检索结果-内蒙古大学图书馆

Deep learning model for pleural effusion detection via active learning and pseudo-labeling: a multisite study

BMC Medical Imaging 2024年第1期24卷 92页

作者： Chang, Joseph Lin, Bo-Ru Wang, Ti-Hao Chen, Chung-Ming Department of Biomedical Engineering College of Medicine and College of Engineering National Taiwan University No. 1 Sec. 1 Jen-Ai Road Taipei 100 Taipei 100 Taiwan EverFortune.AI Co. Ltd Taichung Taiwan The Data Science Degree Program College of Electrical Engineering and Computer Science National Taiwan University and Academia Sinica Taipei Taiwan Department of Radiation Oncology China Medical University Hospital Taichung Taiwan Department of Medicine China Medical University Taichung Taiwan

Background: The study aimed to develop and validate a deep learning-based computer Aided Triage (CADt) algorithm for detecting pleural effusion in chest radiographs using an active learning (AL) framework. This is aimed at addressing the critical need for a clinical grade algorithm that can timely diagnose pleural effusion, which affects approximately 1.5 million people annually in the United States. Methods: In this multisite study, 10,599 chest radiographs from 2006 to 2018 were retrospectively collected from an institution in Taiwan to train the deep learning algorithm. The AL framework utilized significantly reduced the need for expert annotations. For external validation, the algorithm was tested on a multisite dataset of 600 chest radiographs from 22 clinical sites in the United States and Taiwan, which were annotated by three U.S. board-certified radiologists. Results: The CADt algorithm demonstrated high effectiveness in identifying pleural effusion, achieving a sensitivity of 0.95 (95% CI: [0.92, 0.97]) and a specificity of 0.97 (95% CI: [0.95, 0.99]). The area under the receiver operating characteristic curve (AUC) was 0.97 (95% DeLong’s CI: [0.95, 0.99]). Subgroup analyses showed that the algorithm maintained robust performance across various demographics and clinical settings. Conclusion: This study presents a novel approach in developing clinical grade CADt solutions for the diagnosis of pleural effusion. The AL-based CADt algorithm not only achieved high accuracy in detecting pleural effusion but also significantly reduced the workload required for clinical experts in annotating medical data. This method enhances the feasibility of employing advanced technological solutions for prompt and accurate diagnosis in medical settings. © The Author(s) 2024.

关键词： Active learning Chest radiographs Deep learning Pleural effusion X-rays

来源：评论

学校读者我要写书评

暂无评论

Analysis of Selective Emitter Formation Technology of n-TOPCon Solar Cell

引用

Transactions of the Korean Institute of electrical Engineers 2022年第1期71卷 114-120页

作者： Jeong, Sungjin Cha, Yewon Kim, Sungheon Kim, Hongrae Park, Somin Kim, Taeyong Park, Jinjoo Ju, Minkyu Yi, Junsin Dept. of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of Interdisciplinary Program in Photovoltaic System Engineering Sungkyunkwan University Korea Republic of Dept. of Energy Convergence Engineering Division of Energy & Optical Technology Convergence Cheongju University Korea Republic of College of Information and Communication Engineering Sungkyunkwan University Korea Republic of

The main efficiency limiting factors for homogeneous emitter solar cells are resistance loss through metal contact on the front side and recombination loss at the surface. Herein, a selective emitter technology is introduced to solve the above problem, and it is currently commercialized in the mainstream p-PERC (Passivated Emitter Rear Contact) solar cell. The selective emitter boosts efficiency by 0.3-0.4% when compared to a homogeneous emitter, and when applied to the n-TOPCon (Tunnel Oxide Passivated Contact) solar cell, high efficiency of 26% or higher may be predicted. The most widely utilized selective emitter technologies are laser and etch-back. The One-Step Technology, which is suited to the n-TOPCon solar cell process, a laser is suitable for mass manufacturing with high yield. Because selective emitters increase electrical characteristics, which impact cell efficiency, it is required to study and create a technology that is optimal for the n-TOPCon manufacturing process. © 2022 Korean Institute of electrical Engineers. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

ADMM-SRNet: Alternating Direction Method of Multipliers Based Sparse Representation Network for One-Class Classification

