检索结果-内蒙古大学图书馆

A Multi-scale Framework for Out-of-Distribution Detection in Dermoscopic Images 1

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Huang, Zhongzheng Wang, Tao Cai, Yuanzheng Liang, Lingyu College of Computer and Data Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering and International Digital Economy College Minjiang University Fuzhou350108 China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University Wuyishan354300 China Fujian Yilian-Health Nursing Information Technology Co. Ltd. Fuzhou350003 China School of Electronic and Information Engineering South China University of Technology Guangzhou510641 China

ISBN: (数字)9783031200960

ISBN: (纸本)9783031200953

The automatic detection of skin diseases via dermoscopic images can improve the efficiency in diagnosis and help doctors make more accurate judgments. However, conventional skin disease recognition systems may produce high confidence for out-of-distribution (OOD) data, which may become a major security vulnerability in practical applications. In this paper, we propose a multi-scale detection framework to detect out-of-distribution skin disease image data to ensure the robustness of the system. Our framework extracts features from different layers of the neural network. In the early layers, rectified activation is used to make the output features closer to the well-behaved distribution, and then an one-class SVM is trained to detect OOD data;in the penultimate layer, an adapted Gram matrix is used to calculate the features after rectified activation, and finally the layer with the best performance is chosen to compute a normality score. Experiments show that the proposed framework achieves superior performance when compared with other state-of-the-art methods in the task of skin disease recognition. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Decentralized Goal Function-Based control of DGSs in Microgrid Applications

Decentralized Goal Function-Based Control of DGSs in Microgr...

引用

Power Tech Conference

作者： Ivana Isakov Milan Rapaić Marko Vekić Ivan Todorović Department of Power Electronic and Telecommunication Engineering Faculty of Technical Sciences University of Novi Sad Novi Sad Serbia Department of Computing and Control Engineering Faculty of Technical Sciences University of Novi Sad Novi Sad Serbia

control structures governing distributed generation sources (DGSs), utilized in microgrids, have to provide several important functionalities and generally secure stable network operation. The large majority of these control structures are based either on droop (or droop-derived) or other, more advanced, control paradigms. The former are overly simplistic and necessitate control layerization and many extensions for the overall control structure to be applicable in the general case. The latter are either too complex or application-specific, rendering them unfit to be adopted as a general tool for controlling DGSs in microgrids. The control scheme derived in this paper is based on a goal function that simultaneously secures safe and stable operation, respecting voltage amplitude and frequency limits, and precise active power exchange. As such, the proposed control scheme integrates what is traditionally called primary and secondary control of microgrids and enables reliable peer-to-peer power exchange. The control scheme was tested using simulation tools and together with the simulation results, a performance analysis is provided.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FREPA: An Automated and Formal Approach to Requirement Modeling and Analysis in Aircraft control Domain

arXiv

引用

arXiv 2023年

作者： Feng, Jincao Miao, Weikai Zheng, Hanyue Huang, Yihao Li, Jianwen Wang, Zheng Su, Ting Gu, Bin Pu, Geguang Yang, Mengfei He, Jifeng East China Normal University China Shanghai Key Lab of Trustworthy Computing China Beijing Institute of Control Engineering China Shanghai Trusted Industrial Control Platform Co. Ltd China China Academy of Space Technology China

Formal methods are promising for modeling and analyzing system requirements. However, applying formal methods to large-scale industrial projects is a remaining challenge. The industrial engineers are suffering from the lack of automated engineering methodologies to effectively conduct precise requirement models, and rigorously validate and verify (V&V) the generated models. To tackle this challenge, in this paper, we present a systematic engineering approach, named Formal Requirement engineering Platform in Aircraft (FREPA), for formal requirement modeling and V&V in the aerospace and aviation control domains. FREPA is an outcome of the seamless collaboration between the academy and industry over the last eight years. The main contributions of this paper include 1) an automated and systematic engineering approach FREPA to construct requirement models, validate and verify systems in the aerospace and aviation control domain, 2) a domain-specific modeling language AASRDL to describe the formal specification, and 3) a practical FREPA-based tool AeroReq which has been used by our industry partners. We have successfully adopted FREPA to seven real aerospace gesture control and two aviation engine control systems. The experimental results show that FREPA and the corresponding tool AeroReq significantly facilitate formal modeling and V&V in the industry. Moreover, we also discuss the experiences and lessons gained from using FREPA in aerospace and aviation projects. Copyright © 2023, The Authors. All rights reserved.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Intelligent Autonomous-Robot control for Medical Applications

