检索结果-内蒙古大学图书馆

27th International Conference on Pattern Recognition, ICPR 2024

作者： Jiang, Yaru Lyu, Shujing Zhan, Hongjian Lu, Yue Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai China

ISBN: (纸本)9783031783531

The occurrence of human fall is a significant threat to human health, especially among the elderly. Unlike standard action recognition, falls manifest a combination of static and dynamic attributes. They are highly sensitive to spatio-temporal motion, marked by sudden and transient occurrences. This paper proposes a novel spatio-temporal convolutional method for end-to-end human fall detection, named Residual Spatio-Temporal Attention Network (RSTAN). The network integrates a Spatial Channel Attention (SCA) module within the convolutional layers of the Residual 3D convolution to enhance feature refinement. selectively accentuates spatial and channel dimensions. In addition, to capture both the extensive spatio-temporal features and the short-range spatio-temporal characteristics of human falls, effectively distinguishing them from daily activities, we propose a Multi-interval Difference Aggregation (MDA) method. The MDA utilizes multiple time interval frame differences to extract motion features. Our proposed method’s superior performance is demonstrated through experiments on three publicly available fall detection datasets. Specifically, achieving 100% accuracy on the UR Fall Detection dataset. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

Learning to Detect Lithography Defects in SEM Images 27th

Learning to Detect Lithography Defects in SEM Images

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Lu, Hu Zhao, Botong Shen, Jiwei Zhan, Hongjian Lyu, Shujing Lu, Yue Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai200241 China

ISBN: (纸本)9783031781681

Lithography defect detection plays a vital role in chip production. A sensitive and reliable defect detection method is very important to ensure the quality of chips. Deep learning has shown promising results in learning generalizable image priors, making it a viable approach for the lithography defect detection task. However, it is still challenging to obtain accurate and stable lithography defect detection results, because of the existence of real noise in Scanning Electron Microscope (SEM) images and the diversity of lithography defects. In this work, we propose a new SEM image lithography defect detection pipeline, which comprises a Transformer-based high-resolution SEM image denoising module to mitigate the interference of real noise on defect detection and a new detection model for detecting defects in denoised SEM images. Particularly, in our detection model, we present a new lightweight feature extraction module for efficiently extracting multi-scale features and a new cross-scale feature fusion module for fully integrating features at different scales. Moreover, we create an advanced lithography defect dataset annotated by experienced experts. Experimental results demonstrate that our method can accurately detect lithography defects in SEM images and our detection model surpasses other state-of-the-art detectors on the lithography defect dataset. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Decentralized fault diagnosis of discrete-event systems with unreliable sensors using linear temporal logic

引用

Science China(information Sciences) 2025年第1期68卷 322-341页

作者： Weijie DONG Shaoyuan LI Xiang YIN Key Laboratory of System Control and Information Processing Ministry of EducationDepartment of Automation Shanghai Jiao Tong University

In this paper,we investigate a decentralized diagnosis problem of a discrete-evnt system(DES) subject to unreliable sensors,where the sensor observations of local diagnosers may be non-deterministic as a result of possible *** studies on decentralized robust diagnosis can only deal with different types of sensor failures separately,e.g.,all sensors suffer from the same type of sensor failures such as intermittent sensor failures or permanent sensor ***,since sensors of different local diagnosers may face different external environments and have different internal characteristics,sensors corresponding to different local diagnosers may also have their own fault *** this paper,we propose a flexible framework of decentralized diagnosis for DES subject to unreliable sensors such that sensors of different local diagnosers are permitted to have different types of sensor *** this end,we extend the existing decentralized diagnosis framework to the case where there exist common sensors broadcasting their observations to all local *** apply linear temporal logic(LTL) to constrain infinite behaviors of private sensors of local diagnosers and common ***,a new notion of φ-codiagnosability is proposed as the necessary and sufficient condition for the existence of a decentralized diagnoser that works correctly under sensors,satisfying LTL-based sensor ***,we provide an effective approach to verify the φ-codiagnosability.

关键词： discrete event systems decentralized diagnosis codiagnosability automata

来源：评论

学校读者我要写书评

暂无评论

Value Iteration-Based Distributed Adaptive Dynamic Programming for Multi-Player Differential Game With Incomplete information

引用

IEEE/CAA Journal of Automatica Sinica 2025年第2期12卷 436-447页

作者： Yun Zhang Yuqi Wang Yunze Cai the Department of Automation Shanghai Jiao Tong University the Key Laboratory of System Control and Information Processing Ministry of Education of China the National Key Laboratory of Air-based Information Perception and Fusion

In this paper, a distributed adaptive dynamic programming(ADP) framework based on value iteration is proposed for multi-player differential games. In the game setting,players have no access to the information of others' system parameters or control laws. Each player adopts an on-policy value iteration algorithm as the basic learning framework. To deal with the incomplete information structure, players collect a period of system trajectory data to compensate for the lack of information. The policy updating step is implemented by a nonlinear optimization problem aiming to search for the proximal admissible policy. Theoretical analysis shows that by adopting proximal policy searching rules, the approximated policies can converge to a neighborhood of equilibrium policies. The efficacy of our method is illustrated by three examples, which also demonstrate that the proposed method can accelerate the learning process compared with the centralized learning framework.

