检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Min, Hancheng Mallada, Enrique Vidal, René Center for Innovation in Data Engineering and Science University of Pennsylvania United States Electrical and Computer Engineering Johns Hopkins University United States

This paper studies the problem of training a two-layer ReLU network for binary classification using gradient flow with small initialization. We consider a training dataset with well-separated input vectors: Any pair of input data with the same label are positively correlated, and any pair with different labels are negatively correlated. Our analysis shows that, during the early phase of training, neurons in the first layer try to align with either the positive data or the negative data, depending on its corresponding weight on the second layer. A careful analysis of the neurons’ directional dynamics allows us to provide an O(log √µn ) upper bound on the time it takes for all neurons to achieve good alignment with the input data, where n is the number of data points and µ measures how well the data are separated. After the early alignment phase, the loss converges to zero at a O(1t ) rate, and the weight matrix on the first layer is approximately low-rank. Numerical experiments on the MNIST dataset illustrate our theoretical findings. Copyright © 2023, The Authors. All rights reserved.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Cooperative Situation Awareness of Multi-UAVs Based on Multi-sensor Information Fusion

Cooperative Situation Awareness of Multi-UAVs Based on Multi...

引用

International Conference on Guidance, Navigation and Control, ICGNC 2022

作者： Liao, Zirui Wang, Shaoping Shi, Jian Li, Zhenkun Sial, Muhammad Baber School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big-Data Based Precision Medicine Beihang University Beijing100191 China Shenyuan Honors College Beihang University Beijing100191 China

ISBN: (纸本)9789811966125

In recent years, situation awareness has been an essential research subject in the field of low altitude combat. However, previous work mainly focused on single unmanned aerial vehicle (UAV) detection, while it may obtain inaccurate information about the environment due to the limited detection ability and uncertainty of single airborne sensor. By contrast, this paper considers the cooperative detection of multi-UAVs and proposes a cooperative situation awareness method on the basis of multi-sensor information fusion. Firstly, obstacle information is detected and obtained by multiple airborne sensors considering the sensors’ uncertainty. Subsequently, D-S evidence theory is introduced to conduct the information fusion of obstacle with high confidence and more accurate obstacle coordinates are obtained. Next, the simulations of information fusion are conducted under fixed and flexible formations. Eventually, numerical results verify the validity of the proposed information fusion method, which can perceive the situation more accurately and reach at most 96.58% degree of confidence in a specific formation, thus achieving a precise cooperative situation awareness. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Attention Semi-Supervised Network Based on Confidence Iteration and Pseudo-Label Optimization for COVID-19 CT Segmentation 42

Multi-Scale Attention Semi-Supervised Network Based on Confi...

引用

42nd Chinese Control Conference, CCC 2023

作者： Liu, Kun Chen, Mei Xie, Junfei Mao, JingKun Liu, WeiPeng School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin300130 China Tianjin University of Technology Department of Automation Tianjin300384 China Hebei University of Technology Control Engineering Technology Innovation Center of Hebei Province Tianjin300401 China

ISBN: (纸本)9789887581543

Computed tomography (CT) image segmentation for COVID-19 lung infection has made great progress. However, accurate segmentation remains a major challenge due to the varying shape and size of COVID-19 infected areas, the more similar tissue of infected lung images to normal lung images, and the additional problem of a limited number of medical images annotated at the pixel level. In this paper, we propose a semi-supervised segmentation network based on confidence iteration and pseudo-label optimization for COVID-19 CT segmentation. In addition, we develop a multi-scale attention module which can achieve attentional feature fusion at different scales. The experiment evaluated on the COVID-19 CT Segmentation dataset, demonstrate our method achieves higher segmentation accuracy than the state-of-art methods. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

An infrastructure with user-centered presentation data model for integrated management of materials data and services

引用

npj Computational Materials 2021年第1期7卷 779-786页

作者： Shilong Liu Yanjing Su Haiqing Yin Dawei Zhang Jie He Haiyou Huang Xue Jiang Xuan Wang Haiyan Gong Zhuang Li Hao Xiu Jiawang Wan Xiaotong Zhang Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology BeijingBeijingChina School of Computer and Communication Engineering University of Science and Technology BeijingBeijingChina Beijing Key Laboratory of Knowledge Engineering for Materials Science BeijingChina Corrosion and Protection Center University of Science and Technology BeijingBeijingChina Collaborative Innovation Center of Steel Technology University of Science and Technology BeijingBeijingChina National Materials Corrosion and Protection Data Center Institute for Advanced Materials and TechnologyUniversity of Science and Technology BeijingBeijingChina Institute for Advanced Materials and Technology University of Science and Technology BeijingBeijingChina Beijing Key Laboratory of Materials Genome Engineering University of Science and Technology BeijingBeijingChina

With scientific research in materials science becoming more data intensive and collaborative after the announcement of the Materials Genome Initiative,the need for modern data infrastructures that facilitate the sharing of materials data and analysis tools is compelling in the materials *** this paper,we describe the challenges of developing such infrastructure and introduce an emerging architecture with high *** call this architecture the Materials Genome engineering databases(MGED).MGED provides cloud-hosted services with features to simplify the process of collecting datasets from diverse data providers,unify data representation forms with user-centered presentation data model,and accelerate data discovery with advanced search *** also provides a standard service management framework to enable finding and sharing of tools for analyzing and processing *** describe MGED’s design,current status,and how MGED supports integrated management of shared data and services.

