• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2009.10a
• /
• pp.267-268
• /
• 2009

In the past, the predictions of beach processes and harbor sedimentation were mainly relied on the hydraulic model tests and empirical methods. In recent years, however, as computers have come into wide use, more accurate models have gradually been developed and thus replaced those conventional methods. For prediction of topographical change near the coastal area.

• Korean Journal of Remote Sensing
• /
• v.17 no.4
• /
• pp.345-357
• /
• 2001

This review provides a summary of data assimilation applied to the seas around Korea. Currently the worldwide efforts are devoted to applying advanced assimilation to realistic cases, thanks to improvements in mathematical foundations of assimilation methods and the computing capabilities, and also to the availability of extensive observational data such as from satellites. Over the seas around Korea, however, the latest developments in the advanced assimilation methods have yet to be applied. Thus it would be timely to review the progress in data assimilation over the seas. Firstly, the definition and necessity of data assimilation are described, continued by a brief summary of major assimilation methods. Then a review of past research on the ocean data assimilation in the regional seas around Korea is given and future trends are considered. Special consideration is given to the assimilation of remotely-sensed data.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.2
• /
• pp.128-132
• /
• 2023

Recently, with the development of deep learning technology, research on pedestrian attribute recognition technology using deep neural networks has been actively conducted. Existing pedestrian attribute recognition techniques can be obtained in such a way as global-based, regional-area-based, visual attention-based, sequential prediction-based, and newly designed loss function-based, depending on how pedestrian attributes are detected. It is known that the performance of these pedestrian attribute recognition technologies varies greatly depending on the type of backbone network that constitutes the deep neural networks model. Therefore, in this paper, several backbone networks are applied to the baseline pedestrian attribute recognition model and the performance changes of the model are analyzed. In this paper, the analysis is conducted using Resnet34, Resnet50, Resnet101, Swin-tiny, and Swinv2-tiny, which are representative backbone networks used in the fields of image classification, object detection, etc. Furthermore, this paper analyzes the change in time complexity when inferencing each backbone network using a CPU and a GPU.

• Korea Trade Review
• /
• v.46 no.2
• /
• pp.281-299
• /
• 2021

This paper analyzes the feasibility of using machine learning methods to forecast the employment. The machine learning methods, such as decision tree, artificial neural network, and ensemble models such as random forest and gradient boosting regression tree were used to forecast the employment in Busan regional economy. The following were the main findings of the comparison of their predictive abilities. First, the forecasting power of machine learning methods can predict the employment well. Second, the forecasting values for the employment by decision tree models appeared somewhat differently according to the depth of decision trees. Third, the predictive power of artificial neural network model, however, does not show the high predictive power. Fourth, the ensemble models such as random forest and gradient boosting regression tree model show the higher predictive power. Thus, since the machine learning method can accurately predict the employment, we need to improve the accuracy of forecasting employment with the use of machine learning methods.

• Korean Journal of Soil Science and Fertilizer
• /
• v.35 no.2
• /
• pp.87-92
• /
• 2002

Soil erosion is detrimental to sustain soil productivity in north Korea, since agriculture of this country depends largely upon the slope land in mountainous area. Taking any measure for protection from erosion should be based on prediction of soil loss. Estimation of rainfall factor, R, in north Korea for the Universal Soil Loss Equation was attempted. The monthly precipitation data of the twenty six locations provided by the Korean Meteorological Adminstration were used. From the relationship between II_30 and the July-August precipitation concentration percents, the regional adjustment factor was obtained. The rainfall factor was calculated with the monthly precipitation data and the regional adjustment factor. The annual precipitation in north Korea ranged from 606 to 1,520mm, and the July-August precipitation concentration percents were 34.4 to 53.8. The regional adjustment factor ranged from 0.53 to 1.33 showing lower value in the highland and east coastal region than in the mid mountainous inland and west region. The R-factor value estimated from the monthly precipitation and the regional adjustment factor ranged from 107 to 483, which was lower than average value in south Korea.

• Journal of Korean Society on Water Environment
• /
• v.25 no.3
• /
• pp.441-451
• /
• 2009

To evaluate the soil erosion best management practices, many computer models has been utilized over the years. Among those, the USLE and SWAT models have been widely used. These models estimate the soil erosion from the field using empirically-based USLE/MULSE in it. However, these models are not good enough to estimate soil erosion from highland agricultural watershed where severe storm events are causing soil erosion and muddy water issues at the receiving watersheds. Thus, physically-based WEPP watershed version was applied to a watershed, located at Jawoon-ri, Gangwon with very detailed rainfall data, rather than daily rainfall data. Then it was validated with measured sediment data collected at the sediment settling ponds and through overland flow. In this study, very detailed rainfall data, crop management data, soil data reflecting soil reconditioned for higher crop production were used in the WEPP runs. The $R^2$ and the EI for runoff comparisons were 0.88 and 0.91, respectively. For sediment comparisons, the $R^2$ and the EI values were 0.95 and 0.91. Since the WEPP provides higher accuracies in predicting runoff and sediment yield from the study watershed, various slope scenarios (2%, 3%, 5.5%, 8%, 10%, 13%, 15%, 18%, 20%, 23%, 25%, 28%, 30%) were made and simulated sediment yield values were analyzed to develop appropriate soil erosion management practices. It was found that soil erosion increase linearly with increase in slope of the field in the watershed. However, the soil erosion increases dramatically with the slope of 20% or greater. Therefore special care should be taken for the agricultural field with slope greater than 20%. As shown in this study, the WEPP watershed version is suitable model to predict soil erosion where torrential rainfall events are causing significant amount of soil loss from the field and it can also be used to develop site-specific best management practices.