关键词： Distributed adaptive dynamic programming incomplete information multi-player differential game (MPDG) value iteration

来源：评论

学校读者我要写书评

暂无评论

A Valuable and Low-Budget Process Scheme of Equivalized 1 nm Technology Node Based on 2D Materials

引用

Nano-Micro Letters 2025年第8期17卷 294-305页

作者： Yang Shen Zhejia Zhang Zhujun Yao Mengge Jin Jintian Gao Yuhan Zhao Wenzhong Bao Yabin Sun He Tian College of Integrated Circuit Science and Engineering Shanghai Key Laboratory of Multidimensional Information ProcessingEast China Normal UniversityShanghai 200241People’s Republic of China Institute of Microelectronics and Beijing National Research Center for Information Science and Technology(BNRist) Tsinghua UniversityBeijing 100084People’s Republic of China State Key Laboratory of ASIC and System School of MicroelectronicsFudan UniversityShanghai 200433People’s Republic of China Shaoxin Laboratory Shaoxing 312000People’s Republic of China

Emerging two-dimensional(2D)semiconductors are among the most promising materials for ultra-scaled transistors due to their intrinsic atomic-level *** the stacking process advances,the complexity and cost of nanosheet field-effect transistors(NSFETs)and complementary FET(CFET)continue to *** 1 nm technology node is going to be based on Si-CFET process according to international roadmap for devices and systems(IRDS)(2022,https://***/),but not publicly confirmed,indicating that more possibilities still *** miniaturization advantage of 2D semiconductors motivates us to explore their potential for reducing process costs while matching the performance of next-generation nodes in terms of area,power consumption and *** this study,a comprehensive framework is built.A set of MoS2 NSFETs were designed and fabricated to extract the key parameters and *** then for benchmarking,the sizes of 2D-NSFET are scaled to a extent that both of the Si-CFET and 2D-NSFET have the same average device *** these conditions,the frequency of ultra-scaled 2D-NSFET is found to improve by 36%at a fixed power *** work verifies the feasibility of replacing silicon-based CFETs of 1 nm node with 2D-NSFETs and proposes a 2D technology solution for 1 nm nodes,i.e.,“2D eq 1 nm”*** the same time,thanks to the lower characteristic length of 2D semiconductors,the miniaturized 2D-NSFET achieves a 28%frequency increase at a fixed power ***,developing a standard cell library,these devices obtain a similar trend in 16-bit RISC-V *** work quantifies and highlights the advantages of 2D semiconductors in advanced nodes,offering new possibilities for the application of 2D semiconductors in high-speed and low-power integrated circuits.

关键词： Two-dimensional semiconductors 1 nm technology node Nanosheet field-effect transistors Complementary field-effect transistors Horizontal scaling

来源：评论

学校读者我要写书评

暂无评论

Copyright Protection for Large Language Model EaaS via Unforgeable Backdoor Watermarking 27th

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Kong, Cong Chen, Jiawei Tan, Shunquan Yin, Zhaoxia Zhang, Xinpeng Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai200241 China Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen518060 China Fudan University Shanghai200433 China

ISBN: (纸本)9783031784972

Large language models (LLMs) have evolved rapidly and demonstrated superior performance over the past few months. Training these models is both expensive and time-consuming. Consequently, some companies have begun to offer embedding as a service (EaaS) based on these LLMs to reap the benefits. However, this makes them potentially vulnerable to model extraction attacks which can replicate a functionally similar model and thereby infringe upon copyright. To protect the copyright of LLMs for EaaS, we propose a backdoor watermarking method by injecting a secret cosine signal into embeddings of original text with triggers. The secret signal, generated and authenticated using identity information, establishes a direct link between the watermark and the copyright owner. Experimental results demonstrate the method’s effectiveness, showing minimal impact on downstream tasks and high detection accuracy, as well as exhibiting resilience to forgery attacks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Medical Image Classification Attack Based on Texture Manipulation 27th

Medical Image Classification Attack Based on Texture Manipul...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Gu, Yunrui Kong, Cong Yin, Zhaoxia Wang, Yan Li, Qingli School of Communication and Electronic Engineering East China Normal University Shanghai200241 China Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai200241 China

