检索结果-内蒙古大学图书馆

IEEE International Conference on Automation Science and engineering (CASE)

作者： Allan S. Almeida Tiago T. Ribeiro Andre G. S. Conceicao Postgraduate Program in Electrical Engineering Federal University of Bahia Salvador Brazil Department of Electrical and Computer Engineering Federal University of Bahia Salvador Brazil

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

One of the most important tasks in autonomous driving and autonomous vehicle navigation is detecting a path or trajectory that the vehicle should follow. Over the past few years, some learning-based works have stood out more than traditional computer vision techniques in detecting such lanes. In this paper we present an approach to solve the lane line detection problem in the context of visual path following by using a residual factorized convolutional neural network. Experimental results show a promising model that can detect lane lines even under severe lighting conditions and in the presence of occlusions and shadows. The path detection system was tested along with a visual path following formulation based on Nonlinear Model Predictive Control. Still, it can be used for any controller in the context of visual navigation for autonomous vehicles. Nonetheless, the proposed model architecture strikes a remarkable balance between accuracy and efficiency, making the system suitable for real-time applications.

关键词： Measurement Visualization Accuracy Navigation Computational modeling Lighting computer architecture Trajectory Convolutional neural networks Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Quantum Wrapper Networking: Investigating the Noise Impact of Classical Headers on the Quantum Payload

Quantum Wrapper Networking: Investigating the Noise Impact o...

引用

2024 Frontiers in Optics, FiO 2024

作者： Gül, Gamze On, Mehmet Berkay Tan, Shannon G. Proietti, Roberto Kanter, Gregory S. Yoo, S.J. Ben Kumar, Prem Graduate Program in Applied Physics Northwestern University 2145 Sheridan Road EvanstonIL60208 United States Department of Electrical and Computer Engineering University of California Davis DavisCA95616 United States Center for Photonic Communication and Computing Dept. of Electrical and Computer Eng. Northwestern University EvanstonIL60208 United States Department of Electronics and Telecommunications Engineering Politecnico di Torino Italy

We study the impact in time and frequency domains of classical headers on quantum payloads in quantum wrapper networking. We identify and characterize in-fiber scattering processes that produce noise photons degrading...

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Prototype Design and Verification of Intelligent Variable Output Control Apply on Micro-Spray Gun Simulation Platform

The Prototype Design and Verification of Intelligent Variabl...

引用

2022 International Conference on Fuzzy Theory and Its Applications, iFUZZY 2022

作者： Lin, Jiun-Hung Tang, Shih-Tsang Chen, Chih-Hong Cheng, Yung-Tsung Tai, Cheng-Chi Lin, Ming-Hung College of Electrical Engineering and Computer Science National Kaohsiung University of Science and Technology Kaohsiung Taiwan Ming Chuang University Department of Biomedical Engineering Taoyuan Taiwan Kun Shan University Department of Electronic Engineering Tainan Taiwan National Cheng Kung University Department of Electrical Engineering Tainan Taiwan Cheng Shiu University Department of Electrical Engineering Kaohsiung Taiwan

ISBN: (数字)9781665495875

ISBN: (纸本)9781665495875

An air compressor is a mechanical device that compresses the volume of air to increase the air pressure, and has a wide range of applications. The micro-air compressor, also known as the micro-air pump, is a small air compressor device that uses an electric motor to drive the vibration of the diaphragm to exhaust from the enclosed space. Combining the micro air pump with lightweight spraying equipment can be used in the beauty and body painting market. However, this type of micro air pump is limited by cost and volume, and only uses simple electrical control to adjust the output air pressure. There is no pressure feedback control in this air pump system, so the exhaust quality cannot be stabilized, which indirectly affects the effect of paint spraying. Therefore, this study proposes a PID control algorithm technology to the micro-air pump system, and drive the electric motor through the adjustable pulse width signal to provide the stable air supply. From the experimental results of the simulation output setting, the selection of the appropriate PID parameters is effective for the exhaust stability. Also, the intelligent control can prevent device from turning on and off frequently to reduce the performance loss and wasted energy. It can have better spraying effect when used with micro-spray gun in the future. © 2022 IEEE.

关键词： Atmospheric pressure

来源：评论

学校读者我要写书评

暂无评论

Detection of Mycobacterium Tuberculosis Using Real-time Detection Transformer

Detection of Mycobacterium Tuberculosis Using Real-time Dete...

