检索结果-内蒙古大学图书馆

Transformer-CNN for small image object detection

Signal Processing: Image Communication 2024年 129卷

作者： Chen, Yan-Lin Lin, Chun-Liang Lin, Yu-Chen Chen, Tzu-Chun Department of Electrical Engineering National Chung Hsing University Taichung 40227 Taiwan Department of Automatic Control Engineering Feng Chia University Taichung 40724 Taiwan

Object recognition in computer vision technology has been a popular research field in recent years. Although the detection success rate of regular objects has achieved impressive results, small object detection (SOD) is still a challenging issue. In the Microsoft Common Objects in Context (MS COCO) public dataset, the detection rate of small objects is typically half that of regular-sized objects. The main reason is that small objects are often affected by multi-layer convolution and pooling, leading to insufficient details to distinguish them from the background or similar objects, resulting in poor recognition rates or even no results. This paper presents a network architecture, Transformer-CNN, that combines a self-attention mechanism-based transformer and a convolutional neural network (CNN) to improve the recognition rate of SOD. It captures global information through a transformer and uses the translation invariance and translation equivalence of CNN to maximize the retention of global and local features while improving the reliability and robustness of SOD. Our experiments show that the proposed model improves the small object recognition rate by 2∼5 % than the general transformer architectures. © 2024

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Approach for Small Image Object Detection Based on Transformer-Cnn

SSRN

引用

SSRN 2024年

作者： Lin, Chun-Liang Chen, Yan-Lin Lin, Yu-Chen Department of Electrical Engineering National Chung Hsing University Taichung40227 Taiwan Department of Automatic Control Engineering Feng Chia University Taichung40724 Taiwan

Although the detection success rate of regular objects has achieved excellent results, small object detection (SOD) is still challenging in object recognition. The main reason is that small objects are often affected by multi-layer convolution and pooling leading to resulting in a lack of sufficient details to distinguish them from the background or similar objects leading to poor recognition rates or even no results. This paper presents a network architecture, named Transformer-CNN, that combines a self-attention mechanism-based transformer and convolutional neural network (CNN) to improve the recognition rate of SOD. It captures global information through a transformer and uses the translation invariance and translation equivalence of CNN to maximize the retention of global and local features while improving the reliability and robustness of SOD. Our experiments show that the proposed model improves the small object recognition rate by 2~5% than the general transformer architectures. © 2024, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Delivering Improved Care through Remote Health Monitoring Systems by Using Microservices. Case Study: Fall Detection Encompassed into Connected Care 24

Delivering Improved Care through Remote Health Monitoring Sy...

引用

24th International Conference on control Systems and Computer Science, CSCS 2023

作者： Ianculescu, Marilena Alexandru, Adriana Giura, Ionut-Emanuel Vasilevschi, Ana-Mihaela National Institute for Research and Development in Informatics Communication Digital Applications and Systems Department Bucharest Romania University Politehnica of Bucharest Doctoral School of Automatic Control and Computers Bucharest Romania Counselors Department National Institute for Research and Development in Informatics Târgovişte Romania Faculty of Electrical Engineering Electronics and Information Technology Târgovişte Romania Valahia University of Târgovişte Târgovişte Romania

ISBN: (纸本)9798350313390

Based on today's modern technologies, patient care can be provided remotely, in a connected way, being, at the same time, personalized, patient-centered and proactive. Such an approach can be achieved using Remote Health Monitoring Systems (RHMS). In case of elderly people, dramatic permanent deteriorations of their health status can be caused by falls. The seniors' health and life style monitoring and the detection and/or prevention of falls can be done by such RHMS, an example being the RO-SmartAgeing system developed inside 'Non-invasive Monitoring System and Health Assessment of the Elderly in a Smart Environment (RO-SmartAgeing)' research project. The paper presents the problem of using microservices for optimizing the architecture and functionalities of RO-SmartAgeing system, and the way in which the problems of ensuring the security of patient data can be solved. © 2023 IEEE.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Detects Anomalies in OPS-SAT Telemetry 23rd

Machine Learning Detects Anomalies in OPS-SAT Telemetry

引用

23rd International Conference on Computational Science, ICCS 2023

作者： Ruszczak, Bogdan Kotowski, Krzysztof Andrzejewski, Jacek Musial, Alicja Evans, David Zelenevskiy, Vladimir Bammens, Sam Laurinovics, Rodrigo Nalepa, Jakub Faculty of Electrical Engineering Automatic Control and Informatics Department of Informatics Opole University of Technology Prószkowska 76 Opole45-758 Poland Faculty of Automatic Control Electronics and Computer Science Department of Algorithmics and Software Silesian University of Technology Akademicka 16 Gliwice44-100 Poland KP Labs Konarskiego 18C Gliwice44-100 Poland European Space Agency/ESOC Robert-Bosch-Str. 5 Darmstadt64293 Germany Telespazio Germany GmbH Europaplatz 5 Darmstadt64293 Germany IrbGS ltd "Viraki" Ance Parish IrbeneLV-3601 Latvia