引用

Computers, Materials & Continua 2021年第8期68卷 2189-2203页

作者： Rihem Farkh Haykel Marouani Khaled Al Jaloud Saad Alhuwaimel Mohammad Tabrez Quasim Yasser Fouad College of Engineering Muzahimiyah BranchKing Saud UniversityRiyadh11451Saudi Arabia Laboratory for Analysis Conception and Control of SystemsDepartment of Electrical EngineeringNational Engineering School of TunisTunis El Manar University1002Tunisia King Abdulaziz City for Science and Technology Riyadh12354Saudi Arabia College of Computing and Information Technology University of BishaBisha67714Saudi Arabia

The COVID-19 pandemic has shown that there is a lack of healthcare facilities to cope with a *** has also underscored the immediate need to rapidly develop hospitals capable of dealing with infectious patients and to rapidly change in supply lines to manufacture the prescription goods(including medicines)that is needed to prevent infection and treatment for infected *** COVID-19 has shown the utility of intelligent autonomous robots that assist human efforts to combat a *** artificial intelligence based on neural networks and deep learning can help to fight COVID-19 in many ways,particularly in the control of autonomous medic *** officials aim to curb the spread of COVID-19 among medical,nursing staff and patients by using intelligent *** propose an advanced controller for a service robot to be used in *** type of robot is deployed to deliver food and dispense medications to individual *** autonomous line-follower robot that can sense and follow a line drawn on the floor and drive through the rooms of patients with control of its *** criteria were met by using two controllers simultaneously:a deep neural network controller to predict the trajectory of movement and a proportional-integral-derivative(PID)controller for automatic steering and speed control.

关键词： Autonomous medic robots PID control neural network control system real-time implementation navigation environment differential drive system

来源：评论

学校读者我要写书评

暂无评论

Incremental Online Learning of Randomized Neural Network with Forward Regularization

arXiv

引用

arXiv 2024年

作者： Wang, Junda Hu, Minghui Li, Ning Al-Ali, Abdulaziz Suganthan, Ponnuthurai Nagaratnam The Key Laboratory of System Control and Information Processing Ministry of Education of China China The Department of Automation Shanghai Jiao Tong University Shanghai200240 China The Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China The School of Electrical and Electronic Nanyang Technological University Singapore The KINDI Computing Research Center College of Engineering Qatar University Qatar

Online learning of deep neural networks suffers from challenges such as hysteretic non-incremental updating, increasing memory usage, past retrospective retraining, and catastrophic forgetting. To alleviate these drawbacks and achieve progressive immediate decision-making, we propose a novel Incremental Online Learning (IOL) process of Randomized Neural Networks (Randomized NN), a framework facilitating continuous improvements to Randomized NN performance in restrictive online scenarios. Within the framework, we further introduce IOL with ridge regularization (-R) and IOL with forward regularization (-F). -R generates stepwise incremental updates without retrospective retraining and avoids catastrophic forgetting. Moreover, we substituted -R with -F as it enhanced precognition learning ability using semi-supervision and realized better online regrets to offline global experts compared to -R during IOL. The algorithms of IOL for Randomized NN with -R/-F on non-stationary batch stream were derived respectively, featuring recursive weight updates and variable learning rates. Additionally, we conducted a detailed analysis and theoretically derived relative cumulative regret bounds of the Randomized NN learners with -R/-F in IOL under adversarial assumptions using a novel methodology and presented several corollaries, from which we observed the superiority on online learning acceleration and regret bounds of employing -F in IOL. Finally, our proposed methods were rigorously examined across regression and classification tasks on diverse datasets, which distinctly validated the efficacy of IOL frameworks of Randomized NN and the advantages of forward regularization. Copyright © 2024, 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

FPGA-Based Convolution Accelerator and Memristor IP Core for Cooperative Acceleration of the YOLO Network 4

FPGA-Based Convolution Accelerator and Memristor IP Core for...

