• Korean Journal of Remote Sensing
• /
• v.36 no.5_4
• /
• pp.1179-1194
• /
• 2020

This study investigates the feasibility of three algorithms, K-Nearest Neighbors (K-NN), Random Forest (RF) and Neural Network (NN), for estimating the air temperature of an unobserved area where the weather station is not installed. The satellite image were obtained from Landsat-8 and MODIS Aqua/Terra acquired in 2019, and the meteorological ground weather data were from AWS/ASOS data of Korea Meteorological Administration and Korea Forest Service. In addition, in order to improve the estimation accuracy, a digital surface model, solar radiation, aspect and slope were used. The accuracy assessment of machine learning methods was performed by calculating the statistics of R² (determination coefficient) and Root Mean Square Error (RMSE) through 10-fold cross-validation and the estimated values were compared for each target area. As a result, the neural network algorithm showed the most stable result among the three algorithms with R² = 0.805 and RMSE = 0.508. The neural network algorithm was applied to each data set on Landsat imagery scene. It was possible to generate an mean air temperature map from June to September 2019 and confirmed that detailed air temperature information could be estimated. The result is expected to be utilized for national disaster safety management such as heat wave response policies and heat island mitigation research.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1032-1032
• /
• 2001

Artificial Neural Network (ANN) calibration techniques have been used commercially for agricultural applications since the mid-nineties. Global models, based on transmission data from 850 to 1050 nm, are used routinely to measure protein and moisture in wheat and barley and also moisture in triticale, rye, and oats. These models are currently used commercially in approx. 15 countries throughout the world. Results concerning earlier European ANN models are being published elsewhere. Some of the findings from that study will be discussed here. ANN models have also been developed for coarsely ground samples of compound feed and feed ingredients, again measured in transmission mode from 850 to 1050 nm. The performance of models for pig- and poultry feed will be discussed briefly. These models were developed from a very large data set (more than 20,000 records), and cover a very broad range of finished products. The prediction curves are linear over the entire range for protein, fat moisture, fibre, and starch (measured only on poultry feed), and accuracy is in line with the performance of smaller models based on Partial Least Squares (PLS). A simple bias adjustment is sufficient for calibration transfer across instruments. Recently, we have investigated the possible use of ANN for a different type of NIR spectrometer, based on reflectance data from 1100 to 2500 nm. In one study, based on data for protein, fat, and moisture measured on unground compound feed samples, dedicated ANN models for specific product classes (cattle feed, pig feed, broiler feed, and layers feed) gave moderately better Standard Errors of Prediction (SEP) compared to modified PLS (MPLS). However, if the four product classes were combined into one general calibration model, the performance of the ANN model deteriorated only slightly compared to the class-specific models, while the SEP values for the MPLS predictions doubled. Brix value in molasses is a measure of sugar content. Even with a huge dataset, PLS models were not sufficiently accurate for commercial use. In contrast an ANN model based on the same data improved the accuracy considerably and straightened out non-linearity in the prediction plot. The work of Mr. David Funk (GIPSA, U. S. Department of Agriculture) who has studied the influence of various types of spectral distortions on ANN- and PLS models, thereby providing comparative information on the robustness of these models towards instrument differences, will be discussed. This study was based on data from different classes of North American wheat measured in transmission from 850 to 1050 nm. The distortions studied included the effect of absorbance offset pathlength variation, presence of stray light bandwidth, and wavelength stretch and offset (either individually or combined). It was shown that a global ANN model was much less sensitive to most perturbations than class-specific GIPSA PLS calibrations. It is concluded that ANN models based on large data sets offer substantial advantages over PLS models with respect to accuracy, range of materials that can be handled by a single calibration, stability, transferability, and sensitivity to perturbations.

• Journal of the Korean Institute of Gas
• /
• v.9 no.4 s.29
• /
• pp.57-61
• /
• 2005

The objective of paper is to carry out a comparative Quantitative Risk Assessment (QRA) of two KOGAS tank designs using a fault tree methodology, a standard 'Full Containment' tank and a 'Membrane' tank. For the membrane tank, both the initial KOGAS design and 4 modified KOGAS designs have been assessed, giving six separate cases. In this paper, the frequencies of releases are quantified using a fault tree approach. For clarity in the analysis, and to ensure consistency, all cases have been quantified using the same fault tree. Logic within the fault tree is used to select each of the cases. Full quantification of risks is often difficult, owing to a lack of relevant failure data, but the aim of this study has been to be as quantitative as possible, with full transparency of failure information. The most significant general cause of external LNG leaks is predicted to be a seismic event, which has been quantified nominally. 4modified KOGAS desiens to Prevent damage of bottom membrane panels that was shown in preparatory estimation could quantitively confirm safety improvement. According to result, the predicted frequencies of an external LNG leak for the full containment and modified membrane tanks are very similar, failures due to dropped pumps are predicted to be significantly greater for the membrane tank with thickened plate than for the full containment tank.

