检索结果-内蒙古大学图书馆

4th IEEE International Conference on Civil Aviation Safety and information technology, ICCASIT 2022

作者： Zhang, Huimin Guan, Guixia Zhao, Haimeng Liu, Xintao Xue, Letang Xiong, Chuan Capital Normal University Information Engineering College Beijing China Remote Sensing Guilin University of Aerospace Technology Guilin China Beijing Key Lab of Spatial Information Integration and Its Applications Peking University Beijing China Jiangsu Jinling Machinery Manufacturing Plant Nanjing China Opto-electronic Department in Changchun Institute of Optics Fine Mechanics and Physics Chinese Academy of Science Changchun China

ISBN: (数字)9781665467667

ISBN: (纸本)9781665467667

In recent years, image processing systems designed on an embedded basis have received increasing attention due to their small size, low power consumption and low cost. In this paper, we design an embedded image transmission system with ARM chip as the core. The system uses STM32F407 as the microcontroller, transplants LwIP protocol as the embedded Ethernet protocol stack, implements the transmission function in combination with Ethernet hardware interface, and completes the image data transmission function through socket send and receive functions. In this paper, the whole system is described in terms of the overall architecture of the system as well as the system software design. The system has been tested to achieve the image transmission function. © 2022 IEEE.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Graph-Tensor FISTA-Net: Edge Computing-Aided Deep Learning for Distributed Traffic Data Recovery

引用

IEEE Transactions on Network science and engineering 2025年

作者： Deng, Lei Liu, Xiao-Yang Zheng, Haifeng Feng, Xinxin Zhu, Ming Tsang, Danny H. K. Fuzhou University Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou China Internet of Things Thrust Guangdong Guangzhou511400 China Columbia University Department of Electrical Engineering NY United States Chinese Academy of Sciences Institute of Automation Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Clear Water Bay Hong Kong

In intelligent transportation systems, deep learning is a widely adopted technique for traffic data recovery. In city-wide traffic data recovery tasks, traditional centralized deep-learning-model training strategies become inapplicable because of the expensive storage costs for large-scale traffic datasets. In this scenario, edge computing emerges as a natural choice, allowing decentralized data storage and distributed training on edge nodes. However, there is still a challenge: distributed training on edge nodes suffers from high communication costs for parameter transmission. In this paper, we propose a communication-efficient Graph-Tensor Fast Iterative Shrinkage-Thresholding Algorithm-based neural Network (GT-FISTA-Net) for distributed traffic data recovery. Firstly, we model the recovery task as a graph-tensor completion problem to better capture the low-rankness of traffic data. A recovery guarantee is also provided to characterize the performance bounds of the proposed scheme in terms of recovery error. Secondly, we propose a distributed graph-tensor completion algorithm and unfold it into a deep neural network called GT-FISTA-Net. GT-FISTA-Net requires small communication costs for distributed model training on edge nodes and thus it is applicable for city-wide traffic data recovery. Extensive experiments on real-world datasets show that the proposed GT-FISTA-Net can also provide excellent recovery accuracy compared with state-of-the-art distributed recovery methods. © 2013 IEEE.

关键词： distributed learning Edge computing Graph-tensor tensor completion traffic data recovery

来源：评论

学校读者我要写书评

暂无评论

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xiaoke Zhu Danyang Li Xiaopan Chen Fumin Qi Fan Zhang Xiao-Yuan Jing School of Computer and Information Engineering Henan University Kaifeng China Henan Engineering Research Center of Intelligent Technology and Application Henan University Kaifeng China Department of System Operation National Supercomuting Center in Shenzhen Shenzhen China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China School of Computer Science Wuhan University Wuhan China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Facial image based kinship verification aims to decide whether there exists kinship between the given facial images. In practice, the cross-generation differences will cause adverse effects on kinship verification, which limits the performance. Therefore, how to mine the implied similarity from facial images with large cross-generation divergence is an important problem in kinship verification, which has not yet been well studied. In view of this, we propose a Similarity Mining via Implicit matching pattern LEarning (SMILE) approach for kinship verification. Specifically, SMILE mainly consists of two modules, including a Semi-coupled Multi-pattern Similarity Learning (SMSL) module and a Cross-Generation Feature Normalization (CGFN) module. The SMSL module is designed to learn multiple semi-coupled matching patterns for mining the implicit facial similarity information from different perspectives. The CGFN module aims to reduce the divergence between facial images of parent and child. Extensive experiments demonstrate that the proposed approach outperforms the existing state-of-the-art methods.

