检索结果-内蒙古大学图书馆

REQUIRED NUMBER OF ITERATIONS FOR SPARSE SIGNAL RECOVERY VIA ORTHOGONAL LEAST SQUARES

Journal of Computational Mathematics 2023年第1期41卷 1-17页

作者： Haifeng Li Jing Zhang Jinming Wen Dongfang Li Henan Engineering Laboratory for Big Data Statistical Analysis and Optimal Control College of Mathematics and Information ScienceHenan Normal UniversityXinxiang 453007China College of Information Science and Technology Jinan UniversityGuangzhou 510632China School of Mathematics and Statistics Huazhong University of Science and TechnologyWuhan 430074China Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and TechnologyWuhan 430074China

In countless applications,we need to reconstruct a K-sparse signal x∈R n from noisy measurements y=Φx+v,whereΦ∈R^(m×n)is a sensing matrix and v∈R m is a noise *** least squares(OLS),which selects at each step the column that results in the most significant decrease in the residual power,is one of the most popular sparse recovery *** this paper,we investigate the number of iterations required for recovering x with the OLS *** show that OLS provides a stable reconstruction of all K-sparse signals x in[2.8K]iterations provided thatΦsatisfies the restricted isometry property(RIP).Our result provides a better recovery bound and fewer number of required iterations than those proposed by Foucart in 2013.

关键词： Sparse signal recovery Orthogonal least squares(OLS) Restricted isometry property(RIP)

来源：评论

学校读者我要写书评

暂无评论

A Two Dimensional Feature engineering Method for Relation Extraction 5

A Two Dimensional Feature Engineering Method for Relation Ex...

引用

5th International Conference on Control, Robotics, and Intelligent System, CCRIS 2024

作者： Wang, Hao Chen, Yanping Yang, Weizhe Lin, Chuan Text Computing & Cognitive Intelligence Engineering Research Center of National Education Ministry Huaxi District Guizhou China State Key Laboratory of Public Big Data Huaxi District Guizhou China Guizhou University Huaxi District Guizhou China

ISBN: (数字)9781510685871

ISBN: (纸本)9781510685864

Transforming a sentence into a 2D representation, similar to table structures, reveals a semantic plane where elements can represent potential relations between paired entities. The 2D representation effectively addresses the common issue of overlapping relations. However, previous works directly transformed the representation from raw input, neglecting the utilization of prior knowledge, which is essential to support the entity relation extraction task. In this paper, we propose a 2D feature engineering method. The method innovatively integrates prior knowledge within 2D sentence representations, marking an advancement over previous strategies, and employs an attention mechanism to build the hitherto overlooked association between entities and prior knowledge. The fusion of prior knowledge and targeted attention enhances the model’s relational discernment capabilities. Evaluations on three benchmark datasets—ACE05 Chinese, ACE05 English, and CLTC—demonstrate the efficacy of the proposed method. It surpasses existing techniques, achieving state-of-the-art performance with F1 score improvements of 0.88%, 3.27%, and 2.83% respectively. The results indicate that 2D feature engineering can take advantage of a 2D sentence representation and make full use of prior knowledge. © 2024 SPIE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Last-X-Generation Archiving Strategy for Multi-Objective Evolutionary Algorithms 13

Last-X-Generation Archiving Strategy for Multi-Objective Evo...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Shu, Tianye Nan, Yang Shang, Ke Ishibuchi, Hisao Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Shenzhen518055 China Southern University of Science and Technology Shenzhen518055 China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China

ISBN: (纸本)9798350308365

For evolutionary multi-objective optimization algorithms (EMOAs), an external archive can be utilized for saving good solutions found throughout the evolutionary process. Recent studies showed that a solution set selected from an external archive is usually superior to the final population. That is, the incorporation of an external archive improves the performance of EMOAs. However, the computation time for maintaining an external archive is long, especially when the archive size is large. To solve this issue, a simple archiving strategy is to save all solutions generated in the last several generations. In this paper, we examine this archiving strategy for three representative EMOAs on artificial test problems (Minus-DTLZ and WFG) and real-world problems (RE). Our results show that archiving the last several generations clearly improves the performance of EMOAs without severely increasing the computation time. © 2024 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Feature Rotation Invariance Learning for Point Cloud Analysis 10