• Journal of Fisheries and Marine Sciences Education
• /
• v.15 no.1
• /
• pp.47-56
• /
• 2003

Recently with the conclusion of fisheries agreements between Korea and Japan, and between Korea and China, trawlers in korea must operate in smaller fishing ground than before. As a result of this, the possibilities of collisionin increases gradually between trawlers under operation in this area. Authors performed a series of experiments on board to give the information of collision avoiding action to navigators of trawlers. The obtained results are summerized as follows : 1. The greater the rudder angle, the smaller the value of T, but there is no big diffierence in K due to rudder angle. 2. The greatest distance is to be kept by the give way vessel to avoid collision when the crossing course angle is $70^{\circ}{\sim}90^{\circ}$. In this case the safety minimum approaching distance must be more than 5 times of her own length. 3. Risk of collision in crossing is more greater in obtuse situation than in acute one. 4. The navigator of the give way vessel must take an action to avoid collisions outside of the minimum safety approaching distance.

• Korean Journal of Environment and Ecology
• /
• v.23 no.6
• /
• pp.545-552
• /
• 2009

This study was conducted to provide basic information for development of habitat-based conservation strategies of biological diversity in agricultural ecosystem. The carabid beetle assemblages were examined at four kinds of habitats(levee, dike, forest patch remnants and streamside) from three differently stressed areas located in Paltan-myun, Hwaseong city, Korea: agricultural and forest area(site 1), industrial area(site 2), and residential area(site 3). Pitfall trap samplings were carried out 39 times from November 2000 to November 2002. Our study's findings were that the composition of carabid beetle fauna, dominance species, and pattern of carabid beetle assemblage were different among the habitats. The similarity index was highest between two levees in site 2 and 3, and lowest between hillock in site 2 and streamside in site 3, and that among habitats fragmented by road with high traffic was lower than that among any other habitat types. So, we could know that agricultural land use respectively do an important role in diversity conservation and networking. These findings will be used to establish the land use and management plans in the aspects of conservation of biodiversity.

• Tunnel and Underground Space
• /
• v.15 no.4 s.57
• /
• pp.264-274
• /
• 2005

The optimum blasting pattern to excavate a quarry efficiently and economically can be determined based on the minimum production cost which is generally estimated according to rock fragmentation. Therefore it is a critical problem to predict fragment size distribution of blasted rocks over an entire quarry. By comparing various prediction models, it can be ascertained that the result obtained from Kuz-Ram model relatively coincides with that of field measurements. Kuz-Ram model uses the concept of rock factor to signify conditions of rock mass such as block size, rock jointing, strength and others. For the evaluation of total production cost, it is imperative to estimate 3-D spatial distribution of rock factor for the entire quarry. In this study, a sequential indicator simulation technique is adopted for estimation of spatial distribution of rock factor due to its higher reproducibility of spatial variability and distribution models than Kriging methods. Further, this can reduce the uncertainty of predictor using distribution information of sample data The entire quarry is classified into three types of rock mass and optimum blasting pattern is proposed for each type based on 3-D spatial distribution of rock factor. In addition, plane maps of rock factor distribution for each ground levels is provided to estimate production costs for each process and to make a plan for an optimum blasting pattern.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.1
• /
• pp.49-55
• /
• 2017

Computed tomographic angiography (CTA) is widely used in the diagnosis and treatment of coronary artery disease because it shows not only the whole anatomical structure of the cardiovascular three-dimensionally but also provides information on the lesion and type of plaque. However, due to the large size of the image, there is a limitation in manually extracting coronary arteries, and related researches are performed to automatically extract coronary arteries accurately. As the coronary artery originate from the ascending aorta, the ascending aorta and ostium should be detected to extract the coronary tree accurately. In this paper, we propose an automatic segmentation for the ostium as a starting structure of coronary artery in CTA. First, the region of the ascending aorta is initially detected by using Hough circle transform based on the relative position and size of the ascending aorta. Second, the volume of interest is defined to reduce the search range based on the initial area. Third, the refined ascending aorta is segmented by using a two-dimensional geodesic active contour. Finally, the two ostia are detected within the region of the refined ascending aorta. For the evaluation of our method, we measured the Euclidean distance between the result and the ground truths annotated manually by medical experts in 20 CTA images. The experimental results showed that the ostia were accurately detected.

