• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.32 no.6
• /
• pp.373-383
• /
• 2020

In this study we established an operational storm-surge system for the northwestern pacific ocean, based on the NEMO (Nucleus for European Modeling of the Ocean). The system consists of the tide and the surge models. For more accurate storm surge prediction, it can be completed not only by applying more precise depth data, but also by optimal parameterization at the boundaries of the atmosphere and ocean. To this end, we conducted several sensitivity experiments related to the application of available bathymetry data, ocean bottom friction coefficient, and wind stress and air pressure on the ocean surface during August~September 2018 and the case of typhoon SOULIK. The results of comparison and verification are presented here, and they are compared with POM (Princeton Ocean Model) based Regional Tide Surge forecasting Model (RTSM). The results showed that the RTSM_NEMO model had a 29% and 20% decrease in Bias and RMSE respectively compared to the RTSM_POM model, and that the RTSM_NEMO model had a lower overall error than the RTSM_POM model for the case of typhoon SOULIK.

• Applied Chemistry for Engineering
• /
• v.32 no.1
• /
• pp.61-67
• /
• 2021

In this study, the adsorption decolorization process of sea buckthorn oil was carried out to verify the possibility of the sea buckthorn oil as a natural UV absorber. The optimization was carried out by using the central composite design model-response surface methodology (CCD-RSM). The response values of CCD-RSM were selected as the decolorization effect through the process, acid value after decolorization, and UV absorbance of the decolored oil at 290nm. The amount of adsorbent, temperature and time were selected as the process variables for the experiments. According to the results of CCD-RSM, the results of optimization were all consistent. The optimal conditions, which satisfy CCD-RSM statically and mathematically, were 4.32 wt.%, 134.90 ℃, and 19.8 min for the amount of adsorbent, temperature and time, respectively. The estimated response values expected under these optimal conditions values were 94.78%, 2.08 mg/g KOH, and 2.91 for the decolorization effect, acid value and UV absorbance at 290 nm, respectively. Also the average error from actual experiment for verifying the conclusions was smaller than 2%. Therefore, it was confirmed that the application of CCD-RSM to the adsorption decolorization process of sea buckthorn oil showed a very high level of acceptable results and that the sea buckthorn oil has high possibility to be used as a natural UV absorber.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.35 no.3
• /
• pp.167-174
• /
• 2022

This study investigates the behavior of a jointless bridge that integrates superstructure and abutment without an expansion joint. Based on the sensitivity analyses conducted in previous studies, a shell-based model was determined to be the most suitable numerical analysis model for jointless bridges due to the similarity of the model's results compared with the obtained displacement shape, which was influenced by relative errors, precision, and practical aspects. Accordingly, the behavior of a jointless bridge was analyzed at various wall depths using shell element-based and solid element models. In addition, the results of MIDAS Civil and ABAQUS analysis programs were compared. In the case of semi-integrated bridges (A and B), the displacement decreased as the wall depth increased due to the ground reaction force in Case 1 under a linear spring condition and +30℃. In the case where temperature was -30℃, the change in displacement was small because the ground reaction did not occur. As for bridge C (a fully integrated alternating bridge) and bridge D (an integrated chest wall alternating bridge), the displacement decreased as the wall depth increased at both +30 and -30℃ due to pile resistance. As for the comparison between the analysis programs used, the relative error in Case 1 was small, whereas a significant difference in Case 2 was observed. The foregoing variation is possibly due to the difference in the application of the nonlinear spring in the programs.

• Journal of Internet Computing and Services
• /
• v.23 no.1
• /
• pp.77-86
• /
• 2022

The Republic of Korea is a country in which coastal surveillance is an imperative national task as it is surrounded by seas on three sides under the confrontation between South and North Korea. However, due to Defense Reform 2.0, the number of R/D (Radar) operating personnel has decreased, and the period of service has also been shortened. Moreover, there is always a possibility that a human error will occur. This paper presents specific guidelines for developing an AI learning model for the intelligent coastal surveillance system. We present a three-step strategy to realize the guidelines. The first stage is a typical stage of building an AI learning model, including data collection, storage, filtering, purification, and data transformation. In the second stage, R/D signal analysis is first performed. Subsequently, AI learning model development for classifying real and false images, coastal area analysis, and vulnerable area/time analysis are performed. In the final stage, validation, visualization, and demonstration of the AI learning model are performed. Through this research, the first achievement of making the existing weapon system intelligent by applying the application of AI technology was achieved.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.7
• /
• pp.49-55
• /
• 2022

