检索结果-内蒙古大学图书馆

Computer-aided diagnosis system for abnormalities classification in gastric endoscopy images using machine learning

Transactions of the Korean Institute of Electrical Engineers 2020年第1期69卷 107-113页

作者： Lee, Sin-Ae Cho, Hyunchin Cho, Hyun-Chong Dept. of Electronics Engineering and Interdisciplinary Graduate Program for BIT Medical Convergence Kangwon National University Korea Republic of Interdisciplinary Graduate Program for BIT Medical Convergence Kangwon National University Korea Republic of Dept. of Internal Medicine & Institute of Health Sciences Gyeongsang National University School of Medicine and Gyeongsang National University Hospital Korea Republic of

Gastric cancer is the most common cancer and has been the number one incidence since 1999 in Korea(as of 2016). Gastrointestinal symptoms and functional gastrointestinal disorders comprise a large proportion of primary care and gastroenterology practice. We propose a Computer-aided Diagnosis (CADx) system that analyzing the traditional gastroscope images and help the medical experts improve the accuracy of medical diagnosis. The data set we used consists of 400 normal images and 285 abnormal images from 103 volunteers. We also extracted four color features and two texture features from each image. The Least Square Support Vector Machine(LS-SVM) classifier was used for normal and abnormal classification. LS-SVM finds the solution by solving a set of linear equations instead of a convex quadratic programming problem for classical SVMs. The AUC value was 0.85, which is 0.02 higher than that of normal SVM. Copyright © The Korean Institute of Electrical Engineers.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

Rats: A robotic arm training system designed for rats

Rats: A robotic arm training system designed for rats

引用

ASME 2020 International Design engineering Technical Conferences and Computers and Information in engineering Conference, IDETC-CIE 2020

作者： Zhang, Haohan Luna, Tatiana Yang, Lillian Martin, John Agrawal, Sunil Robotics and Rehabilitation Laboratory Dept. of Mechanical Engineering Columbia University New YorkNY10027 United States CUNY School of Medicine City College of New York New YorkNY10031 United States Dept. of Molecular Cellular and Biomedical Sciences Center for Discovery and Innovation CUNY School of Medicine Neuroscience Program CUNY Graduate Center New YorkNY10031 United States

ISBN: (纸本)9780791883990

This paper presents a novel robotic system to characterize and retrain reaching in rats. This robot is intended to be a research platform for rehabilitation of forelimb movements in rats. In this paper, we focus on the design of this robotic system. We present the design requirements, mathematical models, and details of the physical device. A parallel mechanism with a special alignment of the component chains is used to accommodate observed reaching motions of a rat’s forelimb. Additionally, we demonstrate the use of this robot to record forelimb trajectories. Three healthy rats were used to record repeated reaching motions while the robot applied nearly zero force. We believe that this robotic system can be used in future training studies with rats who have impaired arm motions due to a neurological insult. Copyright © 2020 ASME

关键词： Rats

来源：评论

学校读者我要写书评

暂无评论

Integration of Machine-Learned Force Fields for Phonon DOS in Nanoscale Heterostructures

引用

Microscopy and Microanalysis 2024年第SUPPLEMENT_1期30卷

作者： Walker, Harrison A Hoglund, Eric R Bao, De-Liang Kamal Hussain, Md Ni, Haoyang Mamun, Abdullah Baxter, Jefferey Khan, Asif Caldwell, Joshua D Hopkins, Patrick E Hachtel, Jordan A Pantelides, Sokrates T Dept. of Physics and Astronomy Vanderbilt Univ. Nashville TN United States Interdisciplinary Materials Science Program Vanderbilt Univ. Nashville TN United States Center for Nanophase Materials Sciences Oak Ridge National Laboratory Oak Ridge TN United States Dept. of Materials Science and Engineering Univ. of Virginia Charlottesville VA United States Dept. of Electrical Engineering Univ. of South Carolina Columbia SC United States Dept. of Materials Science and Engineering Univ. of Illinois at Urbana-Champaign Urbana IL United States Materials Research Laboratory Univ. of Illinois at Urbana-Champaign Urbana IL United States Dept. of Mechanical Engineering Vanderbilt Univ. Nashville TN United States Dept. of Mechanical and Aerospace Engineering Univ. of Virginia Charlottesville VA United States Dept. of Physics Univ. of Virginia Charlottesville VA United States Dept. of Electrical and Computer Engineering Vanderbilt Univ. Nashville TN United States

来源：评论

学校读者我要写书评

暂无评论

Coronary heart diseases prediction based on cardiology clinical features 5

Coronary heart diseases prediction based on cardiology clini...

