检索结果-内蒙古大学图书馆

Application of Deep Learning Models for Vocal Cords Detection in Laryngoscopic Imagery

Procedia Computer Science 2024年 246卷 5007-5016页

作者： Jan Vrba Jakub Steinbach Matouš Cejnek Tomáš Jirsa Zuzana Urbániová Department of mathematics informatics and cybernetics University of Chemistry and Technology in Prague Technická 5 166 28 Praha 6-Dejvice Prague Czech Republic Department of Instrumentation and Control Engineering Faculty of Mechanical Engineering Czech Technical University in Prague Technická 1902/4 160 00 Praha 6 Czech Republic Department of Otorhinolaryngology 3rd Faculty of Medicine and Faculty Hospital Královské Vinohrady Charles University Ruská 87 100 00 Praha 10 Prague Czech Republic

The accurate location of vocal cords is crucial in medical imaging applications for diagnostic and therapeutic purposes. In this study, we evaluated the performance of state-of-the-art object detection models, including the YOLO, EfficientDet D1, Faster R-CNN and Single Shot Detector architectures, for the task of vocal cord detection. Using a data set of annotated medical images, we conducted comprehensive experiments to compare the models in terms of mean average precision (mAP) and inference time. Our results indicate that YOLOv8m achieved the highest performance, with a mAP@[0.5:0.95] of 0.778 and an inference time of 4.7 milliseconds. EfficientDet D1, Faster R-CNNs, and Single Shot Detectors trailed behind with slightly lower mAP scores. These findings highlight the efficacy of YOLOv8m for vocal cord localization on the utilized dataset. In addition, our study provides valuable information for the selection of suitable object detection models in medical imaging applications, facilitating better diagnosis and treatment planning in laryngology and otolaryngology.

关键词： Voice pathology detection object detection YOLO deep learning machine learning vocal folds vocal cords laryngoscopic imaging ORL otorhinolaryngology

来源：评论

学校读者我要写书评

暂无评论

Cau-1 Immobilized on Alumina Bead for Bisphenol a Removal Using Flow Through Adsorption

SSRN

引用

SSRN 2024年

作者： Mohd Pauzi, Mohamad Zahir Makhtar, Siti Nurfatin Nadhirah Yusof, Noor Fadhilah Rahman, Mukhlis A. Abas, Khairul Hamimah Othman, Mohd Hafiz Dzarfan Jaafar, Juhana Universiti Teknologi Malaysia Johor Skudai81310 Malaysia Department of Control & Instrumentation Engineering Faculty of Electrical Engineering Universiti Teknologi Malaysia Johor Skudai81310 Malaysia Microelectronics and Nanotechnology Shamsuddin Research Center Institute for Integrated Engineering Universiti Tun Hussein Onn Malaysia Johor Batu Pahat86400 Malaysia

In this study, an aluminum-based metal–organic framework named Christian Albrechts University-1 (CAU-1) was prepared through solvothermal approach between aluminum ion (Al3+) and aminoterephthalic acid (H2N–H2BDC) at 125 °C for 8 h on alumina bead surface. The alumina bead was produced via phase inversion and spherical precipitates were formed after the mixture is in contact with distilled water. After drying, it was calcined at two different temperatures, 900 and 1250 °C. The synthesized CAU-1 on alumina bead were characterized by FESEM, XRD, FTIR, mechanical compression testing, and N2 adsorption analysis. CAU-1 showed great abundance of functional group (–OH and –NH2) as well as large surface area of 1224.4348 m2∙g−1 and micropore volume of 0.52 cm3∙g−1. CAU-1-1250 had a high adsorption capacity of 392.17 mg∙g−1. In dynamic adsorption study, CAU-1-1250 recorded a better breakthrough point due to smaller particle size, which resulted in higher CAU-1 attachment. © 2024, The Authors. All rights reserved.

关键词： Adsorption

来源：评论

学校读者我要写书评

暂无评论

Visual Localization of Intersections on Autonomous Vehicles Based on HD Map

Visual Localization of Intersections on Autonomous Vehicles ...

