• Smart Structures and Systems
• /
• v.31 no.6
• /
• pp.561-571
• /
• 2023

Ensuring the safety of a structure necessitates that repairs are carried out based on accurate inspections and records of damage information. Traditional methods of recording damage rely on individual paper-based documents, making it challenging for inspectors to accurately record damage locations and track chronological changes. Recent research has suggested the adoption of building information modeling (BIM) to record detailed damage information; however, localizing damages on a BIM model can be time-consuming. To overcome this limitation, this study proposes a method to automatically localize damages on a BIM model in real-time, utilizing consecutive images and measurements from an inertial measurement unit in close proximity to damages. The proposed method employs a visual-inertial odometry algorithm to estimate the camera pose, detect damages, and compute the damage location in the coordinate of a prebuilt BIM model. The feasibility and effectiveness of the proposed method were validated through an experiment conducted on a campus building. Results revealed that the proposed method successfully localized damages on the BIM model in real-time, with a root mean square error of 6.6 cm.

• Clean Technology
• /
• v.29 no.2
• /
• pp.145-150
• /
• 2023

Tele-metering systems have been useful tools for managing domestic wastewater treatment plants (WWTP) over the last decade. They mostly generate water quality data for discharged water to ensure that it complies with mandatory regulations and they may be able to produce every operation parameter and additional measurements in the near future. A sub-big data group, comprised of about 150,000 data points from four domestic WWTPs, was ready to be classified and also analyzed to optimize the WWTP process. We used the Statistical Product and Service Solutions (SPSS) 25 package in order to statistically treat the data with linear regression and correlation analysis. The major independent variables for analysis were water temperature, sludge recycle rate, electricity used, and water quality of the influent while the dependent variables representing the water quality of the effluent included the total nitrogen, which is the most emphasized index for discharged flow in plants. The water temperature and consumed electricity showed a strong correlation with the total nitrogen but the other indices' mutual correlations with other variables were found to be fuzzy due to the large errors involved. In addition, a multilayer perceptron analysis method was applied to TMS data along with root mean square error (RMSE) analysis. This study showed that the RMSE in the SS, T-N, and TOC predictions were in the range of 10% to 20%.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.118-118
• /
• 2020

This study investigates the change of flow characteristics over 10 Asian river basins in the past 30 years (1976-2005). The variation is estimated from The Soil and Water Assessment Tool (SWAT) model outputs based on reanalysis data which was bias-corrected for Asian monsoon reagion. The model was firstly calibrated and validated using observed data for daily streamflow. Four statistical criteria were applied to evaluate the model performance, including Coefficient of determination (R2), Nash - Sutcliffe model efficiency coeffi cient (NSE), Root mean square error-observations standard deviation ratio (RSR), and Percentage Bias (PBIAS). Then parameters of the model were applied for the historical period 1976-2005. The estimates show a temporal non-considerable increasing rate of daily streamflow in most of the basins over the past 30 years. The difference of monthly discharge becomes more significant during the months in the wet season (June to September) in all basins. The seasonal runoff shows significant difference in Summer and Autumn, when the rainfall intensity is higher. The line showing averaged runoff/rainfall ratio in all basins is sharp, presenting high variation of seasonal runoff/rainfall ratio from season to season.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.268-268
• /
• 2020

토양수분량은 수문연구에 있어 중요한 인자 중의 하나이며, 그 필요성이 점차 강조되고 있다. 국내에서도 최근 새로운 관측기기의 도입이나 수자원위성의 개발 등에 관한 연구가 점차 활발하게 이뤄지고 있으나, 토양수분량 자료의 생산, 품질관리 및 배포 시스템에 관한 연구 및 개발이 부족한 실정이다. 반면에 해외에서는 International Soil Moisture Network(ISMN)을 통해 토양수분량 자료의 품질관리 및 배포가 활발하게 이루어지고 있는데, ISMN에서는 토양특성, 강우에 대한 반응, 토양온도, 시계열특성을 이용해 토양수분량 관측 자료를 품질관리 하고 있다. 본 연구에서는 ISMN의 spike 검출 알고리즘에서 그래프 평활화(smoothing)를 위해 이용되는 Savitzky-Golay 필터의 window size와 polynomial order(filter order)를 다양하게 변화시키고, 이를 설마천 관측소에서 측정한 토양수분량 원시자료에 적용하여 window size와 polynomial order별로 편의(bias), 변동(variation), 평균 제곱근 오차(Root Mean Square Error, RMSE)를 산정하였다. 통계산정 결과 원시자료와의 bias는 window size가 3이고 polynomial order가 2인 필터를 적용했을 때 가장 작은 것으로 나타났으며, variance는 window size가 3이고 polynomial order가 2인 필터를 이용했을 때가 원시자료와 가장 유사한 것으로 나타났다. 또한, RMSE는 window size가 5이고 polynomial order가 3일 때 가장 작은 것으로 나타났다. 이는 추후 토양수분량 품질관리를 수행하기 위해 적절한 필터 계수 값을 제시할 수 있는 논문으로 사료된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.170-170
• /
• 2020