引用

5th IEEE International Conference on Big Data Intelligence and Computing, DataCom 2019

作者： Yang, Cheng-Hong Chuang, Li-Yeh Chang, Po-Yin National Kaohsiung University of Science and Technology Ph. D. Program in Biomedical Engineering Kaohsiung Medical University Dept. of Electronic Engineering Kaohsiung Taiwan I-Shou University Dept. of Chemical Engineering Institute of Biotechnology and Chemical Engineering Kaohsiung Taiwan National Kaohsiung University of Science and Technology Dept. of Electronic Engineering Kaohsiung Taiwan

ISBN: (纸本)9781728141176

The development of modern health systems has generated a large amount of medical data. Recent research has shown that data mining technology can discover potential patterns from a vast array of medical data, providing insight into disease and predicting disease. Coronary heart disease (CHD) is one of the most important research topics in the health field. In recent years, research on CHD has been extensively studied;however, the accuracy of CHD prediction needs to be improved. Here, a hybrid prediction method BOSVM combining Bayesian optimization (BO) and support vector machine (SVM) is proposed to predict the CHD. In BOSVM, BO aims to adjust of SVM parameters for enhancing the accuracy of CHD prediction. BOSVM compares performance of CHD prediction with five forecasting algorithms, including classification and regression tree, logistic regression, k-nearest neighbors, AdaBoost, and SVM. The experimental results show that the BOSVM has superior prediction accuracy than other algorithms in CHD prediction, indicating BOSVM can effectively predict CHD. © 2019 IEEE.

关键词： Support vector regression

来源：评论

学校读者我要写书评

暂无评论

First Demonstration of Defect Elimination for Cryogenic Ge FinFET CMOS Inverter Showing Steep Subthreshold Slope by Using Ge-on-Insulator Structure

First Demonstration of Defect Elimination for Cryogenic Ge F...

引用

International Electron Devices Meeting (IEDM)

作者： X.-R. Yu C.-C. Hsieh M.-H. Chuang M.-Y. Chiu T.-C. Sun W.-Z. Geng W.-H. Chang Y.-J. Shih W.-H. Lu W.-C. Chang Y.-C. Lin Y.-C. Pai C.-Y. Lai Y. Dei C.-Y. Yang H.-Y. Lu N.-C. Lin C.-T. Wu K.-H. Kao W. C.-Y. Ma D. D. Lu Y.-J. Lee G.-L. Luo M.-H. Chiang T. Maeda W.-F. Wu Y.-M. Li T.-H. Hou Dept of Electrical Engineering National Cheng Kung University Tainan Taiwan Academy of Innovative Semiconductor and Sustainable Manufacturing National Cheng Kung University Tainan Taiwan Dept. of Electrical Engineering National. Sun Yat-Sen University Kaohsiung Taiwan National Institute of Advanced Industrial Science and Technology Ibaraki Japan Inst. of Artificial Intelligence Innovation National Yang Ming Chiao Tung University Hsinchu Taiwan Inst. of Biomedical Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Intelligent Computing Industrial Doctorate Program Miin Wu School of Computing National Cheng Kung University Taiwan Semiconductor Research Institute Inst. of Pioneer Semiconductor Innovation National Yang Ming Chiao Tung University Hsinchu Taiwan Inst. of Communications Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan

This work presents experimental electrical characteristics and circuit prediction at cryogenic temperatures (down to 10 K) for three different kinds of germanium (Ge)-based FETs with advanced Fin/GAA structures. Among them, the layer transferred Ge-on-Insulator (GeOI) FinFET significantly improves its I-V characteristic during cryogenic measurements, such as a steeper subthreshold swing at 10K and a better I on . The developed GeOI fabrication method provides an effective way to eliminate the defects originating from misfit dislocations at the Ge/Si substrate during epitaxial growth, which would be treated as the key to device performance enhancement under 10 K. According to the measured IV at 10 K and circuit prediction, GeOI FinFETs with high Ge crystallinity are strong candidates for High-Performance-Computing (HPC) applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Digital Twin to Link Flood Models, Sensors, and Earth Observations for Coastal Resilience in Hampton Roads, Virginia, U.S.A

A Digital Twin to Link Flood Models, Sensors, and Earth Obse...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Thomas R. Allen Sridhar Katragadda Yin-Hsuen Chen Brian Terry Joshua Baptist Oguz Yetkin Navid Tahvildari Sunghoon Han Blake Steiner George McLeod Soenke Dangendor Qiang Sun Heather Richter Geography Program and Institute for Coastal Adaptation and Resilience (ICAR) Old Dominion University Norfolk Virginia U.S.A. Information Technology City of Virginia Beach Virginia U.S.A. Center for Geospatial Education and Analytics Old Dominion University Norfolk Virginia U.S.A. Analytical Mechanics Associates Hampton Virginia U.S.A. Department of Civil and Environmental Engineering Old Dominion University Norfolk Virginia U.S.A. Dept. of River-Coastal Science and Engineering Tulane University New Orleans Louisiana U.S.A. Hampton Roads Biomedical Research Consortium Old Dominion University Norfolk Virginia U.S.A.