引用

4th International Conference on Computer Science, Electronic Information engineering and Intelligent control Technology, CEI 2024

作者： Tan, Aolong Yang, Yucheng Duan, Shukai Wang, Lidan College of Artificial Intelligence Southwest University Chongqing400715 China State Key Laboratory of Intelligent Vehicle Safety Technology China National Local Joint Engineering Research Center of Intelligent Transmission and Control Technology 400715 China Chongqing Key Laboratory of Brain-inspired Computing and Intelligent Chips Chongqing400715 China Laboratory of Luminescence Analysis and Molecular Sensing Southwest University Ministry of Education Chongqing400715 China

ISBN: (纸本)9798350378542

Object detection technology is widely used in areas such as autonomous driving, drone reconnaissance, smart surveillance and industrial automation, especially in remote or hazardous scenarios where it can improve efficiency and safety. Therefore, the development of a high-precision, low-power acceleration system integrated with low-power hardware is crucial. This paper proposes a collaborative acceleration scheme for the YOLO network based on an FPGA convolution accelerator and simulated memristors, which successfully implements and accelerates the YOLOv4-Tiny model. First, a reconfigurable single-core accelerator operator is designed for various computational operations in the model. Second, taking advantage of the digital device characteristics of memristors and the hardware resources of the FPGA, a memristor simulation IP core is built to exploit its memory characteristics for convolution operations. Through the synergistic effect of the convolution accelerator and the simulated IP core, a hybrid acceleration of the detection model is achieved. The power consumption of the convolution accelerator is only 2.75W, and in testing, the detection time for a single image is 823ms with an average accuracy of over 0.95, achieving high detection performance. This provides an opportunity to explore and research the efficient acceleration of object detection networks with integrated storage and computation. © 2024 IEEE.

关键词： Reconfigurable hardware

来源：评论

学校读者我要写书评

暂无评论

Decentralized Strategies for Finite Population Linear-Quadratic-Gaussian Games and Teams

arXiv

引用

arXiv 2022年

作者： Wang, Bing-Chang Zhang, Huanshui Fu, Minyue Liang, Yong School of Control Science and Engineering Shandong University Jinan250061 China The School of Electrical Engineering and Computing Science University of Newcastle NSW2308 Australia

This paper is concerned with a new class of mean-field games which involve a finite number of agents. Necessary and sufficient conditions are obtained for the existence of the decentralized open-loop Nash equilibrium in terms of non-standard forward-backward stochastic differential equations (FBSDEs). By solving the FBSDEs, we design a set of decentralized strategies by virtue of two differential Riccati equations. Instead of the Ε-Nash equilibrium in classical mean-field games, the set of decentralized strategies is shown to be a Nash equilibrium. For the infinite-horizon problem, a simple condition is given for the solvability of the algebraic Riccati equation arising from consensus. Furthermore, the social optimal control problem is studied. Under a mild condition, the decentralized social optimal control and the corresponding social cost are given. Copyright © 2022, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Air Traffic Management and Communication over ATN/IPS for Future Datalink Communication

Air Traffic Management and Communication over ATN/IPS for Fu...

引用

2025 Integrated Communications, Navigation and Surveillance Conference, ICNS 2025

作者： Aydogan, Emre Ozmen, Sergun Cetek, Fulya Aybek Valdes, Rosa Maria Arnaldo Jurado, Raquel Delgado-Aguilera Fernandez, Angel Ernesto Carmona Miralles, Adrian Martinez Vendruscolo, Tommaso Bonelli, Stefano Delahaye, Daniel Chaimatanan, Supatcha Chen, Feng Hamzaoui, Raouf Eskişehir Technical University Faculty of Aeronautics and Astronautics Air Traffic Control Department Eskişehir Turkey Turkish Airlines Îstanbul Turkey Universidad Politėcnica de Madrid Department of Aerospace Systems Air Transport and Airports Madrid Spain Servicios Aeronáuticos Control y Navegación Madrid Spain Deep Blue srl Rome Italy OPTIM Lab Toulouse France De Montfort University Faculty of Computing Engineering and Media Leicester United Kingdom

ISBN: (纸本)9798331534738

The growing demand for air traffic presents challenges in air traffic management, making seamless gate-to-gate communication essential. Traditional radio frequency communication faces limitations such as weather dependency and frequency restrictions. To address these issues, data link communications have gained importance, using VHF channels, satellite systems, and ATN/IPS-based networks. This study introduces the ATMACA (Air Traffic Management and Communication Over ATN/IPS) protocol, an advanced context management framework for ATN/IPS, designed to enhance aviation communications. ATMACA integrates instant messaging and software-defined nodes to improve connectivity, session continuity, and mobility management across networks and devices. It ensures seamless user interaction, reduces pilot workload, and enhances flight safety through automated Air Traffic control (ATC) sector handoff in controller-Pilot Data Link Communications (CPDLC) and Data Link Initiation Capability (DLIC) applications. Another key innovation of the ATMACA framework is Green Route Operations (GRO), which enables real-time trajectory prediction and optimization. © 2025 IEEE.

