• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.497-497
• /
• 2016

페루의 Rimac강은 수도인 Rima시를 관통하는 강으로 각종 용수공급 등의 기능을 담당하는 중요한 강이지만 광산, 공장 및 도시 등 점?비점오염원으로 인해 오염이 심각해지고 있는 실정이다. 본 연구에서는 Rimac강의 하천복원을 위하여 3단계 수질개선 목표를 설정하고 각 단계별 BOD, TP 및 중금속(Al, As, Cd, Fe) 예측을 수행함으로써 목표달성 가능 평가를 수행하였다. Rimac강 지류인 Rio Santa Eulalia 하천 유입후부터 하구까지 총 57 km를 대상으로 4개의 대구간(Reach), 57개의 소구간(Element)으로 구분하여 QUAL2E 모델을 구축하였다. 2013년을 대상으로 저유량시기(건기)인 12월과 고유량시기(우기)인 1월을 대상으로 BOD, TP, Al, As, Cd, Fe의 모델 재현성을 검토한 결과, Rimac강 하류의 Huaycoloro강 유입이후 BOD, TP가 증가하는 현상을 적절히 재현하는 것으로 나타났다. 중금속은 Romac강 상류와 하류 Huaycoloro강 유입 수질 농도차이가 크지 않아 거리별로 일정한 농도를 나타내는 것으로 모의되었으나 실측정값은 하구로 갈수록 낮아지는 경향이 다소 나타났지만 대체적으로 실측값의 경향을 따르는 것으로 모의되었다. 수질개선 시나리오는 1단계(2016-2018년), 2단계(2019-2021년) 및 최종 3단계(2022-2024년)로 구분하여 저유량시기와 고유량시기의 수질개선 대책에 따른 수질변화를 예측하여 Rimac강 하류의 대표 지점인 La Atargea 취수장 지점에서 목표수질 달성여부를 평가하였다. 저유량시기의 경우, BOD는 1단계 이후 5.9 mg/L에서 목표수질 5.0 mg/L 이하로 농도가 감소되었으며 최종 3단계에 2.2 mg/L로 63.3% 개선하는 것으로 예측되었다. TP는 1단계 25.8% 개선, 3단계는 51.6% 개선되어 목표수질인 0.15 mg/L를 만족하는 것으로 예측되었다. 중금속의 경우 Cd는 당초 수질목표를 만족시키는 상황이었으며 그 외 항목은 Al>As>Fe 순으로 개선효과가 나타났고, 3단계 이후 모두 목표수질을 달성할 것으로 예측되었다. 고유량시기 수질예측 결과, 1단계 BOD, TP는 약 49, 19% 저감효과가 나타났으며 3단계 이후 57, 25%까지 개선되는 것으로 예측되어 목표수질을 만족시키는 것으로 분석되었다. 중금속은 Al이 가장 큰 개선 효과가 나타났으며 3단계에서 77.5%의 개선 효과가 분석되었다. 페루 리막강 유역 수질개선 대책 수립에 따른 수질개선효과 분석 결과, 3단계까지 모든 수질항목의 목표수질 달성이 가능한 것으로 분석되었으나 TP, Al 및 As의 경우에 2단계까지 목표수질 달성이 어려워 더욱 체계적인 관리가 필요할 것으로 판단되었다.

• Geophysics and Geophysical Exploration
• /
• v.6 no.4
• /
• pp.171-179
• /
• 2003

In land and marine seismic survey, we generally set receivers with equal interval suppose that sampling interval Is too narrow. But the cost of seismic data acquisition and that of data processing are much higher, therefore we should design proper receiver interval. Spatial aliasing can be occurred on seismic data when sampling interval is too coarse. If we Process spatial aliasing data, we can not obtain a good imaging result. Trace interpolation is used to improve the quality of multichannel seismic data processing. In this study, we applied the Spitz algorithm which is widely used in seismic data processing. This algorithm works well regardless of dip information of the complex underground structure. Using prediction filter and original traces with linear event we interpolated in f-x domain. We confirm our algorithm by examining for some synthetic data and marine data. After interpolation, we could find that receiver intervals get more narrow and the number of receiver is increased. We also could see that continuity of traces is more linear than before Applying this interpolation algorithm on seismic data with spatial aliasing, we may obtain a better migration imaging.