ISBN: (纸本)9783031359941

Detecting anomalies in satellite telemetry data is pivotal in ensuring its safe operations. Although there exist various data-driven techniques for the task of determining abnormal parts of the signal, they are virtually never validated over real telemetries. Analyzing such data is challenging due to its intrinsic characteristics, as telemetry may be noisy and affected by incorrect acquisition, resulting in missing parts of the signal. In this paper, we tackle this issue and propose a machine learning approach for detecting anomalies in single-channel satellite telemetry. To validate its capabilities in a practical scenario, we build a dataset capturing the nominal and anomalous telemetry data captured on board OPS-SAT—a nanosatellite launched and operated by the European Space Agency. Our extensive experimental study showed that the proposed algorithm offers high-quality anomaly detection in real-life satellite telemetry, reaching 98.4% accuracy over the unseen test set. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Development of Path Tracking and Obstacle Avoidance based on an Advanced Potential Field controller

Development of Path Tracking and Obstacle Avoidance based on...

引用

2023 International Symposium on electrical and Electronics engineering, ISEE 2023

作者： Tran, Duc Thien Nguyen, Quang Chien Pham, Duc Huy Nguyen, Trong Tai Luu, Nguyen Phong Ho Chi Minh City University of Technology and Education Automatic Control Department Ho Chi Minh City700000 Viet Nam Faculty of Electrical & Electronics Engineering Ho Chi Minh City700000 Viet Nam

ISBN: (纸本)9798350315486

This paper proposes a new method that combines path tracking and obstacle avoidance for a differential drive mobile robot based on the Advanced Potential Field controller (APFC) to increase stability and safety for robot operation. In conventional methods, the transition between path following and obstacle avoidance is typically achieved through a simple switch, which does not ensure the robot returns to the original path after avoiding the obstacle. The proposed methods integrate the Repulsive Potential Field (RPF) and Attractive Potential Field (APF), effectively solving this issue and enhancing smooth navigation in static environments. The RPF is utilized to steer the robot away from obstacles, while the APF is employed to redirect the robot back to its path after obstacle avoidance. The algorithm is verified on the designed robot, and experimental results provide efficiency in achieving autonomous robot navigation. © 2023 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Distributed Time-Varying Gaussian Regression via Kalman Filtering

arXiv

引用

arXiv 2025年

作者： Taddei, Nicola Maggioni, Riccardo Eising, Jaap De Pasquale, Giulia Dörfler, Florian Automatic Control Laboratory Department of Electrical Engineering and Information Technology ETH Zurich Physikstrasse 3 Zurich8092 Switzerland Control Systems Group Department of Electrical Engineering TU Eindhoven Flux Groene Loper 19 Eindhoven5612 AP Netherlands

We consider the problem of learning time-varying functions in a distributed fashion, where agents collect local information to collaboratively achieve a shared estimate. This task is particularly relevant in control applications, whenever real-time and robust estimation of dynamic cost/reward functions in safety critical settings has to be performed. In this paper, we adopt a finite-dimensional approximation of a Gaussian Process, corresponding to a Bayesian linear regression in an appropriate feature space, and propose a new algorithm, DistKP, to track the time-varying coefficients via a distributed Kalman filter. The proposed method works for arbitrary kernels and under weaker assumptions on the time-evolution of the function to learn compared to the literature. We validate our results using a simulation example in which a fleet of Unmanned Aerial Vehicles (UAVs) learns a dynamically changing wind field. Copyright © 2025, The Authors. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Optimal Distribution of UAVs in Crop Spraying Considering Energy Consumption

Optimal Distribution of UAVs in Crop Spraying Considering En...

引用

American control Conference (ACC)

作者： O.F. Archila N. Quijano J. Martinez-Piazuelo Control Systems and Network Control Engineering Department BTU Cottbus-Senftenberg Cottbus Germany Electrical and Electronics Engineering Department Universidad de los Andes Automatic Control Department Universitat Politècnica de Catalunya Barcelona Spain

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

The population growth rate has increased, leading to a need for new technologies like unmanned aerial vehicles (UAVs) to expand crop production and growth. UAVs are used in mapping, spraying, planting, crop monitoring, irrigation, and insect pest diagnosis. However, challenges such as maximum effective signal range, fuel limitations, uncovered crop areas, overlapped spraying, and pesticide waste need to be considered. In this context, we propose a multi-agent control method that associates the energy consumption with the total crop coverage. Our proposed method is able to generate the path planning for the UAVs considering a target density function, while the total flying time is decreased. The simulation results show that the proposed method decreases the total energy consumption with a negligible increment in the spray error.

