检索结果-内蒙古大学图书馆

Journal of Network Intelligence 2023年第2期8卷 347-363页

作者： Liao, Lyuchao Chen, Ruixiang Shi, Jinjin Zheng, Qi Xiong, Rong Zeng, Jiemao Fujian Provincial Universities Key Laboratory of Industrial Control and Data Analysis Fujian Provincial Universities Engineering Research Center for Intelligent Driving Technology Fujian University of Technology Fuzhou350118 China Fujian Provincial Universities Engineering Research Center for Intelligent Driving Technology Fujian University of Technology Fuzhou350118 China

Object identification is a significant computer vision issue with a growing number of applications in the area of autonomous driving. In order to solve the problem of difficult detection of small objects and dense objects in the target detection algorithm in the autonomous driving scenarios,we propose an object detection method with a hybrid domain attention mechanism. In the model, the Neck network is integrated with a parallel mixed-domain attention mechanism to increase the usable features in the feature map from both channel and spatial aspects. Then, we improve the Spatial Pyramid Pooling (SPP) module with dilated convolutions to limit the loss of important information in the feature map after max pooling, which further optimizes the detector performance. Finally, a fusion approach is proposed to improve the detection layer and enhance the capability of detecting tiny objects. Extensive experiments on the BDD100k dataset show that the proposed model outperforms the state-of-the-art YOLOv5s model with an average accuracy increase of 6.22%(mAP @0.5). © 2023, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Fall Detection System Based on YOLO Algorithm and MobileNetV2 Model 10

Fall Detection System Based on YOLO Algorithm and MobileNetV...

引用

10th International Conference on Systems and Informatics, ICSAI 2024

作者： Han, Chunxiao Zhang, Jingyan Wu, Han Tianjin Key Laboratory of Information Sensing & Intelligent Control China School of Automation and Electrical Engineering Tianjin University of Technology and Education Tianjin300222 China

ISBN: (纸本)9798331510138

Accidental falls are the major causes of injury among elderly people living alone. However, traditional fall detection algorithms usually have missed or false detections problems. In this paper, we design a fall detection system based on YOLO algorithm and MobileNetV2 model. First, detection frame coordinates and joint coordinates of the human body are fused as feature information, and background information is filtered out. A lightweight deep learning model, MobileNetV2, is then used for classification. Compared with commonly used lightweight classification models such as ShuffleNet and EfficientNet, the MobileNetV2 model performs better in recognizing fall behavior. Our system can effectively distinguish fall behavior from daily activities, meeting the requirements for fall detection. © 2024 IEEE.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

Stabilization of Perturbed Continuous-Time Systems Using Event-Triggered Model Predictive control

引用

IEEE Transactions on Cybernetics 2022年第5期52卷 4039-4051页

作者： Wang, Mengzhi Sun, Jian Chen, Jie Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China Beijing Institute of Technology Key Laboratory of Intelligent Control and Decision of Complex System Beijing100081 China Beijing Institute of Technology Chongqing Innovation Center Chongqing401120 China

In this article, event-triggered model predictive control (EMPC) of continuous-time nonlinear systems with bounded disturbances is studied. Two novel event-triggered control schemes are proposed. In the first strategy, an event-triggering condition, designed based on the state error between the actual system state and the optimal one, with an absolute threshold is considered. In the second strategy, an event-triggering condition with a mixed threshold is designed to further save the computational resources. The minimal interevent times of both event-triggered control schemes are obtained to avoid the Zeno behavior. Sufficient conditions of recursive feasibility for these two triggering strategies, which refer to the prediction horizon, the triggering level, and the disturbance bound, are obtained, respectively. Input-to-state practical stability (ISpS) of both event-triggered control systems is established without requiring the system state entering the terminal set in finite time, respectively. Finally, the numerical simulation shows the effectiveness of the proposed methods. © 2013 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Chip Architecture Design Management Based on Low-Power Multitasking Simulation 9

Chip Architecture Design Management Based on Low-Power Multi...

