• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.47-52
• /
• 2021

최근 지문을 바탕으로 답을 추론하는 연구들이 많이 이루어지고 있으며, 대표적으로 기계 독해 연구가 존재하고 관련 데이터 셋 또한 여러 가지가 공개되어 있다. 그러나 한국의 대학수학능력시험 국어 영역과 같은 복잡한 구조의 문제에 대한 고차원적인 문제 해결 능력을 요구하는 데이터 셋은 거의 존재하지 않는다. 이로 인해 고차원적인 독해 문제를 해결하기 위한 연구가 활발히 이루어지고 있지 않으며, 인공지능 모델의 독해 능력에 대한 성능 향상이 제한적이다. 기존의 입력 구조가 단조로운 독해 문제에 대한 모델로는 복잡한 구조의 독해 문제에 적용하기가 쉽지 않으며, 이를 해결하기 위해서는 새로운 모델 훈련 방법이 필요하다. 이에 복잡한 구조의 고차원적인 독해 문제에도 대응이 가능하도록 하는 모델 훈련 방법을 제안하고자 한다. 더불어 3가지의 데이터 증강 기법을 제안함으로써 고차원 독해 문제 데이터 셋의 부족 문제 또한 해소하고자 한다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.4
• /
• pp.81-92
• /
• 2022

In this study, interview scripts written in the dropout application was analyzed using BERTopic,, and parental influence, academic adaptation, university dissatisfaction was derived as major topics. An empirical study was conducted through a survey of 199 current students with researchmodel composed of those factors affecting dropout intention. The result shows that parental influence had a negative effect on academic adaptation and university satisfaction. Academic adaptation and university satisfaction had a negative effect on the dropout intention. parental influence did not directly affect the dropout intention, but had an indirect positive effect through academic adaptation and university/major satisfaction. The result shows that university satisfaction and academic adaptation is important factor to lower the dropout intention of students who chose current university by parental influence.

• Journal of Digital Convergence
• /
• v.19 no.5
• /
• pp.285-293
• /
• 2021

With the advent of the 4th Industrial Revolution, AI utilization capabilities are being emphasized in various industries, but AI education design and curriculum research as universal education is currently lacking. This study offers a design for universal AI education to further cultivate its use in universities. For the AI basic education design, a questionnaire was conducted for experts three times, and the reliability of the derived design contents was verified by reflecting the results. As a result, the main competencies for cultivating AI literacy were data literacy, AI understanding and utilization, and the main detailed areas derived were data structure understanding and processing, visualization, word cloud, public data utilization, and machine learning concept understanding and utilization. The educational design content derived through this study is expected to increase the value of competency-centered AI universal education in the future.

• Smart Media Journal
• /
• v.11 no.1
• /
• pp.17-30
• /
• 2022

Like other computer vision research trends, research using satellite images was able to achieve rapid growth with the development of GPU-based computer computing capabilities and deep learning methodologies related to image processing. As a result, satellite images are being used in various fields, and the number of studies on how to use satellite images is increasing. Therefore, in this paper, we will introduce the field of research and utilization of satellite images and datasets that can be used for research using satellite images. First, studies using satellite images were collected and classified according to the research method. It was largely classified into a Regression-based Approach and a Classification-based Approach, and the papers used by other methods were summarized. Next, the datasets used in studies using satellite images were summarized. This study proposes information on datasets and methods of use in research. In addition, it introduces how to organize and utilize domestic satellite image datasets that were recently opened by AI hub. In addition, I would like to briefly examine the limitations of satellite image-related research and future trends.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.392-392
• /
• 2022