ISBN: (纸本)9783031781971

The security of artificial intelligence systems has received great attention, especially in the field of smart medical diagnosis in over the past few years. In order to enhance the security of smart medical systems, it is important to study adversarial attack methods to increase defense performance, and the central aspect of adversarial attacks lies in crafting effective strategies that can integrate covert malicious behaviors within the system. However, due to the diversity of medical imaging modes and dimensions, creating a unified attack approach that produces imperceptible examples with high content similarity and applies them across various medical image classification systems presents significant challenges. Most existing attack methods aim at attacking natural image classification models, which inevitably add global noise to the image and make the attack more visible, simultaneously does not taking into account that medical image classification task considers texture information more. To address this issue, we propose a new adversarial attack method based on changing texture information that utilizes the CycleGAN approach, while also incorporating AdvGAN to ensure the attack success rate. Our method can provide attacks in various medical image classification tasks. Our experiment includes two public medical image datasets, including chest X-Ray image dataset and melanoma dermoscopy dataset, which contain different imaging modes and dimensions. The results indicate that our model has superior performance in attacking medical image classification tasks in different imaging modes and dimensions compared to other state-of-the-art adversarial attack methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Transportation-Energy-Communication Integrated Management of Ship Cyber-Physical Systems Against Cyber Attacks

引用

IEEE Transactions on Smart Grid 2025年第3期16卷 2518-2528页

作者： Xu, Qimin Li, Xin Jiang, Yuliang Zhu, Shanying Chen, Cailian Yang, Bo Guan, Xinping Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Department of Automation Shanghai200240 China

Ship cyber-physical system (SCPS) is a complex system that integrates advanced information and communication technology to achieve efficient energy management and navigation plans. Thus, SCPS is susceptible to cyber attacks due to increased exposed attack surfaces, which poses significant risks to power and navigation management. The interdependence among the navigation, power, and communication management might amplify the impacts of cyber attacks to induce cascading failures. However, the existing research lacks a robust systematic strategy against cyber attacks considering interdependence features. Therefore, this paper proposes a transportation-energy-communication integrated architecture to collaboratively optimize navigation planning, power management, and networking scheduling. The network model integrates time-sensitive networking (TSN) to improve data transmission reliability and determinacy against cyber attacks. Based on the architecture, the impacts of two typical types of cyber attacks are modeled, including data availability and control signal attacks. A robust cyber-physical defense strategy is formulated into a tri-level MINLP problem to minimize load shedding and voyage distance reduction while saving operation costs by identifying the worst case. To reduce computation complexity, the problem after linearization is decomposed based on the time scale of cyber and physical layers. Case studies indicate that the proposed strategy improves system resilience to conventional strategies. © 2010-2012 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

LK-Net: Efficient Large Kernel ConvNet for Document Enhancement 27th

LK-Net: Efficient Large Kernel ConvNet for Document Enhancem...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Shi, Qijun Zhan, Hongjian Li, Yangfu Zou, Weijun Li, Huasheng Pal, Umapada Lu, Yue Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai200241 China Shanghai Hex Information Technology Co. Ltd. Shanghai China Indian Statistical Institute Kolkata Kolkata India

ISBN: (纸本)9783031783043

Various types of degradation in document images, such as blurring, shadow, and physical wear and tear, significantly impact the effectiveness of downstream tasks in multimedia applications. The need for document image enhancement arises from the urgent need to improve the legibility and quality of these images, which are integral for accurate Optical Character Recognition(OCR), information retrieval, document analysis, etc. This paper introduces a novel and simple approach employing Large Kernel Convolutional Networks (ConvNets) for document image enhancement, capitalizing on their ability to encapsulate expansive contextual information to improve image quality. Extensive experimental evaluations across multiple benchmarks have demonstrated that our method achieves state-of-the-art (SOTA) while maintaining low computational cost. Code and pre-trained models are available at https://***/qijunshi/LKNet. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

RECONSTRUCTION-BASED A POSTERIORI ERROR ESTIMATES FOR THE L1 METHOD FOR TIME FRACTIONAL PARABOLIC PROBLEMS

引用

Journal of Computational Mathematics 2025年第2期43卷 345-368页

作者： Jiliang Cao Aiguo Xiao Wansheng Wang Department of Mathematics Shanghai Normal UniversityShanghai 200234China Hunan Key Laboratory for Computation and Simulation in Science and Engineering&Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan UniversityXiangtan 411105China

In this paper,we study a posteriori error estimates of the L1 scheme for time discretizations of time fractional parabolic differential equations,whose solutions have generally the initial *** derive optimal order a posteriori error estimates,the quadratic reconstruction for the L1 method and the necessary fractional integral reconstruction for the first-step integration are *** using these continuous,piecewise time reconstructions,the upper and lower error bounds depending only on the discretization parameters and the data of the problems are *** numerical experiments for the one-dimensional linear fractional parabolic equations with smooth or nonsmooth exact solution are used to verify and complement our theoretical results,with the convergence ofαorder for the nonsmooth case on a uniform *** recover the optimal convergence order 2-αon a nonuniform mesh,we further develop a time adaptive algorithm by means of barrier function recently *** numerical implementations are performed on nonsmooth case again and verify that the true error and a posteriori error can achieve the optimal convergence order in adaptive mesh.

关键词： Time fractional parabolic differential equations A posteriori error estimates Ll method Fractional integral reconstruction Quadratic reconstruction

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：