information in skeleton data that may negatively impact the generation of accurate emotional categories, we propose the Appendage Label Refinement (ALR) module. It refines the generated categories by using the relationships between the skeleton and the various appendages obtai

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

A Smart Roll Wear Check Scheme for Ensuring the Rolling Quality of Steel Plates 1

引用

4th International Conference on Smart computing and Communications, SmartCom 2019

作者： Zhang, Kui Zhou, Xiaohu He, Heng Wang, Yonghao Wang, Weihao Li, Huajian College of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China Faculty of Computing Engineering and the Built Environment Birmingham City University Birmingham United Kingdom

ISBN: (数字)9783030341398

ISBN: (纸本)9783030341381

Roll surface wear morphology directly affects the surface quality of steel plates and even affects the texture composition of plates and strip steel products. Using image processing methods to judge the wear state of a roll is low cost, easy to operate, and easy to realize an automatic smart data processing system. In this paper, we propose a Smart Roll Wear Check (SRWC) scheme for ensuring the rolling quality of steel plates. In the SRWC scheme, roll surface images in different wear stages are analyzed, from which seventeen dimension features are extracted. At the same time, the fractal theory is introduced to explore the relationship between fractal dimensions and roll wear degree. The results show that four characteristic parameters, such as roundness, equivalent area circle radius, second moment and texture entropy, and the fractal dimension can be used as effective parameters to quantitatively judge roll wear state. Lastly, a back-propagation (BP) neural network model for recognition and judgment for roll wear is established. It provides an experimental test to show that the five parameters as a quantitative evaluation for roll wear morphology are effective. By processing the data on the images, the SRWC scheme can demonstrate whether the roll needs to get off mill in time, so as to avoid the hidden danger of safety and ensure the rolling quality of the steel plate. © 2019, Springer Nature Switzerland AG.

关键词： Fractal dimension

来源：评论

学校读者我要写书评

暂无评论

Optically Heralded Entanglement of Superconducting Systems in Quantum Networks

引用

Physical Review Letters 2021年第4期127卷 040503-040503页

作者： Stefan Krastanov Hamza Raniwala Jeffrey Holzgrafe Kurt Jacobs Marko Lončar Matthew J. Reagor Dirk R. Englund Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA John A. Paulson School of Engineering and Applied Sciences Harvard University Cambridge Massachusetts 02138 USA U.S. Army Research Laboratory Computational and Information Sciences Directorate Adelphi Maryland 20783 USA Department of Physics University of Massachusetts at Boston Boston Massachusetts 02125 USA Rigetti Computing 775 Heinz Avenue Berkeley California 94710 USA Research Laboratory of Electronics Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA

Networking superconducting quantum computers is a longstanding challenge in quantum science. The typical approach has been to cascade transducers: converting to optical frequencies at the transmitter and to microwave frequencies at the receiver. However, the small microwave-optical coupling and added noise have proven formidable obstacles. Instead, we propose optical networking via heralding end-to-end entanglement with one detected photon and teleportation. This new protocol can be implemented on standard transduction hardware while providing significant performance improvements over transduction. In contrast to cascaded direct transduction, our scheme absorbs the low optical-microwave coupling efficiency into the heralding step, thus breaking the rate-fidelity trade-off. Moreover, this technique unifies and simplifies entanglement generation between superconducting devices and other physical modalities in quantum networks.

关键词： Entanglement production Optical & microwave phenomena Quantum entanglement Quantum networks Superconducting qubits

来源：评论

学校读者我要写书评

暂无评论

A RIS-Based Vehicle DOA Estimation Method With Integrated Sensing and Communication System

arXiv

引用

arXiv 2022年

作者： Chen, Zhimin Chen, Peng Guo, Ziyu Zhang, Yudong Wang, Xianbin The School of Electronic and Information Shanghai Dianji University Shanghai201306 China State Key Laboratory of Integrated Services Networks Xidian University Xi’an710071 China The State Key Laboratory of Millimeter Waves Southeast University Nanjing210096 China The School of Information Science and Technology Fudan University Shanghai200433 China The State Key Laboratory of Integrated Chips and Systems Fudan University Shanghai200433 China The School of Computing and Mathematical Sciences University of Leicester LeicesterLE1 7RH United Kingdom School of Computer Science and Engineering Southeast University Nanjing210096 China The Department of Electrical and Computer Engineering Western University LondonONN6A 5B9 Canada