세계적 규모의 팬데믹 감염병의 출현은 전 세계적으로 경제적, 문화적, 사회적 파급효과가 매우 강력하며 전 인류를 위협하고 있다. 최근에 발병한 중증급성 호흡기질환 코로나바이러스 2(Severe Acute Respiratory Syndrome Coronavirus 2, SARS-CoV-2)는 2019년 12월 중국 우한에서 첫 보고 되었고 2022년 현재까지 종식되지 않고 있으며 바이러스의 전파력과 치명률이 높고 무증상 감염상태일 때에도 전염이 가능하여 현재 역학조사의 사후적 대응에 대한 한계가 있어 선제적 대응을 위한 수단이 필수 불가결해지고 있는 실정이다. 하수기반역학(Waste Based Epidemiology, WBE)이란 하수처리장으로 유입되기 전의 하수를 분석하여 하수 집수구역 내 도시민의 생활상을 예측하는 것으로 하수로 배출된 감염자의 분비물 및 배설물 속 바이러스를 하수관로에서 신속하게 검출함으로써 특정지역의 감염성 질환 전파 정도와 유행하는 타입(변이)등을 분석하고 기존 역학조사의 문제점을 극복할 수 있으며 선제적인 대응이 가능하다. 현재 COVID-19의 대유행과 관련하여 WBE를 기반으로 한 다양한 연구가 진행되고 있으며 실제 환자의 발생과 상관관계가 있음이 확인되고 있고 백신 접종과 새롭게 발생한 변이바이러스의 관계 속에서 발생하는 변수를 고려한 모델이 없다는 점을 들어 새로운 감염병 확산 예측 모델에 대한 필요성 또한 커지고 있다. 본 연구에서는 병원에서부터 하수처리장까지의 하수관거와 하수처리장에서의 SARS-CoV-2 검출농도 및 거동을 파악하는 것을 목적으로 하고 있으며 COVID-19의 감염규모 확산에 관한 방법론에서 수학적모델 (Euler Method, RK4 Method, Gillespie Algorithm)과 딥러닝 기반의 Nowcasting model과 Fore casting model을 살펴보고자 한다.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.119-133
• /
• 2022

One of the most important current features of food related industry is the growth of food delivery service. Another notable food related culture is, with the advent of Youtube, the popularity of Mukbang, which refers to content that records eating. Based on these background, this study intended to focus on two things. First, we tried to see the impact of Youtube Mukbang and the sentiments of Mukbang comments on the number of related food deliveries. Next, we tried to set up the predictive modeling of chicken delivery order with machine learning method. We used Youtube Mukbang comments data as well as weather related data as main independent variables. The dependent variable used in this study is the number of delivery order of fried chicken. The period of data used in this study is from June 3, 2015 to September 30, 2019, and a total of 1,580 data were used. For the predictive modeling, we used machine learning methods such as linear regression, ridge, lasso, random forest, and gradient boost. We found that the sentiment of Youtube Mukbang and comments have impacts on the number of delivery orders. The prediction model with Mukban data we set up in this study had better performances than the existing models without Mukbang data. We also tried to suggest managerial implications to the food delivery service industry.

• Information Systems Review
• /
• v.23 no.4
• /
• pp.45-67
• /
• 2021

As the transaction volume of the C2C second-hand market is growing, the number of frauds, which intend to earn unfair gains by sending products different from specified ones or not sending them to buyers, is also increasing. This study explores the model that can identify frauds in the online C2C second-hand market by examining the postings for transactions. For this goal, this study collected 145,536 field data from actual C2C second-hand market. Then, the model is built with the characteristics from postings such as the topic and the linguistic characteristics of the product description, and the characteristics of products, postings, sellers, and transactions. The constructed model is then trained by the machine learning algorithm XGBoost. The final analysis results show that fraudulent postings have less information, which is also less specific, fewer nouns and images, a higher ratio of the number and white space, and a shorter length than genuine postings do. Also, while the genuine postings are focused on the product information for nouns, delivery information for verbs, and actions for adjectives, the fraudulent postings did not show those characteristics. This study shows that the various features can be extracted from postings written in C2C second-hand transactions and be used to construct an effective model for frauds. The proposed model can be also considered and applied for the other C2C platforms. Overall, the model proposed in this study can be expected to have positive effects on suppressing and preventing fraudulent behavior in online C2C markets.