关键词： Air traffic control

来源：评论

学校读者我要写书评

暂无评论

ConnectomeAE: Multimodal brain connectome-based dual-branch autoencoder and its application in the diagnosis of brain diseases

引用

Computer Methods and Programs in Biomedicine 2025年 267卷 108801-108801页

作者： Zheng, Qiang Nan, Pengzhi Cui, Yongchao Li, Lin School of Computer and Control Engineering Yantai University Yantai264005 China Faculty of Computing and Information Technology Tunku Abdul Rahman University of Management and Technology Kuala Lumpur53300 Malaysia Department of Radiology Yantaishan Hospital Affiliated to Binzhou Medical University Yantai264003 China

Background and Objective: Exploring the dependencies between multimodal brain networks and integrating node features to enhance brain disease diagnosis remains a significant challenge. Some work has examined only brain connectivity changes in patients, ignoring important information about radiomics features such as shape and texture of individual brain regions in structural images. To this end, this study proposed a novel deep learning approach to integrate multimodal brain connectome information and regional radiomics features for brain disease diagnosis. Methods: A dual-branch autoencoder (ConnectomeAE) based on multimodal brain connectomes was proposed for brain disease diagnosis. Specifically, a matrix of radiomics feature extracted from structural magnetic resonance image (MRI) was used as Rad_AE branch inputs for learning important brain region features. Functional brain network built from functional MRI image was used as inputs to Cycle_AE for capturing brain disease-related connections. By separately learning node features and connection features from multimodal brain networks, the method demonstrates strong adaptability in diagnosing different brain diseases. Results: ConnectomeAE was validated on two publicly available datasets. The experimental results show that ConnectomeAE achieved excellent diagnostic performance with an accuracy of 70.7 % for autism spectrum disorder and 90.5 % for Alzheimer's disease. A comparison of training time with other methods indicated that ConnectomeAE exhibits simplicity and efficiency suitable for clinical applications. Furthermore, the interpretability analysis of the model aligned with previous studies, further supporting the biological basis of ConnectomeAE. Conclusions: ConnectomeAE could effectively leverage the complementary information between multimodal brain connectomes for brain disease diagnosis. By separately learning radiomic node features and connectivity features, ConnectomeAE demonstrated good adaptability t

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Suppression Strategy of Sub-synchronous Oscillation in OWF Connected to the Grid Through MMC-HVDC

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第4期9卷 2621-2641页

作者： Yan, Ren-Wu Fu, Fu-Wei Liu, Yun-Zhang Yu, Ning Zhang, Zhi-Hong College of Electronic Electrical and Physics Engineering Research Center for Smart Grid Simulation Analysis and Integrated Control Fujian University of Technology Fuzhou350118 China Department of Computing Sciences State University of New York Brockport College NY14420 United States

Currently, modular multilevel converter-based flexible direct current transmission technology (MMC-HVDC) is the prevalent method for connecting long-distance offshore wind farms (OWF) to large power grid systems. Due to unique meteorological conditions at sea and the utilization of substantial wind turbines, offshore doubly-fed wind turbines possess a higher axial elastic coefficient compared to their onshore counterparts. When linked to the grid via MMC-HVDC, two types of sub-synchronous oscillations oc-cur: natural torsional vibrations within the wind turbine shafting and sub-synchronous oscillations resulting from interactions between the wind turbine and devices in the MMC-HVDC converter control system. To address these issues, a MMC-HVDC grid connection model for offshore long-distance doubly-fed wind farms has been developed. A cloud computing platform-based wind farm data acquisition system is employed for remote wind turbine data collection. Eigenvalue analysis and participation factors are utilized to determine oscillation modes and corresponding strongly correlated state variables arising from interactions between wind turbine shaft torsional vibration and converter devices. Upon identifying the correlations of state variables, a suppression strategy involving a circulating current suppression DC control collaborative virtual resistance controller is proposed to mitigate sub-synchronous oscillations. The efficacy of the suggested suppression approach is validated using PSCAD/EMTDC electromagnetic transient simulation software. © 2024, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Eigenvalues and eigenfunctions

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：