• Geophysics and Geophysical Exploration
• /
• v.25 no.4
• /
• pp.203-213
• /
• 2022

To understand an underlying geological structure via seismic imaging, the velocity information of the subsurface medium is crucial. Although the full-waveform inversion (FWI) method is considered useful for estimating subsurface velocity models, 3D FWI needs a lot-of computing power and time. Herein, we compare the calculation efficiency and accuracy of frequency-domain 2D and 3D acoustic FWIs. Thereafter, we demonstrate that the artifacts from 2D approximation can be partially suppressed via frequency-domain 2D FWI by employing diffraction angle filtering (DAF). By applying DAF, which employs only big reflection angle components, the impact of noise and out-of-plane reflections can be reduced. Additionally, it is anticipated that the DAF can create long-wavelength velocity structures for 3D FWI and migration.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.246-246
• /
• 2021

본 연구는 강우 발생시 유량을 추정하는 것에 목적이 있다. 이를 위해 본 연구는 선행연구의 모형 개발방법론에서 벗어나 딥러닝 알고리즘 중 하나인 합성곱 신경망 (convolution neural network)과 수문학적 이미지 (hydrological image)를 이용하여 강우 발생시 유량을 추정하였다. 합성곱 신경망은 일반적으로 분류 문제 (classification)을 해결하기 위한 목적으로 개발되었기 때문에 불특정 연속변수인 유량을 모의하기에는 적합하지 않다. 이를 위해 본 연구에서는 합성곱 신경망의 완전 연결층 (Fully connected layer)를 개선하여 연속변수를 모의할 수 있도록 개선하였다. 대부분 합성곱 신경망은 RGB (red, green, blue) 사진 (photograph)을 이용하여 해당 사진이 나타내는 것을 예측하는 목적으로 사용하지만, 본 연구의 경우 일반 RGB 사진을 이용하여 유출량을 예측하는 것은 경험적 모형의 전제(독립변수와 종속변수의 관계)를 무너뜨리는 결과를 초래할 수 있다. 이를 위해 본 연구에서는 임의의 유역에 대해 2차원 공간에서 무차원의 수문학적 속성을 갖는 grid의 집합으로 정의되는 수문학적 이미지는 입력자료로 활용했다. 합성곱 신경망의 구조는 Convolution Layer와 Pulling Layer가 5회 반복하는 구조로 설정하고, 이후 Flatten Layer, 2개의 Dense Layer, 1개의 Batch Normalization Layer를 배열하고, 다시 1개의 Dense Layer가 이어지는 구조로 설계하였다. 마지막 Dense Layer의 활성화 함수는 분류모형에 이용되는 softmax 또는 sigmoid 함수를 대신하여 회귀모형에서 자주 사용되는 Linear 함수로 설정하였다. 이와 함께 각 층의 활성화 함수는 정규화 선형함수 (ReLu)를 이용하였으며, 모형의 학습 평가 및 검정을 판단하기 위해 MSE 및 MAE를 사용했다. 또한, 모형평가는 NSE와 RMSE를 이용하였다. 그 결과, 모형의 학습 평가에 대한 MSE는 11.629.8 m3/s에서 118.6 m3/s로, MAE는 25.4 m3/s에서 4.7 m3/s로 감소하였으며, 모형의 검정에 대한 MSE는 1,997.9 m3/s에서 527.9 m3/s로, MAE는 21.5 m3/s에서 9.4 m3/s로 감소한 것으로 나타났다. 또한, 모형평가를 위한 NSE는 0.7, RMSE는 27.0 m3/s로 나타나, 본 연구의 모형은 양호(moderate)한 것으로 판단하였다. 이에, 본 연구를 통해 제시된 방법론에 기반을 두어 CNN 모형 구조의 확장과 수문학적 이미지의 개선 또는 새로운 이미지 개발 등을 추진할 경우 모형의 예측 성능이 향상될 수 있는 여지가 있으며, 원격탐사 분야나, 위성 영상을 이용한 전 지구적 또는 광역 단위의 실시간 유량 모의 분야 등으로의 응용이 가능할 것으로 기대된다.

• The Journal of Bigdata
• /
• v.7 no.1
• /
• pp.173-185
• /
• 2022

Nowadays, Korean webtoons are leading the global digital comic market. Webtoons are being serviced in various languages around the world, and dramas or movies produced with Webtoons' IP (Intellectual Property Rights) have become a big hit, and more and more webtoons are being visualized. However, with the success of these webtoons, the working environment of webtoon creators is emerging as an important issue. According to the 2021 Cartoon User Survey, webtoon creators spend 10.5 hours a day on creative activities on average. Creators have to draw large amount of pictures every week, and competition among webtoons is getting fiercer, and the amount of paintings that creators have to draw per episode is increasing. Therefore, this study proposes to generate webtoon background images using deep learning algorithms and use them for webtoon production. The main character in webtoon is an area that needs much of the originality of the creator, but the background picture is relatively repetitive and does not require originality, so it can be useful for webtoon production if it can create a background picture similar to the creator's drawing style. Background generation uses CycleGAN, which shows good performance in image-to-image translation, and CartoonGAN, which is specialized in the Cartoon style image generation. This deep learning-based image generation is expected to shorten the working hours of creators in an excessive work environment and contribute to the convergence of webtoons and technologies.