关键词： services service centered

来源：评论

学校读者我要写书评

暂无评论

Comparison between Grad-CAM and EigenCAM on YOLOv5 detection model

Comparison between Grad-CAM and EigenCAM on YOLOv5 detection...

引用

2022 International Symposium on Electronics and Smart Devices, ISESD 2022

作者： Rahman, Arief Nur Andriana, Dian MacHbub, Carmadi Bandung Inst. of Technol. Res. Center for Telecommunications National Research and Innovation Agency School of Electrical Engineering and Informatics Bandung Indonesia Telkom University Research Center for Data and Information Science National Research and Innovation Agency School of Computing Bandung Indonesia

ISBN: (数字)9798350396607

ISBN: (纸本)9798350396607

This paper presents a comparison between Grad-CAM and EigenCAM methods on the YOLOv5 detection model. Explainable Artificial Intelligence (XAI) is a tool to understand and interpret machine learning models. XAI is used to understand which pixel from an image contributes significantly to the model's final output. EigenCAM is quite simple but a very powerful technique for producing visual explanations, but Grad-CAM is better for a low illumination environment. © 2022 IEEE.

关键词： Cams

来源：评论

学校读者我要写书评

暂无评论

Synthesis of Decoherence-Free Modes in Linear Quantum Passive Systems via Robust Pole Placement

Synthesis of Decoherence-Free Modes in Linear Quantum Passiv...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Miao, Zibo Pan, Yu Gao, Qing School of Mechanical Engineering and Automation Adaptive Robotics Harbin Institute of Technology Guangdong Key Laboratory of Intelligent Morphing Mechanisms Shenzhen518055 China The Institute of Cyber-Systems and Control College of Control Science and Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China The School of Automation Science and Electrical Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

ISBN: (纸本)9781665410205

In this paper we extend our previous research on coherent observer-based pole placement approach to study the synthesis of robust decoherence-free (DF) modes for linear quantum passive systems, which is aimed at preservation of quantum information. In particular, DF modes can be generated by placing the poles on the imaginary axis via a coherent feedback design scheme, and these modes can further be simultaneously made robust against perturbations to the system parameters by minimizing the condition number associated with imaginary poles. We develop explicit algebraic conditions for the existence of such a coherent quantum controller, with the corresponding deign procedure provided. Examples are given to illustrate the process of tuning the DF modes towards perfect robustness via the proposed pole placement technique. © 2024 IEEE.

关键词： Poles

来源：评论

学校读者我要写书评

暂无评论

Development of a Mental Health Chatbot Using Large Language Models for Indonesian Undergraduates 11

Development of a Mental Health Chatbot Using Large Language ...

引用

11th International Conference on Computer, Control, Informatics and its Applications, IC3INA 2024

作者： Gumilang, Mukhamad Angga Karsanti, Hayuning Titi Linsiya, Ria Wiyatfi Yudanarko, Kimi Dandy Sari, Lisa Novita Saputra, Ariz Salsabila, Naela Zahwa Department of Electrical Engineering and Information Technology Universitas Gadjah Mada Yogyakarta Indonesia Research Center for Data Science and Information Science National Research and Innovation Agency Jakarta Indonesia Faculty of Psychology Universitas Muhammadiyah Jember Jember Indonesia Department of Information Technology Politeknik Negeri Jember Jember Indonesia Departement of Health Politeknik Negeri Jember Jember Indonesia

ISBN: (纸本)9798331542313

Mental health issues among university students are an escalating global problem, especially in Indonesia. Young adults, especially college students, are a vulnerable demographic due to academic pressures, social transitions, and the challenges of independent living. This paper describes the development of a mental health chatbot specifically for Indonesian university students, utilizing large language models (LLMs). The development encompassed three essential phases: establishing a knowledge base, refining the LLM with culturally pertinent Indonesian data, and assessing the system. The findings demonstrated notable enhancements in the chatbot's precision, with training accuracy rising from 0.6 to 0.85 and validation accuracy from 0.5 to 0.79 due to fine-tuning and regularization. User acceptability testing including 58 students resulted in an acceptance percentage of 87.38%, indicating substantial satisfaction with the chatbot's response and usefulness. This research highlights the efficacy of AI-driven interventions in addressing the mental health requirements of Indonesian university students. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

From Knowledge Graph Development to Serving Industrial Knowledge Automation:A Review 41

From Knowledge Graph Development to Serving Industrial Knowl...

