• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.40-40
• /
• 2021

수재해 방지를 위한 수문해석 모형에서 정량적인 강수자료의 역할은 매우 중요하다. 최근에는 기후변화로 인한 국지성 집중호우 등 돌발 강수의 빈도가 증가하고 있어 지상에 설치된 우량계보다 시·공간적 변동성을 반영할 수 있는 격자형 위성 강수자료의 활용성이 커지고 있다. 하지만 위성강수자료는 관측 시에 대기의 상태 또는 위성별 관측 센서, 공간적 스케일 차이 등에 의해 실제 내린 강수와의 편의가 존재한다. 이를 해결하기 위해 지점 강수자료를 이용한 통계적, 지형정보학적 상세화 기법이 적용되고 있으나, 대부분의 연구에서 강수자료의 양적 보정만을 목적으로 수행되었다. 본 연구에서는 머신러닝 기반의 랜덤포레스트(random forest) 모델을 사용하여 다중위성 강수자료(CHIRPSv2, CMORPH, GSMaP, TRMMv7)와 기상청에서 제공하는 AWS, ASOS 지점 강수를 사용하여 최적 위성강수자료를 생성 후 각 위성강수자료와 비교·분석하였다. 2003년에서 2017년까지의 각 위성강수자료를 수집하여 같은 공간 스케일로 전처리한 뒤 모델에 입력하였으며 AWS 강수자료는 훈련, ASOS 강수자료는 검증에 이용되었다. 그 결과, 생성된 최적 위성강수자료는 각 위성강수자료보다 지점강수와의 편의가 줄고 높은 상관관계를 나타내고 있다. 이는 앞으로 사용될 위성강수자료의 시·공간적 보정 및 단기예측에 활용할 수 있으며, 특히 원격탐사자료의 의존도가 높은 미계측 대유역 수문해석에 정량적인 강수자료를 제공할 수 있을 것으로 판단된다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.16 no.3
• /
• pp.96-101
• /
• 2015

A tongue coating evaluation method for WTCI(Winkel Tongue Coating Index) is proposed in this paper, which is used as the diagnostic criteria in the tongue diagnosis. This method uses the color channel analysis and tongue coating extraction from the ultraviolet tongue image. Proposed method analyzes the histogram distribution of the respective color channel for extracting a tongue coating, and performs the verification test from the selected color channel in the tongue coating extraction. Also, Objectivity of the tongue diagnostic criteria is verified by the artificial sample and real-tongue image experiments. In order to evaluate the performance of the proposed Computerized Assistant WTCI Evaluation method, after verifying a measurement accuracy by using the artificial sample images, and applying to the various real-tongue image of subjects. As a result, the proposed WTCI method is very successful.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.341-342
• /
• 2023

배터리 기술 고도화 및 기술표준 강화에 따라 완성차 제조사와 배터리 업계간 활발한 협업이이어질 전망이다. 또한 기존 배터리 제조사들이 활발한 증설 및 밸류 체인 확장을 통한 기술가격 경쟁력 격차 유지에 적극적으로 나서고 있어, 향후 시장 주도권 경쟁이 가속화될 것으로 전망된다. 배터리의 온도 상승은 배터리 효율을 낮추는 원인이며, 배터리 온도 제어가 전기자동차 차량의 전체 성능 향상에 중요한 부분이라고 할 수 있다. 본 연구는 실제 Battery Pack 실험 전 열유동해석을 통해 배터리온도 상승추이 및 냉각효율 검증을 진행하는 과정에서 발생하는 과도한 시간 소요를 줄이기 위해 Machine Learning 을 활용하여 검증 효율 및 설계 효율을 높이는데 그 목적이 있으며, CFD를 활용한 배터리 효율 최적화 설계를 하는 기존 모델 대비 30%~50%정도의 성능향상을 예측할 수 있다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.4
• /
• pp.226-231
• /
• 2019

A WTCI is an important criteria for evaluating an mount of patient's tongue coating in tongue diagnosis. However, Previous WTCI tongue coating evaluation methods is a most of quantitatively measuring ration of the extracted tongue coating region and tongue body region, which has a non-objective measurement problem occurring by exposure conditions of tongue image or the recognition performance of tongue coating. Therefore, a WTCI based on deep learning is proposed for classifying an amount of tonger coating in this paper. This is applying the AI deep learning method using big data. to WTCI for evaluating an amount of tonger coating. In order to verify the effectiveness performance of the deep learning in tongue coating evaluating method, we classify the 3 types class(no coating, some coating, intense coating) of an amount of tongue coating by using CNN model. As a results by testing a building the tongue coating sample images for learning and verification of CNN model, proposed method is showed 96.7% with respect to the accuracy of classifying an amount of tongue coating.