引用

International Conference on control, Automation and systems ( ICCAS)

作者： Bizza S. Utsula Muhammad D. Ashedananta Nadana A. Azis Yul Y. Nazaruddin Vebi Nadhira Department of Engineering Physics Faculty of Industrial Technology Institut Teknologi Bandung Bandung Indonesia Engineering Physics Doctoral Program Faculty of Industrial Technology Institut Teknologi Bandung Bandung Indonesia Faculty of Industrial Technology Instrumentation and Control Research Group Institut Teknologi Bandung Bandung Indonesia

The increasing number of autonomous vehicles will result in a safety factor that must be maintained. One of the crucial prerequisites for this is proper localization, especially at intersections where most road accidents occur each year. This research is proposed to improve the localization process, which has drawbacks such as the inaccurate Global Positioning system (GPS) when satellite signals are blocked, and Light Detection and Ranging (LiDAR), which is expensive and needs heavy computing time. This is done by implementing the High Definition Map (HD Map) method, which maps the condition of an area that is stored as memory on an autonomous vehicle computer. The proposed system uses a monocular camera to be processed into a semantic segmentation feature map at the pixel level, then uses point cloud to reconstruct a 3D intersection model, which is then segmented semantically as well so that position data is obtained after merging using the occupancy grid and scoring function. The results of this CNN-based approach localization produce less accuracy and Mean Intersection over Union (MIoU) values with 60% average accuracy and 62.3 MioU when compared to GPS data and other 3D semantic segmentation systems, but the proposed approach can save costs and computational burden.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High–Frequency Transformer Development for Compact Dual Active Bridge Converters

High–Frequency Transformer Development for Compact Dual Act...

引用

International Conference on Actual Problems of Electronic Instrument engineering (APEIE)

作者： Galina Demidova Nikolai Poliakov Aleksandr Lukin Dmitry Lukichev Aleksandr Usolchev Jackson J. Justo Faculty of Control System and Robotics ITMO University Saint-Petersburg Russia Department of Electrical Engineering University of Dar es Salaam Dar es Salaam Tanzania

This paper presents a methodology for designing high–frequency transformers operating at 20 kHz made for operation in dual active bridge converter with a voltage setup of 600V/3x100V. The paper begins by explaining the calculation process for the transformer's design, focusing on crucial aspects such as leakage and magnetizing inductances. Specific techniques for the transformer winding process are discussed, ensuring accuracy and efficiency. Furthermore, the paper analyzed into calculating the parameters that make up the transformer's equivalent circuit, offering insights into its electrical characteristics. It also explores the impact of transformer leakage inductance on the converter's active power performance. To ensure the transformer's robust thermal performance, a thorough thermal analysis using Ansys software is conducted by considering various cooling methods. Finally, the construction details of the transformer, bridging the gap between theoretical design and practical realization are presented. The research concludes with the development of the final transformer construction, harmonizing the theoretical design with practical realization. This study contributes to the field of high–frequency transformer design and highlights the significance of design considerations, particularly in applications where compact and highly efficient power conversion solutions are required.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Container Detection system Using CNN Based Object Detectors 7

Container Detection System Using CNN Based Object Detectors

引用

7th International Conference on instrumentation, control, and Automation, ICA 2021

作者： Bandong, Steven Nazaruddin, Yul Yunazwin Joelianto, Endra Institut Teknologi Bandung Engineering Physics Doctoral Program Faculty of Industrial Technology Bandung Indonesia National Center for Sustainable Transportation Technology CRCS Instrumentation and Control Research Group Department of Engineering Physics Bandung Indonesia University Center of Excellence on Artificial Intelligence for Vision NLP and Big Data Analytics Institut Teknologi Bandung Instrumentation and Control Research Group Department of Engineering Physics Bandung Indonesia

ISBN: (纸本)9781665432955

The increase in free trade will also amplify the exchange of goods between countries and islands, especially in the seaports. The manual operation of the gantry-crane at the seaports has a risk due to human negligence. For that reason, automation is strongly needed in the loading and unloading of the container. Camera-based object detection is implemented to achieve this goal. In the recent years, CNN gives better accuracy in term of image classification, recognition and detection compared to the traditional method that use handcrafted features. In this paper, several advanced detection methods using CNN-based object detection, namely MobileNet, ResNet, and Faster RCNN are compared to detect and track the movement of containers. The results of the experiment show that the SSD ResNet and Faster RCNN methods are superior in terms of detection accuracy based on the Precision, Recall, Average Precision, and IoU values. MobileNet v3 excels in speed detection compared to the other methods. © 2021 IEEE.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Mathematical Modeling of the Impact of a 5 Day Interim Relaxation at 21 Days in 42 days Lockdown Strategy on COVID-19 Transmission in India

Mathematical Modeling of the Impact of a 5 Day Interim Relax...

