• Korean Association for Visual Culture
• /
• v.16
• /
• pp.131-161
• /
• 2010

This thesis investigates the cultural meanings of the first optical instrument, Camera obscura, in the pre-modern age, while it explains the development as well as the use of the Camera obscura in Europe and Korea. For this purpose the thesis traces the significant phases of the historical developments of the Camera obscura from L. da Vinci, G. B. della Porta, D. Barbaro, A. Kircher to J. Zahn etc. The Camera obscura was not only the symbolic instrument of the modernism in the sense that human being wanted to observe the outer world by himself and to be freed from the viewpoint of the christianity, but also was the forerunner of the modern visual culture, because it first time reproduced the artificial image of the natural world. Since the second half of the 17th century the box-type reflex Camera obscura had been produced, it began to be used as aid to drawing for painters like J. Vermeer, A. Canaletto and J. Reynolds etc. throughout Europe. It tells the evidence of the close relation between art and technology in the pre-modern age. Around the end of the 18th century the Camera obscura was brought to Korea, the closed country of the Fareast, by the scholars of the so-called 'Realist school' (Silhak-pa) who went to Beijing to acquire knowledges on the Western science from the European priests. In 1780s Yak-yong JUNG, one of the representative scholars of the Realist school, experimented the Camera obscura, and then, it was used for sketches of higher aristocrats' portraits by the supreme portrait painter of that time, Myoung-ki LEE. Those were possible only under the reign of the culturally liberal and reformative King, Jung-jo (ruled 1776-1800), and after his retreatment the inquiry of the Camera obscura had been dimished. It is not a historical coincidence that the Camera obscura could be examined and used in the period of the Enlightment both in Europe and Korea.

• Journal of Korea Water Resources Association
• /
• v.56 no.8
• /
• pp.471-484
• /
• 2023

Deep learning models based on generative adversarial neural networks are specialized in generating new information based on learned information. The deep generative models (DGMR) model developed by Google DeepMind is an generative adversarial neural network model that generates predictive radar images by learning complex patterns and relationships in large-scale radar image data. In this study, the DGMR model was trained using radar rainfall observation data from the Ministry of Environment, and rainfall prediction was performed using an generative adversarial neural network for a heavy rainfall case in August 2021, and the accuracy was compared with existing prediction techniques. The DGMR generally resembled the observed rainfall in terms of rainfall distribution in the first 60 minutes, but tended to predict a continuous development of rainfall in cases where strong rainfall occurred over the entire area. Statistical evaluation also showed that the DGMR method is an effective rainfall prediction method compared to other methods, with a critical success index of 0.57 to 0.79 and a mean absolute error of 0.57 to 1.36 mm in 1 hour advance prediction. However, the lack of diversity in the generated results sometimes reduces the prediction accuracy, so it is necessary to improve the diversity and to supplement it with rainfall data predicted by a physics-based numerical forecast model to improve the accuracy of the forecast for more than 2 hours in advance.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.5
• /
• pp.323-330
• /
• 2023

The development of an analysis model that reflects the microstructure characteristics of polyvinyl alcohol (PVA) fiber-reinforced cementitious composites, which have a highly complex microstructure, enables synergy between efficient material design and real experiments. PVA fiber orientations are an important factor that influences the mechanical behavior of PVA fiber-reinforced cementitious composites. Owing to the difficulty in distinguishing the gray level value obtained from micro-CT images of PVA fibers from adjacent phases, fiber segmentation is time-consuming work. In this study, a micro-CT test with a voxel size of 0.65 ㎛³ was performed to investigate the three-dimensional distribution of fibers. To segment the fibers and generate training data, histogram, morphology, and gradient-based phase-segmentation methods were used. A U-net model was proposed to segment fibers from micro-CT images of PVA fiber-reinforced cementitious composites. Data augmentation was applied to increase the accuracy of the training, using a total of 1024 images as training data. The performance of the model was evaluated using accuracy, precision, recall, and F1 score. The trained model achieved a high fiber segmentation performance and efficiency, and the approach can be applied to other specimens as well.