A Digital Twin (DT) for coastal resilience in a low-lying coastal city necessarily entails characterizing the geophysical terrain, complex hydrologic flows, and infrastructure modifications that affect flooding. Coastal flooding in ports such as Hampton Roads, Virginia, arise from coastal storms, regular tidal estuarine circulation processes, seasonal to interannual external forcing from the ocean via the Gulf Stream and Atlantic Meridional Overturning Circulation (AMOC), and associated local influences on sea-level anomalies. We take a geospatial, hub-based approach to integrate digital linkages and threads among real-time Internet of Things (IoT) water level and flood sensors, an operational hydrodynamic model, localized probabilistic sea-level rise projections, hydro-corrected LiDAR Digital Elevation Models and GIS stormwater infrastructure, and an open data cube that ingests, hosts, and processes Application-Ready Datasets (ARDs.) Our paper describes the structure and cloud integration of a flood sensor network, StormSense, and its augmentation with end-user identified gap sites to improve network coverage and sensitivity to vulnerable communities. The enhancement of the multiple flood sensor networks incorporates multiple APIs and Amazon Web Services to normalize and homogenize data feeds among municipal sensors, private sector sensors, NOAA and USGS gauges, and new sensors sited in partnership with emergency managers, non-profits, and the National Weather Service. We describe the development and improvements of a Delft3D model for hydrodynamic simulation, including characterization and grid improvements of shallow estuarine creeks. The model includes sea-level rise parameters for the Hampton Roads study area. The paper also outlines Earth Observing data in the Virginia Open Data Cube, including products from NASA, NOAA, ESA, and newly incorporated drone data. The data cube hosts multi-purpose data products, such as satellite derived Land Use/Land Cover, MODIS,

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sequential Action-Based Dynamic Decision-Support Model for Urban Ecological Planning

SSRN

引用

SSRN 2023年

作者： Kim, Eun Sub Yun, Seok Hwan Kim, Ji Yeon Thorne, James H. Hyun, Jung Hee Lee, Dong Kun Interdisciplinary Program in Landscape Architecture Seoul National University Seoul08826 Korea Republic of Integrated Major in Smart City Global Convergence Program Seoul National University Seoul08826 Korea Republic of Specialized Graduate School of Intelligent Eco-Science 4 Dept. of Landscape Architecture Seoul National University Seoul08826 Korea Republic of Smart Green Solution Team SK forest Department of Environmental Science and Policy University of California One Shields Ave DavisCA95616 United States Systemic Risk and Resilience Research Group Advancing Systems Analysis International Institute for Applied Systems Analysis Austria Department of Landscape Architecture and Rural System Engineering Seoul National University Seoul08826 Korea Republic of

Decision-makers often encounter the challenge of efficient long-term ecological planning to consider economic and environmental trade-offs. However, tools to support stepwise mitigation strategies that account for dynamic ecological responses to continuing urban development are limited. Therefore, we developed a sequential action-based dynamic decision-making model to simulate stepwise mitigation measures in space over time using a multi-objective optimization algorithm. We focused on exploring the ecological corridors and habitat creation as mitigation measures through four decades to identify trade-offs and optimal plans that minimize landscape connectivity and edge density as ecological responses to urban development and minimize implementation costs per action. The results showed that adopting an initial low-investment strategy with sequential planning significantly enhanced potential ecological benefits beyond the 2000s compared with one-action planning. In contrast, the initial high-cost investment exhibited a gradual decline in the ecological benefits over time from 1995. The initial low-cost investment presented an opportunity to enhance ecological benefits by implementing early mitigation measures in locations capable of sustaining long-term ecological functions. The results suggest that sequential planning offers valuable insights into effective urban ecological planning by analyzing time-series data. This study enables step-by-step scenario testing, thereby supporting the facilitation of urban and regional sustainability planning. © 2023, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Deep learning based computer-aided diagnosis system for gastric lesion using endoscope

引用

Transactions of the Korean Institute of Electrical Engineers 2018年第7期67卷 928-933页