With the development of intelligent transportation, growing attention has been received to integrated sensing and communication (ISAC) systems. In this paper, we formulate a novel passive sensing technique to obtain information on the vehicle’s direction of arrival (DOA) using reconfigurable intelligent surfaces (RIS). A novel estimation method is proposed in the scenario with a receiver using only one full-functional channel, where multiple measurements for the DOA estimation are achieved by controlling the reflection matrix (measurement matrix) in the RIS. Moreover, different from the existing estimation methods, we also consider the interference signals introduced by wireless communication in the ISAC system. Then, we propose a novel atomic norm-based method to remove the interference signals and reconstruct the sparse signal. Additionally, a novel Hankel-based multiple signal classification (MUSIC) method is formulated to obtain the DOA information after the interference removal. To reduce the interference signals more efficiently and improve the performance of the sparse reconstruction, we optimize the measurement matrix to improve the signal-to-interference-plus-noise ratio (SINR). Finally, the theoretical Cram’er-Rao lower bound (CRLB) is derived for the ISAC system on the vehicle DOA estimation. Simulation results show that the proposed method can achieve better performance in the DOA estimation, and the corresponding CRLB with different distributions of the sensing nodes are shown. The code for the proposed method is available online https://***/chenpengseu/***. Copyright © 2022, The Authors. All rights reserved.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

SZ3: A Modular Framework for Composing Prediction-Based Error-Bounded Lossy Compressors

arXiv

引用

arXiv 2021年

作者： Liang, Xin Zhao, Kai Di, Sheng Li, Sihuan Underwood, Robert Gok, Ali M. Tian, Jiannan Deng, Junjing Calhoun, Jon C. Tao, Dingwen Chen, Zizhong Cappello, Franck Department of Computer Science Missouri University of Science and Technology RollaMO65409 United States Department of Computer Science & Engineering University of California Riverside RiversideCA92521 United States Facebook Inc. Menlo ParkCA94025 United States Mathematics and Computer Science Division Argonne National Laboratory Lemont IL60439 United States Cerebras Systems SunnyvaleCA94085 United States Department of Computer Science Washington State University PullmanWA99164 United States School of Computing Clemson University ClemsonSC29634 United States Holcombe Department of Electrical and Computer Engineering Clemson University ClemsonSC29634 United States

Today’s scientific simulations require a significant reduction of data volume because of extremely large amounts of data they produce and the limited I/O bandwidth and storage space. Error-bounded lossy compressor has been considered one of the most effective solutions to the above problem. In practice, however, the best-fit compression method often needs to be customized/optimized in particular because of diverse characteristics in different datasets and various user requirements on the compression quality and performance. In this paper, we develop a novel modular, composable compression framework (namely SZ3), which involves three significant contributions. (1) SZ3 features a modular abstraction for the prediction-based compression framework such that the new compression modules can be plugged in easily. (2) SZ3 supports multi algorithm predictors and can automatically select the best-fit predictor for each data block based on the designed error estimation criterion. (3) SZ3 allows users to easily compose different compression pipelines on demand, such that both compression quality and performance can be significantly improved for their specific datasets and requirements. (4) In addition, we evaluate several lossy compressors composed from SZ3 using the real-world datasets. Specifically, we leverage SZ3 to improve the compression quality and performance for different use-cases, including GAMESS quantum chemistry dataset and Advanced Photon Source (APS) instrument dataset. Experiments show that our customized compression pipelines lead to up to 20% improvement in compression ratios under the same data distortion compared with the state-of-the-art approaches. Copyright © 2021, The Authors. All rights reserved.

关键词： Compressors

来源：评论

学校读者我要写书评

暂无评论

Carrying out CNN Channel Pruning in a White Box

arXiv

引用

arXiv 2021年

作者： Zhang, Yuxin Lin, Mingbao Lin, Chia-Wen Chen, Jie Wu, Yongjian Tian, Yonghong Ji, Rongrong The Media Analytics and Computing Laboratory Department of Artificial Intelligence School of Informatics Xiamen University Xiamen361005 China The Youtu Laboratory Tencent Shanghai200233 China The Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Hsinchu30013 Taiwan The Peng Cheng Laboratory Shenzhen518000 China Department of Computer Science and Technology Peking University Beijing100871 China Institute of Artificial Intelligence Xiamen University Xiamen361005 China

