• Journal of Korean Association for Spatial Structures
• /
• v.21 no.2
• /
• pp.99-110
• /
• 2021

This study presents the estimation of crack depth by analyzing temperatures extracted from thermal images and environmental parameters such as air temperature, air humidity, illumination. The statistics of all acquired features and the correlation coefficient among thermal images and environmental parameters are presented. The concrete crack depths were predicted by four different machine learning models: Multi-Layer Perceptron (MLP), Random Forest (RF), Gradient Boosting (GB), and AdaBoost (AB). The machine learning algorithms are validated by the coefficient of determination, accuracy, and Mean Absolute Percentage Error (MAPE). The AB model had a great performance among the four models due to the non-linearity of features and weak learner aggregation with weights on misclassified data. The maximum depth 11 of the base estimator in the AB model is efficient with high performance with 97.6% of accuracy and 0.07% of MAPE. Feature importances, permutation importance, and partial dependence are analyzed in the AB model. The results show that the marginal effect of air humidity, crack depth, and crack temperature in order is higher than that of the others.

• Economic and Environmental Geology
• /
• v.55 no.4
• /
• pp.353-366
• /
• 2022

Spatial estimation of geoscience data (geo-data) is challenging due to spatial heterogeneity, data scarcity, and high dimensionality. A novel spatial estimation method is needed to consider the characteristics of geo-data. In this study, we proposed the application of Gaussian Mixture Model (GMM) among machine learning algorithms with multivariate data for robust spatial predictions. The performance of the proposed approach was tested through soil chemical concentration data from a former smelting area. The concentrations of As and Pb determined by ex-situ ICP-AES were the primary variables to be interpolated, while the other metal concentrations by ICP-AES and all data determined by in-situ portable X-ray fluorescence (PXRF) were used as auxiliary variables in GMM and ordinary cokriging (OCK). Among the multidimensional auxiliary variables, important variables were selected using a variable selection method based on the random forest. The results of GMM with important multivariate auxiliary data decreased the root mean-squared error (RMSE) down to 0.11 for As and 0.33 for Pb and increased the correlations (r) up to 0.31 for As and 0.46 for Pb compared to those from ordinary kriging and OCK using univariate or bivariate data. The use of GMM improved the performance of spatial interpretation of anthropogenic metals in soil. The multivariate spatial approach can be applied to understand complex and heterogeneous geological and geochemical features.

• Journal of Mechanical Science and Technology
• /
• v.16 no.5
• /
• pp.619-632
• /
• 2002

In recent study on design of experiments, the complicate metamodeling has been studied because defining exact model using computer simulation is expensive and time consuming. Thus, some designers often use approximate models, which express the relation between some inputs and outputs. In this paper, we review and compare the complicate metamodels, which are expressed by the interaction of various data through trying many physical experiments and running a computer simulation. The prediction model in this paper employs interpolation schemes known as ordinary kriging developed in the fields of spatial statistics and kriging in Design and Analysis of Computer Experiments (DACE) model. We will focus on describing the definitions, the prediction functions and the algorithms of two kriging methods, and assess the error measures of those by using some validation methods.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.194-194
• /
• 2017

Flooding is one of the most serious and frequently occurred natural disaster at many regions around the world. Especially, under the climate change impact, it is more and more increasingly trend. To reduce the flood damage, flood forecast and its accuracy analysis are required. This study is conducted to analyze the accuracy of the real-time flood forecasting of a coupled meteo-hydrological model for the Han River basin, South Korea. The LDAPS (Local Data Assimilation and Prediction System) products with the spatial resolution of 1.5km and lead time of 36 hours are extracted and used as inputs for the SURR (Sejong University Rainfall-Runoff) model. Three statistical criteria consisting of CC (Corelation Coefficient), RMSE (Root Mean Square Error) and ME (Model Efficiency) are used to evaluate the performance of this couple. The results are expected that the accuracy of the flood forecasting reduces following the increase of lead time corresponding to the accuracy reduction of LDAPS rainfall. Further study is planed to improve the accuracy of the real-time flood forecasting.

• Spatial Information Research
• /
• v.23 no.4
• /
• pp.79-89
• /
• 2015

This study aims to design and implement a traffic model that can simulate the traffic behavior on the microscopic level by using the GIS. In the design of the model, the vehicle in the simulation environment recognizes the GIS road centerline data as road network data reflecting number of lanes, speed limit and so on. In addition, the behavior model was designed by dividing functions into the environmental perception model, time headway distribution model, car following model, and lane changing model. The implemented model was applied to Jahamun-road of Jongno-gu district to verify the accuracy of the model. As a result, the simulation results on the Jahamun-road had no great error compared with the actual observation data. In the aspect of usability of model, it is judged that this model will be able to effectively contribute to analysis of amount of carbon emission by traffic, evaluation of traffic flow, plans for location of urban infrastructure and so on.

