检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhou, Jiajun Xie, Chenxuan Gong, Shengbo Qian, Jiaxu Yu, Shanqing Xuan, Qi Yang, Xiaoniu Institute of Cyberspace Security Zhejiang University of Technology Hangzhou310023 China Binjiang Institute of Artificial Intelligence Hangzhou310056 China College of Computer Science and Technology Zhejiang University of Technology Hangzhou310023 China Science and Technology on Communication Information Security Control Laboratory Jiaxing314033 China

Real-world graphs exhibit increasing heterophily, where nodes no longer tend to be connected to nodes with the same label, challenging the homophily assumption of classical graph neural networks (GNNs) and impeding their performance. Intriguingly, from the observation of heterophilous data, we notice that certain high-order information exhibits higher homophily, which motivates us to involve high-order information in node representation learning. However, common practices in GNNs to acquire high-order information mainly through increasing model depth and altering message-passing mechanisms, which, albeit effective to a certain extent, suffer from three shortcomings: 1) oversmoothing due to excessive model depth and propagation times;2) high-order information is not fully utilized;3) low computational efficiency. In this regard, we design a similarity-based path sampling strategy to capture smooth paths containing high-order homophily. Then we propose a lightweight model based on multi-layer perceptrons (MLP), named PathMLP, which can encode messages carried by paths via simple transformation and concatenation operations, and effectively learn node representations in heterophilous graphs through adaptive path aggregation. Extensive experiments demonstrate that our method outperforms baselines on 16 out of 20 datasets, underlining its effectiveness and superiority in alleviating the heterophily problem. In addition, our method is immune to over-smoothing and has high computational efficiency. The source code will be available in https://***/Graph4Sec-Team/PathMLP. Copyright © 2023, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Based Risk Identification Method for Illegal Pig Slaughtering

A Machine Learning Based Risk Identification Method for Ille...

引用

2023 International Conference on Intelligent Communication and Networking, ICN 2023

作者： Miao, Jiajun Shen, Yujun Zhang, Yan Liu, Lingjie Tian, Ye Zhao, Yu Zhou, Chunyan Harbin Engineering University College of Computer Science and Technology Harbin China Hangzhou Hikvision Digital Technology Co. Ltd Hangzhou China China Industrial Control Systems Cyber Emergency Response Team Beijing China Environment and Food and Drug Crime Investigation Detachment of Hangzhou Public Security Bureau Hangzhou China Xidian University Hangzhou Institute of Technology Harbin China Key Laboratory of Peace-Building Big Data of Zhejiang Province Hangzhou China

ISBN: (纸本)9798350357677

With the impact of African swine fever, the survival rate of domestic pigs has sharply decreased, and pork prices continue to rise. Many unscrupulous elements obtain illegal profits by avoiding inspection and quarantine, processing sick and dead pigs, and injecting water, etc. Unquarantined meat products pose serious food safety risks. In this context, we propose a machine learning based risk identification method for illegal slaughter of live pigs. Firstly, we use the RetinaNet algorithm to detect live pig transport vehicles and use a dual residual network to Super-Resolution the vehicle area in the detected image to improve facial clarity. Subsequently, the ArcFace algorithm is used to match the facial information with the ex-convicts, and finally, the Location of vehicles passing through, time, frequency and facial analysis results are combined for calculation and scoring and provide the risk warning for illegal slaughter of live pigs. © 2023 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

HunSum-1: an Abstractive Summarization Dataset for Hungarian

arXiv

引用

arXiv 2023年

作者： Barta, Botond Lakatos, Dorina Nagy, Attila Nyist, Milán Konor Ács, Judit Department of Automation and Applied Informatics Budapest University of Technology and Economics Hungary Institute for Computer Science and Control Eötvös Loránd Research Network Hungary

We introduce HunSum-1: a dataset for Hungarian abstractive summarization, consisting of 1.14M news articles. The dataset is built by collecting, cleaning and deduplicating data from 9 major Hungarian news sites through CommonCrawl. Using this dataset, we build abstractive summarizer models based on huBERT and mT5. We demonstrate the value of the created dataset by performing a quantitative and qualitative analysis on the models' results. The HunSum-1 dataset, all models used in our experiments and our code are available open source. © 2023, CC BY.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

On modal observers for beyond rigid body H∞ control in high-precision mechatronics

arXiv

引用

arXiv 2022年

作者： Broens, Yorick Butler, Hans Tóth, Roland The Department of Electrical Engineering Eindhoven University of Technology Eindhoven Netherlands ASML Veldhoven Netherlands The Systems and Control Laboratory Institute for Computer Science and Control Hungary

The ever increasing need for performance results in increasingly rigorous demands on throughput and positioning accuracy of high-precision motion systems, which often suffer from position dependent effects that originate from relative actuation and sensing of the moving-body. Due to the highly stiff mechanical design, such systems are typically controlled using rigid body control design approaches. Nonetheless, the presence of position dependent flexible dynamics severely limits attainable position tracking performance. This paper presents two extensions of the conventional rigid body control framework towards active control of position dependent flexible dynamics. Additionally, a novel control design approach is presented, which allows for shaping of the full closed-loop system by means of structured H∞ co-design. The effectiveness of the approach is validated through simulation using a high-fidelity model of a state-of-the-art moving-magnet planar *** Codes 37M15 © 2022, CC BY.

