• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.721-724
• /
• 2018

최근 청소년들은 욕설, 폭력적, 선정적, 비하적 표현을 일상생활에서 자연스럽게 사용하고 있다. 현재 청소년들은 자극적이고 폭력적인 개인 방송을 시청하며 유해 표현을 학습한다. 그래서 여러 기업에서는 모니터링 요원을 배치하거나 사용자들의 신고를 통해 유해 영상을 제재하는 중이다. 하지만 방대한 규모의 동용상 때문에 사람이 직접 모든 영상을 확인하는 것은 물리적으로 불가능하다. 따라서 본 논문에서는 자연어 처리 기술을 활용하여 자동으로 유해 영상을 탐지하는 시스템을 제안하고자 한다. 본 시스템은 데이터 수집, 텍스트 변환, 형태소 분석, 유해 사전 구성, 유해 판단 5가지 과정으로 이루어진다.

• Journal of Science Education
• /
• v.36 no.1
• /
• pp.139-152
• /
• 2012

The purpose of this study is to provide some suggestions for future improvement of scientific inquiry activities in Korean elementary science textbook. The modified framework of Lee(2005) and Millar et al.(1998) was used to compare inquiry activities in the Korean and Singaporean science textbooks. The results of this study are as follows: Korean text books have more activities than Singapore's, but both countries have similar time allotment for science classes. In the area of 'inquiry process skill', Singapore is more balanced in 'Basic inquiry process skills' and 'Integrated inquiry process skills' than Korea. Singapore's integrated inquiry rate is also higher than Korea's. Next the results of comparing leaning objectives to scientific inquiry activities shows that Korean text books tend to focus on 'contents objectives', while Singapore's text books focus on balancing 'contents objectives' and 'process objectives'. Korean science textbooks encourage students to communicate the results of experiments but in most case these communication activities are actually not performed. Lastly Korea and Singapore have low degree of openness in inquiry activities. Remarkably 'Suggest questions' are totally conducted by teachers. This study implies that Korean science textbooks should have lower amounts of inquiry activities to accomodate enough time for communication about results. Next we need to make balance not only 'Basic inquiry process skills' and 'Integrated inquiry process skills' but also 'Content objectives' and 'Process objectives'. Lastly we need to make student to be the leader in science classes through encouraging them to plan procedures for experiments and to discover results by themselves.

• Journal of The Korean Association For Science Education
• /
• v.18 no.2
• /
• pp.209-219
• /
• 1998

This study is the first part of the investigation of the students' and teachers' understanding of ideal conditions in physics. To do this, here, we provided the theoretical basis for the above study by discussing the meaning and characteristics of idealization. Idealization, introduced and elaborated by Galileo therefore characterized the nature of modem science, can be generated by four procedures: neglecting the minor variables, giving without any description about the minor variables, assuming the limit case, assuming constancy or uniformity. Idealization generated by these procedures can produce models and laws from the sensory informations about real world. And physics world is constructed by formalization or mathematization of these models and laws obtained through idealization about real world. Therefore, it can be said that idealization have a major role in the context of discovery. By this aspects, physics world can be viewed as the approximation of the real world, and this view, again, give rise the philosophical debate about the reality in nature. Idealization take an important role in the process of application of physics world and the understanding the real world. That is, physicists accept the discrepancies between real world, and physics world and make a great effort to explain, moreover, reduce these discrepancies by modifying or eliminating idealization involved in physics world. Continued from this study, we will proceed to obtain the implications of idealization on the physics learning and investigate the students' and teachers' understanding of the ideal condition involved in the theoretical explanation and the experiment in physics.

• Journal of Korea Water Resources Association
• /
• v.51 no.6
• /
• pp.503-514
• /
• 2018

In recent, the hydrological regime of the Mekong river is changing drastically due to climate change and haphazard watershed development including dam construction. Information of hydrologic feature like streamflow of the Mekong river are required for water disaster prevention and sustainable water resources development in the river sharing countries. In this study, runoff simulations at the Kratie station of the lower Mekong river are performed using SWAT (Soil and Water Assessment Tool), a physics-based hydrologic model, and LSTM (Long Short-Term Memory), a data-driven deep learning algorithm. The SWAT model was set up based on globally-available database (topography: HydroSHED, landuse: GLCF-MODIS, soil: FAO-Soil map, rainfall: APHRODITE, etc) and then simulated daily discharge from 2003 to 2007. The LSTM was built using deep learning open-source library TensorFlow and the deep-layer neural networks of the LSTM were trained based merely on daily water level data of 10 upper stations of the Kratie during two periods: 2000~2002 and 2008~2014. Then, LSTM simulated daily discharge for 2003~2007 as in SWAT model. The simulation results show that Nash-Sutcliffe Efficiency (NSE) of each model were calculated at 0.9(SWAT) and 0.99(LSTM), respectively. In order to simply simulate hydrological time series of ungauged large watersheds, data-driven model like the LSTM method is more applicable than the physics-based hydrological model having complexity due to various database pressure because it is able to memorize the preceding time series sequences and reflect them to prediction.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.116-116
• /
• 2021

