• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.571-575
• /
• 2022

본 논문에서는 통계청에서 매월 작성되는 온라인쇼핑동향조사를 위해, 언어모델 전이학습 기반 분류모델 학습 방법론을 이용하여, 관세청 제공 전자상거래 수입 목록통관 자료를 처리하기 위해서 해외 직접 구매 상품군 분류 모델을 구축한다. 최근에 텍스트 분류 태스크에서 많이 이용되는 BERT 기반의 언어모델을 이용하며 기존의 색인어 정보 분석 과정이나 사례사전 구축 등의 중간 단계 없이 해외 직접 판매 및 구매 상품군을 94%라는 높은 예측 정확도로 분류가 가능해짐을 알 수 있다.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.2
• /
• pp.569-574
• /
• 2023

For maintenance of concrete structures, it is necessary to identify and maintain various defects. With the current method, there are problems with efficiency, safety, and reliability when inspecting large-scale social infrastructure, so it is necessary to introduce a new inspection method. Recently, with the development of deep learning technology for images, concrete defect classification research is being actively conducted. However, studies on contamination and spalling other than cracks are limited. In this study, a variety of concrete defect type classification models were developed through transfer learning on a pre-learned deep learning model, factors that reduce accuracy were derived, and future development directions were presented. This is expected to be highly utilized in the field of concrete maintenance in the future.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.77-82
• /
• 2022

GUI(Graphical User Interface)를 대신하는 차세대 인터페이스로서 NUI(Natural User Interace)에 기대가 모이는 것은 자연스러운 흐름이다. 본 연구는 NUI의 손가락 관절을 포함한 손동작 전체를 인식시키기 위해 웹캠과 카메라를 활용하여 다양한 배경과 각도의 손동작 데이터를 수집한다. 수집된 데이터는 전처리를 거쳐 데이터셋을 구축하며, ResNet50 모델을 활용하여 전이학습한 합성곱 신경망(Convolutional Neural Network) 알고리즘 분류기를 설계한다. 구축한 데이터셋을 입력시켜 분류학습 및 예측을 진행하며, 실시간 영상에서 인식되는 손동작을 설계한 모델에 입력시켜 나온 결과를 통해 가위바위보 게임을 구현한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.493-494
• /
• 2023

본 논문은 벚꽃나무 영상 데이터를 활용하여 벚꽃의 상태(개화, 만개, 낙화)를 실시간으로 분류하는 연구를 소개한다. 이 연구의 목적은, 실시간으로 취득되는 벚꽃나무의 영상 데이터를 사전에 학습된 CNN 기반 이미지 분류 모델을 통해 벚꽃의 상태에 따라 분류하는 것이다. 약 1,000장의 벚꽃나무 이미지를 활용하여 CNN 모델을 학습시키고, 모델이 새로운 이미지에 대해 얼마나 정확하게 벚꽃의 상태를 분류하는지를 평가하였다. 학습데이터는 훈련 데이터와 검증 데이터로 나누었으며, 개화, 만개, 낙화 등의 상태별로 폴더를 구분하여 관리하였다. 또한, ImageNet 데이터셋에서 사전 학습된 ResNet50 가중치를 사용하는 전이학습 방법을 적용하여 학습 과정을 더 효율적으로 수행하고, 모델의 성능을 향상시켰다.

• Journal of vocational education research
• /
• v.37 no.2
• /
• pp.167-190
• /
• 2018

This study examines based on Cultural-Historical Activity Theory, graduate school student-workers' learning and developmental transfer in school and work. For this purpose, a question is raised. how do components of activities in school and workplace impact on learning and developmental transfer? For this study, based on the results of In-depth interview, questionnaire was designed and quantitative research has been conducted. This study analyzed 288 graduate school student-workers. As a results, First, the components which have an effect on learning were analyzed and the results show that among the components of the school activity system, the competitiveness reinforcement from object, the role of academic major from division of labor, and the interaction with professors from community are significant variables. Second, in case of developmental transfer, the activeness of class participation from tool, the role of academic major from division of labor, and the interaction with professors from community are significant variables of the school activity system and the self realization from object, the role in the workplace from division of labor, the interaction with supervisors from community, and the systemization of work from rule are significant variables of workplace activity system. On the basis of the findings, implications of the study and suggestions for further research are discussed.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_2
• /
• pp.695-706
• /
• 2022