• Journal of the Korea Concrete Institute
• /
• v.19 no.5
• /
• pp.529-537
• /
• 2007

The purpose of this study is to discuss how strength and ductility of each system in low-rise reinforced concrete buildings composed of extremely brittle, shear and flexural failure lateral-load resisting systems have influence on seismic capacities of the overall system, which is based on nonlinear seismic response analyses of single-degree-of-freedom structural systems. In order to simulate the triple lateral-load resisting system, structures are idealized as a parallel combination of two modified origin-oriented hysteretic models and a degrading trilinear hysteretic model that fail primarily in extremely brittle, shear and flexure, respectively. Stiffness properties of three models are varied in terms of story shear coefficients, and structures are subjected to various ground motion components. By analyzing these systems, interaction curves of demand strengths of the triple system for various levels of ductility factors are finally derived for practical purposes. The result indicates that demand strength levels derived can be used as a basic information for seismic evaluation and design criteria of low-rise reinforced concrete buildings having the triple lateral-load resisting system.

• Tunnel and Underground Space
• /
• v.28 no.3
• /
• pp.258-276
• /
• 2018

The accurate and quantitative ground information on the hydraulic conductivity characteristics of rock mass is one of the key factors for evaluation of the hydro-geological behaviour of rock mass around an excavated opening under high water pressure. For tunnel and rock structures in seabed, where the sea acts as an infinite source of water, its importance become greater with increasing construction depth below sea level. In this study, to improve the problems related with poor system configuration and incorrect data acquisition of previous hydraulic packer testing equipment, we newly developed an integrated main frame and 30 bar level waterproof downhole sonde apparatus, which were optimized for deep hydraulic packer test in seabed rock mass. Integration of individual test equipment into one frame allows safe and efficient field testing work on a narrow offshore drilling platform. For the integrated type main frame, it is possible to make precise stepwise control of downhole net injection pressure at intervals of $2.0kg_f/cm^2$ or less with dual hydraulic oil volume controller. To ensure the system performance and the operational stability of the prototype mainframe and downhole sonde apparatus, the field feasibility tests were completed in two research boreholes, and using the developed apparatus, the REV(Representative Elementary Volume) scale deep hydraulic packer tests were successfully carried out at a borehole located in the basalt region, Jeju. In this paper, the characteristics of the new testing apparatus are briefly introduced and also some results from the laboratory and in-situ performance tests are shown.

• Korean Journal of Remote Sensing
• /
• v.29 no.2
• /
• pp.235-241
• /
• 2013

$NO_2$ vertical column densities were retrieved via ground based Multi-Axis Differential Optical Absorption Spectroscopy (MAX-DOAS) measurements for the first time for 6 months over the spring season in 2007 and 2008 in Seoul, one the megacities in the Northeast Asia. The retrieved $NO_2$ vertical column densities were compared with those obtained from space borneOzone Monitoring Instrument (OMI). Over the entire measurement period, the $NO_2$ vertical column densities measured by MAX-DOAS ranged from $1.0{\times}10^{15}molec{\cdot}cm^{-2}$ to $6.0{\times}10^{16}molec{\cdot}cm^{-2}$ while those obtained by OMI ranged $1.0{\times}10^{15}molec{\cdot}cm^{-2}$ to $7.0{\times}10^{16}molec{\cdot}cm^{-2}$. The correlation coefficient between $NO_2$ vertical column densities obtained from MAX-DOAS and OMI is 0.73 for the entire measurement period whereas the correlation coefficient of 0.85 is found for the dates under the clear sky condition. The cloudy condition is thought to play a major role in increase in uncertainty of the retrieved OMI $NO_2$ vertical column densities since air mass factor may induce high uncertainty due to the lack of cloud and aerosol vertical distribution information.