자연 하천에서의 부유사 농도 계측은 주로 재래식 채집방식을 활용한 직접계측 방식에 의존하여 비용과 시간이 많이 소요되며 점 계측 방식으로 고해상도의 시공간 자료를 측정하기엔 한계가 존재한다. 이러한 한계점을 극복하기 위해 최근 위성영상과 드론을 활용하여 촬영된 다분광 혹은 초분광 영상을 통해 고해상도의 부유사 농도 시공간분포를 측정하는 기법에 대한 연구가 활발히 진행되고 있다. 하지만, 다른 하천 물리량 계측에 비해 부유사 계측 연구는 하천에 따라 부유사가 비균질적으로 분포하여 원격탐사를 통해 정확하고 전역적인 농도 분포를 재현하기는 어려운 실정이다. 이러한 부유사의 비균질성은 부유사의 입도분포, 광물특성, 침강성 등이 하천에서 다양하게 분포하기 때문이며 이로 인해 부유사는 지역별로 다양한 분광특성을 가지게 된다. 따라서, 본 연구에서는 이러한 영향을 고려한 전역적인 부유사 농도 예측 모형을 개발하기 위해 실내 실험을 통해 부유사 특성별 고유 분광 라이브러리를 구축하고 실규모 수로에서 다양한 부유사 조건에 대한 초분광 스펙트럼과 부유사 농도를 측정하는 실험을 수행하였다. 실제 부유사 농도는 광학 기반 센서인 LISST-200X와 샘플링을 통한 실험실 분석을 통해 계측되었으며, 초분광 스펙트럼 자료는 초분광 카메라를 통해 촬영한 영상에서 부유사 계측 지점에 대한 픽셀의 스펙트럼을 추출하여 구축하였다. 이렇게 생성된 자료들의 분광 다양성을 주성분 분석(Principle Component Analysis; PCA)를 통해 분석하였으며, 부유사의 입도 분포, 부유사 종류, 수온 등과의 상관관계를 통해 분광 특성과 가장 상관관계가 높은 물리적 인자를 규명하였다. 더불어 구축된 자료를 바탕으로 기계학습 기반 주요 특징 선택 알고리즘인 재귀적 특징 제거법 (Recursive Feature Elimination)과 기계학습기반 회귀 모형인 Support Vector Regression을 결합하여 초분광 영상 기반 부유사 농도 예측 모형을 개발하였으며, 이 결과를 원격탐사 계측 연구에서 일반적으로 사용되어 오던 최적 밴드비 분석 (Optimal Band Ratio Analysis; OBRA) 방법으로 도출된 회귀식과 비교하였다. 그 결과, 기존의 OBRA 기반 방법은 비선형성을 증가시켜도 좁은 영역의 파장대만을 고려하는 한계점으로 인해 부유사의 다양한 분광 특성을 반영하지 못하였으며, 본 연구에서 제시한 기계학습 기반 예측 모형은 420 nm~1000 nm에 걸쳐 폭 넓은 파장대를 고려함과 동시에 높은 정확도를 산출하였다. 최종적으로 개발된 모형을 적용해 다양한 유사 조건에 대한 부유사 시공간 분포를 매핑한 결과, 시공간적으로 고해상도의 부유사 농도 분포를 산출하는 것으로 밝혀졌다.

• Journal of Korean Elementary Science Education
• /
• v.40 no.4
• /
• pp.443-459
• /
• 2021

In this study, a TPACK-based STEAM program was developed and applied under the theme of excretory organs in the 'Structure and Function of Our Body' of the elementary science curriculum. The program was produced and conducted through curriculum analysis and learning goal detailing, learning environment analysis, teaching·learning method and technology selection, TPACK elements arrangement and teaching·learning material development, application and effectiveness verification. Teacher's TPACK considered in STEAM program design process is content knowledge (appearance and work of excretory organs), pedagogical knowledge (STEAM, problem-based learning, research learning, discussion learning, cooperative learning, scientific writing) and technology knowledge (3D printer and smart device application technology). The program consisted of a total of 8 hours of project learning activities and was applied to 29 students in the fifth grade as an experimental group. A program of the same theme developed mainly from textbooks was applied to 27 students in the fifth grade of a comparison group. As a result of the application of the program, the experimental group showed significant improvement in creative problem-solving ability and scientific attitude compared to the comparison group, and the class satisfaction with the STEAM program was also high. However, there was no significant difference in academic achievement ability.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.104-104
• /
• 2022

