• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.71-73
• /
• 2022

최근 인프라를 관리할 필요가 없고 폭발적으로 늘어나는 요청을 유연하게 대처할 수 있는 장점 때문에 서버리스 컴퓨팅 사용이 늘어나고 있다. 하지만 서버리스 컴퓨팅은 사용자 코드의 실행 환경을 준비하기 위한 콜드 스타트 과정이 필요하고, 서비스가 복잡해짐에 따라 전체 실행 시간 중 콜드 스타트로 인한 지연시간이 늘어나는 문제가 발생한다. 본 논문에서는 서버리스 컴퓨팅 기반의 워크플로우에 대해 콜드 스타트로 인한 지연 시간을 완화하는 아키텍처 및 기법을 제안한다.

• International Journal of Computer Science & Network Security
• /
• v.23 no.1
• /
• pp.125-139
• /
• 2023

Facial expression recognition, a topical problem in the field of computer vision and pattern recognition, is a direct means of recognizing human emotions and behaviors. This paper first summarizes the datasets commonly used for expression recognition and their associated characteristics and presents traditional machine learning algorithms and their benefits and drawbacks from three key techniques of face expression; image pre-processing, feature extraction, and expression classification. Deep learning-oriented expression recognition methods and various algorithmic framework performances are also analyzed and compared. Finally, the current barriers to facial expression recognition and potential developments are highlighted.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.01a
• /
• pp.103-104
• /
• 2020

본 논문은 예비유아교사 양성과정에서 요구되는 핵심역량 중 재개념화가 필요한 지식정보처리역량의 구성방향과 이를 위한 교육내용 탐색을 목표로 한다. 이를 위해 과거 정보화역량과 지식정보처리역량의 개념 및 가치를 비교하여 기초내용을 구성한 후 현장전문가, 교육전문가, 예비교사 등 15인을 대상으로 포커스그룹 인터뷰 연구방법을 통하여 연구결과를 도출한다. 본 논문에서는 선행연구를 참고하여 예비유아교사의 지식정보처리역량을 교육현장의 문제해결을 위하여 다양한 영역의 지식과 정보를 처리하고 활용할 수 있는 역량이라 개념정의 하였고 전문가 인터뷰를 통해 이를 위한 교육내용을 설정할 것이다. 본 논문을 통해 제시된 예비유아교사의 지식정보처리역량의 개념 및 교육내용은 예비유아 교사양성과정의 교육과정개발을 위한 기초자료로 활용될 것이다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.368-368
• /
• 2022

The Soil and Water Assessment Tool (SWAT) has been widely used to simulate the long-term hydrological conditions of a catchment. Two output variables, outflow and sediment yield have been widely investigated in the field of water resources management, especially in determining the conditions of ungauged subbasins. The presence of missing data in weather input data can cause poor representation of the climate conditions in a catchment especially for large or mountainous catchments. Therefore, in this study, a custom module was developed and evaluated to determine the efficiency of utilizing basic spatial interpolation methods in the estimation of weather input data. The module has been written in Python language and can be considered as a pre-processing module prior to using the SWAT model. The results of this study suggests that the utilization of the proposed pre-processing module can improve the simulation results for both outflow and sediment yield in a catchment, even in the presence of missing data.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.557-560
• /
• 2023

In this paper, we introduce a pre-training method leveraging the capabilities of the Vision Transformer (ViT) for disease diagnosis in conventional Fundus images. Recognizing the need for effective representation learning in medical images, our method combines the Vision Transformer with a Masked Autoencoder to generate meaningful and pertinent image augmentations. During pre-training, the Masked Autoencoder produces an altered version of the original image, which serves as a positive pair. The Vision Transformer then employs contrastive learning techniques with this image pair to refine its weight parameters. Our experiments demonstrate that this dual-model approach harnesses the strengths of both the ViT and the Masked Autoencoder, resulting in robust and clinically relevant feature embeddings. Preliminary results suggest significant improvements in diagnostic accuracy, underscoring the potential of our methodology in enhancing automated disease diagnosis in fundus imaging.

• Korean Journal of Child Studies
• /
• v.20 no.3
• /
• pp.231-244
• /
• 1999

This study examined the effects of short and long term playing of video gamer on children's visual parallel processing. All of the 64 fourth grade subjects were above average in IQ. They were classified into high and low video game users. Instruments were a visual parallel processing task consisting of imagery integration items, computers, and the arcade video game, Pac-Man. Subjects were pre-tested with a visual parallel processing task. After one week, the experimental group played video games for 15 minutes, but the control group didn't play. Immediately following this, all children were post-tested by the same task used on the pretest. The data was analyzed by ANCOVA and repeated measures ANOVA. The results showed that relaying short-term video games improved visual parallel processing and that long term experience with video games also affected visual parallel processing. there were no differences between high and low users in visual parallel processing after playing short term video games.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.34 no.2
• /
• pp.128-134
• /
• 2014

Infrared thermography is an emerging approach to non-contact, non-intrusive, and non-destructive inspection of various solid materials such as metals, composites, and semiconductors for industrial and research interests. In this study, data processing was applied to infrared thermography measurements to detect defects in metals that were widely used in industrial fields. When analyzing experimental data from infrared thermographic testing, raw images were often not appropriate. Thus, various data analysis methods were used at the pre-processing and processing levels in data processing programs for quantitative analysis of defect detection and characterization; these increased the infrared non-destructive testing capabilities since subtle defects signature became apparent. A 3D finite element simulation was performed to verify and analyze the data obtained from both the experiment and the image processing techniques.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.59-68
• /
• 2021

As artificial intelligence(AI) technologies, which have made rapid growth recently, began to be applied to the marine environment such as ships, there have been active researches on the application of CNN-based models specialized for digital videos. In E-Navigation service, which is combined with various technologies to detect floating objects of clash risk to reduce human errors and prevent fires inside ships, real-time processing is of huge importance. More functions added, however, mean a need for high-performance processes, which raises prices and poses a cost burden on shipowners. This study thus set out to propose a method capable of processing information at a high rate while maintaining the accuracy by applying Quantization techniques of a deep learning model. First, videos were pre-processed fit for the detection of floating matters in the sea to ensure the efficient transmission of video data to the deep learning entry. Secondly, the quantization technique, one of lightweight techniques for a deep learning model, was applied to reduce the usage rate of memory and increase the processing speed. Finally, the proposed deep learning model to which video pre-processing and quantization were applied was applied to various embedded boards to measure its accuracy and processing speed and test its performance. The proposed method was able to reduce the usage of memory capacity four times and improve the processing speed about four to five times while maintaining the old accuracy of recognition.

• Transactions of Materials Processing
• /
• v.18 no.2
• /
• pp.99-106
• /
• 2009

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 1999.11a
• /
• pp.141-142
• /
• 1999