引用

IEEE Transactions on Image Processing 2023年 32卷 2843-2856页

作者： Chiou, Chien-Yu Lee, Kuang-Ting Huang, Chun-Rong Chung, Pau-Choo National Cheng Kung University Department of Electrical Engineering Tainan 701 Taiwan National Chung Hsing University Department of Computer Science and Engineering Taichung 402 Taiwan National Cheng Kung University Cross College Elite Program and Academy of Innovative Semiconductor and Sustainable Manufacturing Tainan 701 Taiwan

One-class classification aims to learn one-class models from only in-class training samples. Because of lacking out-of-class samples during training, most conventional deep learning based methods suffer from the feature collapse problem. In contrast, contrastive learning based methods can learn features from only in-class samples but are hard to be end-to-end trained with one-class models. To address the aforementioned problems, we propose alternating direction method of multipliers based sparse representation network (ADMM-SRNet). ADMM-SRNet contains the heterogeneous contrastive feature (HCF) network and the sparse dictionary (SD) network. The HCF network learns in-class heterogeneous contrastive features by using contrastive learning with heterogeneous augmentations. Then, the SD network models the distributions of the in-class training samples by using dictionaries computed based on ADMM. By coupling the HCF network, SD network and the proposed loss functions, our method can effectively learn discriminative features and one-class models of the in-class training samples in an end-to-end trainable manner. Experimental results show that the proposed method outperforms state-of-the-art methods on CIFAR-10, CIFAR-100 and ImageNet-30 datasets under one-class classification settings. Code is available at https://***/nchucvml/ADMM-SRNet. © 1992-2012 IEEE.

关键词： contrastive learning deep learning dictionary learning One-class classification sparse representation

来源：评论

学校读者我要写书评

暂无评论

Prospective evaluation of data-driven models to predict daily risk of Clostridioides difficile infection at 2 large academic health centers (vol 2, pg 1, 2022)

引用

INFECTION CONTROL & HOSPITAL EPIDEMIOLOGY 2023年第10期44卷 1705-1705页

作者： Kamineni, Meghana Otles, Erkin Oh, Jeeheh Rao, Krishna Young, Vincent B. Li, Benjamin Y. West, Lauren R. Hooper, David C. Shenoy, Erica S. Guttag, John G. Wiens, Jenna Makar, Maggie Electrical Engineering and Computer Science Department Massachusetts Institute of Technology Cambridge Massachusetts Medical Scientist Training Program University of Michigan Medical School Ann Arbor Michigan Department of Industrial and Operations Engineering University of Michigan College of Engineering Ann Arbor Michigan Division of Computer Science and Engineering University of Michigan College of Engineering Ann Arbor Michigan Department of Internal Medicine Division of Infectious Diseases University of Michigan Medical School Ann Arbor Michigan Infection Control Unit Massachusetts General Hospital Boston Massachusetts Division of Infectious Diseases Massachusetts General Hospital Boston Massachusetts Harvard Medical School Boston Massachusetts

Many data-driven patient risk stratification models have not been evaluated prospectively. We performed and compared the prospective and retrospective evaluations of 2 Clostridioides difficile infection (CDI) risk-prediction models at 2 large academic health centers, and we discuss the models’ robustness to data-set shifts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neurocognitive assessment under various human-robot teaming environments

Neurocognitive assessment under various human-robot teaming ...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Anna L. Packy Jayesh Jayahankar Arya Teymourlouei Joshua Stone Hyuk Oh Garrett E. Katz James A. Reggia Rodolphe J. Gentili Neuroscience and Cognitive Science Program University of Maryland College Park USA Department of Computer Science University of Maryland College Park USA Department of Electrical & Computer Engineering University of Maryland College Park USA Department of Kinesiology University of Maryland College Park USA Department of Electrical Engineering & Computer Science Syracuse University Syracuse USA

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Human-robot teaming has become increasingly important with the advent of intelligent machines. Prior efforts suggest that performance, mental workload, and trust are critical elements of human-robot dynamics that can be altered by the robot’s behavior. Most prior human-robot teaming studies used behavioral analyses, but a limited number used neural markers, without the use of physical robots and complex tasks. Here we combine behavioral and EEG cortical dynamics to examine cognitive-motor processes when individuals complete a complex task under various team environments with a robot. The results revealed that altering the robot quality affected both behavioral and EEG dynamics. Task completion with an experienced robot led to greater team performance and human trust along with lower mental workload compared to an inexperienced teammate or when individuals performed alone. EEG changes suggest that different attentional processes were engaged when humans worked with the robot and performed alone, and that visual processing was more prominent when teaming with an inexperienced teammate. This work can inform human cognitive-motor processes and the design of robotic controllers in human-robot teams.

