检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Li, Lin Gou, Jianping Yu, Baosheng Du, Lan Yi, Zhang Tao, Dacheng The School of Computer Science and Communication Engineering Jiangsu Key Laboratory of Security Tech. for Industrial Cyberspace Jiangsu University Zhenjiang212013 China The College of Computer and Information Science College of Software Southwest University Chongqing400715 China The School of Computer Science Faculty of Engineering The University of Sydney DarlingtonNSW2008 Australia The Faculty of Information Technology Monash University ClaytonVIC Australia The School of Computer Science Sichuan University Chengdu610065 China The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore

Federated Learning (FL) seeks to train a model collaboratively without sharing private training data from individual clients. Despite its promise, FL encounters challenges such as high communication costs for large-scale models and the necessity for uniform model architectures across all clients and the server. These challenges severely restrict the practical applications of FL. To address these limitations, the integration of knowledge distillation (KD) into FL has been proposed, forming what is known as Federated Distillation (FD). FD enables more flexible knowledge transfer between clients and the server, surpassing the mere sharing of model parameters. By eliminating the need for identical model architectures across clients and the server, FD mitigates the communication costs associated with training large-scale models. This paper aims to offer a comprehensive overview of FD, highlighting its latest advancements. It delves into the fundamental principles underlying the design of FD frameworks, delineates FD approaches for tackling various challenges, and provides insights into the diverse applications of FD across different scenarios. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

FedCST: Federated Learning on Heterogeneous Resource-constrained Devices Using Clustering and Split Training

FedCST: Federated Learning on Heterogeneous Resource-constra...

引用

IEEE International Conference on software Quality, Reliability and Security Companion (QRS-C)

作者： Zhilu Wang Haiyang Lin Qi Liu Yonghong Zhang Xiaodong Liu Nanjing University of Information Science and Technology School of Computer Science Nanjing Jiangsu China Nanjing University of Information Science and Technology School of Software Nanjing Jiangsu China Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services Nanjing Jiangsu China Nanjing University of Information Science and Technology School of Automation Nanjing Jiangsu China Edinburgh Napier University School of Computing Edinburgh UK

ISBN: (数字)9798350365658

ISBN: (纸本)9798350365665

With the rapid development of 5G and Internet of Things (IoT) technologies, edge devices such as sensors, smartphones, and wearable devices have become increasingly prevalent. The massive amount of distributed data generated by these devices offers unprecedented opportunities for deep learning, especially in fields like computer vision and edge computing. However, this data often exists in isolated data silos, and due to its privacy-sensitive nature, it cannot be directly processed in a centralized manner. Additionally, the data heterogeneity and devices heterogeneity further exacer-bates the challenges in federated learning (FL). Moreover, with the implementation of data privacy protection regulations, user demand for privacy protection is growing significantly. Therefore, how to effectively utilize dispersed data for distributed collaborative learning while ensuring data privacy is a pressing issue that needs to be addressed in the field of FL. In response to these challenges, this work has conducted research on clustering and segmentation FL algorithms for heterogeneous resource-constrained devices. A lightweight homogeneous device clustering strategy has been designed, which incorporates a split learning (SL) mechanism to enhance the accuracy and training efficiency of FL models. This approach reduces the load on resource-constrained devices and improves privacy security. Consequently, this method can meet the dual requirements of privacy protection and computational efficiency in real-world scenarios.

关键词： Training Data privacy Privacy Federated learning Computational modeling Distributed databases Security Internet of Things Protection Edge computing

来源：评论

学校读者我要写书评

暂无评论

Development of a Soft Hand and Wrist Rehabilitation Robot Utilizing Lattice Structure Actuators

Development of a Soft Hand and Wrist Rehabilitation Robot Ut...

