• Tunnel and Underground Space
• /
• v.30 no.3
• /
• pp.214-225
• /
• 2020

Uniaxial compressive strength (UCS) of rock is one of the important factors to determine the advance speed during shield TBM tunnel excavation. UCS can be obtained through the Geotechnical Data Report (GDR), and it is difficult to measure UCS for all tunneling alignment. Therefore, the purpose of this study is to predict UCS by utilizing TBM machine driving data and machine learning technique. Several machine learning techniques were compared to predict UCS, and it was confirmed the stacking model has the most successful prediction performance. TBM machine data and UCS used in the analysis were obtained from the excavation of rock strata with slurry shield TBMs. The data were divided into 8:2 for training and test and pre-processed including feature selection, scaling, and outlier removal. After completing the hyper-parameter tuning, the stacking model was evaluated with the root-mean-square error (RMSE) and the determination coefficient (R²), and it was found to be 5.556 and 0.943, respectively. Based on the results, the sacking models are considered useful in predicting rock strength with TBM excavation data.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.24 no.1
• /
• pp.170-186
• /
• 2019

The marine ecosystem survey investigates and analyzes multi-parameters at various times from various sites. Therefore, it is very difficult to analyze the complex ecological data of multi-items effectively, and it is more difficult to identify the current status and diagnose the problems of ecosystem through data analysis. Therefore, this paper aims to provide an example of interpretation of complex ecological data through analysis of distribution characteristics and outliers of ecological survey data. The main contents of the study are to elucidate the background levels of coastal ecosystem parameters considering the distribution characteristics of data, and to establish ecosystem monitoring indicators and an adaptive management system for the coastal waters in Korean Peninsula. The data used in this paper are based on the coastal ecosystem survey of the National Marine Ecosystem Monitoring Program conducted by the Ministry of Oceans and Fisheries (MOF) and the Korea Marine Environment Management Corporation (KOEM), and the major citations are from year 2015 to 2017. This article is a preliminary study to establish the above processes and the final result will be derived in 2020 when the coastal ecosystem survey is completed three times along the Korean coast.

• Fire Science and Engineering
• /
• v.33 no.3
• /
• pp.1-8
• /
• 2019

The international standard for FT-IR gas analysis of fire effluents in ISO 5660-1 cone calorimeter has been being developed in ISO TC 92. A comparison of the round-robin test of WD 21397 was conducted with six participating laboratories in 2018. The test specimens were PMMA, rigid PU foam board, and PVC flooring. The measurement quantities were the time-to-ignition, peak heat release rate, total heat release, and effective heat of combustion for a cone calorimeter test and peak gas concentration, gas generation, and gas yield for FT-IR gas analysis. No outliers were identified. For the cone calorimeter quantities, the repeatability and reproducibility were 1.5% and 9.8%, respectively. For FT-IR gas analysis, the repeatability and reproducibility was 12.9% and 27.9%, respectively.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.29-39
• /
• 2022

Crack detection plays an important role in the maintenance and protection of steel box girder of bridges. However, since the cracks only occupy an extremely small region of the high-resolution images captured from actual conditions, the existing methods cannot deal with this kind of image effectively. To solve this problem, this paper proposed a novel three-stage method based on deep learning technology and morphology operations. The training set and test set used in this paper are composed of 360 images (4928 × 3264 pixels) in steel girder box. The first stage of the proposed model converted high-resolution images into sub-images by using patch-based method and located the region of cracks by CBAM ResNet-50 model. The Recall reaches 0.95 on the test set. The second stage of our method uses the Attention U-Net model to get the accurate geometric edges of cracks based on results in the first stage. The IoU of the segmentation model implemented in this stage attains 0.48. In the third stage of the model, we remove the wrong-predicted isolated points in the predicted results through dilate operation and outlier elimination algorithm. The IoU of test set ascends to 0.70 after this stage. Ablation experiments are conducted to optimize the parameters and further promote the accuracy of the proposed method. The result shows that: (1) the best patch size of sub-images is 1024 × 1024. (2) the CBAM ResNet-50 and the Attention U-Net achieved the best results in the first and the second stage, respectively. (3) Pre-training the model of the first two stages can improve the IoU by 2.9%. In general, our method is of great significance for crack detection.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2006.04a
• /
• pp.181-185
• /
• 2006

Image co-registration is the process of overlaying two images of the same scene, one of which represents a reference image, while the other is geometrically transformed to the one. In order to improve efficiency and effectiveness of the co-registration approach, the author proposed a pre-qualified area matching algorithm which is composed of feature extraction with canny operator and area matching algorithm with cross correlation coefficient. For refining matching points, outlier detection using studentized residual was used and iteratively removes outliers at the level of three standard deviation. Throughout the pre-qualification and the refining processes, the computation time was significantly improved and the registration accuracy is enhanced. A prototype of the proposed algorithm was implemented and the performance test of 3 Landsat images of Korea showed: (1) average RMSE error of the approach was 0.436 Pixel (2) the average number of matching points was over 38,475 (3) the average processing time was 489 seconds per image with a regular workstation equipped with a 3 GHz Intel Pentium 4 CPU and 1 Gbytes Ram. The proposed approach achieved robustness, full automation, and time efficiency.