引用

International Conference on Biosignals, Images and instrumentation (ICBSII)

作者： Flavia Immaculyne BakiyaAmbikapathy Kamalanand Krishnamurthy Lourduraj De Britto Schlumberger- Reda Production System Benoi Cresent Singapore Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Chennai India Department of Instrumentation Engineering MIT Campus Anna University Chennai India Indian Council of Medical Research Vector Control Research Centre Puducherry India

ISBN: (数字)9798350350951

ISBN: (纸本)9798350350968

As of the first week of May 2020, the COVID-19 pandemic is present in 212 nations globally. Many countries have enforced lockdown measures strategically to slow down the epidemic's spread, with the objective of relieving pressure on healthcare systems. Mathematical modelling serves as a useful tool for the prediction of the future numbers of the infected population and for analyzing the effects of various intervention strategies. In this work, a mathematical model based on ordinary differential equations has been developed for analyzing the impact of an interim relaxation of 5 days at 21 days in a 42 days lockdown period. Results of the simulation demonstrate that the relaxation of 5 days during the 42 days lockdown does not result in any adverse effects if the transmission rate remains the same. However, the model-based analysis suggests that an increase in the transmission rate by a factor of 1.2 times during the relaxation period due to the possible aggregation of the susceptible with the infected, it could shift the growth pattern of infected cases from sub-exponential to exponential.

关键词： COVID-19 Analytical models Biological system modeling Sociology Predictive models Ordinary differential equations Routing

来源：评论

学校读者我要写书评

暂无评论

Lossless Compression Technique For ECG Signals Using A-law Companding Algorithm 3

Lossless Compression Technique For ECG Signals Using A-law C...

引用

3rd International Conference on Innovative Research in Applied Science, engineering and Technology, IRASET 2023

作者： Hanine, Mustapha El Ouldzira, Hicham Boudaoud, Abdelghani Abdelmounim, Elhassane Higher Institute of Health Sciences Hassan First University of Settat Laboratory of Health Sciences and Technologies Department of Biomedical Instrumentation and Medical Physics Settat Morocco Department of Industrial Engineering Safi Morocco High School of Technology Sultan Moulay Slimane University Laboratory of Engeneering and Applied Physics Department of Mechatronics Beni Mellal Morocco Hassan First University Laboratory of System Analysis and Information Technology Faculty of Sciences and Technology Department of Applied Physics Settat Morocco

ISBN: (纸本)9798350398366

In this work, we present a lossless compression technique based on the use of the A-law companding algorithm, associated with the inter-leads correlation to compress ECG signals by reducing the dynamic range and number of encoded signals. Experiments are conducted on the selected records from the PTB Arrhythmia Database, and the performance is evaluated using the compression ratio (CR) and the percent root mean square difference (PRD). the results show that this technique efficiently retains pathological informations, whether for patients in normal condition or with arrhythmias, a total compression ratio CR of 4.92 is achieved with a PRD of 0 %. © 2023 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Adequacy and Security Assessment: Machine Learning Trends for Reliable Smart Energy Networks

Data-Driven Adequacy and Security Assessment: Machine Learni...

引用

Smart Grid Conference (SGC)

作者： Mohammad Mohsen Hayati Hassan Majidi Hossein Shahinzadeh Mehdi Abapour Mahmud Fotuhi-Firuzabad Gevork B. Gharehpetian Faculty of Electrical and Computer Engineering Energy Systems Research Institute (ESRI) University of Tabriz Tabriz Iran Department of Electrical Engineering Amirkabir University of Technology Tehran Iran Center of Excellence in Power System Management and Control (CEPSMC) Sharif University of Technology Tehran Iran