• Convergence Security Journal
• /
• v.22 no.3
• /
• pp.25-32
• /
• 2022

Recently, the image processing industry has been activated as deep learning-based technology is introduced in the image recognition and detection field. With the development of deep learning technology, learning model vulnerabilities for adversarial attacks continue to be reported. However, studies on countermeasures against poisoning attacks that inject malicious data during learning are insufficient. The conventional countermeasure against poisoning attacks has a limitation in that it is necessary to perform a separate detection and removal operation by examining the training data each time. Therefore, in this paper, we propose a technique for reducing the attack success rate by applying modifications to the training data and inference data without a separate detection and removal process for the poison data. The One-shot kill poison attack, a clean label poison attack proposed in previous studies, was used as an attack model. The attack performance was confirmed by dividing it into a general attacker and an intelligent attacker according to the attacker's attack strategy. According to the experimental results, when the proposed defense mechanism is applied, the attack success rate can be reduced by up to 65% compared to the conventional method.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.825-834
• /
• 2023

The demands of people who purchase fashion products on Internet shopping are gradually increasing, and attempts are being made to provide user-friendly images with 3D contents and web 3D software instead of pictures and videos of products provided. As a reason for this issue, which has emerged as the most important aspect in the fashion web shopping industry, complaints that the product is different when the product is received and the image at the time of purchase has been heightened. As a way to solve this problem, various image processing technologies have been introduced, but there is a limit to the quality of 2D images. In this study, we proposed an automatic conversion technology that converts 2D images into 3D and grafts them to web 3D technology that allows customers to identify products in various locations and reduces the cost and calculation time required for conversion. We developed a system that shoots a mannequin by placing it on a rotating turntable using only 8 cameras. In order to extract only the clothing part from the image taken by this system, markers are removed using U-net, and an algorithm that extracts only the clothing area by identifying the color feature information of the background area and mannequin area is proposed. Using this algorithm, the time taken to extract only the clothes area after taking an image is 2.25 seconds per image, and it takes a total of 144 seconds (2 minutes and 4 seconds) when taking 64 images of one piece of clothing. It can extract 3D objects with very good performance compared to the system.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.5
• /
• pp.217-228
• /
• 2023

Video instance segmentation is an intelligent visual task with high complexity because it not only requires object instance segmentation for each image frame constituting a video, but also requires accurate tracking of instances throughout the frame sequence of the video. In special, human instance segmentation in drama videos has an unique characteristic that requires accurate tracking of several main characters interacting in various places and times. Also, it is also characterized by a kind of the class imbalance problem because there is a significant difference between the frequency of main characters and that of supporting or auxiliary characters in drama videos. In this paper, we introduce a new human instance datatset called MHIS, which is built upon drama videos, Miseang, and then propose a novel video data augmentation method, CDVA, in order to overcome the data imbalance problem between character classes. Different from the previous video data augmentation methods, the proposed CDVA generates more realistic augmented videos by deciding the optimal location within the background clip for a target human instance to be inserted with taking rich spatio-temporal context embedded in videos into account. Therefore, the proposed augmentation method, CDVA, can improve the performance of a deep neural network model for video instance segmentation. Conducting both quantitative and qualitative experiments using the MHIS dataset, we prove the usefulness and effectiveness of the proposed video data augmentation method.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.42-42
• /
• 2022