关键词： Pattern matching Similarity learning

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Pneumatic Soft Gripper with Suction and Grasp Composite Structure 5th

Design and Implementation of Pneumatic Soft Gripper with Suc...

引用

5th International Conference on Cognitive systems and Signal Processing, ICCSIP 2020

作者： Huang, Haiming Liang, Xiaotao Zhuo, Yufan Wu, Linyuan Wen, Zhenkun Sun, Fuchun College of Electronic and Information Engineering Shenzhen University Shenzhen518060 China Peng Cheng Lab Shenzhen GD518055 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Department of Computer Science and Technology Tsinghua University Beijing100084 China

ISBN: (纸本)9789811623356

Robot gripper is used in many different places at present, but traditional gripper is difficult to grasp and sort soft and fragile fruits and vegetables effectively. Based on manipulator technology, this paper presents a design scheme of pneumatic multi-fingered gripper. This design combines the vacuum chunk and soft fingers to make the gripper precisely grasp the target object without damaging the surface of the object. The flexible fingers can be made quickly by using a compound injection molding method. Combined with the STM32 microcontroller and the Universal Robots 5 (UR Arm), the operation system of the soft gripper is realized, and the man-machine interaction presents a good performance. Through the grasping experiment, it is proved that the prototype can grasp, transport, and place soft and fragile objects stably and accurately. Overall, this design implements the combination of pneumatic unit and soft gripper, and provides a new orientation to the research of soft robot. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Grippers

来源：评论

学校读者我要写书评

暂无评论

Attribution of regional Hadley circulation intensity changes in the Northern Hemisphere

引用

Atmospheric and Oceanic science Letters 2025年

作者： Zheng, Yi Sun, Bo Li, Wanling Zhou, Siyu Cai, Jiarui Li, Huixin He, Shengping State Key Laboratory of Climate System Prediction and Risk Management/Key Laboratory of Meteorological Disaster Ministry of Education/Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters Nanjing University of Information Science and Technology Nanjing China Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai) Zhuhai China Geophysical Institute University of Bergen Bergen Norway

The discrepancy in the trends of the global zonal mean (GZM) intensity of the Hadley circulation (HCI) between reanalysis data and model simulations has been a problem for understanding the changes in HCI and the influence of external forcings. To understand the reason for this discrepancy, this study investigates the trends of intensity of regional HCI of the Northern Hemisphere over the eastern Pacific (EPA), western Pacific (WPA), Atlantic (ATL), Africa (AFR), the Indian Ocean (IDO), and residual area (RA), based on six reanalysis datasets and 13 CMIP6 models. In reanalysis data, the trends in regional HCI over EPA and ATL (WPA and AFR) contribute to (partially offset) the increasing trend in GZM HCI, while the trends in regional HCI over IDO are different in different reanalysis data. The CMIP6 models skillfully reproduce the trends in regional HCI over EPA, ATL, WPA, and AFR, but simulate notable decreasing trends in regional HCI over IDO, which is a key reason for the opposite trends in GZM HCI between reanalysis data and models. The discrepancy in IDO can be attributed to differences in the simulation of diabatic heating and zonal friction between reanalysis data and models. Optimal fingerprint analysis indicates that anthropogenic (ANT) and non-greenhouse gas (NOGHG) forcings are the dominant drivers of the HCI trends in the EPA and ATL regions. In the WPA (AFR) region, NOGHG (ANT) forcing serves as the primary driver. The findings contribute to improving the representation of regional HCI trends in models and improving the attribution of external forcings. 摘要基于6套再分析资料和13个CMIP6模式, 研究发现模式能够较好地再现北半球东太平洋, 西太平洋, 大西洋和非洲的哈德来环流强度变化趋势. 但在印度洋区域, 再分析数据与模式模拟的趋势存在较大差异. 这一差异主要归因于模式与再分析数据在非绝热加热和纬向摩擦力模拟上的不同表现. 最优指纹法分析表明, 人为强迫和非温室气体强迫是北半球局地哈德来环流强度变化的主要驱动因素. 本研究揭示了人类活动对北半球不同区域哈德来环流变化的重要影响, 并阐明了再分析资料与CMIP6模式中北半球哈德来环流变化差异的原因. © 2025

关键词： Attribution External forcing Hadley circulation intensity Kuo–Eliassen equation Optimal fingerprint method

来源：评论

学校读者我要写书评

暂无评论

A Solution Analysis of U.S. Weapon Equipment systems-of-systems Development and Application 7

A Solution Analysis of U.S. Weapon Equipment Systems-of-Syst...

