• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.26 no.4
• /
• pp.307-326
• /
• 2021

Real-time sea level observations from tide gauges include missing and erroneous values. Classification as abnormal values can be done for the latter by the quality control procedure. Although the 3𝜎 (three standard deviations) rule has been applied in general to eliminate them, it is difficult to apply it to the sea-level data where extreme values can exist due to weather events, etc., or where erroneous values can exist even within the 3𝜎 range. An artificial intelligence model set designed in this study consists of non-annotated recurrent neural networks and ensemble techniques that do not require pre-labeling of the abnormal values. The developed model can identify an erroneous value less than 20 minutes of tide gauge recording an abnormal sea level. The validated model well separates normal and abnormal values during normal times and weather events. It was also confirmed that abnormal values can be detected even in the period of years when the sea level data have not been used for training. The artificial neural network algorithm utilized in this study is not limited to the coastal sea level, and hence it can be extended to the detection model of erroneous values in various oceanic and atmospheric data.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.3
• /
• pp.97-102
• /
• 2010

The purpose of medical data mining for efficient algorithms and techniques throughout the various diseases is to increase the reliability of estimates to classify. Previous studies, an algorithm based on a single model, and even the existence of the model to better predict the classification accuracy of multi-model ensemble-based research techniques are being applied. In this paper, the higher the medical data to predict the reliability of the existing scope of the ensemble technique applied to the I-ENSEMBLE offers. Data for the diagnosis of hypothyroidism is the result of applying the experimental technique, a representative ensemble Bagging, Boosting, Stacking technique significantly improved accuracy compared to all existing, respectively. In addition, compared to traditional single-model techniques and ensemble techniques Multi modeling when applied to represent the effects were more pronounced.

• 한국디지털정책학회:학술대회논문집
• /
• 2006.12a
• /
• pp.273-283
• /
• 2006

우리나라에서도 비즈니스 모델(Business Method) 관련 발명에 대한 출원이 많아지고 이제 특허를 받는 발명들이 나오면서 비즈니스 모델(BM) 특허에 대한 분쟁이 빈번해지는 것은 피할 수 없는 대세로 여겨지고 있다. 이에 향후 세계 각국에서 새로운 양상으로 전개될 특허권 분쟁에 슬기롭게 대처하기 위해서는 이러한 논의의 핵심을 파악하고 이를 바탕으로 대처 방안을 세우는 것이 시급한 과제일 것이다. 본 연구는 위와 같은 필요성에 따라 비즈니스 모델(BM)의 이론을 고찰하고, 국내 ${\cdot}$ 외 분쟁사례를 조사하고 이를 바탕으로 비즈니스 모델(BM) 특허 전략에 대한 방안을 제시하고자 한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.4
• /
• pp.654-660
• /
• 2012

The goal of this paper is to calculate flood elevation by applying temporal distribution of rainfall through HEC-RAS(Hydrologic Engineering Center's River Analysis System) and to automatically create areas of flooding by a user-defined spatial model based on GIS using calculated values of flood elevation and detailed data of topography. Accuracy of topographic data is the most important factor because of deeply changing analysis results of flooding areas of a river. Therefore, this paper suggests a method of attributive and spatial data construction based on the GIS using UIS(Urban Information System, river-related reports, and hydrologic information. Also, we implement an expression system to provide analysis results extracted from the proposed model.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.19-28
• /
• 2021

Esophagogastroduodenoscopy is a method commonly used for early diagnosis of upper gastrointestinal lesions. However, 10-20 percent of the gastric lesions are reported to be missed, due to human error. And countries including the US, the UK, and Japan, the World Endoscopy Organization (WEO) suggested guidelines about essential gastrointestinal parts to take pictures of so that all gastric lesions are observed. In this paper, we propose deep learning techniques for classification of anatomical sites, aiming for the system that informs practitioners whether they successfully did the gastroscopy without blind spots. The proposed model uses pre-processing modules and data augmentation techniques suitable for gastroscopy images. Not only does the experiment result with a maximum F1 score of 99.6%, but it also shows a error rate of less than 4% based on the actual data. Given the performance results, we found the model to be explainable with the potential to be utilized in the clinical area.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.422-422
• /
• 2018