Feature Rotation Invariance Learning for Point Cloud Analysi...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Shi, Lu Cao, Qi Zhang, Guoqing Yi, Jin Huang, Yansen Cen, Yigang Beijing Jiaotong University State Key Laboratory of Advanced Rail Autonomous Operation The School of Computer Science and Technology Visual Intellgence +X International Cooperation Joint Laboratory of Moe Beijing100044 China University of Glasgow The School of Computing Science 567739 Singapore Beijing Jiaotong University With the Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education The State Key Laboratory of Advanced Rail Autonomous Operation The School of Computer and Information Technology Beijing100044 China Guizhou University Guizhou Lianjian Civil Engineering Quality Testing Monitoring Center Co. Ltd The College of Civil Engineering Guizhou550025 China

ISBN: (纸本)9798331520861

While deep learning has significantly advanced point cloud analysis, extracting effective features from their disordered structure remains challenging. Existing approaches often rely on complex network architectures or manual feature engineering to achieve rotation invariance, which increases inference latency. This paper offers a novel perspective on this challenge, showing that rotation-sensitive models can achieve performance comparable to rotation-invariant models when trained with rotation-augmented data. Given the significant differences in the feature distributions of rotation-sensitive and rotation-invariant models, we propose Feature Rotation Invariance Learning (FRIL), a framework that leverages Distance Metric Learning and rotation-based constraints to help rotation-sensitive models extract rotation-invariant features. This approach eliminates the need for additional modules, enabling robust performance against rotations. Extensive experiments demonstrate that FRIL consistently outperforms existing rotation-invariant methods across various visual tasks. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Towards Stricter Black-box Integrity Verification of Deep Neural Network Models 24

Towards Stricter Black-box Integrity Verification of Deep Ne...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： He, Chaoxiang Bai, Xiaofan Ma, Xiaojing Zhu, Bin B. Hu, Pingyi Fu, Jiayun Jin, Hai Zhang, Dongmei Huazhong University of Science and Technology Hubei Wuhan China Shanghai Jiao Tong University Shanghai China Microsoft Corporation Beijing China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

ISBN: (纸本)9798400706868

Cloud-based machine learning services offer significant advantages but also introduce the risk of tampering with cloud-deployed deep neural network (DNN) models. Black-box integrity verification (BIV) allows model owners and end-users to determine if a cloud-deployed DNN model has been tampered with by examining only the top-1 label responses. Fingerprinting generates fingerprint samples to query the model, achieving BIV with no impact on the model's accuracy. In this paper, we present BIVBench, the first comprehensive benchmark for BIV of DNN models. BIVBench covers 16 types of model modifications, providing extensive coverage of practical modification scenarios. Our analysis reveals that existing fingerprinting methods, which are typically focused on significant tampering, lack the sensitivity needed to effectively detect subtle yet common and potentially severe modifications. To address this limitation, we propose MiSentry (Model Integrity Sentry), a novel fingerprinting method that leverages meta-learning. MiSentry strategically incorporates a few subtly modified models into the meta-learning model zoo and maximizes the divergence of output predictions between the target model and the modified models in the model zoo to generate highly sensitive, generalizable, and effective fingerprint samples. Extensive evaluations using BIVBench demonstrate that MiSentry outperforms existing state-of-the-art methods overall and significantly surpasses them in detecting subtle modifications. The BIVBench and supplementary materials are available at: https://***/CGCL-codes/BIVBench. © 2024 ACM.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Improved Capon Estimator for High-Resolution DOA Estimation and Its Statistical Analysis