引用

7th International Conference on information science and Control engineering, ICISCE 2020

作者： Lin, Menglong Yi, Shuanghui Zhang, Mengmeng Shu, Zhen National University of Defense Technology Science and Technology on Information Systems Engineering Laboratory Changsha China National Key Laboratory for Complex System Simulation Beijing China

ISBN: (纸本)9781728164069

In recent years, the development and deployment of the U.S. weapon equipment systems-of-systems (SoS) have yielded rich research results. However, there are still large gaps in the SoS development, joint testing, and design and acquisition of our own equipment SoS. The barriers of these steps have not yet been opened up. This article mainly analyzes the solutions of the U.S. weapon equipment SoS from three aspects, such as capability-based requirement generation and architecture design technology, interconnected-oriented integration test technology, and weapon equipment design and acquisition technology based on complex adaptive systems. We explore key technologies involved in order to form an overall understanding and explore related research approaches. © 2020 IEEE.

关键词： system of systems

来源：评论

学校读者我要写书评

暂无评论

Α-Moc@Cs Carrier Modulated Platinum Single Atoms to Enhance Catalytic Activity in Solar Cells

SSRN

引用

SSRN 2022年

作者： Yao, Jixin Wang, Jie Wang, Wen Meng, Ying Wang, Haibo Lu, Shibin Du, Feng Yang, Li Zuo, Xueqin Li, Guang Anhui Province Key Laboratory of Simulation and Design for Electronic Information System Universitie s Joint Key Laboratory of Photoelectric Detection Science and Technology Hefei Normal University Anhui Province Hefei230601 China School of Materials Science and Engineering Anhui Key Laboratory of Information Materials and Devices Key Laboratory of Structure and Functional Regulation of Hybrid Materials Ministry of Education Institute of Physical Science and Information Technology Anhui University Hefei230601 China Institute of Materials Science and Devices School of Materials Science and Engineering Suzhou China University of Science and Technology Suzhou215011 China

Single-atom electrocatalysts have been proven to be the great promising catalysts for energy-related fields yet their active site structure remains elusive, especially in dye-sensitized solar cell (DSSC). Herein, atomically dispersed Pt is confined into α-MoC@CS carrier (Pt/α-MoC@CS), which vigorously stimulates the activity of Pt single atoms under strong interactions. As expected, the Pt/α-MoC@CS as the cathode in DSSC exhibits high power conversion efficiency (PCE) of 9.87%, exceeding Pt electrode (7.61%). X-ray photoelectron spectroscopy combined with density functional theory calculations reveals that the high activity is mainly derived from charge re-distribution of Pt/α-MoC@CS caused by the interaction between Pt atoms and α-MoC. This interaction not only achieves the optimized adsorption/desorption energy of reactants but also brings synergic advantages to expedite the reaction kinetics of the overall system. This work paves further research prospects for charge re-distribution, stimulating electrocatalysts to effectively enhance their catalytic properties by an atomic-level engineering strategy. © 2022, The Authors. All rights reserved.

