• Journal of the Korea Institute of Building Construction
• /
• v.23 no.4
• /
• pp.441-452
• /
• 2023

Buildings that have been long neglected can suffer severe durability reduction due to factors such as rebar rust and concrete quality deterioration resulting from exposure to outside air. Furthermore, the issues associated with these suspended buildings, including safety accidents, social crimes, and environmental pollution, are becoming increasingly serious. This study investigates the current status of these buildings in the Jeju area, identifies the problems, and examines the durability of the structure in a specific location to assess the possibility of future use. Aesthetic surveys(visual and slope inspections) as well as non-destructive tests(compressive strength tests, neutralization tests, and rebar detection tests) were conducted to assess durability. The analysis revealed that the structure maintained satisfactory durability and the building's condition was good in comparison to the years of neglect.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.312-320
• /
• 2023

Recently, there has been an increasing attempt to replace defect detection inspections in the manufacturing industry using deep learning techniques. However, obtaining substantial high-quality labeled data to enhance the performance of deep learning models entails economic and temporal constraints. As a solution for this problem, semi-supervised learning, using a limited amount of labeled data, has been gaining traction. This study assesses the effectiveness of semi-supervised learning in the defect detection process of manufacturing using the MixMatch algorithm. The MixMatch algorithm incorporates three dominant paradigms in the semi-supervised field: Consistency regularization, Entropy minimization, and Generic regularization. The performance of semi-supervised learning based on the MixMatch algorithm was compared with that of supervised learning using defect image data from the metal casting process. For the experiments, the ratio of labeled data was adjusted to 5%, 10%, 25%, and 50% of the total data. At a labeled data ratio of 5%, semi-supervised learning achieved a classification accuracy of 90.19%, outperforming supervised learning by approximately 22%p. At a 10% ratio, it surpassed supervised learning by around 8%p, achieving a 92.89% accuracy. These results demonstrate that semi-supervised learning can achieve significant outcomes even with a very limited amount of labeled data, suggesting its invaluable application in real-world research and industrial settings where labeled data is limited.

• Journal of the Korea Safety Management & Science
• /
• v.26 no.3
• /
• pp.1-9
• /
• 2024

This study aims to develop a regression model using data from the Ammunition Stockpile Reliability Program (ASRP) to predict the shelf life of 81mm mortar high-explosive shells. Ammunition is a single-use item that is discarded after use, and its quality is managed through sampling inspections. In particular, shelf life is closely related to the performance of the propellant. This research seeks to predict the shelf life of ammunition using a regression model. The experiment was conducted using 107 ASRP data points. The dependent variable was 'Storage Period', while the independent variables were 'Mean Ammunition Velocity,' 'Standard Deviation of Mean Ammunition Velocity,' and 'Stabilizer'. The explanatory power of the regression model was an R-squared value of 0.662. The results indicated that it takes approximately 55 years for the storage grade to change from A to C and about 62 years to change from C to D. The proposed model enhances the reliability of ammunition management, prevents unnecessary disposal, and contributes to the efficient use of defense resources. However, the model's explanatory power is somewhat limited due to the small dataset. Future research is expected to improve the model with additional data collection. Expanding the research to other types of ammunition may further aid in improving the military's ammunition management system.

• Analytical Science and Technology
• /
• v.26 no.1
• /
• pp.99-105
• /
• 2013

To identify oxidative hair dyes in hair-coloring products, the thin-layer chromatography (TLC) screening method was used in accordance with Korean Quasi-drug Codex. However, the TLC method is not reliable when there are very small amount of materials to be tested or when $R_f$ values of several components are similar. In this study, Ultra Performance Liquid Chromatography (UPLC) with a rapid sample preparation method was developed for the reliable and sensitive identification of active components contained in oxidative hair-coloring products. Hexane-distilled water was used for the extraction of active components contained in the products prior to UPLC analysis. The limit of detection of active components was 6.7-77.9 ${\mu}g/L$, and the limit of quantitation was 22.3-259.7 ${\mu}g/L$. Except for ${\alpha}$-naphthol, the range of recovery ratio was 96.2-101.5%. From this study, we demonstrated that oxidative active hair-coloring components can easily be analyzed by rapid extraction method followed by UPLC analysis.

• Journal of the Korean Society of Radiology
• /
• v.13 no.4
• /
• pp.605-611
• /
• 2019

The purpose of this study is to manufacture a multi-function device (MFD) which can be applied to various types of weight-bearing view of the lower leg, and to compare the results with the images from the existing weight-bearing platforms (WBPs), thereby suggesting a clinical utilization. The MFD was manufactured, by considering the minimum adjustable heights of the platform for weight-bearing foot/ankle, platform for hindfoot alignment view, and X-ray tube of the X-ray device. A foot/ankle phantom was used to take the images of weight-bearing lateral foot in MFD and WBPs to compare the resolutions of the X-ray images using a quick modulation transfer function (MTF) program. Between both the images taken from the MFD and WBPs, there was no statistically significant difference found in the mean cycles per pixel (C/P) and the lines per image height (LPH) of the 50%-Contrast Spatial Frequency (MTF50), and 10-90% of Maximum Energy Rise Distance (10-90%), where p>0.05. The MFD is suggested for its clinical trial as a useful positioning device that can secure the patient's safety and manifoldly perform various inspections. Also, the recommendation of the positioning device as a policy can activate dedicated manufacturers, while also improving the quality of medical services.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.2
• /
• pp.786-792
• /
• 2013