Medium and high-resolution optical satellites have proven their effectiveness in detecting wildfire areas. However, smoke plumes generated by wildfire scatter visible light incidents on the surface, thereby interrupting accurate monitoring of the area where wildfire occurs. Therefore, a technology to extract smoke in advance is required. Deep learning technology is expected to improve the accuracy of smoke extraction, but the lack of training datasets limits the application. However, for clouds, which have a similar property of scattering visible light, a large amount of training datasets has been accumulated. The purpose of this study is to develop a smoke extraction technique using deep learning, and the limits due to the lack of datasets were overcome by using a cloud dataset on transfer learning. To check the effectiveness of transfer learning, a small-scale smoke extraction training set was made, and the smoke extraction performance was compared before and after applying transfer learning using a public cloud dataset. As a result, not only the performance in the visible light wavelength band was enhanced but also in the near infrared (NIR) and short-wave infrared (SWIR). Through the results of this study, it is expected that the lack of datasets, which is a critical limit for using deep learning on smoke extraction, can be solved, and therefore, through the advancement of smoke extraction technology, it will be possible to present an advantage in monitoring wildfires.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.26 no.4
• /
• pp.361-370
• /
• 2023

Swarm has recently become a critical component of offensive and defensive systems. Multi-agent reinforcement learning(MARL) empowers swarm systems to handle a wide range of scenarios. However, the main challenge lies in MARL's scalability issue - as the number of agents increases, the performance of the learning decreases. In this study, transfer learning is applied to advanced MARL algorithm to resolve the scalability issue. Validation results show that the training efficiency has significantly improved, reducing computational time by 31 %.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.4
• /
• pp.474-484
• /
• 2024

Reinforcement learning, which are also studied in the field of defense, face the problem of sample efficiency, which requires a large amount of data to train. Transfer learning has been introduced to address this problem, but its effectiveness is sometimes marginal because the model does not effectively leverage prior knowledge. In this study, we propose a stochastic initial state randomization(SISR) method to enable robust knowledge transfer that promote generalized and sufficient knowledge transfer. We developed a simulation environment involving a cooperative robot transportation task. Experimental results show that successful tasks are achieved when SISR is applied, while tasks fail when SISR is not applied. We also analyzed how the amount of state information collected by the agents changes with the application of SISR.

• Annual Conference of KIPS
• /
• 2018.10a
• /
• pp.660-663
• /
• 2018

최근 5년간 식용 나물과 독초를 구별하지 못한 채 섭취하여 다수의 환자가 발생하였다. 본 논문에서는 인체에 치명적인 결과를 일으킬 수 있는 독초를 CNN을 통해 분류하는 시스템을 제안한다. 부족한 양의 샘플 데이터는 데이터 확장 기법을 통해 확보하였고, 연구에 사용된 하드웨어의 한계를 극복하기 위해 전이학습을 적용하였다. 실험은 데이터 확장과 전이 학습 적용 여부에 따라 4가지 유형별로 진행되었으며, 각 유형은 20회씩 반복한 테스트의 결과를 종합하여 평균을 내었다. 이와 같은 실험에서 의미 있는 결과를 얻었다. 본 논문의 시스템을 이용한 독초 섭취 사고의 예방이 기대된다.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.415-417
• /
• 2023

비디오 프레임 오류는 스트리밍 클라이언트에서 프레임을 표출할 때 정상적인 영상이 아닌 손상된 프레임이 표출되는 현상이다. 프레임 오류가 발생하는 빈도는 높지 않지만 긴급하거나 중요한 상황에서 발생한다면 업무에 지장을 초래할 수도 있으므로 신속한 대처가 중요하다고 할 수 있다. 또한 프레임 오류를 인지하고 해결하기 위해서는 인간의 개입이 불가피하지만 사용자가 24시간 스크린을 모니터링 하는 것은 사실상 불가능하다. 따라서 본 논문에서는 전이학습을 이용하여 스트리밍 클라이언트에서 비디오 프레임 오류가 발생하는 것을 자동으로 감지하는 모델을 제안한다.