지금까지도 유역에서의 녹조 모니터링은 현장채수를 통한 점 단위 모니터링에 크게 의존하고 있어 기후, 유속, 수온조건 등에 따라 수체에 광범위하게 발생하는 녹조를 효율적으로 모니터링하고 대응하기에는 어려운 점들이 있어왔다. 또한, 그동안 제한된 관측 데이터로 인해 현장 측정된 실측 데이터 보다는 녹조와 관련이 높은 NDVI, FGAI, SEI 등의 파생적인 지수를 산정하여 원격탐사자료와 매핑하는 방식의 분석연구 등이 선행되었다. 본 연구는 녹조의 모니터링시 정확도와 효율성을 향상을 목표로 하여, 우선은 녹조 측정장비를 활용, 7000개 이상의 녹조 관측 데이터를 확보하였으며, 이를 바탕으로 동기간의 고해상도 위성 자료와 실측자료를 매핑하기 위해 다양한Machine Learning기법을 적용함으로써 그 효과성을 검토하고자 하였다. 연구대상지는 낙동강 내성천 상류에 위치한 영주댐 유역으로서 데이터 수집단계에서는 면단위 현장(in-situ) 관측을 위해 2020년 2~9월까지 4회에 걸쳐 7291개의 녹조를 측정하고, 동일 시간 및 공간의 Sentinel-2자료 중 Band 1~12까지 총 13개(Band 8은 8과 8A로 2개)의 분광특성자료를 추출하였다. 다음으로 Machine Learning 분석기법의 적용을 위해 algae_monitoring Python library를 구축하였다. 개발된 library는 1) Training Set과 Test Set의 구분을 위한 Data 준비단계, 2) Random Forest, Gradient Boosting Regression, XGBoosting 알고리즘 중 선택하여 적용할 수 있는 모델적용단계, 3) 모델적용결과를 확인하는 Performance test단계(R², MSE, MAE, RMSE, NSE, KGE 등), 4) 모델결과의 Visualization단계, 5) 선정된 모델을 활용 위성자료를 녹조값으로 변환하는 적용단계로 구분하여 영주댐뿐만 아니라 다양한 유역에 범용적으로 적용할 수 있도록 구성하였다. 본 연구의 사례에서는 Sentinel-2위성의 12개 밴드, 기상자료(대기온도, 구름비율) 총 14개자료를 활용하여 Machine Learning기법 중 Random Forest를 적용하였을 경우에, 전반적으로 가장 높은 적합도를 나타내었으며, 적용결과 Test Set을 기준으로 NSE(Nash Sutcliffe Efficiency)가 0.96(Training Set의 경우에는 0.99) 수준의 성능을 나타내어, 광역적인 위성자료와 충분히 확보된 현장실측 자료간의 데이터 학습을 통해서 조류 모니터링 분석의 효율성이 획기적으로 증대될 수 있음을 확인하였다.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.11
• /
• pp.481-492
• /
• 2023

This study explores how to build a Korean dataset to extract information from text using generative large language models. In modern society, mixed information circulates rapidly, and effectively categorizing and extracting it is crucial to the decision-making process. However, there is still a lack of Korean datasets for training. To overcome this, this study attempts to extract information using text-based zero-shot learning using a generative large language model to build a purposeful Korean dataset. In this study, the language model is instructed to output the desired result through prompt engineering in the form of "system"-"instruction"-"source input"-"output format", and the dataset is built by utilizing the in-context learning characteristics of the language model through input sentences. We validate our approach by comparing the generated dataset with the existing benchmark dataset, and achieve 25.47% higher performance compared to the KLUE-RoBERTa-large model for the relation information extraction task. The results of this study are expected to contribute to AI research by showing the feasibility of extracting knowledge elements from Korean text. Furthermore, this methodology can be utilized for various fields and purposes, and has potential for building various Korean datasets.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.537-549
• /
• 2023

The distribution characteristics of tidal flat sediment components are used as an essential data for coastal environment analysis and environmental impact assessment. Therefore, a reliable classification map of surface sedimentary facies is essential. This study evaluated the applicability of regression kriging to generate a classification map of the sedimentary facies of tidal flats. For this aim, various factors such as the number of field survey data and remote sensing-based auxiliary data, the effect of regression models on regression kriging, and the comparison with other prediction methods (univariate kriging and regression analysis) on surface sedimentary facies classification were investigated. To evaluate the applicability of regression kriging, a case study using unmanned aerial vehicle (UAV) data was conducted on the Hwang-do tidal flat located at Anmyeon-do, Taean-gun, Korea. As a result of the case study, it was most important to secure an appropriate amount of field survey data and to use topographic elevation and channel density as auxiliary data to produce a reliable tidal flat surface sediment facies classification map. In addition, regression kriging, which can consider detailed characteristics of the sediment distributions using ultra-high resolution UAV data, had the best prediction performance compared to other prediction methods. It is expected that this result can be used as a guideline to produce the tidal flat surface sedimentary facies classification map.

• Journal of Internet Computing and Services
• /
• v.24 no.6
• /
• pp.73-80
• /
• 2023

The recent steep increase in the minimum hourly wage has increased the burden of labor costs, and the share of unmanned stores is increasing in the aftermath of COVID-19. As a result, theft crimes targeting unmanned stores are also increasing, and the "Just Walk Out" system is introduced to prevent such thefts, and LiDAR sensors, weight sensors, etc. are used or manually checked through continuous CCTV monitoring. However, the more expensive sensors are used, the higher the initial cost of operating the store and the higher the cost in many ways, and CCTV verification is difficult for managers to monitor around the clock and is limited in use. In this paper, we would like to propose an AI image processing fusion algorithm that can solve these sensors or human-dependent parts and detect customers who perform abnormal behaviors such as theft at low costs that can be used in unmanned stores and provide cloud-based notifications. In addition, this paper verifies the accuracy of each algorithm based on behavior pattern data collected from unmanned stores through motion capture using mediapipe, object detection using YOLO, and fusion algorithm and proves the performance of the convergence algorithm through various scenario designs.