检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Kim, Junmo Lee, Namkyeong Kim, Jiwon Kim, Kwangsoo Interdisciplinary Program in Bioengineering Seoul National University Korea Republic of Dept. of Industrial and Systems Engineering KAIST Korea Republic of Interdisciplinary Program of Medical Informatics Seoul National University Korea Republic of Dept. of Transdisciplinary Medicine ICMIT Seoul National University Hospital Korea Republic of Center for Data Science Healthcare AI Research Institute Seoul National University Hospital Korea Republic of Dept. of Medicine College of Medicine Seoul National University Korea Republic of

Electronic health record (EHR) foundation models have been an area ripe for exploration with their improved performance in various medical tasks. Despite the rapid advances, there exists a fundamental limitation: Processing unseen medical codes out of the vocabulary. This problem limits the generality of EHR foundation models and the integration of models trained with different vocabularies. To deal with this problem, we propose MedRep for EHR foundation models based on the observational medical outcome partnership (OMOP) common data model (CDM), providing the integrated medical concept representations and the basic data augmentation strategy for patient trajectories. For concept representation learning, we enrich the information of each concept with a minimal definition through large language model (LLM) prompts and enhance the text-based representations through graph ontology of OMOP vocabulary. Trajectory augmentation randomly replaces selected concepts with other similar concepts that have closely related representations to let the model practice with the concepts out-of-vocabulary. Finally, we demonstrate that EHR foundation models trained with MedRep better maintain the prediction performance in external datasets. Our code implementation is publicly available at https://***/kicarussays/MedRep. Copyright © 2025, The Authors. All rights reserved.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Modeling Supports the Implementation of Urban Greening as a Response to the Challenges of Sustainable Spatial Planning

SSRN

引用

SSRN 2024年

作者： Kim, Eun Sub Lee, Dong Kun Hyun, Jung Hee Kim, Na Yeon Heo, Su Jeong Kim, Da Sle 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 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

Urban greening is a critical strategy for sustainable urban development, climate change mitigation, and biodiversity conservation. However, the effectiveness of urban greening varies depending on the specific goals (e.g., enhancing biodiversity, reducing urban heat, or both) and their spatial implementation. To address the spatial variability in the effectiveness of greening, we propose a spatial decision support model based on the non-dominated sorting genetic algorithm-II (NSGA-II). This model aims to optimize urban greening locations to maximize biomass density, mitigate urban heat stress, and simultaneously improve landscape connectivity. Applied to Suwon City, South Korea, the model's effectiveness was evaluated against a Business-As-Usual (BAU) scenario across four scenarios: Connectivity-based, Biomass density-based, Heat stress-based, and an Integrated-based scenario. The integrated approach, balancing trade-offs between ecological benefits and implementation costs, outperformed the BAU scenario by 8.84%. This outcome indicated of significant improvements in biomass density and landscape connectivity, despite highlighting a weaker correlation with heat stress mitigation. Our findings underscore the necessity of an integrated planning approach to urban greening, as it can contribute toward the attainment of urban development goals. Additionally, by proposing an app-based model for policymakers to utilize, our outputs should enable the reconciliation of multiple environmental objectives in urban landscapes. © 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

Development of artificial intelligence system for dangerous object recognition in X-ray baggage images

引用

Transactions of the Korean Institute of Electrical Engineers 2020年第7期69卷 1067-1072页

作者： Lee, Jeong-Nam Cho, Hyun-Chong Dept. of Electronics Engineering Interdisciplinary Graduate Program for BIT Medical Convergence Kangwon National University Korea Republic of

The importance of flight safety has been highlighted lately due to the increase of aviation industry. Baggage screening tasks are still difficult and the failures of dangerous object detection are frequent despite the improvement of screening equipment. The purpose of this study to develop the AI system on dangerous object detection for improving aviation safety. The convolutional neural network model, Xception, were applied to perform dangerous object recognition using X-ray baggage image dataset which contains 25,405 images of twelve items. Based on experiments, the accuracy and F1-score are 0.9939 and 0.9942. The significantly high success rate makes the model a very effective advisory or early warning tool, and an approach that could be further expanded to support a dangerous object identification system to operate in real airport screening process. © Korean Institute of Electrical Engineers

