检索结果-内蒙古大学图书馆

22nd International Conference on Optical Communications and Networks, ICOCN 2024

作者： Cao, Yang Luo, Yanhua Chen, Wei Wen, Jianxiang Dong, Yanhua Wang, Tingyun Song, Zhiqiang Zhang, Xiaolei Ni, Jiasheng Wang, Jiaying Peng, Gang-Ding Chu, Yushi Zhang, Jianzhong Shanghai Institute for Advanced Communication and Data Science Shanghai University Institute of Optical Fiber Key Laboratory of Specialty Fiber Optics and Optical Access Networks Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication Shanghai200444 China Shanghai Institute for Advanced Communication and Data Science Shanghai University Key Laboratory of Specialty Fiber Optics and Optical Access Networks Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication Shanghai200444 China Laser Institute Qilu University of Technology Shandong Academy of Sciences Shandong Key Laboratory of Optical Fiber Sensing Technologies Jinan250014 China School of Electrical Engineering and Telecommunications University of New South Wales Photonics and Optical Communications Group SydneyNSW2052 Australia College of Physics and Optoelectronic Engineering Harbin Engineering University Key Laboratory of In-fiber Integrated Optics Ministry of Education Harbin150001 China

ISBN: (纸本)9798350367652

A novel vector bending sensor is proposed based on 3D printed seven core fiber (SCF). There are two sensing elements in the proposed sensor. One is the fiber Bragg grating (FBG) inscribed in the 3D printed SCF, and the other is the Mach-Zehnder interferometer (MZI) with the structure of single-mode fiber (SMF)-SCF-SMF. Two sensing elements exhibit significantly different responses to bending. In the curvature range of 1.115 to M-1, the curvature sensitivity of the MZI element is 22.622 nm/M-1, while that of the FBG element is 0.044 nm/M-1 in the same direction. Especially, due to the asymmetrical structure of 3D printed SCF, the proposed bending sensor clearly displays directional dependence. Given to the flexible design and manufacture of 3D printed fiber in structure and material, this study demonstrates that 3D printing fiber technology brings more opportunities for the development of advanced fiber sensors in future Internet of Things. © 2024 IEEE.

关键词： Mach-Zehnder interferometers

来源：评论

学校读者我要写书评

暂无评论

Smart Assessment of Urban Old Residential Areas Based on Object Detection

Smart Assessment of Urban Old Residential Areas Based on Obj...

引用

2023 International Conference on Construction and Real Estate Management: The Human-Centered Construction Transformation, ICCREM 2023

作者： Wang, Shijia Gao, Ming Wang, Hao Gao, Ran School of Management Science and Engineering Central Univ. of Finance and Economics Beijing China School of Management Science and Engineering Key Laboratory of Big Data Management Optimization and Decision of Liaoning Province Dongbei Univ. of Finance and Economics Dalian China

ISBN: (数字)9780784485217

ISBN: (纸本)9780784485217

In the stage of rapid urban renewal, the renovation of old residential areas is moving along very slowly. Traditional methods of old residential areas assessment have the pain points of low efficiency and high consumption of manpower and material resources, while the application of object detection technology in the field of intelligent assessment is more and more extensive, and satisfactory results have been achieved. This paper attempts to explore how to use object detection technology to automatically identify and locate key objects in old communities, such as buildings, parking spaces, and trash bins, so as to realize smart assessment and management of the environment in old residential areas. Through the analysis of experimental results, the effectiveness and practicality of the proposed method are verified. © ASCE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Federated Causally Invariant Feature Learning 39

Federated Causally Invariant Feature Learning

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Guo, Xianjie Yu, Kui Cui, Lizhen Yu, Han Li, Xiaoxiao School of Computer Science and Information Engineering Hefei University of Technology China Key Laboratory of Knowledge Engineering with Big Data of Ministry of Education China School of Software Shandong University China College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical and Computer Engineering The University of British Columbia Canada Vector Institute Canada

ISBN: (纸本)157735897X

Federated feature selection (FFS) is a promising field for selecting informative features while preserving data privacy in federated learning (FL) settings. Existing FFS methods focus on capturing the correlations between features and labels. They struggle to achieve satisfactory performance in the face of data distribution heterogeneity among FL clients, and cannot address the out-of-distribution (OOD) problem that arises when a significant portion of clients do not actively participate in FL training. To address these limitations, we propose Federated Causally Invariant Feature Learning (FedCIFL), a novel approach for learning causally invariant features in a privacy-preserving manner. We design a sample reweighting strategy to eliminate spurious correlations introduced by selection bias and iteratively estimate the federated causal effect between each feature and the labels (with the remaining features initially treated as confounders). By iteratively refining the confounding feature set to identify the true confounders, FedCIFL mitigates the impact of limited local data on the accuracy of federated causal effect estimation. Theoretical analysis proves the correctness of FedCIFL under reasonable assumptions. Extensive experiments on synthetic and real-world datasets demonstrate the superiority of FedCIFL against eight state-of-the-art baselines, beating the best-performing approach by 3.19%, 9.07% and 2.65% in terms of average test Accuracy, RMSE and F1 score, respectively. It is a first-of-its-kind FFS approach capable of handling Non-IID and OOD data simultaneously. The source code is available at https://***/Xianjie-Guo/FedCIFL. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Constant-round auction with insulated bidders