引用

World Rehabilitation Robot Convention (WRRC)

作者： Jianwei Lai Aiguo Song Wenbin Zhang Ye Lu Jiajin Wang Ye Li State Key Laboratory of Digital Medical Engineering Jiangsu Key Laboratory of Remote Measurement and Control School of Instrument Science and Engineering Southeast University Nanjing China College of Computer Science and Software Engineering Hohai University Nanjing China

ISBN: (数字)9798350355123

ISBN: (纸本)9798350355130

Soft robots offer promising solutions for rehabilitation due to their inherent attributes such as suppleness, lightweight construction, and safety features. However, prevalent soft actuators face limitations in output force and bending angle, impeding their effective application in rehabilitation. This paper proposes a novel design approach employing a two-layer lattice structure actuator, comprising flexion, guiding, and extension layers. This innovative design facilitates supple and efficient bi-directional rehabilitation training for fingers and wrists. Experimental results demonstrate the efficacy of the proposed dual-layer lattice structure actuator. At an air pressure of 150 kPa, it achieves an end force of 14.88 N, marking a remarkable 906% increase compared to its single-layer counterpart. Additionally, the dual-layer structure exhibits a minimum bending radius of 2.77 cm under 60 kPa, representing a 38.5% reduction relative to the single-layer actuator. Leveraging these actuators, a hand and wrist rehabilitation robot was developed and subjected to a clinical trial involving two healthy subjects. The trial outcomes reveal significant improvements in finger grasping ability and wrist range of motion with the assistance of the rehabilitation robot. These results underscore the practical usability and effectiveness of the soft hand and wrist rehabilitation robot, thereby holding promise for enhancing patient rehabilitation outcomes.

关键词： Wrist Training Actuators Force Lattices Bending Soft robotics Assistive robots Usability Periodic structures

来源：评论

学校读者我要写书评

暂无评论

Lane marking detection algorithm based on high-precision map and multisensor fusion

Lane marking detection algorithm based on high-precision map...

引用

作者： Yao, Haichang Chen, Chen Liu, Shangdong Li, Kui Ji, Yimu Huang, Guangyan Wang, Ruchuan School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China School of Computer and Software Nanjing Institute of Industry Technology Nanjing China Industrial Software Engineering Technology Research and Development Center of Jiangsu Education Department Nanjing Institute of Industry Technology Nanjing China Jiangsu HPC and Intelligent Processing Engineer Research Center Nanjing China Institute of High Performance Computing and Bigdata Nanjing University of Posts and Telecommunications Nanjing China School of Information Technology Deakin University Melbourne Australia

In case of sharp road illumination changes, bad weather such as rain, snow or fog, wear or missing of the lane marking, the reflective water stain on the road surface, the shadow obstruction of the tree, and mixed lane markings and other signs, missing detection or wrong detection will occur for the traditional lane marking detection algorithm. In this manuscript, a lane marking detection algorithm based on high-precision map and multisensor fusion is proposed. The basic principle of the algorithm is to use the centimeter-level high-precision positioning combined with high-precision map data to complete the detection of lane markings. In the process of generating high-precision maps or in the uncovered areas of high-precision maps, LIDAR (LIght Detection And Ranging) is used to estimate the curvature of the road to assist in lane marking detection. The experimental results show that the algorithm has lower false detection rate in case of bad road conditions, and the algorithm is robust. © 2020 John Wiley & Sons, Ltd.

关键词： Roads and streets

来源：评论

学校读者我要写书评

暂无评论

Convolution-Enhanced Transformer with Frequency Domain Contrastive Learning for Image Deraining

Convolution-Enhanced Transformer with Frequency Domain Contr...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Cheng Wang Wei Li School of Artificial Intelligence and Computer Science & Jiangsu Key Laboratory of Media Design and Software Technology & Engineering Research Center of Itelligent Technology for Healthcare Ministry of Education Jiangnan University Wuxi China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Rainfall, as a ubiquitous atmospheric phenomenon, causes visual image degradation through rain streaks, which in turn hinders human vision and degrades the performance of subsequent computer vision algorithms. In order to further improve the performance of visual algorithms in harsh rain environments, image rain removal technology has become a hot topic in this field. In computer vision, the integration of the Vision Transformer (ViT) marks an important progress, and its transfer application to the image rain removal task has achieved remarkable success. However, the application of transformers in this task still faces challenges. While they excel at modelling long-range dependencies, transformers are less adept at modelling local contexts for image restoration tasks. Moreover, the internal transmission of features within dense transformer layers often needs more finesse. In this paper, we tackle these shortcomings by incorporating convolutional mechanisms within both the self-attention components of the transformer blocks and the subsequent feed-forward networks. We refine the feature flows amalgamated between recursive transformer blocks by utilizing feature fusion strategies. To further refine the high-frequency textural details of images, we employ frequency domain contrastive learning techniques to augment the delineation of contrastive sample information, ensuring that the restored image closely resembles the clear image in terms of texture structure while maintaining a distinction from the rain image. Extensive quantitative and qualitative experimental results show that the proposed deraining network surpasses mainstream methods on public datasets.