Channel Pruning has been long studied to compress CNNs, which significantly reduces the overall computation. Prior works implement channel pruning in an unexplainable manner, which tends to reduce the final classification errors while failing to consider the internal influence of each channel. In this paper, we conduct channel pruning in a white box. Through deep visualization of feature maps activated by different channels, we observe that different channels have a varying contribution to different categories in image classification. Inspired by this, we choose to preserve channels contributing to most categories. Specifically, to model the contribution of each channel to differentiating categories, we develop a class-wise mask for each channel, implemented in a dynamic training manner w.r.t. the input image’s category. On the basis of the learned class-wise mask, we perform a global voting mechanism to remove channels with less category discrimination. Lastly, a fine-tuning process is conducted to recover the performance of the pruned model. To our best knowledge, it is the first time that CNN interpretability theory is considered to guide channel pruning. Extensive experiments on representative image classification tasks demonstrate the superiority of our White-Box over many state-of-the-arts. For instance, on CIFAR-10, it reduces 65.23% FLOPs with even 0.62% accuracy improvement for ResNet-110. On ILSVRC-2012, White-Box achieves a 45.6% FLOPs reduction with only a small loss of 0.83% in the top-1 accuracy for ResNet-50. Code is available at https://***/zyxxmu/White-Box. © 2021, CC BY.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Mobile data offloading in the vehicular networks: A truthful incentive mechanism 21

Mobile data offloading in the vehicular networks: A truthful...

引用

21st IEEE International Conference on High Performance computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on Data science and Systems, HPCC/SmartCity/DSS 2019

作者： Enfang, Zhong Li, Peng Zhang, Tao Huang, Weiyi Liu, Qin College of Computer Science and Technology Wuhan University of Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System China Department of Computer Science New York Institute of Technology United States School of Cyber Science and Engineering Wuhan University China

ISBN: (纸本)9781728120584

Mobile data offloading is a cost-effective and promising approach to alleviate the burden of the cellular network. In this paper, we focus on designing a truthful incentive mechanism that the auction cloud platform motivates mobile users with deadline constraints and capacity constraints to offload data. First, we formulate the mobile data offloading problem as a reverse auction. Then, we reduce this social welfare maximization reverse auction for data offloading as an integer linear programming (ILP) problem. To solve this problem, we propose a data offloading auction greedy algorithm to choose the most cost-effective bids. We decompose the data offload auction greedy algorithm into the winner determination problem (WDP) and the threshold payment scheme. Moreover, we propose a delay winner winning algorithm based on the data offloading auction greedy algorithm. Extensive simulation experiments demonstrate that the data offloading auction mechanism dramatically reduces the burden of the cellular network while meeting the offloading tasks deadline constraints and mobile user capacity constraints. © 2019 IEEE.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Budget constraint roadside units placement for traffic flows monitoring system with reliability in vehicular networks 21

Budget constraint roadside units placement for traffic flows...

引用

作者： Jiang, Peng Li, Peng Zhang, Tao Huang, Weiyi He, Heng Nie, Lei Liu, Qin College of Computer Science and Technology Wuhan University of Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing Real-time Industrial System China Department of Computer Science New York Institute of Technology United States School of Cyber Science and Engineering Wuhan University China

ISBN: (纸本)9781728120584

In Traffic Flows Monitoring System (TFMS), the key problem is how to install Roadside Units (RSUs) reliably to monitor traffic flows with the constrained budget. The reliability of Traffic Flows Monitoring System(TFMS) is determined by the number of RSUs each traffic flow pass through, and the RSUs placement number is determined by the budget and the placement strategy. In this paper, we investigate the budget constraint RSUs placement problem for traffic flows monitoring system with reliability in vehicular networks. Given a budget constraint, the problem is how to install RSUs to ensure the reliability of TFMS, that is each traffic flow pass through RSUs as many as possible with the limited budget. We prove that this problem is NP-hard. Then, we propose two greedy algorithms to solve the problem according to the pigeonhole principle. Moreover, approximation ratios of proposed algorithms are given. Finally, we verify the feasibility of proposed algorithms through extensive experiments, and the results show that the proposed algorithms are superior to the other algorithms. © 2019 IEEE.

关键词： Reliability

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：