引用

Science China(Information Sciences) 2022年第4期65卷 264-266页

作者： Jie MA Bin QI Kewei LV State Key Laboratory of Information Security Institute of Information EngineeringChinese Academy of Sciences Data Assurance and Communication Security Research Center Chinese Academy of Sciences School of Cyber Security University of Chinese Academy of Sciences

Dear editor,In recent years, online auction has gained widespread popularity as a primary characteristic of electronic commerce among masses. It has also become a primary topic of research interest. Cryptographic primitives such as secure multiparty computation(MPC) [1], zero-knowledge proof(ZKP) [2] and commitment scheme [3] are being effectively utilized for the proposal of various schemes. Therefore,

关键词： Auction Commitment Integer Comparison Protocol Constant-round Blockchain

来源：评论

学校读者我要写书评

暂无评论

Road Crack Detection Algorithm Based on Improved YOLOv8 5

Road Crack Detection Algorithm Based on Improved YOLOv8

引用

2023 5th International Conference on Artificial Intelligence and Computer Applications, ICAICA 2023

作者： Yanfei, Peng Yue, Ji School of Electronic and Information Engineering Liaoning Technical University Liaoning Key Laboratory of Radio Frequency and Big Data for Intelligent Applications Liaoning Huludao125105 China School of Electronic and Information Engineering Liaoning Technical University Liaoning Huludao125105 China

ISBN: (纸本)9798350323313

Road crack detection is of great significance for maintaining road quality, improving road safety, optimizing resource allocation and protecting environment. Aiming at the problems of low recognition accuracy, high false detection rate and false detection rate of existing road crack detection, an improved road crack detection algorithm YOLOv8-YP based on YOLOv8 is proposed. Firstly, the attention mechanism GAM is introduced into the backbone network and neck network to enhance the ability of extracting features of different scales from fracture images. Secondly, SPDConv is used to replace Conv in the backbone network to improve the recognition rate of slender and tiny cracks in the backbone network. Finally, DIoU function is used to optimize the bounding box loss of the network, so that the network can converge quickly and provide finer detection results. The experimental results show that the improved algorithm model YOLOv8-YP and the original algorithm YOLOv8n are improved by 2.2% and 2.3% in mAP @ 0.5 and mAP @ 0.5: 0.95, respectively. The improved algorithm YOLOv8-YP has better detection effect on road cracks, and can identify and locate road cracks quickly and accurately. © 2023 IEEE.

关键词： Crack detection

来源：评论

学校读者我要写书评

暂无评论

Auxiliary Tasks Benefit Skeleton-based Action Recognition

Auxiliary Tasks Benefit Skeleton-based Action Recognition

引用

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

作者： Yuheng Yang Haipeng Chen College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Skeleton-based action recognition has long been a fundamental and intriguing problem in machine intelligence. This task is challenging due to pose occlusion and rapid motion, which typically results in incomplete or noisy skeleton data. State-of-the-art methods tend to learn human motion directly from these corrupted skeletons as if they were reliable. Unfortunately, this might lead to unsatisfactory results when key regions of the skeleton are occluded or disturbed. To tackle the problem, we propose a novel framework that integrates auxiliary tasks into a motion modeling network. These auxiliary tasks corrupt partial human skeletons with masking or noise and then force the network to recover the corrupted data, explicitly facilitating robust feature representation learning. We further propose supervising the auxiliary tasks with mutual information losses, mathematically ensuring feature consistency and spatial alignment between the recovered and original skeleton data. Empirically, our approach sets the new state-of-the-art performance on three benchmark datasets.

关键词： Representation learning Noise Speech recognition Benchmark testing Skeleton Mathematical models Reliability Noise measurement Speech processing Mutual information

来源：评论

学校读者我要写书评

暂无评论

Deep learning approaches in flow visualization

引用

Advances in Aerodynamics 2022年第1期4卷 327-340页

作者： Can Liu Ruike Jiang Datong Wei Changhe Yang Yanda Li Fang Wang Xiaoru Yuan Key Laboratory of Machine Perception(Ministry of Education) and School of AIPeking UniversityBeijingChina China Aerodynamics Research and Development Center MianyangChina National Engineering Laboratory for Big Data Analysis and Application Peking UniversityBeijingChina

With the development of deep learning(DL)techniques,many tasks in flow visualization that used to rely on complex analysis algorithms now can be replaced by DL *** reviewed the approaches to deep learning technology in flow visualization and discussed the technical benefits of these *** also analyzed the prospects of the development of flow visualization with the help of deep learning.