• Journal of Internet Computing and Services
• /
• v.24 no.6
• /
• pp.91-98
• /
• 2023

Recently, according to development of artificial intelligence, a wide range of industry being automatic and optimized. Also we can find out some research of using supervised learning for deteceting defect of railway in domestic rail industry. However, there are structures other than rails on the track, and the fastener is a device that binds the rail to other structures, and periodic inspections are required to prevent safety accidents. In this paper, we present a method of reducing cost for labeling using semi-supervised and transfer model trained on rail fastener data. We use Resnet50 as the backbone network pretrained on ImageNet. At first we randomly take training data from unlabeled data and then labeled that data to train model. After predict unlabeled data by trained model, we adopted a method of adding the data with the highest probability for each class to the training data by a predetermined size. Futhermore, we also conducted some experiments to investigate the influence of the number of initially labeled data. As a result of the experiment, model reaches 92% accuracy which has a performance difference of around 5% compared to supervised learning. This is expected to improve the performance of the classifier by using relatively few labels without additional labeling processes through the proposed method.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1451-1466
• /
• 2023

In the context of maritime emergencies, the utilization of drones has rapidly increased, with a particular focus on their application in search and rescue operations. Deep learning models utilizing drone images for the rapid detection of distressed vessels and other maritime drift objects are gaining attention. However, effective training of such models necessitates a substantial amount of diverse training data that considers various weather conditions and vessel states. The lack of such data can lead to a degradation in the performance of trained models. This study aims to enhance the performance of deep learning models for distress ship detection by developing a maritime environment simulator to augment the dataset. The simulator allows for the configuration of various weather conditions, vessel states such as sinking or capsizing, and specifications and characteristics of drones and sensors. Training the deep learning model with the dataset generated through simulation resulted in improved detection performance, including accuracy and recall, when compared to models trained solely on actual drone image datasets. In particular, the accuracy of distress ship detection in adverse weather conditions, such as rain or fog, increased by approximately 2-5%, with a significant reduction in the rate of undetected instances. These results demonstrate the practical and effective contribution of the developed simulator in simulating diverse scenarios for model training. Furthermore, the distress ship detection deep learning model based on this approach is expected to be efficiently applied in maritime search and rescue operations.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1679-1692
• /
• 2023

South Korea is a country that emits a large amount of pollutants as a result of population growth and industrial development and is also severely affected by transboundary air pollution due to its geographical location. As pollutants from both domestic and foreign sources contribute to air pollution in Korea, the location of air pollutant emission sources is crucial for understanding the movement and distribution of pollutants in the atmosphere and establishing national-level air pollution management and response strategies. Based on this background, this study aims to effectively acquire spatial information on domestic and international air pollutant emission sources, which is essential for analyzing air pollution status, by utilizing high-resolution optical satellite images and deep learning-based image segmentation models. In particular, industrial parks and quarries, which have been evaluated as contributing significantly to transboundary air pollution, were selected as the main research subjects, and images of these areas from multi-purpose satellites 3 and 3A were collected, preprocessed, and converted into input and label data for model training. As a result of training the U-Net model using this data, the overall accuracy of 0.8484 and mean Intersection over Union (mIoU) of 0.6490 were achieved, and the predicted maps showed significant results in extracting object boundaries more accurately than the label data created by course annotations.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1693-1705
• /
• 2023

Rural areas, which account for about 90% of the country's land area, are increasing in importance and value as a space that performs various public functions. However, facilities that adversely affect residents' lives, such as livestock facilities, factories, and solar panels, are being built indiscriminately near residential areas, damaging the rural environment and landscape and lowering the quality of residents' lives. In order to prevent disorderly development in rural areas and manage rural space in a planned manner, detection and monitoring of hazardous facilities in rural areas is necessary. Data can be acquired through satellite imagery, which can be acquired periodically and provide information on the entire region. Effective detection is possible by utilizing image-based deep learning techniques using convolutional neural networks. Therefore, U-Net model, which shows high performance in semantic segmentation, was used to classify potentially hazardous facilities in rural areas. In this study, KOMPSAT ortho-mosaic optical imagery provided by the Korea Aerospace Research Institute in 2020 with a spatial resolution of 0.7 meters was used, and AI training data for livestock facilities, factories, and solar panels were produced by hand for training and inference. After training with U-Net, pixel accuracy of 0.9739 and mean Intersection over Union (mIoU) of 0.7025 were achieved. The results of this study can be used for monitoring hazardous facilities in rural areas and are expected to be used as basis for rural planning.