In this study was explored minimize side effects due to the additional injection of contrast medium and maintaining a high resolution imaging applied to the inspection and analysis of the contrast medium that affect the peak time biomechanics factors. Included 48 patients using the test bolus method, after measuring a patient's biomechanics factors of inspection before and during the test, correlation between contrast medium peak time and learn, matches the regression equation calculated and measured contrast medium peak time was assessed by the Bland Altman plot. Research result, inspections of SBP, HR contrast medium peak time and a significant negative correlation was, step 1, every increase, the contrast medium peak time significantly to -0.018 and -0.159 decreased, a fairly high concordance no difference between the two method. In conclusion, the regression equation using the existing methods, while maintaining excellent image quality that contrast medium is reduced to a patient, it can conclude that the alternative to the existing methods.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.12
• /
• pp.6550-6557
• /
• 2013

The public road construction projects awarded by the regional construction and management office, which is an affiliate of the Ministry of Land, Infrastructure and Transport, are managed by construction supervision officers. These officials frequently visit a large number of construction sites to conduct inspections and supervision tasks. Therefore, the site management efficiency is essential in terms of the time and money spent in travelling to the sites. The introduction of a site monitoring management system is considered necessary to minimize the number of site visits and enable remote monitoring of the construction progress to enhance the business efficiency of the construction supervision officers. In this study, a remote site monitoring system was constructed using web cameras for public road construction works. The trial applications were implemented by selecting ten constructions sites. The effectiveness of the system was analyzed to assess its applicability. In an assessment of the applicability of the verification results, remote site monitoring showed cost savings of approximately 35% compared to the existing site management. The guidelines for applying the site monitoring management system were provided, the introduction plan was investigated, and the improvement method was presented. The results showed that the system is likely to minimize the unnecessary site visits, remove the risk factors at vulnerable areas in the sites beforehand, and prevent a range of disasters and accidents. In addition, the quality of the infrastructures is likely to improve through the prevention of accidents and the elimination of substandard and faulty construction work.

• Journal of the Korean Society of Radiology
• /
• v.14 no.5
• /
• pp.577-584
• /
• 2020

In this study, the number of non-English speaking visitors is increasing day by day, and accordingly, there was a limitation in language communication and communication during radiographic examination. To this end, after distributing the handbook produced for inspection, the improvement effect of before and after explanation was examined. The score scale was not statistically significant as to whether it was the test site or not, and the degree of discomfort of the test, the degree of understanding of the breathing guidelines, and the satisfaction of the test description were improved and the score scale was improved before and after the description of the guide. Non-English-speaking foreign visitors were more satisfied with explanations in their own text than in English or Korean, and the method was also able to conduct effective inspections by informing the foreign guests when to control their breathing by using the lighting signals in the laboratory. In the future, the quality of medical services and imaging medical examinations can be improved only when communication methods are implemented from various perspectives, such as developing various language interpretation programs, developing guides for various test sites, and developing tools and improving foreign language skills of radiologists and medical staff. There will be. In the future, it may be used as a basic resource to prepare a manual that can be used to examine non-English speaking foreigners who do not understand English or Korean in other radiology labs.

• Journal of Korean Society for Geospatial Information Science
• /
• v.19 no.4
• /
• pp.119-126
• /
• 2011

During precise survey on the top of High rise buildings and civil structures, optical surveying equipments like a Total Station are not recommended to use because of some reasons that uneasier alignment with reflectors located at the top of building, increasing error depends on increasement of observation distance and unavailable dynamic positioning etc. Recently various GPS positioning methods have been applied to this job however almost of them are post-processing method which is required much longer time during for whole process includes stake-out, cross checking, fixing positions and final inspections. Therefore, in this study, we applied with RTK surveying system which allows stake-out and inspection in realtime to avoid delaying of construction schedule and also applied with Quasi Static RTK measurement and network adjustment to get a high accuracy within a few millimeters in structure positioning to achieve a successful management for process and quality control of the project. As a result, very high accurate surveying for structures within approx. 2mm in realtime has been achieved when surveyor conduct a network adjustment using least square method for 4 base lines created by Quasi Static RTK data and we expect this method will be applied to construction survey for high rise buildings and civil structures in the future.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.6
• /
• pp.583-598
• /
• 2022

As human-based tunnel inspections are affected by the subjective judgment of the inspector, making continuous history management difficult. There is a lot of deep learning-based automatic crack detection research recently. However, the large public crack datasets used in most studies differ significantly from those in tunnels. Also, additional work is required to build sophisticated crack labels in current tunnel evaluation. Therefore, we present a method to improve crack detection performance by inputting existing datasets into a deep learning model. We evaluate and compare the performance of deep learning models trained by combining existing tunnel datasets, high-quality tunnel datasets, and public crack datasets. As a result, DeepLabv3+ with Cross-Entropy loss function performed best when trained on both public datasets, patchwise classification, and oversampled tunnel datasets. In the future, we expect to contribute to establishing a plan to efficiently utilize the tunnel image acquisition system's data for deep learning model learning.