Due to the development of technologies, complex computation of huge data set is possible with a prevalent personal computer. Therefore, machine learning methods have been widely applied in the hydrologic field such as regression-based regional frequency analysis (RFA). The main purpose of this study is to compare two frameworks of RFA based on the artificial neural network (ANN) models: quantile regression technique (QRT-ANN) and parameter regression technique (PRT-ANN). As an output layer of the ANN model, the QRT-ANN predicts quantiles for various return periods whereas the PRT-ANN provides prediction of three parameters for the generalized extreme value distribution. Rainfall gauging sites where record length is more than 20 years were selected and their annual maximum rainfalls and various hydro-meteorological variables were used as an input layer of the ANN model. While employing the ANN model, 70% and 30% of gauging sites were used as training set and testing set, respectively. For each technique, ANN model structure such as number of hidden layers and nodes was determined by a leave-one-out validation with calculating root mean square error (RMSE). To assess the performances of two frameworks, RMSEs of quantile predicted by the QRT-ANN are compared to those of the PRT-ANN.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.255-255
• /
• 2020

아프리카 대륙에서 존재하는 가장 큰 사하라 사막(Sahara desert)의 면적은 지난 1세기 동안 기후변화로 인하여 10% 정도 증가하였고, 미래에도 기온상승으로 인하여 증가할 것으로 판단된다. 사하라 사막 면적의 증가로 인하여 아프리카의 자연식생과 수자원뿐만 아니라 아프리카에 거주하는 사람들의 삶에 많은 영향을 미치기에 사막의 면적 또는 경계선의 위치를 예측함은 매우 중요하다. 본 연구에서는 Coupled Model Intercomparison Project Phase 5 (CMIP5)의 36개 Global Climate Models (GCMs)과 ERA-interim 재분석 자료의 1979~2000년 강수 자료들을 이용하여 사헬(Sahel) 지대 서쪽(15W~15E, 10N~20N)과 동쪽(15E~35E, 10N~20N)의 강수량과 사막경계선을 비교하였다. 또한, 각 모델의 과거 모의 성능을 평가하여 미래 기후 예측성을 판단하고자 한다. 본 연구에서는 22년 평균 강수량이 200mm 이하인 지역을 사막이라 정의하고, 모델별로 연평균 강수량과 사막경계선에 대한 root mean square error(RMSE)를 산정하여 평가하였다. 또한, 습윤 정적 에너지(Moist. Static Energy; MSE), 바람(풍속 및 풍향) 자료를 이용하여 각 모델의 사막경계선의 오차에 대한 이유를 분석하였다. 이 연구를 바탕으로 하여 사헬 지대의 강수량 및 사막면적 모의의 불확실성 요소를 이해하고, 미래 상세 지역 수문기후 변화 예측에 활용 가능한 GCMs을 선별할 수 있을 것으로 판단한다.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.2
• /
• pp.70.4-70.4
• /
• 2019

Image super-resolution (SR) is a technique that enhances the resolution of a low resolution image. In this study, we use three SR models (RCAN, ProSRGAN and Bicubic) for enhancing solar SDO/HMI magnetograms using deep learning. Each model generates a high resolution HMI image from a low resolution HMI image (4 by 4 binning). The pixel resolution of HMI is about 0.504 arcsec. Deep learning networks try to find the hidden equation between low resolution image and high resolution image from given input and the corresponding output image. In this study, we trained three models with HMI images in 2014 and test them with HMI images in 2015. We find that the RCAN model achieves higher quality results than the other two methods in view of both visual aspects and metrics: 31.40 peak signal-to-noise ratio(PSNR), Correlation Coefficient (0.96), Root mean square error (RMSE) is 0.004. This result is also much better than the conventional bi-cubic interpolation. We apply this model to a full-resolution SDO/HMI image and compare the generated image with the corresponding Hinode NFI magnetogram. As a result, we get a very high correlation (0.92) between the generated SR magnetogram and the Hinode one.

