• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.340-341
• /
• 2021

In this paper, Aesthetic Measure measurements were performed on user images. Aesthetic Measure refers to the sensibility that our sensory organs are stimulated from outside to produce sensations or perceptions. Using this Aesthetic Measure, the problem of color harmony and disharmony treated as emotion was calculated numerically.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.497-499
• /
• 2020

자율주행 차량이 많아지고 차량의 ECU가 고도화되면서 정확한 차량의 데이터를 획득하고 분석하여 활용하는 것이 중요해지고 있다. 현재에는 내연 기관 차량의 ECU 데이터를 얻기 위해서 OBDII 포트(규격)에 기반한 CAN동선을 주로 이용하고 있다. 하지만 OBDII 규격을 통해서 연비와 같은 중요한 차량 정보를 얻는 경우, 변환식 (MAF 센서(흡입 공기량 센서)와 공기/연료 비율을 이용)의 오차 범위가 커서 데이터의 정확도가 낮다. 본 연구에서는 머신 러닝 기법 중에 하나인 회귀 기법을 통해서 기존의 계산보디 더 정확한 연비를 구할 수 있는 모델을 개발하였다. 이러한 모델 개발을 통하여 차량의 RAW 데이터를 기반으로 필요한 차량 데이터를 정확하게 구할 수 있게 되었으며 20회가 넘는 실 도로주행을 통해서 본 모델의 정확도를 검증하였다.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.6
• /
• pp.883-889
• /
• 2021

The South Korean fishing industry is experiencing a rapid growth owing to an increase in its leisure-fishing population. Consequently, fishing boats weighing 9-10 [ton] have also been increasing. Current fishing boats operate their essential equipment by switching their engines with batteries to reduce the cost of gas and engine noise. However, stranding incidents have been increasingly recorded annually, in which boats fail to start owing to discharged batteries, and these incidents can lead to serious casualties. This study proposes the installation of a solar auxiliary power system to safeguard fishing boats, particularly those weighing between 9-10 [ton]. The feasibility of securing space for the solar auxiliary power of boats under consideration was verified. To examine the application of solar power, this study calculates the load necessary to operate it for fishing and models such a system using an electricity analysis program The modeled system, which applies the monthly horizontal solar insolation, validated the adoption of a solar auxiliary power in fishing boats.

• The Korean Journal of Archival Studies
• /
• no.32
• /
• pp.177-217
• /
• 2012

The National Archives of Korea(NAK) has a mission to ingest large-scaled digital records and information from a number of different government agencies annually from 2015. There are important issues related to the digital records and information transfer between NAK and agencies, and one of them is how to configure deployment of digital repositories for the archives management systems. The purpose of this paper is to offer the way to design it by examining the checkpoints through the whole life cycle of digital records and information in the archives management systems and calculating the amount of ingested digital records and information to the systems in 2015 and deploying the digital repositories configured according to the amount the records and information. Firstly, this paper suggests that the archives management systems in NAK should be considered and examined into at least three different parts called Ingest tier, Preservation tier and Access tier in aspects to the characteristics of the flow and process of the digital records and information. Secondly, as a results of the calculation the amount of the digital records and information ingested to the archives management systems in 2015 is sum up to around 2.5 Tera bytes. This research draws several requirements related to the large-scaled data and bulk operations which should be satisfied by the database or database management system implemented on to the archives management systems. Thirdly, this paper configures digital repositories deployment according to the characteristics of the three tiers respectively. This research triggers discussion in depth and gives specific clues about how to design the digital repositories in the archives management systems for preparing the year of 2015.

