• Corrosion Science and Technology
• /
• v.18 no.6
• /
• pp.253-257
• /
• 2019

A deep learning based real-time painting surface inspection algorithm is proposed herein, designed for developing an autonomous inspection drone. The painting surface inspection is usually conducted manually. However, the manual inspection has a limitation in obtaining accurate data for correct judgement on the surface because of human error and deviation of individual inspection experiences. The best method to replace manual surface inspection is the vision-based inspection method with a camera, using various image processing algorithms. Nevertheless, the visual inspection is difficult to apply to surface inspection due to diverse appearances of material, hue, and lightning effects. To overcome technical limitations, a deep learning-based pattern recognition algorithm is proposed, which is specialized for painting surface inspections. The proposed algorithm functions in real time on the embedded board mounted on an autonomous inspection drone. The inspection results data are stored in the database and used for training the deep learning algorithm to improve performance. The various experiments for pre-inspection of painting processes are performed to verify real-time performance of the proposed deep learning algorithm.

• Journal of Digital Convergence
• /
• v.12 no.2
• /
• pp.513-518
• /
• 2014

According to the development of IT technology, various new technologies are being produced. As the complexity of the information system like using the network and convergence devices is increasing, threat and vulnerability against various security problems are increasing even though new IT services provide the convenience of users' accessibility to services. In order to secure the safety of information system, the weakness is being removed through the information protection vulnerability analysis starting from information and communication service construction stage and the system is being prepared for pre-inspection activities about whether the information protection measures were established and applied. In this paper, introduction and current status of each country about advanced check-up systems in the information system are to be identified. Progress direction about the advanced pre-inspection system which is driven by Korea Internet Security Agency and its activation plan to secure the safety are to be suggested.

• Korean Journal of Radiology
• /
• v.19 no.6
• /
• pp.1053-1065
• /
• 2018

Objective: To evaluate the clinical impact of using registration software for ablative margin assessment on pre-radiofrequency ablation (RFA) magnetic resonance imaging (MRI) and post-RFA computed tomography (CT) compared with the conventional side-by-side MR-CT visual comparison. Materials and Methods: In this Institutional Review Board-approved prospective study, 68 patients with 88 hepatocellulcar carcinomas (HCCs) who had undergone pre-RFA MRI were enrolled. Informed consent was obtained from all patients. Pre-RFA MRI and post-RFA CT images were analyzed to evaluate the presence of a sufficient safety margin (${\geq}3mm$) in two separate sessions using either side-by-side visual comparison or non-rigid registration software. Patients with an insufficient ablative margin on either one or both methods underwent additional treatment depending on the technical feasibility and patient's condition. Then, ablative margins were re-assessed using both methods. Local tumor progression (LTP) rates were compared between the sufficient and insufficient margin groups in each method. Results: The two methods showed 14.8% (13/88) discordance in estimating sufficient ablative margins. On registration software-assisted inspection, patients with insufficient ablative margins showed a significantly higher 5-year LTP rate than those with sufficient ablative margins (66.7% vs. 27.0%, p = 0.004). However, classification by visual inspection alone did not reveal a significant difference in 5-year LTP between the two groups (28.6% vs. 30.5%, p = 0.79). Conclusion: Registration software provided better ablative margin assessment than did visual inspection in patients with HCCs who had undergone pre-RFA MRI and post-RFA CT for prediction of LTP after RFA and may provide more precise risk stratification of those who are treated with RFA.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2022.11a
• /
• pp.233-234
• /
• 2022

In Korea, various policies are implemented so that the socially disadvantaged (disabled, elderly, pregnant women, temporary disabled, etc.) can easily access individual facilities and areas. As the nation's interest in the socially disadvantaged increases, the need for BF certification is also emerging in buildings in private facilities. However, this system requires a lot of cost and time in the examination process, so if certification fails, social costs and time losses are high. To solve this problem, this paper presents a measurement plan for mixed reality devices using HoloLens, a mixed reality device hardware that can pre-check BF certification based on augmented reality, and Unity 3D, MRTK, a development tool.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.10 no.5
• /
• pp.121-129
• /
• 2006

This study look into the mechanisms of growth and magnification of the cracks and delamination in the pre-cracked RC beams repaired with carbon fiber sheets. The experimental parameters were loading type, loading speed and crack. In the experiments, it was confirmed that a failure of beams began with development and propagation of the stepped delamination in the below the loading point due to the rapid change of shear force, but mechanisms of the failure were not influenced with loading type, loading speed and pre-cracks. Particularly, in the case of beams having the pre-cracks, growth of crack concentrated at the special crack below the loading point and led to failure of the beam by delamination due to magnification of crack.