引用

9th International Conference on Advances in Machinery, Materials Science and Engineering Applications, MMSE 2023

作者： Zhang, Ying Sun, Kai National Key Laboratory of Science and Technology on Aerospace Intelligent Beijing Aerospace Automatic Control Institute Beijing100854 China

ISBN: (纸本)9781643684383

From the aspects of low-power DSP design, low-power SOC design, and low-power power switch design, this paper proposes a chip architecture 'high-low matching' scheme for low-power multitasking requirements. The low-power DSP design starts with operating voltage and operating frequency control, and uses three low-power modes, PD1, PD2, and PD3;the low-power SOC design carries out low-power mode management from the clock control of APB and AHB bus;In terms of low-power power switch design, no-load low-power control, and input under-voltage protection, output over-voltage protection, over-temperature protection, and output over-current protection are implemented. The paper proposes different low-power control modes. After the evaluation of the built test platform, it is proved that the design of the scheme is reasonable, and it can realize the engineering application of low-power multi-task management. © 2023 The Authors.

关键词： Electric power utilization

来源：评论

学校读者我要写书评

暂无评论

ADAPTIVE BOUNDARY control VIBRATION SUPPRESSION OF FLEXIBLE MANIPULATOR BASED ON IMPROVED RBF NEURAL NETWORK

引用

UPB Scientific Bulletin, Series D: Mechanical Engineering 2024年第2期86卷 3-18页

作者： Zheng, Qingchun Wei, Zhiyong Zhu, Peihao Ma, Wenpeng Deng, Jieyong Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin University of Technology Tianjin300384 China China School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China Jiangxi Technical College of Manufacturing Jiangxi Nanchang330095 China

With lighter weight, lower power consumption, and higher flexibility, flexible manipulators have been widely used in industrial fields. However, it is easy to produce elastic deformation, resulting in vibration. In this paper, an improved radial basis function (RBF) neural network (NN) for adaptive boundary control is proposed. The partial differential equation (PDE) model of the flexible manipulator is established, and the asymptotic stability of the system is proved by the first Lyapunov method. Finally, simulation results show that the proposed control method can eliminate the low-amplitude angular fluctuation and the high-amplitude angular velocity fluctuation. © 2024, Politechnica University of Bucharest. All rights reserved.

关键词： Flexible manipulators

来源：评论

学校读者我要写书评

暂无评论

Architectural Color Image Scale Computing of Beijing Forbidden City

Architectural Color Image Scale Computing of Beijing Forbidd...

引用

2024 International Conference on Culture-Oriented Science and technology, CoST 2024

作者： Liu, Bowen Huang, Wenli Yu, Xiumeng Ma, Zongliu Guo, Ziyi Wang, Shuang Jiang, Wei Communication University of China State Key Laboratory of Media Convergence and Communication 100024 China Communication University of China Key Laboratory of Acoustic Visual Technology and Intelligent Control System 100024 China Communication University of China Beijing Key Laboratory of Modern Entertainment Technology 100024 China

ISBN: (纸本)9798350380347

The traditional color system of Beijing Forbidden City is comprehensive and complex. The research focuses on collecting color data from the Forbidden City, analyzing subjective and objective color attributes, and compute architectural color image scale. First this research used K-means algorithm to extract the theme color cards of Beijing Forbidden City. Subsequently, single colors were extracted using the idea of community detection, and matching colors were extracted based on the thought of association rule mining. Then this research extracted objective attributes of colors and designed experiments to quantify subjective attributes. Finally, the color subjective and objective data fitting was completed. This outcome is helpful for the digital preservation of traditional colors and the advancement of color culture inheritance practices. © 2024 IEEE.

关键词： Color computer graphics

来源：评论

学校读者我要写书评

暂无评论

Semantic Analysis and Modeling of the Color of Stage Costume - A Case Study of 'The Painting Journey'

Semantic Analysis and Modeling of the Color of Stage Costume...

引用

2024 International Conference on Culture-Oriented Science and technology, CoST 2024

作者： Huang, Wenli Liu, Bowen Sun, Fang Wang, Shuang Communication University of China State Key Laboratory of Media Convergence and Communication 100024 China Key Laboratory of Acoustic Visual Technology and Intelligent Control System Communication University of China 100024 China Beijing Key Laboratory of Modern Entertainment Technology Communication University of China 100024 China

ISBN: (纸本)9798350380347

The creation of Chinese dance dramas plays an important role in the dissemination of Chinese culture in the context of pluralistic unity. As one of the outstanding poetry dramas in the past two years, 'The Journey of a Legendary Landscape Painting' (JLLP) has rich national cultural connotations and aesthetic value in its stage costume colors. This article first studied the data extraction method of stage costume colors based on clustering and association rule mining, and constructed the color dataset for JLLP. On this basis, the color semantic mining and extraction including subjective and objective factors were conducted. Finally, combined with color semantics, the character personality of JLLP was further analyzed. The research results show that the color extraction method designed in this article can accurately preserve the color characteristics of stage costumes. In addition, the costume colors of JLLP play a good supporting role in shaping the character personality. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Ozone oxidation of 4H-SiC and flat-band voltage stability of SiC MOS capacitors