In this paper, we propose an obstacle detection method that can operate robustly even in external environmental factors such as weather. In particular, we propose an obstacle detection system that can accurately inform dangerous situations in AR through DB-based feature matching and RANSAC-based multiplane method. Since the approach to detecting obstacles based on images obtained by RGB cameras relies on images, the feature detection according to lighting is inaccurate, and it becomes difficult to detect obstacles because they are affected by lighting, natural light, or weather. In addition, it causes a large error in detecting obstacles on a number of planes generated due to complex terrain. To alleviate this problem, this paper efficiently and accurately detects obstacles regardless of lighting through DB-based feature matching. In addition, a criterion for classifying feature points is newly calculated by normalizing multiple planes to a single plane through RANSAC. As a result, the proposed method can efficiently detect obstacles regardless of lighting, natural light, and weather, and it is expected that it can be used to secure user safety because it can reliably detect surfaces in high and low or other terrains. In the proposed method, most of the experimental results on mobile devices reliably recognized indoor/outdoor obstacles.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.10 no.3
• /
• pp.351-357
• /
• 2022

In this study, offshore modular pier system using the ultra-high performance concrete was developed for the offshore construction environment. For the application of offshore modular pier system, the design, fabrication, and construction performance evaluation were performed using ultra-high performance concrete a compressive strength 120 MPa or more and a direct tensile strength 7 MPa or more. For offshore piers previously constructed with precast concrete, it was intended to verify the idea and possibility of solving errors due to position or vertical deformation during the driving of the foundation pile part during the construction stage. Furthermore, a offshore modular pier system was fabricated with ultra-high performance concrete for the construction performance evaluation. The results showed that a offshore modular pier system secured about 9 % of sectional performance of load bearing capacity under ultimate load conditions. If the offshore modular pier system developed through this study is utilized in the future, it is judged that competitiveness due to sufficient durability and constructability can be secured.

• Journal of the Korean Society of Radiology
• /
• v.16 no.5
• /
• pp.585-594
• /
• 2022

The detector for digital radiography testing, which is currently mainly used, consists of a detector with a flat structure, making it impossible to fully adhere to the digital radiography testing of the test object with curvature. In this study, a curved panel detector capable of adhering to curvature was fabricated to improve the quality of the digital image during the digital radiography testing of piping welds at industrial sites, and digital radiography images using flat and curved panel detectors were obtained for 6in pipes with different nominal thickness. As a result of the experiment, it was confirmed that the flat panel detector does not fully adhere to the pipe, resulting in a gap between the outer part of the pipe and the detector, resulting in a difference in the unsharpness and diffusion of the digital image. On the other hand, it was confirmed that the curved panel detector minimizes the gap between the pipe outer part and the detector, so that digital image diffusion is less than that of the flat panel detector. The higher the confidence of the image, the lower the quality and error in reading, so it is believed that higher quality images can be obtained than conventional flat panel detectors when using detectors that can be closely attached to the inspection object.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.5
• /
• pp.537-542
• /
• 2021

This paper improves the possibility of recognizing fast-moving objects through the YOLO (You Only Look Once) deep learning recognition model in an application environment for object recognition in images. The purpose was to study the method of collecting semantic data through processing. In the recognition model, the moving object recognition error was identified as unrecognized because of the difference between the frame rate of the camera and the moving speed of the object and a misrecognition due to the existence of a similar object in an environment adjacent to the object. To minimize the recognition errors by compensating for errors, such as unrecognized and misrecognized objects through the proposed data collection method, and applying vision processing technology for the causes of errors that may occur in images acquired for sports (tennis games) that can represent real similar environments. The effectiveness of effective secondary data collection was improved by research on methods and processing structures. Therefore, by applying the data collection method proposed in this study, ordinary people can collect and manage data to improve their health and athletic performance in the sports and health industry through the simple shooting of a smart-phone camera.

• 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.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.4
• /
• pp.313-323
• /
• 2021

The purpose of this study is to propose rules that can identify the speaker referred by the speaker directive in the text for the realization of a machine learning-based virtual character using a literary text. Through previous studies, we found that when applying literary texts to machine learning, the machine did not properly discriminate the speaker without any specific rules for the analysis of speaker directives such as other names, nicknames, pronouns, and so on. As a way to solve this problem, this study proposes 'nine rules for finding a speaker indicated by speaker directives (including pronouns)': location, distance, pronouns, preparatory subject/preparatory object, quotations, number of speakers, non-characters directives, word compound form, dispersion of speaker names. In order to utilize characters within a literary text as virtual ones, the learning text must be presented in a machine-comprehensible way. We expect that the rules suggested in this study will reduce trial and error that may occur when using literary texts for machine learning, and enable smooth learning to produce qualitatively excellent learning results.