作者： Kim, Dong-Hyun Cho, Hyun-Chong Dept. of Electronic Engineering and Interdisciplinary Graduate Program for BIT Medical Convergence Kangwon National University Korea Republic of

Nowadays, gastropathy is a common disease. As endoscopic equipment are developed and used widely, it is possible to provide a large number of endoscopy images. Computer-aided Diagnosis (CADx) systems aim at helping physicians to identify possibly malignant abnormalities more accurately. In this paper, we present a CADx system to detect and classify the abnormalities of gastric lesions which include bleeding, ulcer, neuroendocrine tumor and cancer. We used an Inception module based deep learning model. And we used data augmentation for learning. Our preliminary results demonstrated promising potential for automatically labeled region of interest for endoscopy doctors to focus on abnormal lesions for subsequent targeted biopsy, with Az values of Receiver Operating Characteristic(ROC) curve was 0.83. The proposed CADx system showed reliable performance. © The Korean Institute of Electrical Engineers.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Effectiveness of Heat Adaptation Strategies Through Citizen Science-Based Outdoor Thermal Comfort

SSRN

引用

SSRN 2024年

作者： Kim, Eun Sub Lee, Dong Kun Bae, Chae Young Ko, Se Yean Won, Ji Eun Lee, Jae Hong Interdisciplinary Program in Landscape Architecture Seoul National University Seoul08826 Korea Republic of Seongnam Research Institute 46 Dallaenae-ro Sujeong-gu Gyeonggi-do Seongnam-si Korea Republic of Carbon-Neutral Strategy Institute Inc 103 Hyundai ESA2 122 Banpo-daero Seocho-gu Seoul06647 Korea Republic of Suwon Climate Change Education Center 46-38 Homaesil-ro Gwonseon-gu Gyeonggi-do Suwon-si Korea Republic of Specialized Graduate School of Intelligent Eco-Science 4 Dept. of Landscape Architecture Seoul National University Seoul08826 Korea Republic of Department of Landscape Architecture and Rural System Engineering Seoul National University Seoul08826 Korea Republic of

Urbanization and climate change increase heat stress and health risks in cities, necessitating effective response strategies. Traditional research has focused on thermal sensation in specific locales, overlooking the broad impacts of urban environments and the importance of regional and citizen input in crafting mitigation approaches. This study examines the effects of heat waves in Suwon City, analyzing thermal perception among residents across different urban spaces using citizen science. Data on temperature and subjective heat sensations were collected through homemade sensors over three years. The analysis investigated thermal sensation differences across spatial types— open high rise, open low rise, compact mid-rise, urban park, and lake park—utilizing boxplots, and examined thermal perception variations by age using the R program localized smoothing methodology. The results revealed significant differences in thermal sensation, especially above 32°C, with the highest discomfort reported in lake park areas and the lowest in open high-rise and low-rise zones. An age-related trend showed increased heat sensitivity among the 19–30 age group, decreasing in older participants. These findings underscore the limitations of one-size-fits-all heatwave responses and advocate for customized strategies informed by local conditions and resident experiences, highlighting the value of a bottom-up approach through citizen science. © 2024, The Authors. All rights reserved.

关键词： Climate change

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to "Variations of oxidative potential of PM2.5 in a medium-sized residential city in South Korea measured using three different chemical assays" [920 (2024) 171053]

引用

The Science of the total environment 2024年 926卷 172075页

作者： Pyung-Rae Kim Sung-Won Park Young-Ji Han Myong-Hwa Lee Thomas M Holsen Cheol-Heon Jeong Greg Evans Agriculture and Life Sciences Research Institute Kangwon National University Chuncheon Gangwon-do 24341 Republic of Korea. Dept. of Interdisciplinary Graduate Program in Environmental and Biomedical Convergence Kangwon National University Chuncheon Gangwon-do 24341 Republic of Korea. Dept. of Environmental Science Kangwon National University Chuncheon Gangwon-do 24341 Republic of Korea Gangwon particle pollution research and management center Kangwon National University Chuncheon Gangwon-do 24341 Republic of Korea. Electronic address: youngji@kangwon.ac.kr. Gangwon particle pollution research and management center Kangwon National University Chuncheon Gangwon-do 24341 Republic of Korea Dept. of Environmental Engineering Kangwon National University Chuncheon Gangwon-do 24341 Republic of Korea. Dept. of Civil and Environmental Engineering Clarkson University Potsdam NY 13699 USA. Dept. of Chemical Engineering and Applied Chemistry University of Toronto Toronto Ontario MS5 3E5 Canada.

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：