关键词： Energy consumption Irrigation Power demand Simulation Spraying Crops Production

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Semi-Active Suspension System for Design of Vehicle Stability control System

An Adaptive Semi-Active Suspension System for Design of Vehi...

引用

International Conference on Intelligent Transportation

作者： Yu-Chen Lin Chien-Wen Sun Bo-Han Lyu Ting-Jia Yeh Department of Automatic control engineering Feng Chia University Taichung Taiwan Institute of Electrical and Control Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Department of Automatic Control Engineering Feng Chia University Taichung Taiwan

In this paper, an adaptive semi-active suspension system by adjusting air springs is proposed to design of vehicle stability control system, which can achieve handling stability. In order to develop the adaptive control algorithm, the CarSim dynamic model is acquired, and a reinforcement learning scheme using the deep deterministic policy gradient (DDPG) control strategy is used to decide the best amount of air spring pressure. This method is able to adjust the yaw activity to avoid understeer and oversteer issues as well as increasing the vehicle stability. In summary, the simulation results show that the handling stability is improved by 25.78 % under high road curvatures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the Gaussian Filtering for Nonlinear Dynamic Systems Using Variational Inference 27

On the Gaussian Filtering for Nonlinear Dynamic Systems Usin...

引用

27th International Conference on Information Fusion, FUSION 2024

作者： Liu, Yi Li, Xi Yang, Le Mihaylova, Lyudmila Li, Ji University of Canterbury Department of Electrical and Computer Engineering Christchurch New Zealand National University of Defense Technology State Key Lab of Complex Electromagnetic Environment Effects on Electronics and Information Systems Changsha China University of Sheffield Department of Automatic Control and System Engineering Sheffield United Kingdom Locaris Electronic Technology Co. Ltd Zhengzhou China

ISBN: (纸本)9781737749769

This paper introduces a new variational Gaussian filtering approach for estimating the state of a nonlinear dynamic system. We first assume that the predictive distribution of the state is Gaussian and derive an iterative method for updating the state posterior in the natural parameter space through KullbackLeibler divergence minimization. The obtained update rule is the same as that of the conjugate-computation variational inference technique in Bayesian learning. The derivation here is simpler and more insightful. We then impose a Wishart prior on the inverse of the state prediction covariance to take into account the impact of approximating the state predictive distribution using a Gaussian density on the state posterior estimation. The prediction covariance is identified jointly with the state using variational inference and the established state posterior update rule to achieve the desired Gaussian filtering. Simulation study examines the performance of the proposed filtering framework in target tracking based on bearing and range measurements. © 2024 ISIF.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Numerical Simulation of 3D Printed Resin Droplet-Based Microfluidic Device with T-Junction Geometry 8

Numerical Simulation of 3D Printed Resin Droplet-Based Micro...

引用

8th International Conference on Instrumentation, control, and Automation, ICA 2023

作者： Sarwono, Febricetta Zahraketzia Azhar Fa'Iq, Muhammad Anshori, Isa Putra, Narendra Kurnia Institut Teknologi Bandung Faculty of Industrial Technology Engineering Physics Department Bandung Indonesia Institut Teknologi Bandung School of Electrical Engineering and Informatics Biomedical Engineering Department Bandung Indonesia Institut Teknologi Bandung Instrumentation and Control Research Group Faculty of Industrial Technology Bandung Indonesia

ISBN: (纸本)9798350301274

Droplet-based microfluidics is a device that can process fluids on a micro-scale to be broken down into uniform droplets at a relatively fast rate. The droplet forming process can be done in a T-junction droplet-based microfluidics configuration where a dispersed fluid is injected into a continuous fluid flow to produce dispersed fluid droplets. In general, droplet-based microfluidics research is done using experimental tests which are limited in empirical observation, especially for mass production cases where an optimized design is needed. In this study, a numerical simulation was carried out to replicate the droplet generation in the droplet-based microfluidic device based on three-dimensional (3D) printed resin T-junction geometric scheme. Numerical simulation was carried out in a two-dimensional (2D) simulation using the level-set method (LSM) based on the finite element method (FEM) using computational fluid dynamics (CFD) tools for two-phase flow. Water is used as the dispersed fluid, and silicone oil 350 cp is used as the continuous fluid streamed into microfluidic channels with a height of 0.5 mm and a flow rate of 2.5 ml/hr. This study provides the influence of physical parameters such as the shear stress, pressure, and velocity profile which are evaluated at an evaluation point which directly affects the formation of droplets due to the interaction between two immiscible fluids. In addition, suggestions for future droplet generation simulations in microfluidics simulations are also obtained. © 2023 IEEE.

关键词： Microfluidics

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：