• Journal of the Korea Convergence Society
• /
• v.12 no.9
• /
• pp.11-19
• /
• 2021

A software system is required to change during its life cycle due to various requirements such as adding functionalities, fixing bugs, and adjusting to new computing environments. Such program code modification should be considered as carefully as a new system development becase unexpected software errors could be introduced. In addition, when reusing open source programs, we can expect higher quality software if code changes of the open source program are predicted in advance. This paper proposes a Convolutional Neural Network (CNN)-based deep learning model to predict source code changes. In this paper, the prediction of code changes is considered as a kind of a binary classification problem in deep learning and labeled datasets are used for supervised learning. Java projects and code change logs are collected from GitHub for training and testing datasets. Software metrics are computed from the collected Java source code and they are used as input data for the proposed model to detect code changes. The performance of the proposed model has been measured by using evaluation metrics such as precision, recall, F1-score, and accuracy. The experimental results show the proposed CNN model has achieved 95% in terms of F1-Score and outperformed the multilayer percept-based DNN model whose F1-Score is 92%.

• Journal of Korean Society of Disaster and Security
• /
• v.14 no.3
• /
• pp.17-27
• /
• 2021

In this study, classification models were built using machine learning techniques that can classify the soil creep risk into three classes from A to C (A: risk, B: moderate, C: good). A total of six machine learning techniques were used: K-Nearest Neighbor, Support Vector Machine, Logistic Regression, Decision Tree, Random Forest, and Extreme Gradient Boosting and then their classification accuracy was analyzed using the nationwide soil creep field survey data in 2019 and 2020. As a result of classification accuracy analysis, all six methods showed excellent accuracy of 0.9 or more. The methods where numerical data were applied for data training showed better performance than the methods based on character data of field survey evaluation table. Moreover, the methods learned with the data group (R1~R4) reflecting the expert opinion had higher accuracy than the field survey evaluation score data group (C1~C4). The machine learning can be used as a tool for prediction of soil creep if high-quality data are continuously secured and updated in the future.

• Journal of the Korean Geotechnical Society
• /
• v.35 no.6
• /
• pp.17-26
• /
• 2019

In this study, the statistical characteristics of the resistance bias factors were analyzed using a high-quality field load test database, and the total resistance bias factors were estimated considering the soil uncertainty and construction errors for the application of the limit state design of aggregate pier foundation. The MLR model by Bong and Kim (2017), which has a higher prediction performance than the previous models was used for estimating the resistance bias factors, and its suitability was evaluated. The chi-square goodness of fit test was performed to estimate the probability distribution of the resistance bias factors, and the normal distribution was found to be most suitable. The total variability in the nominal resistance was estimated including the uncertainty of undrained shear strength and construction errors that can occur during the aggregate pier construction. Finally, the probability distribution of the total resistance bias factors is shown to follow a log-normal distribution. The parameters of the probability distribution according to the coefficient of variation of total resistance bias factors were estimated by Monte Carlo simulation, and their regression equations were proposed for simple application.

• Journal of Korean Society on Water Environment
• /
• v.35 no.4
• /
• pp.316-331
• /
• 2019

Carbon dioxide($CO_2$) emission from rivers to the atmosphere is a key component in the global carbon cycle. Most of the rivers are supersaturated with $CO_2$. At a global scale, the amount of $CO_2$ emission from rivers is reported to be five-fold greater than that from lakes and reservoirs, but relevant data are rare in Korea. The objectives of this study is to estimate the $CO_2$ net atmospheric flux(NAF) from the upstream of Gangjeong-Goryeong Weir(GGW), Dalseong Weir(DSW), Hapcheon-Changnyeong Weir(HCW), and Changnyeong-Haman Weir(CHW) located in Nakdong River South Korea) using field and laboratory experiments and to apply data mining techniques to develop parsimonious prediction models that can be used to estimate $CO_2$ NAF with physical and water quality variables that can be collected easily. As a result, the study sites were all heterotrophic systems that often released $CO_2$ to the atmosphere, except when the algal photosynthesis was active.The median $CO_2$ NAF was minimum $391.5mg-CO_2/m^2$ day at GGW and maximum $1472.7mg-CO_2/m^2$ day at DSW. The $CO_2$ NAF showed a negative correlation with pH and Chl-a since the overgrowth of the algae consumed $CO_2$ in the water and increased the pH. As the parsimonious multiple regression model and random forest model developed, this study showed an excellent performance with the $Adj.R^2$ value higher than 0.77 in all weirs. Thus, these methods can be used to estimate $CO_2$ NAF in the river even if there is no $pCO_2$ measurement data.