• Progress in Medical Physics
• /
• v.24 no.1
• /
• pp.48-53
• /
• 2013

Monte Carlo method has been known as the most accurate method for calculating absorbed dose in the human body, and an anthropomorphic phantom has been mainly used as a method of simulating internal organs for using such a calculation method. However, various efforts are made to extract data on several internal organs in the human body directly from CT DICOM files in recent Monte Carlo calculation using Geant4 code and to use by converting them into the geometry necessary for simulation. Such a function makes it possible to calculate the internal absorbed dose accurately while duplicating the actual human anatomical structure. Thus, this study calculated the absorbed dose in the human body by using Geant4 associating with DICOM files, and aimed to confirm the usefulness by compare the result with the measured dose using a Gafchromic EBT2 film. This study compared the dose calculated using simulation and the measured dose in beam central axis using the EBT2 film. The results showed that the range of difference was an average of 3.75% except for a build-up region, in which the dose rapidly changed from skin surface to the depth of maximum dose. In addition, this study made it easy to confirm the target absorbed dose by internal organ and organ through the output of the calculated value of dose by CT slice and the dose value of each voxel in each slice. Thus, the method that outputs dose value by slice and voxel through the use of CT DICOM, which is actual image data of human body, instead of the anthropomorphic phantom enables accurate dose calculations of various regions. Therefore, it is considered that it will be useful for dose calculation of radiotherapy planning system in the future. Moreover, it is applicable for currently-used several energy ranges in current use, so it is considered that it will be effectively used in order to check the radiation absorbed dose in the human body.

• Journal of health informatics and statistics
• /
• v.41 no.1
• /
• pp.49-56
• /
• 2016

Objectives: Carotid intima-media thickness (CIMT) and the presence of carotid artery plaque are widely used as preclinical markers of atherosclerosis. Due to operator dependency in measuring CIMT, it is important to evaluate the reliability of measuring CIMT and plaque between centers in a multicenter study. The purpose of this study is to evaluate the inter-rater reliability of CIMT and plaque presence among three clinical centers of the Cardiovascular and Metabolic Disease Etiology Research Center (CMERC). Methods: Twenty people without known cardiovascular disease (age 37-64) were enrolled during 2014-2015, and their left and right carotid arteries were examined repeatedly with ultrasonography for CIMT measurements at three clinical centers according to a predetermined protocol. Maximum and mean values of CIMT at distal common carotid artery were recorded. Plaque presence at a carotid artery was checked by an operator. The reliability of CIMT and carotid plaque presence was assessed using an intraclass correlation coefficient (ICC) and kappa statistics, respectively. Results: Calculated ICC was 0.647 (95% CI: 0.487-0.779) for maximum CIMT, and 0.758 (95% CI: 0.632- 0.854) for mean CIMT. In Bland Altman plot, most observed values were distributed within mean difference ${\pm}1.96$ SD ranges. Kappa statistics of plaque presence between two centers were 0.304 (center 1 and 2), 0.507 (center 1 and 3), and 0.606 (center 2 and 3), respectively, while Fleiss kappa for overall agreement was 0.445. Conclusions: The inter-rater reliability of CIMT measurements among three clinical centers turned out to be high, and the agreement of measuring carotid plaque presence was fair.

• Korean Journal of Clinical Pharmacy
• /
• v.21 no.2
• /
• pp.106-114
• /
• 2011

While multiple medication is an important global medication safety issue, ununified concomitant medication by multiple prescriptions may cause more severe problems by the fact that those are neither intended nor watched. This could cause therapy duplication and severe drug interaction and etc. Korean Government made region wide scale programs twice to detect such problems and give warnings to pharmacists and doctors through the internet system in 2009-2010, which are called Drug Use Review Services Pilot Project. This study is an analysis and comparison of the results of the two DUR pilot projects. There were 5.0 and 4.2 cases of severe drug interaction by the concomitant medication of multiple doctors' prescriptions per 10 thousand prescriptions, while only 0.37 and 0 cases by the medication of same doctor's prescription(s). There were 426 and 381 cases of drug duplication by the concomitant medication of multiple doctors' prescriptions per 10 thousand cases, while only 197 and 23 cases by medication of same doctors' prescription(s). Doctors' participation to those projects improved at Jejudo the later one compared to Goyangsi the former, which means the efforts of them to make less prescription problems succeeded to decrease the number of cases caused from same doctor's prescription. But they could not decrease the number of problem cases caused from concomitant medication by multiple doctors prescriptions enough. The findings support the issue of strengthening and widening the project nation wide and the issue of recommending the patients to designate their own pharmacy, which can provide them counseling for unified and safety controlled medication.