• Journal of Digital Convergence
• /
• v.19 no.12
• /
• pp.477-486
• /
• 2021

This study was conducted to detect metabolic syndrome risk factors and gender difference in adults. 18,616 cases of adults are collected by Korea Health and Nutrition Examination Study from 2016 to 2019. Using 4 types of machine Learning(Logistic Regression, Decision Tree, Naïve Bayes, Random Forest) to predict Metabolic Syndrome. The results showed that the Random Forest was superior to other methods in men and women. In both of participants, BMI, diet(fat, vitamin C, vitamin A, protein, energy intake), number of underlying chronic disease and age were the upper importance. In women, education level, menarche age, menopause was additional upper importance and age, number of underlying chronic disease were more powerful importance than men. Future study have to verify various strategy to prevent metabolic syndrome.

• Journal of the Korea Convergence Society
• /
• v.11 no.12
• /
• pp.15-22
• /
• 2020

In this paper, we proposed a deep learning based super-resolution method that combines Channel Attention and Spatial Attention feature enhancement methods. It is important to restore high-frequency components, such as texture and features, that have large changes in surrounding pixels during super-resolution processing. We proposed a super-resolution method using feature enhancement that combines Channel Attention and Spatial Attention. The existing CNN (Convolutional Neural Network) based super-resolution method has difficulty in deep network learning and lacks emphasis on high frequency components, resulting in blurry contours and distortion. In order to solve the problem, we used an emphasis block that combines Channel Attention and Spatial Attention to which Skip Connection was applied, and a Residual Block. The emphasized feature map extracted by the method was extended through Sub-pixel Convolution to obtain the super resolution. As a result, about PSNR improved by 5%, SSIM improved by 3% compared with the conventional SRCNN, and by comparison with VDSR, about PSNR improved by 2% and SSIM improved by 1%.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.338-338
• /
• 2023

최근 특정 지역에 짧은 시간동안 많은 강우가 내리는 국지성 집중호우가 빈번히 발생하고 있으나, 이에 대한 예측과 대비에도 불구하고 피해는 지속적으로 증가하고 있다. 지속적인 강우량 증가 추이로 시간최대 및 일최대 강우량 관측기록이 해마다 갱신되고, 도시, 하천 및 주요 홍수방어 시설의 설계용량을 초과하는 피해가 발생하고 있다. 다수의 인구가 거주하고 대규모 기반시설이 집중된 도시지역에서 발생하는 집중호우는 심각한 인명 및 재산피해로 이어질 수 있다. 따라서, 부처별 재난의 저감대책은 정량적인 피해규모의 피해금액 예측보다는 설계 빈도에 대한 규모의 크기로 대책을 마련하고 있다. 국내에서는 풍수해 피해를 저감시키기 위해 개발에 따르는 재해영향요인을 개발 사업 시행 이전에 예측·분석하고 적절한 저감대책안을 수립·시행하고 있으나 설계빈도에 대한 규모일 뿐 정량적인 저감대책으로 예방되는 피해금액은 알 수 없다. 본 연구에서는 재해연보를 기반으로 호우재해(호우, 태풍)에 대한 시군구-재해기간의 피해데이터를 1999년부터 2019년까지 총 20년의 빅데이터와 전국 68개 강우관측소를 대상으로 총 20년(1999년 ~ 2019년)의 강우자료를 구축하였다. 머신러닝의 학습별 알고리즘을 조사하여 호우재해 피해데이터의 적용성이 높고 다양한 분야에 적용이 가능한 Neural networks의 분석기술인 ANN기법을 선정하였다 피해데이터의 재해발생기간별 총강우량, 일최대강우량, 총피해금액에 대하여 1999년 ~ 2018년을 학습하고 2019년에 대하여 강우특성과 피해특성의 분석하였다. 분석결과 Neural Networks의 지도학습은 총 6,902개 중 2019년을 제외한 6,414개를 학습하였으며 분석 타깃은 호우재해의 피해규모를 분석할 수 있는 총강우량, 일최대강우량, 총피해금액에 대하여 은닉노드 5개씩 2계층에 대하여 분석하였다.