检索结果-内蒙古大学图书馆

33rd IEEE International Conference on Microelectronics, MIEL 2023

作者： Bogacki, P. Dlugosz, M. Talaska, T. Dlugosz, R. Aptiv Services Poland Kraków30-399 Poland Agh University of Science and Technology Institute of Telecommunications Faculty of Computer Science Electronics and Telecommunications Kraków30-059 Poland Poznan University of Technology Faculty of Control Robotics and Electrical Engineering Institute of Automation and Robotics Division of Signal Processing and Electronic Systems Poznan60-965 Poland Bydgoszcz University of Science and Technology Faculty of Telecommunication Computer Science and Electrical Engineering Bydgoszcz85-796 Poland

ISBN: (纸本)9798350347760

The paper presents a family of novel light blob shape descriptors for use in selected active safety algorithms used in Advanced Driver Assistance Systems (ADAS). One of the motivations was to obtain a descriptor that would ensure low computational complexity. This makes it easy to implement both in software and hardware. One assumption is that the location of the center of a given light spot is approximately known. The principle of its operation is then to count white pixels in selected directions, starting from this central point. A key issue here is an efficient way of determining indexes of particular pixels belonging to the image patch, as well as the location of points representing places where the white area turns into black. In the case of a hardware implementation, this can be done using a parallel circuit operating in asynchronous mode, without the need for a control clock. © 2023 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Assessment of Depression Level Based on Multi-Scale 3D Convolution and Expression Videos 3

Assessment of Depression Level Based on Multi-Scale 3D Convo...

引用

3rd International Conference on Computer Vision and Pattern Analysis, ICCPA 2023

作者： Cao, Qishuang Gao, Junlong Lv, Zeying Li, Mi Department of Automation Faculty of Information Technology Beijing University of Technology Beijing100124 China Beijing International Collaboration Base on Brain Informatics and Wisdom Services Beijing100124 China Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education Beijing100124 China Engineering Research Center of Digital Community Ministry of Education Beijing100124 China

ISBN: (纸本)9781510667563

The automatic diagnosis of depression using deep learning has recently shown significant progress, and 3DCNN has been applied to assessing depression levels from videos. There are two problems to be encountered applying 3DCNN, including insufficient data to train the model and an insufficient diversity of features extracted on a single scale. An approach is presented in this paper to address these issues. Firstly, we augmented the raw data by adding noise and applying rotations to increase the amount of the training set. Secondly, we constructed a 3DCNN to extract more diverse features from multiscales. We evaluated our proposed method on the AVEC 2014. Our approach achieved MAE=7.13 and RMSE=9.16, demonstrating its effectiveness in improving the accuracy of depression assessment compared to existing approaches. © 2023 SPIE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Unmanned Aerial Vehicles for Inspection of Power Lines

Unmanned Aerial Vehicles for Inspection of Power Lines

引用

International Russian Smart Industry Conference (SmartIndustryCon)

作者： I. I. Naumov R. R. Ibadov S. P. Oboimova Faculty of Automation Mechatronics and Control Don State Technical University Rostov-on-Don Russia Department of Electrical Engineering and Electronics Don State Technical University Rostov-on-Don Russia

ISBN: (数字)9798331511241

ISBN: (纸本)9798331511258

Problem Statement. New unmanned aerial vehicle (UAV) technology has become more accessible and practical for transmission line inspection. In this paper, we propose a multi-platform UAV system and a multi-model communication system designed for high-efficiency transmission line inspection tasks. Different UAVs perform both long-range and short-range surveillance functions, and provide communication relay. High-quality images and videos are transmitted in real time to the local control station for UAV navigation and to the remote office for analysis. Practice shows that joint inspection using multiple UAVs can significantly outperform traditional inspection methods. Objective. To propose a new method for inspecting and checking the condition of power lines using several types of UAVs using certain signal transmission and relay methods. Results. A new concept of power line inspection using joint actions of unmanned aerial vehicles (UAVs) is proposed. The functional capabilities of the UAVs and the communication system are considered and discussed. Practical experience shows that due to joint work, the time spent on inspection can be significantly reduced and the efficiency can be significantly increased. The feasibility and advantages of inspections using UAVs are confirmed. Future work can focus on optimizing the configuration of UAVs as part of a group. Practical significance. The presented method allows increasing the efficiency of inspection and testing of power transmission lines in comparison with existing methods.