关键词： Airport security

来源：评论

学校读者我要写书评

暂无评论

Cultivation of Chlorella sp. HS2 using wastewater from soy sauce factory

引用

Chemosphere 2023年 342卷 140162页

作者： Kim, Minsik Lee, Sang-Ah Yun, Jin-Ho Ko, So-Ra Cho, Dae-Hyun Kim, Hee Su Oh, Hee-Mock Kim, Hee-Sik Ahn, Chi-Yong Daejeon34141 Korea Republic of Dept. of Biological Engineering Inha University Incheon22212 Korea Republic of Faculty of Biotechnology College of Applied Life Sciences Jeju National University Jeju63243 Korea Republic of Interdisciplinary Graduate Program in Advance Convergence Technology and Science Jeju National University Jeju63243 Korea Republic of Department of Integrative Biotechnology Sungkyunkwan University Gyeonggi-do Suwon16419 Korea Republic of FarmHannong Chungcheongnam-do Nonsan33010 Korea Republic of

Incorporation of wastewater from industrial sectors into the design of microalgal biorefineries has significant potential for advancing the practical application of this emerging industry. This study tested various food industrial wastewaters to assess their suitability for microalgal cultivation. Among these wastewaters, defective soy sauce (DSS) and soy sauce wastewater (SWW) were chosen but DSS exhibited the highest nutrient content with 13,500 ppm total nitrogen and 3051 ppm total phosphorus. After diluting DSS by a factor of 50, small-scale cultivation of microalgae was conducted to optimize culture conditions. SWW exhibited optimal growth at 25–30 °C and 300–500 μE m−2 s−1, while DSS showed optimal growth at 30–35 °C. Based on a 100-mL lab-scale and 3-L outdoor cultivation with an extended cultivation period, DSS outperformed SWW, exhibiting higher final biomass productivity. Additionally, nutrient-concentrated nature of DSS is advantageous for transportation at an industrial scale, leading us to select it as the most promising feedstock for microalgal cultivation. With further optimization, DSS has the potential to serve as an effective microalgal cultivation feedstock for large-scale biomass production. © 2023 The Authors

关键词： Microalgae

来源：评论

学校读者我要写书评

暂无评论

Quantifying Outdoor Cooling Effects of Vertical Green System on Mean Radiant Temperature

SSRN

引用

SSRN 2023年

作者： Kim, Eun Sub Yun, Seok Hwan Lee, Dong Kun Kim, Na Youn Piao, Zheng Gang Kim, Sang Hyuck Park, Seunghwan 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 Department of Landscape Architecture and Rural System Engineering Seoul National University Seoul08826 Korea Republic of Department of Building Energy Research Korea Institute of Civil Engineering and Building Technology Goyang10223 Korea Republic of

Vertical green systems (VGS) are expected to mitigate outdoor heat stress through a transpiration cooling effect. There is a lack of knowledge on how VGS influence outdoor thermal comfort, particularly focusing on energy flux. This study quantifies the outdoor cooling effects of VGS, and distinguishes the energy flux between them and outdoor urban spaces. In addition, we discuss their cooling efficiency. Outdoor experiments were conducted during the hot summer period on building facades in city. Our study on VGS focused on the measurement of climatic variables, surface temperatures of plant leaves (Fatsia japonica), net radiation, and estimating transpiration and evaporation. The surface temperature of VGS were up to 4.3 °C higher than those of high albedo walls, while the reflected radiations (short and long-wave radiation) were 120 w/m2 lower than albedo walls during the day. The mean radiant temperature (MRT) of VGS was 3.02 °C lower than the high albedo wall during daytime, except in the case of shaded areas (0.45 °C). We confirmed that the cooling efficiency of transpiration was 7.38 times more effective than evaporation from soil without plants. Therefore, VGS is efficient in terms of long-term heat reduction and can be an effective strategy to mitigate outdoor heat stress. © 2023, The Authors. All rights reserved.

关键词： Transpiration

来源：评论

学校读者我要写书评

暂无评论

Detecting location of fire in video stream environment using deep learning

引用

Transactions of the Korean Institute of Electrical Engineers 2020年第3期69卷 474-479页

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

To avoid the large scale of damage of fire occurred, it is necessary to have a system to detect the incident as soon as possible. Traditional sensors and vision based systems for fire detection is limited in indoors and need more computational time and memory, restricting its implementation. In this paper, we propose a video-based fire detection system using deep learning to solve these problems. To run real-time detection in video stream, the activity detection is performed within a single image frame and makes prediction with a single network evaluation. The object detection algorithm we applied can tell the location as well as the presence of fire. It allows us to analyze the cause of the fire through video and monitor extensive areas efficiently. The results of the proposed system showed 99% precision, 99% accuracy and 100% recall. Experimental results show that the proposed method has excellent fire detection performance. Copyright © The Korean Institute of Electrical Engineers.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