• International conference on construction engineering and project management
• /
• 2005.10a
• /
• pp.1193-1198
• /
• 2005

The pre-assembly takes a large portion of the fabrication cost of steel bridges. In order to save the fabrication cost through the improvement of the conventional pre-assembling process, this research investigates a numerical pre-assembly simulation as an alternative to current pre-assembling process. The 3D laser scanning was utilized in site and measuring data for steel box were analyzed. The productivity of pre-assembly simulation system is compared with the conventional pre-assembling system. This paper identifies feasibility on the alternative pre-assembling process and then proposes the scheme of the pre-assembly simulation system development satisfying the current pre-assembly inspection of standards.

• Journal of the Korean Geosynthetics Society
• /
• v.13 no.4
• /
• pp.133-141
• /
• 2014

This study was carried out to establish the database system by using the safety inspection and in-depth inspection results for infrastructures such as bridges, tunnels, dams, and water supplies. A classification system of each facility was proposed by standardizing items for inspection & diagnosis in order to automatize work process. Also, it justifies data structure based on database from pre-investigation to field survey, evaluation of facilities, and report making. In addition to this, it suggests improvement plans of relative regulations and guidelines such as Facility Management System(FMS), operational regulation, and inspection detailed guideline to make inspection result database of infrastructures which can be used effectively.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.1131-1135
• /
• 2005

Since human is vulnerable to emotional, physical and environmental distractions, most human inspectors cannot sustain a consistent 8-hour inspection in a day specifically for small components like door locking levers. As an alternative for human inspection, presented in this study is the development of a machine vision inspection system (MVIS) purposely for door locking levers. Comprises the development is the structure of the MVIS components, designed to meet the demands, features and specifications of door locking lever manufacturing companies in increasing their production throughput upon keeping the quality assured. This computer-based MVIS is designed to perform quality measures of detecting missing portions and defects like burr on every door locking lever. NI Vision Builder software for Automatic Inspection (AI) is found to be the optimum solution in configuring the needed quality measures. The proposed software has measurement techniques such as edge detecting and pattern-matching which are capable of gauging, detecting missing portion and checking alignment. Furthermore, this study exemplifies the incorporation of the optimized NI Builder inspection environment to the pre-inspection and post-inspection subsystems.

• Journal of the Korean Society of Earth Science Education
• /
• v.13 no.1
• /
• pp.74-89
• /
• 2020

The purpose of this study was to develop a concept test tool for seasonal change with reliability and validity, and to objectively observe and analyze sub-concepts and misconceptions related to the concept of seasonal change to explain the relationship between variables. The development process of the conceptual change concept inspection tool consisted of the development of the inspection tool development plan, the development of the inspection tool draft, the modification of the preliminary inspection and inspection tools, the development of the final inspection tool, and the implementation of this inspection. The developed test tool can be used to provide students with appropriate learning and help by examining students' degree of seasonal change concept formation and analyzing the cause of the difficulty in concept formation. As a result of regression analysis of 198 students in 6th grade using the developed test tool, it was found that the understanding of pre-learning concept and correction of misconception had a statistically significant effect on the concept learned in the seasonal change unit, and misconception had greater effect. Correction of misconceptions had a significant effect on students above the average score among the two sections created and cut based on the average score, and on the students below the average score, the understanding of pre-learning concept had a significant effect.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.1
• /
• pp.142-147
• /
• 2018

Private electrical facilities are judged whether it is suitable for the insulation aging condition of their incoming underground cables using DC leakage current test method. In the case where the service point of utility is the secondary side of cut out switch installed in the electric pole, there is a problem that it is difficult to separate the lightning arresters(LA) because of their high position of the pole. Therefore, the field test voltage is applied at value lower than DC 30 kV, which are stated in the inspection guideline. However, this test could reduced the insulation performance of the LA by accelerating the electrical stress of the metal oxide varistor element in the pre-breakdown region. In this study, we analyzed the relationship between the DC test voltage and the leakage current using the non-destructive DC high voltage equipment with leakage current measurement function. The results show that the leakage current increases sharply above the specified test voltage. As a consequence, it could be contributed to improve insulation aging inspection method by selecting the possible test area on the VI characteristic curve of the pre-breakdown area of the LA.