关键词： computer vision Visualization Rain Frequency-domain analysis Computational modeling Contrastive learning Transformers

来源：评论

学校读者我要写书评

暂无评论

A Robust 3-D Medical Watermarking Based on Wavelet Transform for Data Protection

引用

computer Systems Science & engineering 2022年第6期41卷 1043-1056页

作者： Xiaorui Zhang Wenfang Zhang Wei Sun Xingming Sun Sunil Kumar Jha Engineering Research Center of Digital Forensics Ministry of EducationJiangsu Engineering Center of Network MonitoringSchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Nanjing University of Information Science&TechnologyNanjing210044China Wuxi Research Institute Nanjing University of Information Science&TechnologyWuxi214100China IT Fundamentals and Education Technologies Applications University of Information Technology and Management in RzeszowRzeszowVoivodeship100031Poland

In a telemedicine diagnosis system,the emergence of 3D imaging enables doctors to make clearer judgments,and its accuracy also directly affects doctors’diagnosis of the *** order to ensure the safe transmission and storage of medical data,a 3D medical watermarking algorithm based on wavelet transform is proposed in this *** proposed algorithm employs the principal component analysis(PCA)transform to reduce the data dimension,which can minimize the error between the extracted components and the original data in the mean square ***,this algorithm helps to create a bacterial foraging model based on particle swarm optimization(BF-PSO),by which the optimal wavelet coefficient is found for embedding and is used as the absolute feature of watermark embedding,thereby achieving the optimal balance between embedding capacity and imperceptibility.A series of experimental results from MATLAB software based on the standard MRI brain volume dataset demonstrate that the proposed algorithm has strong robustness and make the 3D model have small deformation after embedding the watermark.

关键词： 3-D medical watermarking robust watermarking PCA BF-PSO

来源：评论

学校读者我要写书评

暂无评论

Robust Reversible Audio Watermarking Scheme for Telemedicine and Privacy Protection

引用

computers, Materials & Continua 2022年第5期71卷 3035-3050页

作者： Xiaorui Zhang Xun Sun Xingming Sun Wei Sun Sunil Kumar Jha Engineering Research Center of Digital Forensics Ministry of EducationJiangsu Engineering Center of Network MonitoringSchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China Wuxi Research Institute Nanjing University of Information Science&TechnologyWuxi214100China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science&TechnologyNanjing210044China IT Fundamentals and Education Technologies Applications University of Information Technology and Management in RzeszowRzeszow Voivodeship100031Poland

The leakage of medical audio data in telemedicine seriously violates the privacy of *** order to avoid the leakage of patient information in telemedicine,a two-stage reversible robust audio watermarking algorithm is proposed to protect medical audio *** scheme decomposes the medical audio into two independent embedding domains,embeds the robust watermark and the reversible watermark into the two domains *** order to ensure the audio quality,the Hurst exponent is used to find a suitable position for watermark *** to the independence of the two embedding domains,the embedding of the second-stage reversible watermark will not affect the first-stage watermark,so the robustness of the first-stage watermark can be well *** the second stage,the correlation between the sampling points in the medical audio is used to modify the hidden bits of the histogram to reduce the modification of the medical audio and reduce the distortion caused by reversible *** experiments show that this scheme has strong robustness against signal processing operations such as MP3 compression of 48 db,additive white Gaussian noise(AWGN)of 20 db,low-pass filtering,resampling,re-quantization and other attacks,and has good imperceptibility.