• Journal of Environmental Science International
• /
• v.26 no.10
• /
• pp.1167-1180
• /
• 2017

Numerical Weather Prediction (NWP) models such as the Weather Research and Forecasting (WRF) model are essential for forecasting one-day-ahead solar irradiance. In order to evaluate the performance of the WRF in forecasting solar irradiance over the Korean Peninsula, we compared WRF prediction data from 2008 to 2010 corresponding to weather observation data (OBS) from the Korean Meteorological Administration (KMA). The WRF model showed poor performance at polluted regions such as Seoul and Suwon where the relative Root Mean Square Error (rRMSE) is over 30%. Predictions by the WRF model alone had a large amount of potential error because of the lack of actual aerosol radiative feedbacks. For the purpose of reducing this error induced by atmospheric particles, i.e., aerosols, the WRF model was coupled with the Community Multiscale Air Quality (CMAQ) model. The coupled system makes it possible to estimate the radiative feedbacks of aerosols on the solar irradiance. As a result, the solar irradiance estimated by the coupled system showed a strong dependence on both the aerosol spatial distributions and the associated optical properties. In the NF (No Feedback) case, which refers to the WRF-only stimulated system without aerosol feedbacks, the GHI was overestimated by $50-200W\;m^{-2}$ compared with OBS derived values at each site. In the YF (Yes Feedback) case, in contrast, which refers to the WRF-CMAQ two-way coupled system, the rRMSE was significantly improved by 3.1-3.7% at Suwon and Seoul where the Particulate Matter (PM) concentrations, specifically, those related to the $PM_{10}$ size fraction, were over $100{\mu}g\;m^{-3}$. Thus, the coupled system showed promise for acquiring more accurate solar irradiance forecasts.

• Atmosphere
• /
• v.17 no.4
• /
• pp.327-337
• /
• 2007

In this study, we examined the new ensemble training approach to reduce the systematic error and improve prediction skill of wind by using the Short-range Ensemble prediction system (SENSE), which is the mesoscale multi-model ensemble prediction system. The SENSE has 16 ensemble members based on the MM5, WRF ARW, and WRF NMM. We evaluated the skill of surface wind prediction compared with AWS (Automatic Weather Station) observation during the summer season (June - August, 2006). At first stage, the correction of initial state for each member was performed with respect to the observed values, and the corrected members get the training stage to find out an adaptive weight function, which is formulated by Root Mean Square Vector Error (RMSVE). It was found that the optimal training period was 1-day through the experiments of sensitivity to the training interval. We obtained the weighted ensemble average which reveals smaller errors of the spatial and temporal pattern of wind speed than those of the simple ensemble average.

• Journal of the Economic Geographical Society of Korea
• /
• v.23 no.2
• /
• pp.125-146
• /
• 2020

There is an increasing need to foster new industries at the local level. This study aims to analyze the spatial patterns of new industries in Korea from 2007-2017 and to figure out its determinants of agglomeration in 2017. Through this study, it is found that new industries are unevenly distributed around Seoul Metropolitan Area(SMA). The regional disparity between SMA and non-SMA is prominent. Furthermore, new industries represent a strong spatial positive autocorrelation, showing a strong concentration on a few regions in Korea. This study explores the determinants on agglomeration of new industries with spatial statistical model. From the results of spatial error model, it is indicated that the number of graduate students, the ratio of technology based start-ups, and the number of elementary, middle, and high schools have a significant effect on new industries. In addition, the specialization and the diversity of industrial structure on knowledge-based manufacturing industries and knowledge-based service industries have been statistically significant. This study provides implications that non-SMA needs policies with respect to attracting talented people, developing human resources, and improving regional environment in order to improve regional competitiveness in promoting new industries.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.10C
• /
• pp.950-958
• /
• 2007

This paper presents an efficient packet loss resilient scheme for real-time video transmission over the Internet. By analyzing the temporal and spatial dependencies in inter- and intra-frames, we assign forward error correction codes (FEC) across video packets for minimizing the effect of error concealment and error propagation from packet loss. To achieve optimal allocation of FEC codes, we formulate the effect of packet loss on video quality degradation as packet distortion model. Then we propose an unequal FEC assignment scheme with low complexity based on packet correction rate, which uses the packet distortion model and includes channel status information. Simulation results show that the proposed FEC assignment scheme gives substantial improvement for the received video quality in packet lossy networks. Furthermore the proposed scheme achieves relatively smaller degradation of video quality with higher packet loss rates.

• Korean Journal of Legislative Studies
• /
• v.26 no.2
• /
• pp.113-140
• /
• 2020

This study is meaningful in that it is the first analysis of Korean elections using the concept of spatial autocorrelation. Spatial autocorrelation means that an event occurring in one location in space has a high correlation with an event occurring in the surrounding area. The voter turnout rate in the 21^st general election of Seoul area was divided into the early-voting turnout and voting-day turnout, and the spatial pattern of the turnout was examined. Most of the previous studies were based on the unit of the precinct and personal data, but this study analyzed on the basis of the lower unit, Eup-myeon-dong, and analyzed using spatial data and aggregate data. Moran I index showed a fairly high spatial autocorrelation of 0.261 in the voting-day turnout, while the index of the early-voting turnout was low at 0.095, indicating that there was little spatial autocorrelation despite statistical significance. The voting-day turnout, which showed strong spatial autocorrelation, was compared and analyzed using the OLS regression model and the spatial statistics model. In the general regression model, the coefficient of determination R² rose from 0.585261 to 0.656631 in the spatial error model, showing an increase in explanatory power of about 7 percentage points. This means that the spatial statistical model has high explanatory power. The most interesting result is the relationship between the early-voting turnout and the voting-day turnout. The higher the early-voting turnout is, the lower the voting-day turnout is. When the early-voing turnout increases by about 2%, the voting-day turnout drops by about 1%. In this study, the variables affecting the early-voting turnout and the voting-day turnout are very different. This finding is different from the previous researches.