引用

IEEE/CAA Journal of Automatica Sinica 2023年第8期10卷 1716-1729页

作者： Weiliang Zuo Jingmin Xin Changnong Liu Nanning Zheng Akira Sano IEEE the National Key Laboratory of Human-Machine Hybrid Augmented Intelligence the National Engineering Research Center for Visual Information and Applicationsand the Institute of Artificial Intelligence and RoboticsXi’an Jiaotong UniversityXi’an 710049China the Data Center China Construction BankBeijing 100033China the Department of System Design Engineering Keio UniversityYokohama 223-8522Japan

Despite some efforts and attempts have been made to improve the direction-of-arrival(DOA)estimation performance of the standard Capon beamformer(SCB)in array processing,rigorous statistical performance analyses of these modified Capon estimators are still *** paper studies an improved Capon estimator(ICE)for estimating the DOAs of multiple uncorrelated narrowband signals,where the higherorder inverse(sample)array covariance matrix is used in the Capon-like cost *** establishing the relationship between this nonparametric estimator and the parametric and classic subspace-based MUSIC(multiple signal classification),it is clarified that as long as the power order of the inverse covariance matrix is increased to reduce the influence of signal subspace components in the ICE,the estimation performance of the ICE becomes equivalent to that of the MUSIC regardless of the signal-to-noise ratio(SNR).Furthermore the statistical performance of the ICE is analyzed,and the large-sample mean-squared-error(MSE)expression of the estimated DOA is *** the effectiveness and the theoretical analysis of the ICE are substantiated through numerical examples,where the Cramer-Rao lower bound(CRB)is used to evaluate the validity of the derived asymptotic MSE expression.

关键词： Capon beamformer direction-of-arrival(DOA)estimation large-sample mean-squared-error(MSE) subspace-based methods uniform linear array

来源：评论

学校读者我要写书评

暂无评论

Intersecting-Boundary-Sensitive Fingerprinting for Tampering Detection of DNN Models 41

Intersecting-Boundary-Sensitive Fingerprinting for Tampering...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Bai, Xiaofan He, Chaoxiang Ma, Xiaojing Zhu, Bin Benjamin Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China Microsoft United States School of Computer Science and Technology Huazhong University of Science and Technology China Cluster and Grid Computing Lab China

Cloud-based AI services offer numerous benefits but also introduce vulnerabilities, allowing for tampering with deployed DNN models, ranging from injecting malicious behaviors to reducing computing resources. Fingerprint samples are generated to query models to detect such tampering. In this paper, we present Intersecting-Boundary-Sensitive Fingerprinting (IBSF), a novel method for black-box integrity verification of DNN models using only top-1 labels. Recognizing that tampering with a model alters its decision boundary, IBSF crafts fingerprint samples from normal samples by maximizing the partial Shannon entropy of a selected subset of categories to position the fingerprint samples near decision boundaries where the categories in the subset intersect. These fingerprint samples are almost indistinguishable from their source samples. We theoretically establish and confirm experimentally that these fingerprint samples' expected sensitivity to tampering increases with the cardinality of the subset. Extensive evaluation demonstrates that IBSF surpasses existing state-of-the-art fingerprinting methods, particularly with larger subset cardinality, establishing its state-of-the-art performance in black-box tampering detection using only top-1 labels. The IBSF code is available at: https://***/CGCL-codes/IBSF. Copyright 2024 by the author(s)

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

4D foetal cardiac ultrasound image detection based on deep learning with weakly supervised localisation for rapid diagnosis of evolving hypoplastic left heart syndrome

引用

CAAI Transactions on Intelligence Technology 2024年第6期9卷 1485-1499页

作者： Gang Wang Weisheng Li Mingliang Zhou Haobo Zhu Guang Yang Choon Hwai Yap Chongqing Key Laborotory of Image Rocognition Chongqing University of Posts and TelecommunicationsChongqingChina School of Computing and Data Engineering NingboTech UniversityNingboChina Department of Bioengineering Imperial College LondonLondonUK Key Laboratory of Cyberspace Big Data Intelligent Security(Chongqing University of Posts and Telecommunications) Ministry of EducationChongqingChina School of Computer Science Chongqing UniversityChongqingChina University of Oxford OxfordUK Cardiovascular Research Centre Royal Brompton HospitalLondonUK National Heart and Lung Institute Imperial College LondonLondonUK