우리나라의 간척사업은 고려시대 중엽부터 서남해안에 다수 산재되어 있는 천혜적인 간척 적지를 대상으로 지속적으로 추진되어 국토확장 및 식량 자급달성에 기여하여 왔다. 그러나, 최근 들어 쌀 수급 등 농업정책의 변화, 비용에 대한 경제성 평가의 변화, 개발과 보전에 관한 이해당사자간의 대립 등으로 신규 간척사업의 추진이 어려워지고 기존 간척지의 토지이용 목적 변화와 이치수 기능개선을 목적으로 배수갑문을 확장하는 등의 사업이 추진되고 있다. 본 연구에서는 방조제 상류지역 및 지천에서 이상홍수 유입에 따른 방조제 안정성 검토를 실시하였다. 호내로 유입되는 빈도별 홍수량에 따른 각 지점별 수위변화를 이용하여 방조제 비상대처계획에 대한 재난관리 지표로 활용할 수 있는지를 확인한다. 이를 위해 선정된 방조제를 중심으로 빈도별 홍수량을 산정하여 수문학적 안정성을 검토하고, 빈도별 홍수량에 따른 호내의 홍수위 변화를 통하여 비상대처계획 시나리오를 구성하고자 한다. 새만금 유역의 수치모델링에 필요한 범위를 설정하고, 모델 구성 및 자료를 입력한 후 검 보정을 통하여 모델의 신뢰성을 검증한 후 모델운영 조건을 설정하였다. 새만금 종합개발계획(MP)이 완료되었을 경우를 가정하여 통합운영을 실시하였다. 호내 관리수위에 따른 100, 200, 500, PMF 홍수량 유입시에 호내 홍수위 모의를 수행하였다. 또한, 비상단계 중 초기단계인 '관심단계'를 "이상홍수 발생부터 관리수위 EL-1.5m까지"로 설정한다면 방조제 초기 재난대응이 유리해 질 것으로 판단된다. 또한, '주의단계'는 "관리수위 EL-1.5m부터 호내 관리홍수위 EL+1.5m까지"로 '경계단계'를 "호내 관리홍수위 EL+1.5m부터 제당 내측사석보호공 홍수위까지", '심각단계'를 "제당 내측사석보호공(만경유역 EL+4.5m, 동진유역 EL+2.5m) 이상의 홍수위"로 설정한다면 방조제 관리자에게 세부화된 정보 및 지표를 제공해 줄 것이라 판단된다. 방조제 비상상황 단계별 분류에서 이상홍수위 발생후의 시간을 수치모의를 통해 구분하였으며 정성적인 위기상황 판단이 아닌 구체적인 수치로 된 지표들을 방조제 위기상황 재난지표로 활용한다면 상황 관리자의 위기상황 판단과 대처를 위한 의사결정에 도움이 될 것으로 기대한다.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.46 no.6
• /
• pp.97-110
• /
• 2018

This study examined the value of the old roads and roadscapes as modern assets. Topographic maps of the two years (1916 and 1919, which were produced by the Japanese Government-General of Korea) and the digital topographic map produced in 2017, were analyzed. The total amount of roads that have survived for the past 100 years are located in 108 places and total 26.32km. After examining the remnants of the roads in YeongDo, the type of scenery experienced along the roads were classified into nine kinds. The place where a sequential scenery experience takes place due to the survival of the past, the experience is based on the transition of historical scenery, not the scenery of the present time. A new model that can preserve, manage and plan this scenery is required. Therefore, we propose a new landscape model that elevates the concept of gaze from a spatial concept to a spatiotemporal concept. Based on this model, we propose a conservation criterion of the landscape viewed on the road as a viewpoint. As a modern asset for the next 100 years of YeongDo, it is necessary to understand and preserve the meaning of the landscape and roadside scenery as a transit landscape network. The remnant of roads from 100 years ago suggests that the scenery on the road was has been maintained, and it is the historical landscape of the YeongDo area. Through the landscape conservation plan proposed in this study, it is expected that the historical roads and their landscape will be positioned as a modern asset and an aspect of local heritage, and the future conservation and management of the roads and roadscapes will continue.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2004.04a
• /
• pp.217-224
• /
• 2004

Open-coast storm surge computations are of value in planning and constructing engineering works, especially in coastal regions. Prediction of typhoon surge elevations is based primarily on the use of a numerical model in this study, since it is difficult to study these events in real time or with use of physical models. A simple quasi-two dimensional numerical model for storm surge is considered. In order to understand the model's underlying assumptions, range of validity, and application, we discussed several aspects of typhoons and the physical factors governing storm generation processes. We also followed the basic governing equation, together with the assumption generally taken in their development, to see the principle characteristics of the model from a physical as well as a mathematical point of view. The equations consistent with the model described here are reduced forms of the basic equations and their effects on the resulting numerical scheme are discussed. Finally we applied the model discussed above to a storm surge problem at Masan Bay, the south coast of Korea Effects of astronomical tide, initial water level, and atmospheric pressure setup are considered. We then analyzed the flood at the coastal city and proposed a reasonable way of flood control.

• Proceedings of the KSCN Conference
• /
• 1997.10a
• /
• pp.51-51
• /
• 1997

• Proceedings of the Military Operations Research Society of Korea Conference
• /
• 2000.02a
• /
• pp.116-132
• /
• 2000