• Journal of Korea Water Resources Association
• /
• v.34 no.4
• /
• pp.347-356
• /
• 2001

Even though the increase of greenhouse gases such as $CO_2$ is thought to be the main cause for global warming, its impact on global climate has not been revealed clearly in rather quantitative manners. However, researches using Genral Circulation Model(GCM) has shown that the accumulation of greenhouse gases increases the global mean temperature, which in turn impacts on the global water circulation pattern. A climate predictive capability is limited by lack of understanding of the different process governing the climate and hydrologic systems. The prediction of the complex responses of the fully coupled climate and hydrologic systems can be achieved only through development of models that adequately describe the relevant process at a wide range of spatial and temporal scales. These models must ultimately couple the atmospheres, oceans, and lad and will involve many submodels that properly represent the individual processes at work within the coupled components of systems. So far, there are no climate and related hydrologic models except local rainfall-runoff models in Korea. The purpose of this research is to predict the change of temperature in Korean Peninsula using regional scale model(IRSHAM96 model) and GCM data obtained from the increasing scenarios of $CO_2$ Korean Peninsula increased by $2.5^{\circ}C$ and the duration of Winter in $lxCO_2$ condition would be shorter the $2xCo_2$ condition due to global warming.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.31-38
• /
• 2022

The article highlights the educational potential of information and communication technologies in the study of philological disciplines in higher education institutions. The study aims to analyze the didactic potential of ICT in the study of philological disciplines, as well as to check the scientific hypothesis that the use of ICT in HEIs in the study of philological disciplines will intensify and enhance the effectiveness of the learning process. To confirm the validity of the hypothesis, experimental testing was carried out and the results are illustrated in the article. The above-mentioned goal of the study determined the use of theoretical and empirical methods: analysis, synthesis, generalization, and systematization of pedagogical and scientific-methodological literature to clarify the state of research problem development and to identify pedagogical foundations on which the process of ICT use is based, comparison and prediction; questioning and testing of educational process participants to understand the effectiveness of ICT use in their training in HEIs. The research results showed positive changes in all analyzed criteria in the experimental group, which is due to the introduction of additional ICT tools into the educational process of the mentioned group. The scientific novelty of the study consists in highlighting the main characteristics and didactic functions of ICT in the learning process of philological students; in covering the classification of ICT, ICT tools, and typology of training sessions using ICT in the study of philological disciplines. In the conclusion it is summarized that the introduction of modern ICT in the educational process allows intensifying the learning process, implementation of a variety of ideas, increases the pace of classes and material assimilation, influencing the motivation for learning, increases the amount of independent work of students.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.20 no.1
• /
• pp.1-15
• /
• 2015

Impacts of Sea Surface Temperature (SST) assimilation to the prediction of upper ocean temperature is investigated by using a regional ocean forecasting system, in which 3-dimensional optimal interpolation is applied. In the present study, Sea Surface Temperature and Sea Ice Analysis (OSTIA) dataset is adopted for the daily SST assimilation. This study mainly compares two experimental results with (Exp. DA) and without data assimilation (Exp. NoDA). When comparing both results with OSTIA SST data during Sept. 2011, Exp. NoDA shows Root Mean Square Error (RMSE) of about $1.5^{\circ}C$ at 24, 48, 72 forecast hour. On the other hand, Exp. DA yields the relatively lower RMSE of below $0.8^{\circ}C$ at all forecast hour. In particular, RMSE from Exp. DA reaches $0.57^{\circ}C$ at 24 forecast hour, indicating that the assimilation of daily SST (i.e., OSTIA) improves the performance in the early SST prediction. Furthermore, reduction ratio of RMSE in the Exp. DA reaches over 60% in the Yellow and East seas. In order to examine impacts in the shallow costal region, the SST measured by eight moored buoys around Korean peninsula is compared with both experiments. Exp. DA reveals reduction ratio of RMSE over 70% in all season except for summer, showing the contribution of OSTIA assimilation to the short-range prediction in the coastal region. In addition, the effect of SST assimilation in the upper ocean temperature is examined by the comparison with Argo data in the East Sea. The comparison shows that RMSE from Exp. DA is reduced by $1.5^{\circ}C$ up to 100 m depth in winter where vertical mixing is strong. Thus, SST assimilation is found to be efficient also in the upper ocean prediction. However, the temperature below the mixed layer in winter reveals larger difference in Exp. DA, implying that SST assimilation has still a limitation to the prediction of ocean interior.

• Journal of the Korean earth science society
• /
• v.28 no.7
• /
• pp.857-870
• /
• 2007

The structure and evolution of a thunderstorm outflow in two dimensions with no environmental wind are investigated using a cloud-resolving model with explicit liquid-ice phase microphysical processes (ARPS: Advanced Regional Prediction System). The turbulence structure of the outflow is explicitly resolved with a high-resolution grid size of 50m. The simulated single-cell storm and its associated Kelvin-Helmholtz (KH) billows are found to have the lift stages of development maturity, and decay. The secondary pulsation and splitting of convective cells resulted from interactions between cloud dynamics and microphysics are observed. The cooled downdrafts caused by the evaporation of rain and hail in the relatively dry lower atmosphere result in thunderstorm cold-air outflow. The outflow head propagates with almost constant speed. The KH billows formed by the KH instability cause turbulence mixing from the top of the outflow and control the structure of the outflow. Ihe KH billows are initiated at the outflow head, and pow and decay as moving rearward relative to the gust front. The numerical simulation results of the ratio of the horizontal wavelength of the fastest growing perturbation to the critical shear-layer depth and the ratio of the horizontal wavelength of the billow to its maximum amplitude are matched well with the results of other studies.