关键词： Visualization Process control Humanoid robots Collaboration Human factors Control systems Electroencephalography Behavioral sciences engineering in medicine and biology Robots

来源：评论

学校读者我要写书评

暂无评论

Sales forecasting for life insurance on primary and supplementary policies using seasonal and trend methods

Sales forecasting for life insurance on primary and suppleme...

引用

IEEE PES Asia-Pacific Power and Energy engineering Conference (APPEEC)

作者： Panrawe Boonsom Chanin Wongyai Duang-Arthit Srimoon Student in Master of Electrical and Computer Engineering Program College of Engineering Rangsit University Pathumthani Lak-Hok Thailand Faculty of Computer Engineering College of Engineering Rangsit University Pathumthani Lak-Hok Thailand

ISBN: (数字)9798350318098

ISBN: (纸本)9798350318104

Sales of insurance are collected monthly or yearly as statistics which most insurance companies haven’t estimated the sales for the next year. The current sales of insurance make it difficult to evaluate the market and organize various campaigns for customers. Therefore, this research has collected sales of life insurance from the website of the Office of Insurance Commission from the year 2018 - 2022. The forecasting of sales for life insurance using 4 forecasting methods which are Holt Winters' Additive, Holt Winters' Multiplicative, Simple Exponential Smoothing, and Double Exponential Smoothing. These forecasting methods are used to forecast insurance premiums one year ahead from the year 2021. The computation of total sales for 3 insurance types which are Primary-General, Primary, and Additional found that the Holt Winters' Multiplicative method is the best forecasting method with an accuracy percentage for forecasting methods of 97.56%.

关键词： Smoothing methods Additives Accuracy Measurement uncertainty Insurance Companies Market research

来源：评论

学校读者我要写书评

暂无评论

Asynchronous Multi-Task Learning Based on One Stage YOLOR Algorithm 32

Asynchronous Multi-Task Learning Based on One Stage YOLOR Al...

引用

32nd IEEE International Symposium on Industrial Electronics, ISIE 2023

作者： Liou, Cheng-Fu Lee, Tsung-Han Guo, Jiun-In National Yang Ming Chiao Tung University Graduate Degree Program of College of Electrical and Computer Engineering Hsinchu Taiwan Wistron-NCTU Embedded Artificial Intelligence Research Center National Yang Ming Chiao Tung University Hsinchu Taiwan

ISBN: (纸本)9798350399714

The You Only Learn One Representation (YOLOR) approach is an object detector that can encode implicit knowledge and explicit knowledge of multiple tasks simultaneously. However, the requirement of jointly feeding data is not a friendly setting for an edge device due to the high computational cost. A better strategy is to learn the concept of the new task on the device individually, one by one, without access to the old data. In other words, the model has to deal with multiple tasks asynchronously. In this work, we extend the multi-purpose network YOLOR to asynchronous multi-task learning to learn domain invariant features, which focus on capturing the relatedness between the weight of the previous task and data of the subsequent task. Further, as the number of tasks gradually increases, we accumulate significant weights by introducing task-specific masks and expert modules;the former can automatically identify important filters to prevent modification caused by new tasks, and the latter address the kernel space misalignment problem to perform multi-task feature selection. We experimentally demonstrate that the proposed training strategy significantly outperforms the traditional solution in learning multiple tasks at different times on a public dataset, which supports that the proposed approach is more competitive for resource-limited edge devices. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Development of Smart Waste Bin Segregation using Image Processing 13

Development of Smart Waste Bin Segregation using Image Proce...