引用

Chinese Physics B 2022年第11期31卷 500-509页

作者： Zhi-Peng Yin Sheng-Sheng Wei Jiao Bai Wei-Wei Xie Zhao-Hui Liu Fu-Wen Qin De-Jun Wang Key Laboratory of Intelligent Control and Optimization for Industrial Equipment Ministry of Education School of Control Science and Engineering Faculty of Electronic Information and Electrical EngineeringDalian University of TechnologyDalian 116024China State Key Laboratory of Materials Modification by Laser Ionand Electron Beams(Ministry of Education)Dalian University of TechnologyDalian 116024China

We investigate the effect of ozone(O_(3))oxidation of silicon carbide(SiC)on the flat-band voltage(Vfb)stability of SiC metal–oxide–semiconductor(MOS)*** SiC MOS capacitors are produced by O_(3)oxidation,and their Vfbstability under frequency variation,temperature variation,and bias temperature stress are *** ion mass spectroscopy(SIMS),atomic force microscopy(AFM),and x-ray photoelectron spectroscopy(XPS)indicate that O_(3)oxidation can adjust the element distribution near SiC/SiO_(2)interface,improve SiC/SiO_(2)interface morphology,and inhibit the formation of near-interface defects,*** addition,we elaborate the underlying mechanism through which O_(3)oxidation improves the Vfbstability of SiC MOS capacitors by using the measurement results and O_(3)oxidation kinetics.

关键词： SiC MOS capacitors ozone oxidation bias temperature instability Deal-Grove model

来源：评论

学校读者我要写书评

暂无评论

Prescribed Performance control for Switched Nonlinear Systems 42

Prescribed Performance Control for Switched Nonlinear System...

引用

42nd Chinese control Conference, CCC 2023

作者： Lian, Jie Chen, Kang Wu, Feiyue Wang, Dong Dalian University of Technology The Key Laboratory of Intelligent Control and Optimization for Industrial Equipment Ministry of Education Dalian116024 China

ISBN: (纸本)9789887581543

This paper presents a prescribed performance control scheme for a class of switched nonlinear systems. First, the prescribed performance control (PPC) is used to guarantee the transient and steady-state performance of the tracking error. Then, the bounds of all signals in the resulting closed-loop system are ensured by the adaptive control and the dwell time method. At the same time, the 'complexity explosion' is avoided by using command filters. At the end, the effectiveness of the proposed control scheme is demonstrated by a simulation. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Closed loop systems

来源：评论

学校读者我要写书评

暂无评论

Research and Design of an intelligent New Energy Surface Garbage Recycling Vessel Based on STM32

Research and Design of an Intelligent New Energy Surface Gar...

引用

2024 International Conference on Computing, Robotics and System Sciences, ICRSS 2024

作者： Shan, Yang Hao, Jianxiu Ding, Jianqun Mi, Xianwu Zhou, Chengling Zhang, Minzhe Zhang, Leqi Yuan, Jiali School of Physics Electronics and Intelligent Manufacturing Huaihua University Huaihua China Huaihua University Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Huaihua China

ISBN: (纸本)9798331511296

To address the issue of water surface garbage pollution, a new energy-powered intelligent water surface garbage recycling boat has been designed. The intelligent water surface garbage recycling boat takes the STM32F103 single-chip microcontroller as the core control unit. And it integrates some modules such as visual recognition, Beidou/GPS dual-mode positioning, and millimeter-wave radar. The unit module design method and the collaborative working mechanism of each module effectively guarantee the realization of the functions of the intelligent water surface garbage recycling boat. Specifically, the motor driving module ensures the normal running and steering of the water surface garbage recycling boat. Besides, the visual module facilitates garbage recycling and intelligent classification on the water surface. Moreover, the Beidou positioning module is utilized not only for daily navigation of intelligent fixed-point garbage recycling, but also for the recovery and utilization of solar and wind energy from all directions. In addition, the millimeter-wave radar on the hull can ensure the safe travelling of the garbage recycling boat comprehensively. The boat designed in this paper exhibits the characteristics of low energy consumption, high performance, and energy conservation and emission reduction. © 2024 IEEE.

关键词： Emission control

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：