Search

Your search keyword '"Park, Kihong"' showing total 735 results
Start Over Author "Park, Kihong"
Sorry, I don't understand your search. ×
735 results on '"Park, Kihong"'

3. Investigating the Relationship Between Water Vapor and Precipitation in Northern Africa

Author

Cha, Hoyoung, Baik, Jongjin, Kim, Hyeon-Joon, Lee, Jinwook, Byun, Jongyun, Park, Kihong, Sung, Jeemi, Hwang, Seunghyun, Jun, Changhyun, Pisello, Anna Laura, Editorial Board Member, Hawkes, Dean, Editorial Board Member, Bougdah, Hocine, Editorial Board Member, Rosso, Federica, Editorial Board Member, Abdalla, Hassan, Editorial Board Member, Boemi, Sofia-Natalia, Editorial Board Member, Mohareb, Nabil, Editorial Board Member, Mesbah Elkaffas, Saleh, Editorial Board Member, Bozonnet, Emmanuel, Editorial Board Member, Pignatta, Gloria, Editorial Board Member, Mahgoub, Yasser, Editorial Board Member, De Bonis, Luciano, Editorial Board Member, Kostopoulou, Stella, Editorial Board Member, Pradhan, Biswajeet, Editorial Board Member, Abdul Mannan, Md., Editorial Board Member, Alalouch, Chaham, Editorial Board Member, Gawad, Iman O., Editorial Board Member, Nayyar, Anand, Editorial Board Member, Amer, Mourad, Series Editor, Chenchouni, Haroun, editor, Zhang, Zhihua, editor, Bisht, Deepak Singh, editor, Gentilucci, Matteo, editor, Chen, Mingjie, editor, Chaminé, Helder I., editor, Barbieri, Maurizio, editor, Jat, Mahesh Kumar, editor, Rodrigo-Comino, Jesús, editor, Panagoulia, Dionysia, editor, Kallel, Amjad, editor, Biswas, Arkoprovo, editor, Turan, Veysel, editor, Knight, Jasper, editor, Çiner, Attila, editor, Candeias, Carla, editor, and Ergüler, Zeynal Abiddin, editor

Published
2024
Full Text
View/download PDF

30. Unified Depth Prediction and Intrinsic Image Decomposition from a Single Image via Joint Convolutional Neural Fields

Author

Kim, Seungryong, Park, Kihong, Sohn, Kwanghoon, and Lin, Stephen

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

We present a method for jointly predicting a depth map and intrinsic images from single-image input. The two tasks are formulated in a synergistic manner through a joint conditional random field (CRF) that is solved using a novel convolutional neural network (CNN) architecture, called the joint convolutional neural field (JCNF) model. Tailored to our joint estimation problem, JCNF differs from previous CNNs in its sharing of convolutional activations and layers between networks for each task, its inference in the gradient domain where there exists greater correlation between depth and intrinsic images, and the incorporation of a gradient scale network that learns the confidence of estimated gradients in order to effectively balance them in the solution. This approach is shown to surpass state-of-the-art methods both on single-image depth estimation and on intrinsic image decomposition.

Published
2016

42. Urban Canyon Design with Aspect Ratio and Street Tree Placement for Enhanced Thermal Comfort: A Comprehensive Thermal Comfort Assessment Accounting for Gender and Age in Seoul, Republic of Korea.

Author

Park, Kihong, Jun, Changhyun, Baik, Jongjin, and Kim, Hyeon-Joon

Subjects
THERMAL comfort, URBAN trees, URBAN planning, CITIES & towns, OLDER people
Abstract

Rapid urbanization and increased human activity have negatively impacted the microclimate of cities, leading to unfavorable conditions for human thermal comfort, particularly in outdoor spaces. Thermal comfort can be improved through various means, such as adjusting the height of urban buildings, the aspect ratio of road widths, and the placement of street trees. This study employed the ENVI-met software V5.5.1 to simulate the microclimate based on aspect ratio (H/W = 1.5) and street tree spacing (6 m) similar to actual conditions with different aspect ratios (H/W = 0.5, 1.0, and 2.0) and street tree spacing (2 m) in Seoul, Republic of Korea. Thermal comfort was assessed through a comprehensive predicted mean vote (PMV) evaluation, considering the gender (male and female) and age (8, 35, and 80 years) of residents in the target area, to determine the optimal urban canyon scenario. The results of the study indicated that the height of the building and the percentage of trees had a significant impact on the temperature and PMV results. When comparing PMV results, women have higher thermal vulnerability than men, and based on age, older adults have higher thermal vulnerability. The aspect ratio of 1.5 and tree spacing of 2 m resulted in the lowest temperature of 35.91 °C at 12:00 p.m. at 0° wind direction and 36.09 °C at 90° wind direction, lower than the actual input value of 36.9 °C. The PMV values were also under the same conditions, with an average PMV by gender of 3.87 at 0° and 4.21 at 90° and an average PMV by age of 3.86 at 0° and 4.19 at 90°. This finding is significant because it can inform the development of planned cities that prioritize urban thermal comfort during summer. This can be achieved through the strategic design of urban canyons and incorporation of street trees in both new and existing cities. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

43. Morphological classification of fine particles in transmission electron microscopy images by using pre-trained convolution neural networks.

Author

Khadgi, Jasmita, Lee, Haebum, Seo, Juchan, Hong, Jin-hyuk, and Park, Kihong

Subjects
CONVOLUTIONAL neural networks, MORPHOLOGY, PARTICULATE matter, TRANSMISSION electron microscopy, DIESEL motor exhaust gas, MACHINE learning, SPARK ignition engines, BIOMASS burning
Abstract

Morphological information on fine particles is essential for understanding their transport behavior in the ambient atmosphere and in the human respiratory system. More than 3000 transmission electron microscopy (TEM) images of fine particles were collected from ambient atmosphere and directly from various sources, such as diesel and gasoline engine exhaust, biomass burning, coal combustion, and road dust, and were then morphologically categorized into four major classes (spherical, agglomerate, polygonal, and dendrite). Pre-trained convolutional neural network (CNN) models (DenseNet169, InceptionV3, MobileNetV3Small, ResNet50, and VGG16) and traditional machine learning models (decision trees, random forests, and support vector machines) were trained using the classified particles. The fine-tuned CNN model (DenseNet169) having the deepest feature learning exhibited the best performance among the tested models, with an overall classification accuracy of 89% and an average per-class accuracy ranging from 84% to 97%. The reliable classification of thousands of images was performed within several minutes. The agglomerated class was the least misclassified because of its significantly different features from those of the other classes. The critical regions of the particles for classification decisions varied among the pre-trained models. Our results suggest that the pre-trained CNN models would be useful for the rapid morphological classification of a large number of fine particles. Copyright © 2024 American Association for Aerosol Research [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results