关键词： Power transmission lines Propellers Surveillance Refining Inspection Autonomous aerial vehicles Real-time systems Relays Videos Testing

来源：评论

学校读者我要写书评

暂无评论

Haar Feature Based Object Detection Using Adaboost Classifier

Haar Feature Based Object Detection Using Adaboost Classifie...

引用

International Conference on Industrial engineering, Applications and Manufacturing (ICIEAM)

作者： I. I. Naumov R. R. Ibadov D. G. Chebotarev Faculty of Automation Mechatronics and Control Don State Technical University Rostov-on-Don Russia Department of Electrical Engineering and Electronics Don State Technical University Rostov-on-Don Russia

ISBN: (数字)9798331512194

ISBN: (纸本)9798331512200

Modern methods of remote sensing data processing require preliminary knowledge of the coordinates of objects or their manual selection. This study proposes a new approach that allows automatic and rapid detection of large-scale objects in satellite images, which creates the basis for their subsequent detailed analysis. The developed algorithm is based on key principles, the use of adaptive structural features similar to Haar wavelets, the application of cascade classification with a modified Adaboost algorithm, optimization of computational processes due to a three-level filtering system. Forest areas with areas of cut trees are considered as a test example. To improve the accuracy of recognition, automatic calibration of object sizes and dynamic adaptation of scanning parameters were used. The choice of the optimal processing method is based on a comprehensive analysis of the characteristics of the original image. The results obtained open up new opportunities for automated monitoring of territories and analysis of changes.

关键词： Adaptation models Analytical models Accuracy Object detection Feature extraction Data processing Data models Classification algorithms Satellite images Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Secure Routing Protocol Based on FANET

Secure Routing Protocol Based on FANET

引用

International Russian Smart Industry Conference (SmartIndustryCon)

ISBN: (数字)9798331511241

ISBN: (纸本)9798331511258

The flying ad-hoc network (FANET) technology-based secure routing protocol described in this study functions between a ground station and a UAV network. This protocol employs a hybrid authentication technique to guarantee communication dependability. The system is based on an asymmetric method that ensures secure connections between the UAV and the ground control station, as well as between the UAVs themselves. A symmetric scheme with digital signatures is used to encrypt the routing. Before joining the network, the UAV must register. During the registration process, the Key Distribution Center provides the necessary public and private keys for each node that wants to connect. Furthermore, crucial routing data is safeguarded using the TWINE algorithm. Wormhole attacks are avoided by using the packet binding method. Even in the event of an aggressor attack, simulations show that this routing system can sustain effective network functioning, ensuring a high packet delivery ratio and optimal network costs.

关键词： Industries Network topology Authentication Autonomous aerial vehicles Routing Routing protocols Ad hoc networks Safety Registers Grippers

来源：评论

学校读者我要写书评

暂无评论

Novel Cascaded Incremental Nonlinear Dynamic Inversion controller Approach for a Tiltrotor VTOL

Novel Cascaded Incremental Nonlinear Dynamic Inversion Contr...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Mark Henkenjohann Udo Nolte Christian Henke Ansgar Trächtler Scientific Automation Fraunhofer Institute for Mechatronic Systems Design Paderborn Germany Chair for Control Engineering and Mechatronics Paderborn University Heinz Nixdorf Institute Paderborn Germany

This paper presents a novel cascaded incremental nonlinear dynamic inversion (INDI) flight controller approach for a tiltrotor VTOL. The main focus is the adaption of INDI to a specific tiltrotor VTOL configuration aiming for optimal exploitation of the actuator capabilities combined with the advantages of a cascaded INDI. For this purpose the tilt angle of the overall thrust vector with respect to the aircraft is introduced as important connection between two cascaded INDIs: For the outer INDI linearizing translational dynamics this serves as virtual control variable. For the inner INDI linearizing rotational dynamics this variable is a pseudo control input. Thus, the tilt mechanisms of the aircraft can be utilized creating rotational and translational dynamics in a cascaded INDI approach linearizing translational and rotational dynamics separately. The approach is evaluated in simulation studies focusing on functionality, linearization and decoupling.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automated Depression Diagnosis Based on Facial Expression and Deep Dual-Stream Convolutional Neural Networks 3

Automated Depression Diagnosis Based on Facial Expression an...