关键词： Telemedicine privacy protection audio watermarking robust reversible watermarking two-stage embedding

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Object Detection:A Survey

引用

computer Systems Science & engineering 2021年第8期38卷 165-182页

作者： Jun Wang Tingjuan Zhang Yong Cheng Najla Al-Nabhan Science and Technology Industry Department Nanjing University of Information Science&Technology210044China School of Computer&Software Jiangsu Engineering Center of Network MonitoringNanjing University of Information Science&Technology210044China Department Computer Science King Saud UniversityRiyadhKSA

Object detection is one of the most important and challenging branches of computer vision,which has been widely applied in people s life,such as monitoring security,autonomous driving and so on,with the purpose of locating instances of semantic objects of a certain *** the rapid development of deep learning algorithms for detection tasks,the performance of object detectors has been greatly *** order to understand the main development status of target detection,a comprehensive literature review of target detection and an overall discussion of the works closely related to it are presented in this *** paper various object detection methods,including one-stage and two-stage detectors,are systematically summarized,and the datasets and evaluation criteria used in object detection are *** addition,the development of object detection technology is ***,based on the understanding of the current development of target detection,we discuss the main research directions in the future.

关键词： Object detection convolutional neural network computer vision

来源：评论

学校读者我要写书评

暂无评论

Design of Concurrent engineering Systems for Global Product Development Using Artificial Intelligence 10th

Design of Concurrent Engineering Systems for Global Product ...

引用

10th International Conference on Innovations in computer Science and engineering, ICICSE 2022

作者： Karn, Arodh Lal Mehbodniya, Abolfazl Webber, Julian L. Jayagopal, Vellingiri Stalin David, D. Rangasamy, Rajasekar Sengan, Sudhakar Department of Financial and Actuarial Mathematics School of Mathematics and Physics Xi’an Jiaotong-Liverpool University Jiangsu Suzhou215123 China Kuwait City Kuwait Department of Software and System Engineering School of Information Technology and Engineering Vellore Institute of Technology Tamil Nadu Vellore632014 India Department of Information Technology Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College Tamil Nadu Chennai600072 India Department of Computer Science and Engineering GITAM School of Technology GITAM University Karnataka Bengaluru561203 India Department of Computer Science and Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli627152 India

ISBN: (纸本)9789811974540

Competition and concurrent engineering (CE) businesses are growing. Faster product creation, quality improvement, manufacturing process adoption, and reduced client demand cost are vital for corporate success. Implement concurrent engineering to make high-quality goods. CE is a parallel, systematic method to design. The chief executive officer (CEO’s) approach impacted how many firms build products. You may use the fundamental ideas of concurrent engineering conversation and the failure mode and effects analysis (FMEA) tool. To provide a smooth and efficient CE environment, conduct the product development process from market research to detailed design. Concurrent engineering is a novel product development (NPD) approach. Concurrency and cross-functional integration separate CE from traditional product development. NPD continues through developing ideas, validation, proof-of-concept validation, Minimum Viable Product development, pre-launch, and post-launch. In other words, product discovery should continue throughout its life span. Each organization's growth operations operate simultaneously. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Product development

来源：评论

学校读者我要写书评

暂无评论

Extended Abstract of Candidate Test Set Reduction for Adaptive Random Testing: An Overheads Reduction Technique

Extended Abstract of Candidate Test Set Reduction for Adapti...

引用

IEEE International Conference on software Analysis, Evolution and Reengineering (SANER)

作者： Rubing Huang Haibo Chen Weifeng Sun Dave Towey Faculty of Information Technology Macau University of Science and Technology Taipa Macau China School of Computer Science and Communication Engineering Jiangsu University Zhenjiang Jiangsu China School of Big Data and Software Engineering Chongqing University Chongqing China School of Computer Science University of Nottingham Ningbo China Ningbo Zhejiang China

This document 1 is an extended abstract of a Science of computer Programming paper, "Candidate Test Set Reduction for Adaptive Random Testing: An Overheads Reduction Technique," presented as a J1C2 (Journal publication first, Conference presentation following) at the 30th IEEE International Conference on software Analysis, Evolution and Reengineering (Saner 2023).The paper presents a candidate set reduction strategy to enhance the Fixed-Sized-Candidate-Set version of Adaptive Random Testing (FSCS-ART). The proposed method reduces the number of randomly-generated candidate test cases by retaining valuable, unused candidates from previous iterations. As the computational costs associated with a stored/retained candidate are less than the costs associated with a randomly-generating one, the overall computational overheads of FSCS-ART are reduced. The reported experimental studies show that the proposed method has a comparable failure-detection effectiveness to FSCS-ART, but less computational overheads.

关键词： Costs Programming software Power capacitors Computational efficiency Testing

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：