ISBN: (数字)9798331511333

ISBN: (纸本)9798331511340

Smart energy networks (SENs) face numerous challenges related to security, reliability, operational uncertainties, and increasing penetration of renewable energies (REs), necessitating advanced methodologies for adequacy and security assessment. This study delves into the utilization of machine learning-driven approaches (MLDAs) to quantify reliability and gauge the dependability of future sustainable SENs. By autonomously acquiring knowledge from datasets, MLDAs offer swift and reliable evaluations, surpassing traditional methodologies. The integration of artificial intelligence (AI) in enhancing power system reliability is highlighted, emphasizing the importance of extensive datasets and evolving AI algorithms. Data-driven approaches empower energy network operators to proactively identify and mitigate security risks, enhancing the reliability of critical infrastructure systems. The research underscores the significance of constructing reliable databases, addressing challenges in real-time operations, and ensuring the performance and trustworthiness of machine learning (ML) algorithms. Overall, the study showcases the potential of ML techniques in revolutionizing reliability management and risk assessment in smart energy networks, paving the way for sustainable and reliable power systems.

关键词： Uncertainty Machine learning algorithms Databases Machine learning Power system reliability Smart grids Management Reliability Security Risk management

来源：评论

学校读者我要写书评

暂无评论

Human Following Robot Based on Object Detection for Aerospace Application

Human Following Robot Based on Object Detection for Aerospac...

引用

Aerospace Electrical engineering and Informatics (ICAAEEI), International Conference of Adisutjipto on

作者： Arwin Datumava Wahvudi Sumari Ahnaf Bagus Aryandika Ndaru Atmi Purnami Denny Dermawan Ika Noer Syamsiana Department of Electrical Engineering Cognitive Artificial Intelligence Research Group State Polytechnic of Malang Malang Indonesia Electrical Engineering Study Program Adisutjipto Institute of Aerospace Technology Yogyakarta Indonesia Aerospace Navigation Instrumentation Control Automation and Robotics System Research Group Electrical Engineering Study Program Adisutjipto Institute of Aerospace Technology Yogyakarta Indonesia Aerospace Digital System Microprocessor Microcontroller and Programmable Logic Devices Research Group Electrical Engineering Study Program Adisutjipto Institute of Aerospace Technology Yogyakarta Indonesia

ISBN: (数字)9798331507930

ISBN: (纸本)9798331507947

In this research, the Human Following Robot (HFR) prototype has been designed and implemented using YOLO v3-Tiny and Tensor Flow Lite on Raspberry Pi hardware named Rewang. The HFR Rewang is designed to assist aircraft technicians by bringing maintenance tool kits to aircraft shelters. Rewang's movement is based on a camera as a vision sensor following the movement of human entities. Image input is processed by YOLO v3-Tiny through the determination of the bounding box, the calculation of Euclidean Distance, and the determination of the pixel value of the camera as the basis of Rewang's movement which is regulated by an L298N driver motor that controls two Direct Current (DC) motors for the left and right wheels. The test results show that Rewang can move at an average speed of 0.18 m/s at 2 m with a travel time of 11 seconds with a light intensity of more than 250 lux. The minimum and maximum distance of object detection is as far as 120 cm and 400 cm, with an object detection accuracy of 95.8%. Rewang allows the HFR to have a larger carrying capacity to bring more complete aircraft maintenance tools and is prospective for other aerospace and general applications.

关键词： YOLO Tensors Accuracy Prototypes Wheels Cameras Hardware Maintenance Aircraft Aerospace industry

来源：评论

学校读者我要写书评

暂无评论

Energy harvesting for self-powered systems 6

Energy harvesting for self-powered systems

引用

6th International Conference on engineering, Applied Sciences and Technology, ICEAST 2020

作者： Nundrakwang, Songmoung Yingyong, Phonexai Isarakorn, Don King Mongut's Institute of Technology Department of Instrumentation and Control Engineering Faculty of Engineering Ladkrabang Bangkok Thailand

ISBN: (纸本)9781728199788

Harvesting energy from waste energy sources in ambient environmental is the accessible technology in the field of self-power electronic devices for high-efficiency energy due to the power consumption of modern electronic devices that are rapidly developed to microwatt, low-cost, lightweight, and small size. Since numerous research are investigated the technique for converting the ambient energy into useable electrical energy for practical application. Including light, thermal gradients, vibration or motion, and radio-frequency electromagnetic radiation, various forms of waste energy sources are proposed in this review. Their existing power density in the ambient environment is demonstrated. Moreover, the fundamental theory and the application of the energy harvesting devices are discussed as a foundation of the energy conversion technology for self-power electronic devices such as handheld, wearable, and portable devices. © 2020 IEEE.

关键词： Energy harvesting

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：