关键词： Closed loop systems

来源：评论

学校读者我要写书评

暂无评论

Design of multi-channel synchronization signal acquisition method based on FPGA

Design of multi-channel synchronization signal acquisition m...

引用

Chinese control and Decision Conference, CCDC

作者： Feiqing Zhang Dongji Li Zhenyu Yin Guangyuan Xu Shuo Li Shenyang Institute of Computing Technology Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Liaoning Key Laboratory of Domestic Industrial Control Platform Technology on Basic Hardware & Software Shenyang China School of Computer Science and Technology Shenyang University of Chemical Technology Shenyang China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

In the field of aerospace, engines play a vital role, and rolling bearings, as the core components within them, have a significant impact on the production and operation of the entire equipment system. Therefore, real-time monitoring of the engine to ensure the safe operation of the equipment is indispensable. Therefore, this paper designs and implements a multi-channel synchronous acquisition card system based on FPGA platform to realize real-time acquisition of engine vibration signals, and then analyzes its running state and makes accurate judgments. Aiming at the problems of slow information interaction speed and high bit error rate between FPGA and host computer, we design a message interaction optimization method based on UART, which successfully improved the speed and accuracy of data transmission. At the same time, in order to solve the problem of complex and difficult management of system parameters, we design a RAM based addressing storage method, which can effectively realize the long-term storage of parameters and ensure the stability of data. And the method adopts modularization and parametric design strategy, so it has high portability. The simulation results show that the signal-to-noise ratio of the method can reach 95dB and the power consumption is only 0.26W, which meets the requirements of vibration signal acquisition and power consumption. These characteristics make the system have high engineering application value in the field of aerospace engine monitoring.

关键词： Vibrations Power demand Accuracy Simulation Real-time systems Stability analysis Synchronization

来源：评论

学校读者我要写书评

暂无评论

Stability Analysis and Performance Evaluation of Delayed Bilateral Telerobotic Systems over a Lossy Communication Channel

引用

Journal of Systems Science & Complexity 2021年第1期34卷 157-179页

作者： BAKHSHI Ali ALFI Alireza TALEBI Heidar Ali SOURATGAR Amir Aboulfazl YOUSEFI Mahdi Faculty of Electrical and Robotic Engineering Shahrood University of TechnologyShahrood 36199-95161Iran Power Plants Control Systems Technology Development Plan Department of monitoring and ControlNiroo Research InstituteTehran 14665-517Iran Real-Time and Robotics system Laboratory Faculty of Electrical EngineeringAmirkabir University of TechnologyHafez AvenueTehran 15914Iran Electrical and Computer Engineering Department The University of British Columbia2385East MallVan couverBC V6T 1Z4Canada

The focus of this paper is to address a novel control technique for stability and transparency analysis of bilateral telerobotic systems in the presence of data loss and time delay in the communication channel. Different control strategies have been reported to compensate the effects of time delay in the communication channel;however, most of them result in poor performance under data loss. First, a model for data loss is proposed using a finite series representation of a set of periodic continuous *** improve the performance and data reconstruction, a holder circuits is also introduced. The passivity of the overall system is provided via the wave variable technique based on the proposed model for the data loss. The stability analysis of the system is then derived using the Lyapunov theorem under the time delay and the data loss. Finally, experimental results are given to illustrate the capability of the proposed control technique.

关键词： Lossy channel passivity stability telerobotic transparency

来源：评论

学校读者我要写书评

暂无评论

Bi-layered coded metasurface for multi-functional hologram with broadband transmission and efficient reflection

引用

Chinese Optics Letters 2024年第5期22卷 8-16页

作者：朱磊李绪胜董亮谢文静尚关玉 Shah Nawaz Burokur 丁旭旻 School of Computer and Control Engineering Qiqihar UniversityQiqihar 161006China Communication and Electronics Engineering Institute Qiqihar UniversityQiqihar 161006China Heilongjiang Key Laboratory of Big Data Network Security Detection and Analysis Qiqihar UniversityQiqihar 161000China Department of Microwave Engineering Harbin Institute of TechnologyHarbin 150001China LEME UPLUniversitéParis NanterreF92410 Ville d’AvrayFrance Advanced Microscopy and Instrumentation Research Center Harbin Institute of TechnologyHarbin 150080China Key Laboratory of Millimeter Waves Southeast UniversityNanjing 210096China

A multi-functional full-space metasurface based on frequency and polarization multiplexing is *** metasurface unit consists of metallic patterns printed on the two faces of a single-layered dielectric *** unit cell can control electromagnetic wavefronts to achieve a broadband transmission with amplitudes greater than 0.4 from 4.4 to 10.4 ***,at 11.7 GHz and 15.4 GHz,four high-efficiency reflection channels with a reflection amplitude greater than 0.8 are also *** illuminated by linearly polarized waves,five different functions can be realized at five different frequencies,which are demonstrated by theoretical calculations,full-wave simulations,and experimental measurements.