引用

International Seminar on Intelligent Technology and Its Applications (ISITIA)

作者： Khairul Umam I Ketut Eddy Purnama Reza Fuad Rachmadi Sari Ayu Wulandari Department of Electrical Engineering Institut Teknologi Sepuluh Nopember Surabaya Indonesia Department of Electrical Engineering Department of Computer Engineering Institut Teknologi Sepuluh Nopember Surabaya Indonesia Department of Biomedical Engineering Universitas Dian Nuswantoro Semarang Indonesia

ISBN: (数字)9798350378573

ISBN: (纸本)9798350378580

Tuberculosis is a severe disease caused by Mycobacterium tuberculosis (MT). In handling it, the sputum examination method was used because it is relatively cheap and easy. The importance of MT detection in medical personnel analysis. We propose detection of Mycobacterium tuberculosis (MT) with a 1-stage detection object using two models: Detection Transformer (DETR) and Real-time Detection Transformer (RT-DETR) with different backbone variations to determine the performance of both models and conduct experiments using other models, such as yolov5l and Faster-RCNN, to compare their evaluation results with those of the DETR and RT-DETR models. In this study, MT detection using DETR with the Backbone ResNet 101 variation obtained AP:50 = 0.681 and AP:50:95 = 0.276. The RT-DETR model with HGNetv2l backbone variations yielded AP:50 = 0.837 and AP:50:95 = 0.147. The Yolov5l model produced AP:50 = 0.75 and AP:50:95 = 0.326 values. while the Faster-RCNN model produced AP:50 = 0.696 and AP:50:95 = 0.30. The results of RT-DETR with the HGNetv2-l backbone demonstrated good performance in the detection of Mycobacterium tuberculosis.

关键词： Seminars Tuberculosis Transformers Real-time systems Personnel

来源：评论

学校读者我要写书评

暂无评论

Classification of Human Blastocyst Quality Using Wavelets and Transfer Learning

Classification of Human Blastocyst Quality Using Wavelets an...

引用

International Conference on computer, Communication and Computational Sciences, IC4S 2019

作者： Irmawati Basari Gunawan, Dadang Department of Electrical Engineering Universitas Indonesia Depok Indonesia Biomedical Engineering Program Department of Electrical Engineering Universitas Indonesia Depok Indonesia

ISBN: (纸本)9789811544088

Embryo culture and transfer are the procedure of maturation and transmission of the embryo into the uterus. This procedure is one of a stage in the series of in vitro fertilization processes, better known as IVF. The selection of good quality embryos to be implanted presents a problem because of the blastocyst image. Blastocyst image is a very intricate texture to be visually determined, which is good or poor quality. This research aims to implement the pre-trained Inception-v3 network to predict blastocyst quality with add image pre-processing using wavelets. Using only 249 of human blastocyst microscope images, we developed an accurate classifier that can classify blastocyst quality with a transfer learning. The experiment with twenty epochs, the accuracy of training for only raw blastocyst images is 95%, and the best training accuracy uses a pre-processing image with Daubechies 6-tap of 99.29%. Our model was then tested on the 14 of blastocyst images and classified the images of two kinds of grade with the best accuracy of around 64.29%. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Retinal IPA: Iterative KeyPoints Alignment for Multimodal Retinal Imaging

arXiv

引用

arXiv 2024年

作者： Wang, Jiacheng Li, Hao Hu, Dewei Xu, Rui Yao, Xing Tao, Yuankai K. Oguz, Ipek Department of Computer Science Vanderbilt University United States Department of Electrical and Computer Engineering Vanderbilt University United States Department of Biomedical Engineering Vanderbilt University United States

We propose a novel framework for retinal feature point alignment, designed for learning cross-modality features to enhance matching and registration across multi-modality retinal images. Our model draws on the success of previous learning-based feature detection and description methods. To better leverage unlabeled data and constrain the model to reproduce relevant keypoints, we integrate a keypoint-based segmentation task. It is trained in a self-supervised manner by enforcing segmentation consistency between different augmentations of the same image. By incorporating a keypoint augmented self-supervised layer, we achieve robust feature extraction across modalities. Extensive evaluation on two public datasets and one in-house dataset demonstrates significant improvements in performance for modality-agnostic retinal feature alignment. Our code and model weights are publicly available at https://***/MedICL-VU/RetinaIPA. © 2024, CC BY.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Trajectory Planning with Obstacle Avoidance using APF and COLREGS for USVs

Trajectory Planning with Obstacle Avoidance using APF and CO...

引用

IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)

作者： Kelvin K. C. F. Nunes Tiago T. Ribeiro Andre G. S. Conceicao Postgraduate Program in Electrical Engineering Federal University of Bahia Salvador Brazil Department of Electrical and Computer Engineering Federal University of Bahia Salvador Brazil

ISBN: (数字)9798350352344

ISBN: (纸本)9798350352351

This paper presents a trajectory planning and obstacle avoidance system for Unmanned Surface Vehicles (USV) in complex and dynamic navigation environments. The developed system employs a modified Artificial Potential Field (APF) algorithm and the International Regulations for Preventing Collisions at Sea (COLREGS) to ensure safe and efficient navigation. Modifications were implemented to the original algorithm to deal with obstacles approaching the autonomous vehicle, including adding vectors to determine the direction of deviation based on the cross-product. The proposed system was validated in the Gazebo simulation environment within a dynamic scenario featuring static and moving obstacles.