关键词： Deep learning Flow visualization data management Feature extraction Particle tracing

来源：评论

学校读者我要写书评

暂无评论

An SGX and Blockchain-Based System for Federated Learning in Classifying COVID-19 Images 21

An SGX and Blockchain-Based System for Federated Learning in...

引用

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on Big data and Cloud Computing, 16th IEEE International Conference on Social Computing and Networking and 13th International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Qin, Sihang Gu, Xianjun Jun, Xing Li, Haitao Huang, Mengqi Dai, Weiqi Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan430074 China State Grid Wuhan Power Supply Company China

ISBN: (纸本)9798350329223

Federated learning, an emerging distributed learning framework, has gained prominence recently. However, two challenges arise when applying federated learning to medical data. The first challenge stems from the inability of model-generating nodes to ensure computational fairness. The second challenge involves the potential leakage of private information through gradient differences. This paper introduces a federated learning system that leverages Software Guard Extensions (SGX) and blockchain technology to enhance the fairness and security of federated learning for analyzing chest imaging data. The modeling of imaging factors for chest radiography data can effectively regulate the data quality of semi-trusted nodes. A blockchain smart contract is employed for data quality-aware proof, and the quality-aware block undergoes a two-stage rewriting process across distinct nodes. A notary membership model achieves notarized cluster consensus for imaging informatics data. The multi-channel layer model quantifies the distribution of computational workload across participating nodes within the medical consortium. Upon successful verification of the enclave command in the aggregation cycle, traceable and packaged signatures are generated to support computational fairness. To ensure robust information security, SGX remote authentication is used between downstream and upstream nodes. The federated learning system, built upon SGX and blockchain, has been implemented using the Fabric federated chain platform. The ResNet model underwent training through cross-sectional federated learning to effectively classify novel coronavirus lung medical image data. Following this, multiple experimental control and security analyses were conducted, revealing that the time loss incurred due to crossing channels is approximately 21.31%, while the time overhead of SGX remains within 5.2%, as allowed by the number of nodes. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

DiffECN: Differential ECN Marking for datacenter Networks

引用

IEEE/ACM Transactions on Networking 2024年

作者： Huang, Hanlin Xu, Ke Li, Tong Liu, Zhuotao Du, Xinle Gao, Xiangyu Tsinghua University Department of Computer Science and Technology Beijing100084 China Zhongguancun Laboratory Beijing100094 China Renmin University of China Key Laboratory of Data Engineering and Knowledge Engineering Beijing100872 China Tsinghua University Institute for Network Sciences and Cyberspace Beijing100084 China Huawei Shenzhen518129 China

ECN marking has been integrated into datacenter switches to enable high-throughput and low-latency transport. We observe that current marking schemes are coarse-grained: they blindly mark all flows when congestion occurs, causing large flows to occupy undeserved bandwidth and preventing newly arriving small flows from finishing quickly. In this paper, we propose, a differential marking strategy that marks only the flows that are the culprits of congestion and protects the remaining flows from being limited. We have implemented it in the Barefoot Tofino switch and performed extensive evaluations via both physical testbed and large-scale simulations. The results show that can restrain flows responsible for congestion successfully while providing desirable network performance. For instance, compared to the legacy way of ECN marking, achieves up to 32.5% (40.1%) lower average (99th percentile) flow completion time (FCT) for small flows while delivering similar FCT for large flows under production workloads. © 1993-2012 IEEE.

关键词： Congestion control (communication)

来源：评论

学校读者我要写书评

暂无评论

TERMS: Task management policies to achieve high performance for mixed workloads using surplus resources

引用

Journal of Parallel and Distributed Computing 2022年 170卷 74-85页

作者： Yu, Jinyu Tong, Wei Lv, Pengze Feng, Dan Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology School of Computer Science and Technology Huazhong University of Science and Technology Ministry of Education of China Hubei Wuhan China

Resource contentions and performance interferences can lead to workload performance degradation in mixed-workload deployment clusters. Previous work guarantees the resource requirements of latency-sensitive tasks and reduces performance losses to batch jobs by reclaiming surplus resources from over-provisioned tasks. While the fragmentation of resources leads to a mismatch between provisioned resources and task requirements, resulting in high operation overheads and losses of task fairness. This paper proposes TERMS, the task management policies based on task relevance, resource distribution, and task fairness to achieve efficient and low-cost task management. TERMS mainly includes three types of management policies. The task scheduling policy can schedule new tasks according to task relevance. Task selection strategies select tasks for resource provisioning and task resumption based on resource requirements and task fairness. If necessary, the node selection strategy can be used to choose befitting target nodes based on task relevance and node resource information for task migration when eliminating straggler tasks. Evaluation results show that TERMS can further improve the performance of latency-sensitive services and batch jobs, reduce management overheads, and avoid operation failures. © 2022 Elsevier Inc.

关键词： Scheduling

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：