Hypoplastic left heart syndrome(HLHS)is a rare,complex,and incredibly foetal congenital heart *** decrease neonatal mortality,evolving HLHS(eHLHS)in pregnant women should be critically diagnosed as soon as ***,diagnosis is currently heavily dependent on skilled medical professionals using foetal cardiac ultrasound images,making it difficult to rapidly and easily examine for this ***,the authors propose a cost-effective deep learning framework for rapid diagnosis of eHLHS(RDeH),which we have named ***,the framework implements a coarseto-fine two-stage detection approach,with a structure classification network for 4D human foetal cardiac ultrasound images from various spatial and temporal domains,and a fine detection module with weakly-supervised localisation for high-precision nidus localisation and physician *** experiments extensively compare the authors’network with other state-of-the-art methods on a 4D human foetal cardiac ultrasound image dataset and show two main benefits:(1)it achieved superior average accuracy of 99.37%on three categories of foetal ultrasound images from different cases;(2)it demonstrates visually fine detection performance with weakly supervised *** framework could be used to accelerate the diagnosis of eHLHS,and hence significantly lessen reliance on experienced medical physicians.

关键词： 4D deep learning fetal cardiac ultrasound hypoplastic left heart syndrome weakly-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Asymmetric scattering behaviors of spin wave dependent on magnetic vortex chirality

引用

Chinese Physics B 2023年第10期32卷 635-640页

作者：张雪枫沈帝虎马晓萍宋成于海明朴红光 Hubei Engineering Research Center of Weak Magnetic-Field Detection China Three Gorges UniversityYichang 443002China Department of Physics College of ScienceYanbian UniversityYanji 133002China Key Laboratory of Advanced Materials(MOE) School of Materials Science and EngineeringTsinghua UniversityBeijing 100084China Fert Beijing Institute School of Integrated Circuit Science and EngineeringBeijing Advanced Innovation Center for Big Data and Brain ComputingBeihang UniversityBeijing 100191China

We investigate asymmetric spin wave scattering behaviors caused by vortex chirality in a cross-shaped ferromagnetic system by using the micromagnetic *** the system,four scattering behaviors are found:(i)asymmetric skew scattering,depending on the polarity of vortex core,(ii)back scattering(reflection),depending on the vortex core stiffness,(iii)side deflection scattering,depending on structural symmetry of the vortex circulation,and(iv)geometrical scattering,depending on waveguide *** first and second scattering behaviors are attributed to nonlinear topological magnon spin Hall effect related to magnon spin-transfer torque effect,which has value for magnonic exploration and application.

关键词： magnonics magnetic vortex spin wave magnetic chirality

来源：评论

学校读者我要写书评

暂无评论

Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need 38

Unlearnable 3D Point Clouds: Class-wise Transformation Is Al...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wang, Xianlong Li, Minghui Liu, Wei Zhang, Hangtao Hu, Shengshan Zhang, Yechao Zhou, Ziqi Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China

Traditional unlearnable strategies have been proposed to prevent unauthorized users from training on the 2D image data. With more 3D point cloud data containing sensitivity information, unauthorized usage of this new type data has also become a serious concern. To address this, we propose the first integral unlearnable framework for 3D point clouds including two processes: (i) we propose an unlearnable data protection scheme, involving a class-wise setting established by a category-adaptive allocation strategy and multi-transformations assigned to samples;(ii) we propose a data restoration scheme that utilizes class-wise inverse matrix transformation, thus enabling authorized-only training for unlearnable data. This restoration process is a practical issue overlooked in most existing unlearnable literature, i.e., even authorized users struggle to gain knowledge from 3D unlearnable data. Both theoretical and empirical results (including 6 datasets, 16 models, and 2 tasks) demonstrate the effectiveness of our proposed unlearnable framework. Our code is available at https://***/CGCL-codes/UnlearnablePC. © 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

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：