引用

2021 IEEE 13th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management, HNICEM 2021

作者： Jimeno, Froilan N. Briz, Briely Jay A. Artiaga, Marvin Roy P. Angelia, Randy E. Limsangan, Noel B. University of Mindanao Electronics Engineering Program College of Engineering Education Davao Philippines University of Mindanao Computer Engineering Program College of Engineering Education Davao Philippines Mapua University School of Electrical Electronics and Computer Engineering Manila Philippines

ISBN: (纸本)9781665401678

In the Philippines, solid waste management is still a significant problem. Improper waste disposal causes serious health problems and environmental risks such as contamination of the water systems, floods, ground and air pollution, and diseases. Unfortunately, most people mistakenly believe that not segregating waste is acceptable. This study aims to develop and design a Smart Waste Bin Segregation using Image Processing and assist waste segregation through waste identification and segregation built on machine learning capable of navigating the one-time path set by the user. In particular, create an intelligent waste bin segregation prototype using image processing with three classifications. These classifications are the biodegradable, non-bio-degradable, and unknown intended to segregate solid waste into its respective bins and conduct accuracy tests using appropriate statistical tools. This device is designed for school use and may also be used in other establishments if more waste is trained, alleviate the waste segregation problem and help build an eco-friendlier society without compromising health and hygiene. The proponents successfully materialized the device, and function tests yielded an overall result of 97.33% accuracy. © 2021 IEEE.

关键词： Health risks

来源：评论

学校读者我要写书评

暂无评论

Analysis of the mechanism of degradation of p-type silicon solar cell

引用

Transactions of the Korean Institute of electrical Engineers 2021年第8期70卷 1181-1187页

作者： Cha, Yewon Jeong, Sungjin Kim, Sungheon Kim, Youngkuk Yi, Junsin Dept. of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of Interdisciplinary Program in Photovoltaic System Engineering Sungkyunkwan University Korea Republic of College of Information and Communication Engineering Sungkyunkwan University Korea Republic of

Two main factors that limiting the efficiency of the p-type solar cells are LID(Light Induced Degradation) and LeTID(Light and elevated temperature induced degradation). The major cause of LID is the formation of boron-oxygen defects in boron doped silicon. The LeTID is similar kinds as LID, but also occurs in the dark condition and by the recombination of metals and impurities or the reaction between the hydrogen and arbitrary substance. An overall 7% of LeTID degradation rate occurs over long-term scales. Unexpectedly, these degradations have been recently found to also arises in high purity materials such as float-zone(Fz-Si) and Czochralski-grown(Cz-Si). The proposed method to reduce these two degradations is to use appropriate firing process and annealing conditions. © 2021 Korean Institute of electrical Engineers. All rights reserved.

关键词： Degradation

来源：评论

学校读者我要写书评

暂无评论

Design of Motorcycle Speed Limiter through Global Positioning System 13

Design of Motorcycle Speed Limiter through Global Positionin...

引用

2021 IEEE 13th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management, HNICEM 2021

作者： Bajenting, Edmund B. Ompoc, Ralph Eimerson B. Palmero, Reynaldo G. Adtoon, Jetron J. Linsangan, Noel B. University of Mindanao Computer Engineering Program College of Engineering Education Davao Philippines Mapua University School of Electrical Electronics and Computer Engineering Manila Philippines

ISBN: (纸本)9781665401678

This study focused on designing a motorcycle speed limiter using GPS with throttle modification. The study was brought about the increase in road accidents involving motorcycle vehicles tagged to be overspeeding and some not wearing helmets. The designed system focused on controlling the throttle of the motorcycle through a microcontroller and a GPS. Also, communication from the helmet to the motorcycle was established to complete the system functionality. The system does not allow the use of the said motorcycle once the rider does not wear the helmet prescribed for the said motorcycle. Speed control of the designed system relies solely upon the GPS, making it different from typical sensory for speed and PID algorithm applied in servo motor to control the throttle acceleration. The selected road stretch was assigned 30 kph,40kph, and 60 kph, respectively. Initial tests showed a responsive rate of all parameters of the helmet and LCD design. © 2021 IEEE.

关键词： Microcontrollers

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：