引用

第41届中国控制会议

作者： Guangxuan Song Dongmei Fu Dawei Zhang Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical EngineeringUniversity of Science and Technology Beijing Beijing Engineering Research Center of Industrial Spectrum Imaging School of Automation and Electrical EngineeringUniversity of Science and Technology Beijing Shunde Graduate School of University of Science and Technology Beijing Beijing Advanced Innovation Center for Materials Genome Engineering Institute for Advanced Materials and TechnologyUniversity of Science and Technology Beijing National Materials Corrosion and Protection Data Center University of Science and Technology Beijing

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Knowledge is essential for the management,scheduling,and operation of all industrial *** automation refers to the automation of knowledge-based work,which is a disruptive technology of the *** in the era of big data,KG inherits the good interpretability of traditional symbolism system approaches and becomes one of the feasible and important directions to realize industrial knowledge *** paper begins with the origin of KGs,introduces the characteristics of KGs,and reviews the state of the art of KG through the cases of KG constructed and applied in general and vertical *** paper also focuses on the research progress of KG applications in industry,by identifying the current challenges of KG in industrial applications,and highlighting the substantial potential of KG to serve knowledge automation.

关键词： Knowledge Knowledge Graph(KG) Knowledge Automation Symbolism Industry

来源：评论

学校读者我要写书评

暂无评论

MP-DPCC: A Motion Proxy-Based Dynamic Point Cloud Compression Framework

MP-DPCC: A Motion Proxy-Based Dynamic Point Cloud Compressio...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Jiang, ZhaoYi Han, Dong Song, Cao Nan, FangZhe Yang, Bailin School of Computer Science and Technolgy Zhejiang Gongshang University China School of Statistics and Mathematics Zhejiang Gongshang University China Economic Forecasting and Policy Simulation Laboratory Zhejiang Gongshang University China Collaborative Innovation Center of Statistical Data Engineering Technology & Application Zhejiang Gongshang University China

ISBN: (纸本)9798350368741

The increasing data volume and the demand for real-time transmission highlight the necessity for efficient compression of dynamic point cloud data. Existing methods primarily focus on reducing inter-frame redundancy by calculating per-point motion information, overlooking the computational and storage costs involved. In this paper, we propose a novel motion proxy-based dynamic point cloud compression framework to enhance the efficiency and accuracy of motion information utilization. Specifically, we introduce a feature proxy module to adaptively locate proxy points, which represent the overall motion through the motion of proxy points. Additionally, a motion enhancement module is employed to refine motion details and prevent local information loss caused by dense motion trajectories. Extensive experiments demonstrate the superiority of our approach. Compared with baseline methods, it achieves an average BD-rate improvement of 12.07% (D1) and 11.90% (D2). © 2025 IEEE.

关键词： compression deep learning neural network point cloud

来源：评论

学校读者我要写书评

暂无评论

Person Re-Identification with Model-Contrastive Federated Learning in Edge-Cloud Environment

引用

Intelligent Automation & Soft Computing 2023年第10期38卷 35-55页

作者： Baixuan Tang Xiaolong Xu Fei Dai Song Wang School of Computer and Software Nanjing University of Information Science and TechnologyNanjing210044China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Nanjing University of Information Science and TechnologyNanjing210044China School of Big Data and Intelligence Engineering Southwest Forestry UniversityKunming650233China Nanjing Meteorological Service Center Nanjing Meteorological BureauNanjing210019China

Person re-identification(ReID)aims to recognize the same person in multiple images from different camera *** person ReID models are time-consuming and resource-intensive;thus,cloud computing is an appropriate model training ***,the required massive personal data for training contain private information with a significant risk of data leakage in cloud environments,leading to significant communication *** paper proposes a federated person ReID method with model-contrastive learning(MOON)in an edge-cloud environment,named ***,based on federated partial averaging,MOON warmup is added to correct the local training of individual edge servers and improve the model’s effectiveness by calculating and back-propagating a model-contrastive loss,which represents the similarity between local and global *** addition,we propose a lightweight person ReID network,named multi-branch combined depth space network(MB-CDNet),to reduce the computing resource usage of the edge device when training and testing the person ReID ***-CDNet is a multi-branch version of combined depth space network(CDNet).We add a part branch and a global branch on the basis of CDNet and introduce an attention pyramid to improve the performance of the *** experimental results on open-access person ReID datasets demonstrate that FRM achieves better performance than existing baseline.

关键词： Person re-identification federated learning contrastive learning

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：