임진강 수계는 북측 지역이 다수를 차지하는 유역 특성으로 예고 없는 상류 급방류, 강우 등으로 인해 댐 운영에 근본적 어려움이 있으며, 이에 따라 홍수조절지 및 댐 하류 계측 가능 지역의 취득 자료를 고려한 하천 수위 변화에 대한 사전 예측을 필요로 하고 있다. 홍수기 하천 도달시간 및 수위예측 기법으로는 물리 기반 및 데이터 기반 모델들이 다양하게 연구되어 왔으며, 일부 연구성과들은 현업에 활용하고 있다. 물리기반 모델은 하천 지형 변화에 대한 자료 취득 및 분석에 많은 시간을 요하는 단점은 있으나, 설명 가능한 모델을 구현할 수 있을 것으로 사료 된다. 반면, 데이터 기반 인공지능 모델은 짧은 시간 및 비용으로 모델을 개발할 수 있으나, 복잡한 알고리즘구현 시 설명이 불가하여 일관성을 의심 받을 수 있다. 본 논문에서는 홍수 도달시간과 하류 수위 상승에 대하여 설명 가능한 인공지능 알고리즘 및 시뮬레이션 프로그램을 개발하고자 하였다. 홍수 도달시간 예측은 기존 조견표 방식에서 고려하지 않았던 홍수파의 영향을 추가 변수화 하고, 데이터의 전후처리를 통하여 도달시간을 예측하였다. 실시간 하류 수위 예측은 댐 방류량, 주변 강우, 조위 등을 고려하여 도달시간 후 수위를 예측할 수 있도록 구현하였으며, 자료 동화 기술을 일부 적용하였다. 미래 방류조건에 대한 시뮬레이션을 위해서는 미래 방류량, 예상 강우 입력 시 하천 지점별 수위 상승을 예측할 수 있도록 알고리즘 및 프로그램을 개발하였다. 이를 구현하기 위하여 다양한 인공지능 알고리즘을 이용한 학습, 유전자 알고리즘을 이용한 가중치 학습 제한 조건내 최적화, 수위파와 조위파의 중첩의 정리 등을 이용하여 예측 정확도 및 신뢰성을 제고 하였다. 인공지능 분석결과의 현업활용성 제고를 위하여 시뮬레이터 프로그램을 개발하여 현업에 적용하였다.

• Geophysics and Geophysical Exploration
• /
• v.22 no.4
• /
• pp.202-209
• /
• 2019

In this study, an acoustic full-waveform inversion using Adam optimizer was proposed. The steepest descent method, which is commonly used for the optimization of seismic waveform inversion, is fast and easy to apply, but the inverse problem does not converge correctly. Various optimization methods suggested as alternative solutions require large calculation time though they were much more accurate than the steepest descent method. The Adam optimizer is widely used in deep learning for the optimization of learning model. It is considered as one of the most effective optimization method for diverse models. Thus, we proposed seismic full-waveform inversion algorithm using the Adam optimizer for fast and accurate convergence. To prove the performance of the suggested inversion algorithm, we compared the updated P-wave velocity model obtained using the Adam optimizer with the inversion results from the steepest descent method. As a result, we confirmed that the proposed algorithm can provide fast error convergence and precise inversion results.

• New Physics: Sae Mulli
• /
• v.68 no.12
• /
• pp.1356-1363
• /
• 2018

The purpose of this study was to investigate science high-school students' creativity and scientific attitude when an integrated science, technology, engineering and mathematics (STEM) project themed 'lighting of quantum dot solution' was applied to them. The subjects were a one team composed of 3 students in the 11th grade desiring to participate in the Korea Science Exhibition. They began with a scientific inquiry related to the physical properties of the QD solution and then gradually showed the process of expansion of their ideas into the integration of engineering, technology, and mathematics. Also, during the process, they showed problem solving ability and scientific attitudes, such as cooperation, endurance, and satisfaction of accomplishment.

• Journal of Korean Physical Therapy Science
• /
• v.30 no.4
• /
• pp.63-70
• /
• 2023

Background: The purpose of this study was to comparison of learning attitude, class satisfaction, and self-regulated learning ability of face-to-face and non-face-to-face classes in college physical therapy students to improve the educational effect and quality of non-face-to-face classes when face-to-face classes such as COVID-19 become inevitable in the future. Design: Cross-section study. Methods: This study was conducted with 91 college students, 3rd year students of physical therapy department at a community college in 'A' region, Gyeongsangbuk-do, who took face-to-face classes in the first semester of 2022 and non-face-to-face classes in 2021 of the previous semester. Results: Class attitude was higher in face-to-face classes than in non-face-to-face classes. There was a significant difference in class satisfaction between face-to-face and non-face-to-face classes, In self-regulated learning ability, face-to-face classes had a more positive effect on self-regulated learning ability than non-face-to-face classes. Conclusion: This study serves as empirical basic data on the actual condition of non-face-to-face classes compared to face-to-face classes for college physical therapy students, suggests the direction of future research, and improves the quality of non-face-to-face classes in the field of physical therapy, which requires a lot of practice. and hope it will be used for development.