关键词： Cathodes

来源：评论

学校读者我要写书评

暂无评论

Rethinking the impact of noisy labels in graph classification: A utility and privacy perspective

arXiv

引用

arXiv 2024年

作者： Li, De Li, Xianxian Gan, Zeming Li, Qiyu Qu, Bin Wang, Jinyan Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin541004 China Guangxi Key Lab of Multi-Source Information Mining & Security Guangxi Normal University Guilin541004 China School of Computer Science and Engineering Guangxi Normal University Guilin541004 China

Graph neural networks (GNNs) based on message-passing mechanisms have achieved advanced results in graph classification tasks. However, their generalization performance degrades when noisy labels are present in the training data. Most existing noisy labeling approaches focus on the visual domain or graph node classification tasks and analyze the impact of noisy labels only from a utility perspective. Unlike existing work, in this paper, we measure the effects of noise labels on graph classification from data privacy and model utility perspectives. We find that noise labels degrade the model’s generalization performance and enhance the ability of membership inference attacks on graph data privacy. To this end, we propose the robust graph neural network (RGLC) approach with noisy labeled graph classification. Specifically, we first accurately filter the noisy samples by high-confidence samples and the first feature principal component vector of each class. Then, the robust principal component vectors and the model output under data augmentation are utilized to achieve noise label correction guided by dual spatial information. Finally, supervised graph contrastive learning is introduced to enhance the embedding quality of the model and protect the privacy of the training graph data. The utility and privacy of the proposed method are validated by comparing twelve different methods on eight real graph classification datasets. Compared with the state-of-the-art methods, the RGLC method achieves at most and at least 7.8% and 0.8% performance gain at 30% noisy labeling rate, respectively, and reduces the accuracy of privacy attacks to below 60%. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Secure AI and Blockchain-enabled Framework in Smart Vehicular Networks

Secure AI and Blockchain-enabled Framework in Smart Vehicula...

引用

2021 IEEE Globecom Workshops, GC Wkshps 2021

作者： Rabieinejad, Elnaz Yazdinejad, Abbas Dehghantanha, Ali Parizi, Reza M. Srivastava, Gautam K.N.Toosi University of Technology Information Technology Department Tehran Iran University of Guelph Cyber Science Lab School of Computer Science Ontario Canada Kennesaw State University College of Computing and Software Engineering GA United States Brandon University Department of Mathematics and Computer Science Manitoba Canada

ISBN: (纸本)9781665423908

In recent years, Internet of Things (IoT) devices such as drones, smartphones, and smart vehicles have increased, and Smart Vehicular Networks (SVNs) have formed. SVN are one of the vital components in smart cities and improves their functionality and efficiency. Despite the many applications that SVN have shown, they have security vulnerabilities issues, and there are many reports of them being hacked. Most attacks on SVN occur due to wireless communications and information sharing between vehicles. Also, due to the communication among vehicles, failures can spread from the victim device to the entire network and cause widespread damages. SVN features include mobility, decentralization, resource constraints that make traditional security solutions unsuitable for it. We propose a secure framework using blockchain and Deep Neural networks (DNN) to address these challenges. In this framework, we consider cluster-based architecture that vehicles in each cluster can securely communicate using the blockchain. Also, DNN is adopted to detect abnormal vehicles that have been attacked using their network traffic analysis in each zone. We assess blockchain impacts on throughput using different miners with multiple block sizes in our proposed framework. The experimental result indicates the throughput improvement with an increase in miners and block size. In addition, we evaluated the DNN performance for abnormal vehicle detection, which represents 99.82% in terms of accuracy. © 2021 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Output-Constrained Controller for DC/DC Buck Converter Feeding Constant Power Loads in DC Microgrids

A Novel Output-Constrained Controller for DC/DC Buck Convert...

引用

Annual Conference of Industrial Electronics Society

作者： Xiaoyu Wang Jingjing Huang Ye Cao Tianxiao Yang Qianwen Xu Chuanlin Zhang Aimin Zhang School of Automation Science and Engineering Xi'an Jiaotong University Xi'an China Intelligent Autonomous System Lab Shanghai University of Electric Power Shanghai China Electric Power and Energy Systems Division KTH Royal Institute of Technology Stockholm Sweden

DC microgrids have emerged as a promising solution for efficient and reliable electricity distribution. In DC microgrids, when power electronic loads and motor drives are tightly regulated, they behave as constant power loads (CPLs) and may lead to the instability issue. In this paper, a novel output-constrained controller for the DC/DC buck converter feeding CPLs is proposed. By introducing the output-constrained technique into the backstepping method, the proposed control scheme can keep the DC bus working within the pre-specific boundary even when large-signal disturbances happen. Relevant theoretical analyses are conducted by employing Laypunov stability theorem. Simulations in Matlab/Simulink are presented to verify the proposed controller.

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：