• Journal of the Korean Institute of Gas
• /
• v.25 no.4
• /
• pp.36-42
• /
• 2021

When the landfill gas generated at the landfill site is released into the atmosphere, methane gas with a high global warming potential is emitted, which adversely affects climate change. When methane contained in landfill gas is used as fuel for internal combustion engines and burned to generate electricity, it is emitted into the atmosphere in the form of carbon dioxide, which can contribute to lowering the global warming potential. Therefore, in order to use the landfill gas as fuel for power generation using an internal combustion engine, it is important to increase the thermal efficiency of the engine. Thus, it is necessary to use a fuel supply system in which gas is injected using an electronically controlled injector at an intake port for each cylinder rather than a fuel supply technology using the conventional mixer technology. In order to use the electronically controlled gas injection method, it is important to accurately measure the mass flow rate according to the conditions of using landfill gas. For this, a study was conducted to measure the injection amount and calculate them in order for the intake port gas injection of landfill gas.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.6
• /
• pp.1054-1062
• /
• 2022

The population of Korea's solar salt-producing regions is rapidly aging, resulting in a decrease in the number of productive workers. In solar salt production, salt collection is the most labor-intensive operation because existing salt collection vehicles require human operators. Therefore, we intend to develop an unmanned solar salt collection vehicle to reduce manpower requirements. The unmanned solar salt collection vehicle is designed to identify the salt collection status and location in the salt plate via color detection, the color detection performance is a crucial consideration. Therefore, an image processing algorithm was developed to improve color detection performance. The algorithm generates an around-view image by using resizing, rotation, and perspective transformation of the input image, set the RoI to transform only the corresponding area to the HSV color model, and detects the color area through an AND operation. The detected color area was expanded and noise removed using morphological operations, and the area of the detection region was calculated using contour and image moment. The calculated area is compared with the set area to determine the location case of the collection vehicle within the salt plate. The performance was evaluated by comparing the calculated area of the final detected color to which the algorithm was applied and the area of the detected color in each step of the algorithm. It was confirmed that the color detection performance is improved by at least 25-99% for salt detection, at least 44-68% for red color, and an average of 7% for blue and an average of 15% for green. The proposed approach is well-suited to the operation of unmanned solar salt collection vehicles.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.241-265
• /
• 2023

A corporate insolvency prediction model serves as a vital tool for objectively monitoring the financial condition of companies. It enables timely warnings, facilitates responsive actions, and supports the formulation of effective management strategies to mitigate bankruptcy risks and enhance performance. Investors and financial institutions utilize default prediction models to minimize financial losses. As the interest in utilizing artificial intelligence (AI) technology for corporate insolvency prediction grows, extensive research has been conducted in this domain. However, there is an increasing demand for explainable AI models in corporate insolvency prediction, emphasizing interpretability and reliability. The SHAP (SHapley Additive exPlanations) technique has gained significant popularity and has demonstrated strong performance in various applications. Nonetheless, it has limitations such as computational cost, processing time, and scalability concerns based on the number of variables. This study introduces a novel approach to variable selection that reduces the number of variables by averaging SHAP values from bootstrapped data subsets instead of using the entire dataset. This technique aims to improve computational efficiency while maintaining excellent predictive performance. To obtain classification results, we aim to train random forest, XGBoost, and C5.0 models using carefully selected variables with high interpretability. The classification accuracy of the ensemble model, generated through soft voting as the goal of high-performance model design, is compared with the individual models. The study leverages data from 1,698 Korean light industrial companies and employs bootstrapping to create distinct data groups. Logistic Regression is employed to calculate SHAP values for each data group, and their averages are computed to derive the final SHAP values. The proposed model enhances interpretability and aims to achieve superior predictive performance.