• The Korean Journal of Applied Statistics
• /
• v.31 no.6
• /
• pp.677-692
• /
• 2018

The total fertility rate of Korea was 1.05 in 2017, showing a return to the 1.08 level in the year 2005. 1.05 is a very low fertility level that is far from replacement level fertility or safety zone 1.5. The number may indicate a low fertility trap. It is therefore important to predict fertility than at any other time. In the meantime, we have predicted the age-specific fertility rate and total fertility rate by various statistical methods. When the data trend is disconnected or fluctuating, it applied a nonparametric method applying the smoothness and weight. In addition, the Bayesian method of using the pre-distribution of fertility rates in advanced countries with reference to the three-stage transition phenomenon have been applied. This paper examines which method is reasonable in terms of precision and feasibility by applying estimation, forecasting, and comparing the results of the recent variability of the Korean fertility rate with parametric, non-parametric and Bayesian methods. The results of the analysis showed that the total fertility rate was in the order of KOSTAT's total fertility rate, Bayesian, parametric and non-parametric method outcomes. Given the level of TFR 1.05 in 2017, the predicted total fertility rate derived from the parametric and nonparametric models is most reasonable. In addition, if a fertility rate data is highly complete and a quality is good, the parametric model approach is superior to other methods in terms of parameter estimation, calculation efficiency and goodness-of-fit.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_2
• /
• pp.1193-1202
• /
• 2018

It is important to quantitatively analyze the energy budget for understanding of long-term climate change in Arctic. High-quality and long-term radiative parameters are needed to understand the energy budget. Since most of radiative flux components based on satellite are provide for a short period, several data must be used together. It is important to acquaint differences between data to link for conjunction with several data. In this study, we investigated the comparative analysis of Arctic radiative flux product such as CERES and GEWEX to provide basic information for data linkage and analysis of changes in Arctic climate. As a result, GEWEX was underestimated the radiative variables, and it difference between the two data was about $3{\sim}25W/m^2$. In addition, the difference in high-latitude and sea ice regions have increased. In case of comparing with monthly means, the other variables except for longwave downward flux represent high difference of $9.26{\sim}26.71W/m^2$ in spring-summer season. The results of this study can be used standard data for blending and selecting GEWEX and CERES radiative flux data due to recognition of characteristics according to ice-ocean area, season, and regions.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_1
• /
• pp.1101-1117
• /
• 2018

The clear sky radiance (CSR) is one of the baseline products of the Himawari-8 which was launched on October, 2014. The CSR contributes to numerical weather prediction (NWP) accuracy through the data assimilation; especially water vapor channel CSR has good impact on the forecast in high level atmosphere. The focus of this study is the quality analysis of the CSR of the Himawari-8 geostationary satellite. We used the operational CSR (or clear sky brightness temperature) products in JMA (Japan Meteorological Agency) as observation data; for a background field, we employed the CSR simulated using the Radiative Transfer for TOVS (RTTOV) with the atmospheric state from the global model of KMA (Korea Meteorological Administration). We investigated data characteristics and analyzed observation minus background statistics of each channel with respect to regional and seasonal variability. Overall results for the analysis period showed that the water vapor channels (6.2, 6.9, and $7.3{\mu}m$) had a positive mean bias where as the window channels(10.4, 11.2, and $12.4{\mu}m$) had a negative mean bias. The magnitude of biases and Uncertainty result varied with the regional and the seasonal conditions, thus these should be taken into account when using CSR data. This study is helpful for the pre-processing of Himawari-8/Advanced Himawari Imager (AHI) CSR data assimilation. Furthermore, this study also can contribute to preparing for the utilization of products from the Geo-Kompsat-2A (GK-2A), which will be launched in 2018 by the National Meteorological Satellite Center (NMSC) of KMA.

• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.132-141
• /
• 2019

The necessity of transmitting video data over a narrow-bandwidth exists steadily despite that video service over broadband is common. In this paper, we propose a scalable video coding framework for low-resolution video transmission over a very narrow-bandwidth network by super-resolution of decoded frames of a base layer using a convolutional neural network based super resolution technique to improve the coding efficiency by using it as a prediction for the enhancement layer. In contrast to the conventional scalable high efficiency video coding (SHVC) standard, in which upscaling is performed with a fixed filter, we propose a scalable video coding framework that replaces the existing fixed up-scaling filter by using the trained convolutional neural network for super-resolution. For this, we proposed a neural network structure with skip connection and residual learning technique and trained it according to the application scenario of the video coding framework. For the application scenario where a video whose resolution is $352{\times}288$ and frame rate is 8fps is encoded at 110kbps, the quality of the proposed scalable video coding framework is higher than that of the SHVC framework.