• Journal of Digital Convergence
• /
• v.19 no.5
• /
• pp.197-205
• /
• 2021

Recently, the retail industry has been increasingly demanding information technology convergence and utilization to respond to various external environmental threats such as COVID-19 and to be competitive using AI technologies, but there is a very lack of research and application services. This study is a CCTV video data-driven AI application case study, using CCTV image data collection in retail space, object detection and tracking AI model, time series database to store real-time tracked objects and tracking data, heatmap to analyze congestion and interest in retail space, social access zone.We present the orientation and verify its usability in the direction designed through practical implementation.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.08a
• /
• pp.81-84
• /
• 2000

본 논문은 국제통신연합 전파통신분야(ITU-R)의 간섭분석기의 표준으로 채택한 몬테카를로 기법을 기초로 하여 개발된 간섭분석기를 이용하여 개인 통신 서비스(Personal Communication Service)의 도심지 환경에서 수신 전계강도를 예측하였다. 또한 실제로 측정된 수신 전계강도와 비교하여 간섭분석기의 신뢰도를 검증하였다. 개발된 간섭분석기는 한국 지형에 적합한 전파 전파 모델인 수정된 하타(Modified Hata) 모델을 적용하여 개발하였고, 국내 PCS(IS-95A) 서비스 환경과 규격을 고려한 시나리오를 설정하여 모의 실험을 수행하였다. 실험 결과 간섭 분석기와 실제 측정 수신 전계 강도 사이에는 0.03dBm의 평균오차를 가지며, 이는 간섭분석기를 통해 얻어진 결과가 실제와 매우 유사함을 보여준다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.12
• /
• pp.142-149
• /
• 2015

Most of the mono-camera based lane detection systems are fragile on poor illumination conditions. In order to compensate limitations of single sensor utilization, lane information fusion system using multiple lane sensors is an alternative to stabilize performance and guarantee high precision. However, conventional fusion schemes, which only concerns object detection, are inappropriate to apply to the lane information fusion. Even few studies considering lane information fusion have dealt with limited aids on back-up sensor or omitted cases of asynchronous multi-rate and coverage. In this paper, we propose a lane information fusion scheme utilizing multiple lane sensors with different coverage and cycle. The precise lane information fusion is achieved by the proposed fusion framework which considers individual ranging capability and processing time of diverse types of lane sensors. In addition, a novel lane estimation model is proposed to synchronize multi-rate sensors precisely by up-sampling spare lane information signals. Through quantitative vehicle-level experiments with around view monitoring system and frontal camera system, we demonstrate the robustness of the proposed lane fusion scheme.

• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.357-364
• /
• 2022

This study aims to design a humanities model for preliminary universities using an online platform to develop and expand humanities thinking of preliminary university students. P University Expert Focus Group Interview and student surveys are conducted, and based on the analysis results, a preliminary university model suitable for the humanities field is proposed. Expert FGI suggested the necessity of human resources education to build an online platform-based preliminary university model and improve humanities capabilities. As a result of the student survey, it was found that a majority of the respondents had high interest in humanities and recognized the need for a humanities preliminary university. This study proposes a humanities-based preliminary university model that enables interactive communication in virtual space using the cross-platform Photo Server. The implication of this study is that it contributes to strengthening the humanities capabilities of preliminary university students by presenting an online platform preliminary university model that can respond to changes in the external environment. Since this study has a limitation in that it does not present examples of preliminary universities, it is necessary to verify the educational effect of platform-based ppreliminary university management in the future.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.91-98
• /
• 2023

Human-object interaction(HOI) detection requires both object detection and interaction recognition, and requires a large amount of data to learn a detection model. Current opened dataset is insufficient in scale for training model enough. In this paper, we propose an easy and effective data augmentation method called Simple Quattro Augmentation(SQA) and Random Quattro Augmentation(RQA) for human-object interaction detection. We show that our proposed method can be easily integrated into State-of-the-Art HOI detection models with HICO-DET dataset.

• Korea Science and Art Forum
• /
• v.21
• /
• pp.437-449
• /
• 2015

The research aims to verify the effects of preference for science and self-directed learning ability of the science puppet show program that the researcher has developed as a STEAM education model. The results for conducting the survey with the same questionnaire before and after the program targeting the students showed that the science puppet show had effects on increasing the science related assignment performance will of the behavioral will among the three sub-dimensions including emotional respond, value cognition and behavioral will, but there was no effect on overall aspects of science preference. It can be interpreted as reflecting the characteristics of the scientific talents who already have a high level of preference for science. In addition, the three sub-dimensions including the cognitive regulation, motivational regulation and behavioral regulation had effects on the self-directed learning ability. Especially it had great effects on the directed learning ability of cognitive regulation, learning motivation of motivational regulation, tool application of behavioral regulation, and cooperation capacity which were greater for female students than male students. It is judged that the three-staged science puppet show program including the 'content integrating stage' that the students integrate the curriculum contents, 'integrated mission stage' of solving the visualization, auralization and performance missions by themselves, and 'process integration stage' of making the stage piece all together.