引用

3rd International Conference on Computer Vision and Pattern Analysis, ICCPA 2023

作者： Chen, Yangyang Chen, Yingyu Li, Mi Department of Automation Faculty of Information Technology Beijing University of Technology Beijing100124 China Beijing International Collaboration Base on Brain Informatics and Wisdom Services Beijing100124 China Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education Beijing100124 China Engineering Research Center of Digital Community Ministry of Education Beijing100124 China

ISBN: (纸本)9781510667563

Depression is a common mental illness characterized by symptoms such as low mood, pessimism, and insomnia. In this study, we developed a deep Dual-Stream CNN to automatically diagnose and classify depression in expression video sequences. The network has two branches that extract static features and dynamic features from static and dynamic expressions, respectively, which are then fused for depression classification. The experiments were performed on the AVEC2014 database, and the results showed that the Dual-Stream model significantly improved the classification performance of depression, achieving an accuracy of 69.08% in depression categorization. © 2023 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Average Communication Rate for Networked Event-Triggered Stochastic control Systems

引用

IEEE Transactions on control of Network Systems 2025年

作者： Zhang, Zengjie Liu, Qingchen Mamduhi, Mohammad H. Hirche, Sandra Eindhoven University of Technology Department of Electrical Engineering Netherlands University of Science and Technology of China Department of Automation Hefei China University of Birmingham School of Computer Science United Kingdom Technical University of Munich Chair of Information-Oriented Control Munich Germany

Quantifying the average communication rate (ACR) of a networked event-triggered stochastic control system (NET-SCS) with deterministic thresholds is challenging due to the non-stationary nature of the system's stochastic processes. For a NET-SCS, the propagation of nonlinear statistics of the network communication status brought up by deterministic thresholds makes the precise computation of ACR difficult. Previous work used to over-simplify the computation using a Gaussian distribution without incorporating this nonlinearity, leading to sacrificed precision. This paper proposes a novel approach to calculate the exact ACR for a NET-SCS using a recursive model. We use theoretical analysis and a numerical study to qualitatively evaluate the deviation gap of the conventional approach that ignores the side information. The accuracy of our proposed method, alongside its comparison with the simplified results of the conventional approach, is validated by experimental studies. Our work is promising to benefit the efficient resource planning of networked control systems with limited communication resources by providing accurate ACR computation. © 2025 IEEE.

关键词： Networked control systems

来源：评论

学校读者我要写书评

暂无评论

Multi-population particle swarm optimization concerning the worst information 3

Multi-population particle swarm optimization concerning the ...

引用

3rd International Conference on Computer Vision and Pattern Analysis, ICCPA 2023

作者： Li, Haiyan Chen, Yanbo Sun, Jiulin Li, Mi Department of Automation Faculty of Information Technology Beijing University of Technology Beijing100124 China Beijing International Collaboration Base on Brain Informatics and Wisdom Services Beijing100124 China Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education Beijing100124 China Engineering Research Center of Digital Community Ministry of Education Beijing100124 China

ISBN: (纸本)9781510667563

Currently, the majority of multi-population algorithms ignore the worst particles and instead learn from the gbest or lbest. Hence, it is simple for these strategies to result in inadequate population variety, which causes early convergence. A multi-population particle swarm optimization considering the worst particles into account (CWMPSO) is suggested to demonstrate the importance of the worst particle information. In addition to considering the best particle, the CWMPSO algorithm concentrates on the worst particle globally. The algorithm divides the population into three subgroups, which learns from the gbest, gworst, and gbest + gworst, respectively. The development of the global worst particle information can be achieved by group learning, allowing for a more thorough exploration of potential optimum solutions and an avoidance of local functional ones. 30 complex CEC2017 benchmark functions were used in this work to test a range of algorithms including CWMPSO with various dimensions. The outcomes demonstrate that, in every dimension, the CWMPSO algorithm is better than other advanced PSOs. © 2023 SPIE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Design of control for a serial robot with actuator failures

引用

UPB Scientific Bulletin, Series D: Mechanical engineering 2021年第2期83卷 19-34页

作者： Truc, Le Ngoc Quang, Nguyen Phung Faculty Hung Yen University of Technology and Education Viet Nam Hanoi University of Science and Technology Viet Nam Institute for Control Engineering and Automation Hanoi University of Science and Technology Viet Nam

The paper addresses the actuator failure issue and aims to design a satisfactory control scheme for an n-DOF serial robot under actuator failures. The kind of actuator failures that is put into investigation in this study is the proportional degradation of actuator torque. A sliding mode controller using adaptive techniques is developed to deal with the faults. The switching gains of the proposed controller are alterable and can be suitably regulated to satisfy the Lyapunov criterion. The effectiveness of the proposal control law applied for a 6-DOF serial robot is shown through comparison with a conventional sliding mode controller. © 2021, Politechnica University of Bucharest. All rights reserved.

关键词： Manipulators

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：