关键词： Trajectory planning Navigation Heuristic algorithms Vectors Regulation Safety Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

RoboRover - A Jetson Nano Powered Robot Car for Object Following, Obstacle Avoidance, and Wall Following 14

RoboRover - A Jetson Nano Powered Robot Car for Object Follo...

引用

14th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2023

作者： Huynh, Trinh Walter, James Aveta, Federica University of Michigan Robotics Department Ann ArborMI48109 United States Wentworth Insitute of Technology Electrical and Computer Engineering Program BostonMA02115 United States

ISBN: (纸本)9798350304138

An intelligent and self-sufficient robot is essential across a wide range of fields, including transportation, industry, space exploration, and defense. Mobile robots possess the capability to undertake diverse tasks such as handling materials, aiding in disaster scenarios, conducting patrols, and executing rescue operations. As a result, the development of an autonomous robot that can navigate through both unchanging and ever-changing surroundings has become important. The primary objective of mobile robot navigation revolves around ensuring the seamless and secure traversal of the robot through complex environments, starting from an initial position, and reaching a designated goal position. This paper presents the design and implementation of a Jetson Nano powered robot car which uses local sensors to interact with an unknown environment. Object following, obstacle avoidance, and wall following features are built for the car to navigate to reach its desired destinations. © 2023 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Integration of Convolutional Neural Networks for Real-Time Monitoring of Soil Health in Precision Agriculture 8

Integration of Convolutional Neural Networks for Real-Time M...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Sunil, Tummapudi Pachiappan, Krishnagandhi Senthilrajan, S. Nagendar, Y. Maaliw, Renato R. Pavin, C. Malla Reddy Engineering College Malkajgiri Department of Cse Hyderabad India Nandha Engineering College Electrical and Electronics Engineering Tamil Nadu Erode India Rajalakshmi Engineering College Department of Robotics& Automation Tamil Nadu Chennai India Sr University Department of School of Computer Science and Artificial Intelligence Telangana Warangal India Southern Luzon State University Department of Cse Quezon Lucban Philippines Yar Tech Services Biomedical Engineer Hyderabad India

ISBN: (纸本)9798350367904

Convolutional Neural Networks (CNNs) represent a revolutionary breakthrough in improving crop productivity and sustainability when integrated into real-time monitoring systems for soil health in precision agriculture. CNNs are used in a novel way to analyze soil parameters directly from high-resolution photos taken by in-field sensors, such as moisture content, p H levels, and nutrient concentration. To forecast soil health measures, a CNN model was trained and validated using a collection of soil samples. The model achieved an accuracy rate of approximately 9 2 %. The CNN-based technique shortens the time needed for soil health evaluation by almost 80 % when compared to conventional approaches that involve manual sampling and laboratory analysis, allowing for quick corrective actions in the field. Additionally, more accurate and timely soil health monitoring was found to boost crop output prediction accuracy by 15 %. An up to 20 % decrease in the amount of resources used, especially water and fertilizers, can be achieved by using real-time data processing to make educated decisions about irrigation, fertilizing, and pest management. The CNN model offers scalability and adaptability across a range of crop varieties and soil conditions, and it can be easily integrated into current agricultural IoT frameworks. All things considered, using CNNs for soil health monitoring offers an economical and effective way to improve the accuracy and output of contemporary farming methods. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Exploring Biological Features of Electroencephalography Signals for Explanation-Guided Learning

Exploring Biological Features of Electroencephalography Sign...

引用

International Conference on Electronics, Information and Communications (ICEIC)

作者： Hyosung Joo Dongseok Kim Le Thi Trang Luong Do Anh Quan Jihwan Woo Department of Electrical Electronic and Computer Engineering University of Ulsan Ulsan Republic of Korea Department of Biomedical Engineering University of Ulsan Ulsan Republic of Korea

Explanation-guided learning (EGL) has gained prominence for improving both the explainability and performance of deep neural networks by integrating additional supervision signals based on the elucidation of the model. However, its applicability in analyzing electroencephalography (EEG) signals remains underexplored. This study attempted to identify and evaluate biological features for EGL-based EEG analysis using compact convolutional neural networks. The identified features included anatomical location, dipolarity, relative peak power, and event-related desynchronization of the cortical source. The feasibility of the features was evaluated with performance prediction tests, which predict model performance based on the interpreted features. All features except dipolarity possessed a significant relationship with model performance. These findings indicate the possibility of utilizing these features as biological supervision signals in future EGL-based EEG analysis.

关键词：

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：