• Journal of Venture Innovation
• /
• v.6 no.3
• /
• pp.165-184
• /
• 2023

Since municipal welfare institutions operate for different purposes from general companies or public enterprises, ESG practice items and model construction should be conducted through various and comprehensive social welfare studies. Since there are not many studies available in domestic welfare institutions yet and there are no suitable ESG management utilization indicators, the Cheonan Welfare Foundation's strategy and management strategy system were established to spread the model to other welfare institutions and become a leading foundation through education and training. The foundation and front-line welfare institutions selected issues identification and key issues through the foundation's empirical analysis and criticality analysis, focusing on understanding ESG management and ways to establish a practice model that positively affects institutional image and business performance. Based on this, the promotion system was examined by establishing a performance management plan after deriving appropriate strategies and establishing a strategic system for social welfare institutions. Environmental and social responsibility, transparent management, safety management system establishment, emergency and prevention, user (customer) satisfaction system establishment, anti-corruption prevention and integrity ethics monitoring and evaluation, responsible supply chains, and community contribution programs. This study attempted to specifically present efforts to settle ESG management through the consideration of the Cheonan Welfare Foundation. Therefore, it is considered to be useful data for developing ESG management by referring to the systematic development process of the Cheonan City Restoration Foundation to develop ESG measurement indicators.

• Journal of the Microelectronics and Packaging Society
• /
• v.30 no.4
• /
• pp.44-49
• /
• 2023

In the global pursuit of carbon neutrality, the rapid increase in the adoption of electric vehicles (EVs) has led to a corresponding surge in the demand for batteries. To achieve high efficiency in electric vehicles, considerations of weight reduction and battery safety have become crucial factors. Copper and aluminum, both recognized as lightweight materials, can be effectively joined through laser welding. However, due to the distinct physical characteristics of these two materials, the process of joining them poses technical challenges. This study focuses on conducting simulations to identify the optimal laser parameters for welding copper and aluminum, with the aim of streamlining the welding process. Additionally, a Graphic User Interface (GUI) program has been developed using the Python language to visually present the results. Using machine learning image data, this program is anticipated to predict joint success and serve as a guide for safe and efficient laser welding. It is expected to contribute to the safety and efficiency of the electric vehicle battery assembly process.

• Geomechanics and Engineering
• /
• v.35 no.2
• /
• pp.195-208
• /
• 2023

The nodular diaphragm wall (NDW) is a novel type of foundation with favorable engineering characteristics, which has already been utilized in high-rise buildings and high-speed railways. Compared to traditional diaphragm walls, the NDW offers significantly improved vertical bearing capacity due to the presence of nodular parts while reducing construction time and excavation work. Despite its potential, research on the vertical bearing characteristics of NDW requires further study, and the investigation and visualization of its displacement pattern and failure mode are scant. Meanwhile, the measurement of the force component acting on the nodular parts remains challenging. In this paper, the vertical bearing characteristics of NDW are studied in detail through the indoor model test, and the displacement and failure mode of the foundation is analyzed using particle image velocimetry (PIV) technology. The principles and methods for monitoring the force acting on the nodular parts are described in detail. The research results show that the nodular part plays an essential role in the bearing capacity of the NDW, and its maximum load-bearing ratio can reach 30.92%. The existence of the bottom nodular part contributes more to the bearing capacity of the foundation compared to the middle nodular part, and the use of both middle and bottom nodular parts increases the bearing capacity of the foundation by about 9~12% compared to a single nodular part of the NDW. The increase in the number of nodular parts cannot produce a simple superposition effect on the resistance born by the nodular parts since the nodular parts have an insignificant influence on the exertion and distribution of the skin friction of NDW. The existence of the nodular part changes the displacement field of the soil around NDW and increases the displacement influence range of the foundation to a certain extent. For NDWs with three different nodal arrangements, the failure modes of the foundations appear to be local shear failures. Overall, this study provides valuable insights into the performance and behavior of NDWs, which will aid in their effective utilization and further research in the field.