关键词： multi-functional metasurface broadband transmission efficient reflection full space

来源：评论

学校读者我要写书评

暂无评论

Efficacy of Local Cache for Performance Improvement of Reliable Data Transmission in Aggregated Robot Processing Architecture

Efficacy of Local Cache for Performance Improvement of Relia...

引用

International Conference on control, Automation and Systems ( ICCAS)

作者： Abdul Jalil Jun Kobayashi Department of Computer Science and Systems Engineering Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Japan Department of Intelligent and Control Systems Faculty of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Japan

This study aims to improve the performance of message data transmission in Aggregated Robot Processing (ARP) architecture where the RELIABLE option of the RELIABILITY QoS (Quality of Service) policy is applied to a ROS 2 (Robot Operating System 2) node communication. Basically, the RELIABLE option guarantees that a publisher properly send all message data to a subscriber. However, the publisher could fail to transmit some message data to the subscriber even in the RELIABLE QoS option unless the buffer size of the publisher is enough. We introduce local cache to a sensing component to alleviate the issue in the case that the sensors output the same value in a row. The experimental results showed that the local cache improved the latency and reduced the message loss in node communication.

关键词： Performance evaluation Operating systems Process control Quality of service Robot sensing systems control systems Sensors

来源：评论

学校读者我要写书评

暂无评论

Learning For Predictive control: A Dual Gaussian Process Approach

arXiv

引用

arXiv 2022年

作者： Liu, Yuhan Wang, Pengyu Tóth, Roland Control Systems Group Department of Electrical Engineering Eindhoven University of Technology Eindhoven Netherlands Flight Dynamics and Control Laboratory Department of Aerospace Engineering Korea Advanced Institute of Science and Technology Daejeon Korea Republic of Systems and Control Laboratory Institute for Computer Science and Control Budapest Hungary

An important issue in model-based control design is that an accurate dynamic model of the system is generally nonlinear, complex, and costly to obtain. This limits achievable control performance in practice. Gaussian process (GP) based estimation of system models is an effective tool to learn unknown dynamics directly from input/output data. However, conventional GP-based control methods often ignore the computational cost associated with accumulating data during the operation of the system and how to handle forgetting in continuous adaption. In this paper, we present a novel Dual Gaussian Process (DGP) based model predictive control (MPC) strategy that enables efficient use of online learning based predictive control without the danger of catastrophic forgetting. The bio-inspired DGP structure is a combination of a long-term GP and a short-term GP, where the long-term GP is used to keep the learned knowledge in memory and the short-term GP is employed to rapidly compensate unknown dynamics during online operation. Furthermore, a novel recursive online update strategy for the short-term GP is proposed to successively improve the learnt model during online operation. Effectiveness of the proposed strategy is demonstrated via numerical simulations. © 2022, CC BY-NC-SA.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Adaptive Distance-Based IoU Loss for Accurate and Efficient Bounding Box Regression

SSRN

引用

SSRN 2024年

作者： Gupta, Himanshu Verma, Sourabh Verma, Om Prakash Department of Computer Engineering-Artificial Intelligence Marwadi University Gujrat Rajkot360003 India Department of Instrumentation and Control Engineering Dr B R Ambedkar National Institute of Technology Jalandhar Punjab Jalandhar India

Bounding box regression (BBR) has been considered the most decisive step in object detection, continues to make breakthroughs in wide real-time applications of computer vision and directly affects the localisation performance of deep learning models. Usually, existing BBR employs Intersection over Union (IoU)-based loss function, especially Complete IoU (CIoU). However, it shows inefficiency in depicting the objective of BBR, which leads to slow convergence and inaccurate regression performance due to poor aspect ratio penalty and normalised Euclidean distance in the denominator. To overcome these limitations, the present study proposes an Adaptive distance-based IoU (ADIoU) loss function by excluding the distance term in backpropagation and expanding the penalty in CIoU, which further improves the object detection accuracy. The effectiveness of the proposed ADIoU has been verified on the simulated data. Also, ADIoU has been incorporated into YOLOv5, YOLOv4, and RetinaNet to estimate its effectiveness on popular ground-view (COCO) and aerial-view (VisDrone, AU-AIR, and Airbus) object detection datasets. The experimental results reveal that relative to CIoU, ADIoU improves the mAPcoco by 0.68% to 1.66% for ground-view and 0.39% to 5.53% for aerial-view datasets, which demonstrates that ADIoU has strong robustness and can be considered a general BBR loss function. © 2024, The Authors. All rights reserved.

关键词： Object detection

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：