A development of rose leaf disease classification system using convolutional neural network

引用

Transactions of the Korean Institute of Electrical Engineers 2020年第7期69卷 1040-1045页

作者： Ham, Hyun-Sik Cho, Hyun-Chong Dept. of Electronics Engineering Interdisciplinary Graduate Program for BIT Medical Convergence Kangwon National University Korea Republic of Dept. of Electronics Engineering Kangwon National University Korea Republic of

The classification of plant disease by images has been studied over past decades. In this paper, convolutional neural network models were applied to perform rose leaf disease diagnosis using simple leaves images of healthy and diseased rose leaves, through deep learning methodologies. Training of the models was performed with the use of an open database of 13,125 images, containing field and laboratory images with five different disease and healthy leaves. Based on experiments, the precision and recall are 98.7% and 97.4% and the F1-score is 0.98. The significantly high success rate makes the model a very effective advisory or early warning tool, and an approach that could be further expanded to support an rose leaf disease identification system to operate in real cultivation conditions. © Korean Institute of Electrical Engineers

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Combining imitation and deep reinforcement learning to accomplish human-level performance on a virtual foraging task

arXiv

引用

arXiv 2022年

作者： Giammarino, Vittorio Dunne, Matthew F. Moore, Kylie N. Hasselmo, Michael E. Stern, Chantal E. Paschalidis, Ioannis Ch. Division of Systems Engineering Boston University BostonMA02446 United States Dept. of Electrical and Computer Engineering Boston University BostonMA02446 United States Dept. of Biomedical Engineering Boston University BostonMA02215 United States Cognitive Neuroimaging Center Boston University BostonMA02215 United States Graduate Program for Neuroscience Boston University BostonMA02215 United States Center for Systems Neuroscience Boston University BostonMA02215 United States

We develop a simple framework to learn bio-inspired foraging policies using human data. We conduct an experiment where humans are virtually immersed in an open field foraging environment and are trained to collect the highest amount of rewards. A Markov Decision Process (MDP) framework is introduced to model the human decision dynamics. Then, Imitation Learning (IL) based on maximum likelihood estimation is used to train Neural Networks (NN) that map human decisions to observed states. The results show that passive imitation substantially underperforms humans. We further refine the human-inspired policies via Reinforcement Learning (RL) using the on-policy Proximal Policy Optimization (PPO) algorithm which shows better stability than other algorithms and can steadily improve the policies pretrained with IL. We show that the combination of IL and RL can match human results and that good performance strongly depends on combining the allocentric information with an egocentric representation of the environment. © 2022, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Detecting abnormal behavior of cattle based on object detection algorithm

引用

Transactions of the Korean Institute of Electrical Engineers 2020年第3期69卷 468-473页

作者： Chae, Jung-Woo Cho, Hyun-Chong Dept. of Electronics Engineering 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

Detection of abnormal behavior and unusual signs of cattle has been an important factor for managers in the livestock farming. Among them, it is of great interest for livestock farmers to detect estrus of cattle, which are unusual behaviors related to breeding management. Most studies on detecting estrus combined with IT technologies have been based on sensors attached to the neck or leg of cattle. But sensor-type devices have the potential to cause stress on the cattle by attaching them, and there are additional cost issues for maintenance. In this study, to solve the above problems, we present a estrus detection system which used regular CCTV and applied the object detection algorithm based on the deep learning model. To run real-time detection in video stream, the activity detection is performed within a single image frame and makes prediction with a single network evaluation. The results of the proposed system showed 97% precision and 96% accuracy. Copyright © The Korean Institute of Electrical Engineers.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Deep learning based gastric lesion classification system using data augmentation

引用

Transactions of the Korean Institute of Electrical Engineers 2020年第7期69卷 1033-1039页

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

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. To improve the performance of the CADx system, a data augmentation has also been implemented to increase both the amount and the diversity of the training images. Augmentation method finds the enhancement parameters through RNN through large-scale verified three data, ImageNet, SHVN and CIFAR-10. In this study, we compared the performance of applying data augmentation method using four networks, Inception-V3, Resnet-101, Xception, and Inception-Resnet-V2. For Inception-V3, Resnet-101, Xception, and Inception-Resnet-V2 in normal and abnormal classification, the highest Az values were 0.87, 0.85, 0.88 and 0.82 respectively. The Xception networks and CIFAR-10 data is a promising CADx configuration for gastric lesion which had relatively simple structure and good classification performance. © 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

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：