• Geomechanics and Engineering
• /
• v.33 no.6
• /
• pp.611-624
• /
• 2023

Soil properties make it attractive as a building material due to its mechanical strength, aesthetically appearance, plasticity, and low cost. However, it is frequently necessary to improve and stabilize the soil mechanical properties with binders. Soil-cement is applied for purposes ranging from housing to dams, roads and foundations. Unconfined compression strength (UCS) and split tensile strength (CD) are essential mechanical parameters for ascertaining the aptitude of soil-cement for a given application. However, quantifying these parameters requires specimen preparation, testing, and several weeks. Methodologies that allowed accurate estimation of mechanical parameters in shorter time would represent an important advance in order to ensure shorter deliverable timeline and reduce the amount of laboratory work. In this work, an extensive campaign of UCS and CD tests was carried out in a sandy soil from the Leiria region (Portugal). Then, using the machine learning tool Neural Pattern Recognition of the MATLAB software, a prediction of these two parameters based on six input parameters was made. The results, especially those obtained with resource to a Bayesian regularization-backpropagation algorithm, are frankly positive, with a forecast success percentage over 90% and very low root mean square error (RMSE).

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.117-117
• /
• 2021

본 연구에서는 Sentinel-1A/B C-band SAR(Synthetic Aperture Radar) 위성영상을 기반으로 인공신경망(Artificial Neural Network, ANN) 모형을 활용해 금강 유역 상류 40×50 km² 면적에 대한 토양수분을 산정하였다. 10 m 공간 해상도의 Sentinel-1A/B SAR 영상은 8일 간격으로 2015년부터 2019년까지 5년 동안 구축하였고, SNAP(SentiNel Application Platform)을 통해 기하 보정, 방사 보정 및 잡음(Noise) 보정을 수행하고 VV 및 VH 편파 후방산란계수로 변환하였다. ANN 모형 검증자료로 TDR(Time Domain Reflectometry)로 측정된 9개 지점의 실측 토양수분 자료를 구축하였으며, 수문학적 개념인 선행강우를 고려하기 위해 동지점에 대한 강수량 자료를 구축하였다. ANN은 각 지점에 해당하는 토양 속성별로 모델링하고, 전체 기간 및 계절별로 나누어 모의하였으며, 전체 자료의 60%와 40%를 각각 훈련 및 테스트 데이터로 사용하였다. 산정된 토양수분은 상관계수(Correlation Coefficient, R)와 평균제곱근오차(Root Mean Square Error, RMSE)를 활용하여 검증을 수행할 예정이다.

• Geomechanics and Engineering
• /
• v.29 no.5
• /
• pp.549-565
• /
• 2022

Severe acid rains can be a major source for geotechnical and environmental problems in any soil depending on the acid type and concentration. Hence, this study investigates the individual severe effects of sulfuric, hydrochloric and nitric acids on the geotechnical properties of real field soil through a series of experimental laboratory tests. The laboratory program consists of experimental tests such as consistency, compaction, unconfined compression, pH determination, electrical conductivity, total dissolved salts, total suspended solids, gypsum and carbonates contents. The experimental tests have been performed on the untreated soil and individual acid treated soil for acid concentrations range of 0% to 20% by weight. In addition, a unique hyperbolic mathematical model has been used to predict significant geotechnical characteristics for acid treated soil. The plastic and liquid limits and optimum moisture content have been increased under the effect of all the used acids whereas the maximum dry density and unconfined stress-strain behavior have been decreased with increasing the acid concentrations. Moreover, the used hyperbolic mathematical model has predicted all the geotechnical characteristics very well with a very high coefficient of determination (R²) value and lowest root mean square error (RMSE) estimate.