• Communications for Statistical Applications and Methods
• /
• v.19 no.1
• /
• pp.183-192
• /
• 2012

This study analyzes the travel behavior for short-term demand forecasting model of KTX. This research suggests the following. First, the outlier criteria is considered to appropriate twice the standard deviation of the traffic. Second, the result of a homogeneity test using ANOVA analysis has been divided into weekdays(Mon Thu and weekends(Fri Sun). Third, a cluster analysis for O/D pairs using trip frequency, traffic averages and th distance between stations was performed.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2008.05a
• /
• pp.2156-2160
• /
• 2008

우리나라 연안의 평균해면이 증가하고 있다는 주장과 고극조위, 저극조위가 증가(또는 변동)하고 있다는 주장이 제기되고 있으나, 연구자가 사용한 자료의 기간 및 분석 방법 등에 차이가 있고, 결측자료(missing data) 및 이상자료(outlier) 등을 처리한 방법이 서로 차이가 있기 때문에 전체적으로 또는 부분적으로 분석결과가 차이를 보일 수 있다. 또한 추세분석에서는 통계적인 신뢰수준에 대한 검정과정 없이 단순하게 선형회귀곡선식을 이용하여 기울기의 부호만으로 증가 감소를 판단하는 경우도 있다. 그러나 추세분석은 최적의 추세곡선을 찾아내는 것 이전에 추세의 유무를 통계적인 신뢰수준을 기준으로 검정하는 것이 필요하다. 본 연구에서는 추세분석의 필수과정인 추세검정(추세가 있는가? 없는가?)을 Mann-Kendall 방법을 이용하여 우리나라 전 연안 조위관측소의 평균해수면 및 고극조위, 저극조위 자료에 대하여 수행하였다. 추세검정 결과를 다음과 같이 도출할 수 있었다. 평균해수면은 95% 유의수준으로 분석에 포함된 전체 30개 검조소 중 대산, 보령, 군산, 목포, 통영, 거문도, 부산, 가덕도, 제주, 서귀포, 속초, 포항, 울산, 울릉도 지점 등 19개 지점이 추세가 있는 것으로 파악되었으며, 고극조위, 저극조위는 각각 15개, 17개 지점이 추세가 있는 것으로 파악되었다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2004.05b
• /
• pp.1103-1106
• /
• 2004

The objective of this study is to induce the design drought rainfall by the methodology of L-moment including testing homogeneity, independence and outlier of the data of annual minimum monthly rainfall in 57 rainfall stations in Korea in terms of consecutive duration for 1, 2, 4, 6, 9 and 12 months. To select appropriate distribution of the data for annual minimum monthy rainfall by rainfall station, the distribution of generalized extreme value (GEV), generalized logistic (GLO) as well as that of generalized pareto (GPA) are applied and the appropriateness of the applied GEV, GLO, and GPA distribution is judged by L-moment ratio diagram and Kolmogorov-Smirnov (K-S) test. As for the annual minimum monthly rainfall measured by rainfall station and that stimulated by Monte Carlo techniques, the parameters of the appropriately selected GEV and GPA distributions are calculated by the methodology of L-moment and the design drought rainfall is induced. Through the comparative analysis of design drought rainfall induced by GEV and GPA distribution by rainfall station, the optimal design drought rainfall by rainfall station is provided.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.1
• /
• pp.33-39
• /
• 2013

In the transformation of response variable in partial linear models outliers can cause a bad effect on estimating the transformation parameter, just as in the linear models. To solve this problem the processes of estimating transformation parameter and detecting outliers are needed, but have difficulties to be performed due to the arbitrariness of the nonparametric function included in the partial linear model. In this study, through the estimation of nonparametric function and outlier detection methods such as a sequential test and a maximum trimmed likelihood estimation, processes for transforming response variable robust to outliers in partial linear models are suggested. The proposed methods are verified and compared their effectiveness by simulation study and examples.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.15 no.5
• /
• pp.687-698
• /
• 2012

LADAR systems can rapidly acquire 3D point clouds by sampling the target surfaces using laser pulses. Such point clouds are widely used for diverse applications such as DSM/DTM generation, forest biomass estimation, target detection, wire avoidance and so on. Many kinds of LADAR systems have been developed with their respective purposes and applications. Particularly, Geiger mode imaging LADAR systems are increasingly utilized since they are energy efficient thank to extremely sensitive detectors incorporated into the systems. The purpose of this research is the performance assessment of a Geiger mode imaging LADAR system based on simulation with the real system parameters. We thus developed a simulation method of such a LADAR system by modeling its geometric, radiometric, optic and electronic aspects. Based on the simulation, we performed the performance assessment of a newly designed system to derive the outlier ratio and false alarm rate expected during its operation in almost real environment with reasonable system parameters. The proposed simulation and performance assessment method will be effectively utilized for system design and optimization, and test data generation.