• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.27-35
• /
• 2023

In this paper, we propose a process of increasing productivity by applying a deep learning-based defect detection and classification system to the prepreg fiber manufacturing process, which is in high demand in the field of producing composite materials. In order to apply it to toe prepreg manufacturing equipment that requires a solution due to the occurrence of a large amount of defects in various conditions, the optimal environment was first established by selecting cameras and lights necessary for defect detection and classification model production. In addition, data necessary for the production of multiple classification models were collected and labeled according to normal and defective conditions. The multi-classification model is made based on CNN and applies pre-learning models such as VGGNet, MobileNet, ResNet, etc. to compare performance and identify improvement directions with accuracy and loss graphs. Data augmentation and dropout techniques were applied to identify and improve overfitting problems as major problems. In order to evaluate the performance of the model, a performance evaluation was conducted using the confusion matrix as a performance indicator, and the performance of more than 99% was confirmed. In addition, it checks the classification results for images acquired in real time by applying them to the actual process to check whether the discrimination values are accurately derived.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.5
• /
• pp.331-337
• /
• 2023

In this paper, we propose a deep learning model to detect lumbar 3 (L3) CT images to determine the occurrence and degree of sarcopenia. In addition, we would like to propose an optimization technique that uses oversampling ratio and class weight as design parameters to address the problem of performance degradation due to data imbalance between L3 level and non-L3 level portions of CT data. In order to train and test the model, a total of 150 whole-body CT images of 104 prostate cancer patients and 46 bladder cancer patients who visited Gangneung Asan Medical Center were used. The deep learning model used ResNet50, and the design parameters of the optimization technique were selected as six types of model hyperparameters, data augmentation ratio, and class weight. It was confirmed that the proposed optimization-based L3 level extraction model reduced the median L3 error by about 1.0 slices compared to the control model (a model that optimized only 5 types of hyperparameters). Through the results of this study, accurate L3 slice detection was possible, and additionally, we were able to present the possibility of effectively solving the data imbalance problem through oversampling through data augmentation and class weight adjustment.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.1
• /
• pp.27-33
• /
• 2023

Recently, water shortages have occurred due to climate change, and the need for water management of agricultural water has increased due to the occurrence of algal blooms in reservoirs. Existing algae prevention is operated by putting many people on site and misses the optimal spraying time due to movement through boats. In order to solve this problem, it is necessary to block contamination in advance and move within time to uniformly spray complex microorganisms uniformly. Control drones are used for pesticide spraying and can be applied to algae prevention work by utilizing control drones. In this paper, basic research for the establishment of a marine control system was conducted for application to the reservoir environment, and as one of the results, the characteristics of a drone nozzle, a core technology that can be used for control drones, were calculated. In particular, it was found that the existing agricultural control drones had a disadvantage that the concentration was non-uniform within the suggested spraying interval, and to compensate for this, nozzle positioning and nozzle spraying uniformity were calculated. Based on the experimental results, we develop a core algorithm for establishing an algal bloom monitoring system in the reservoir environment and propose a precision control technology that can be used for marine control work in the future.

• Tunnel and Underground Space
• /
• v.33 no.6
• /
• pp.435-444
• /
• 2023

In the licensing application for the deep geological disposal system of high-level radioactive waste in Finland, the disposal tunnel backfilling has been changed from the block/pellet (for the construction) to the granular type (for the operation). Accordingly, for establishing the design concept for backfilling, it is necessary to examine applicability to the domestic facility through analyzing problems of the existing method and improvements in the alternative design. In this paper, we first reviewed the principal studies conducted for changing the backfill method in the licensing process of the Finnish facility, and identified the expected problems in applying the block/pellet backfill method. In addition, we derived the evaluation factors to be considered in terms of technical and operational aspects for the backfilling solution, and then conducted a comparative analysis for two types of backfill methods. This analysis confirmed the overall superiority of the design change. It is expected that these results could be utilized as the technical basis for deriving the optimum design plan in development process of the Korean-specific deep disposal facility. However, applicability should be reviewed in advance based on the latest technical data for the detailed evaluation factors that must be considered for selecting the backfilling method.

• Tunnel and Underground Space
• /
• v.33 no.6
• /
• pp.547-560
• /
• 2023

Recently, research on predicting ground classification using machine learning techniques, TBM excavation data, and ground data is increasing. In this study, a multi-classification prediction study for uniaxial compressive strength (UCS) was conducted by applying random forest model based on a decision tree among machine learning techniques widely used in various fields to machine data and ground data acquired at three slurry shield TBM sites. For the classification prediction, the training and test data were divided into 7:3, and a grid search including 5-fold cross-validation was used to select the optimal parameter. As a result of classification learning for UCS using a random forest, the accuracy of the multi-classification prediction model was found to be high at both 0.983 and 0.982 in the training set and the test set, respectively. However, due to the imbalance in data distribution between classes, the recall was evaluated low in class 4. It is judged that additional research is needed to increase the amount of measured data of UCS acquired in various sites.

• Journal of Navigation and Port Research
• /
• v.47 no.6
• /
• pp.315-323
• /
• 2023

Marine accidents due to loss of stability of small ships have continued to increase over the past decade. In particular, since sudden winds have been pointed out as main causes of most small ship accidents, safety measures have been established to prevent them. In this regard, to prevent accidents caused by sudden winds, a systematic analysis technique is required. The aim of the present study was to develop a probabilistic approach to estimate extreme value and evaluate effects of wind on motion characteristics of ships. The present study included studies of motion analysis, extraction of extreme values, and motion characteristics. A series analysis was conducted for three conditions: wave only, wave with uniform wind speed, and wave with the NPD wind model. Hysteresis filtering and Peak-Valley filtering techniques were applied to time-domain motion analysis results for extreme value extraction. Using extracted extreme values, the goodness of fit test was performed on four distribution functions to select the optimal distribution-function that best expressed extreme values. Motion characteristics of a fishing boat were evaluated for three periodic motion conditions (Heave, Roll, and Pitch) and results were compared. Numerical analysis was performed using a commercial solver, ANSYS-AQWA.

• Food Science and Preservation
• /
• v.30 no.5
• /
• pp.885-895
• /
• 2023

This study aims to investigate the production and characteristics of protein hydrolysates derived from tuna byproducts (TP) using various proteolytic enzymes and to compare the antioxidant activity of the resulting hydrolysates. The TP were subjected to enzymatic hydrolysis using five different proteases: alcalase, bromelain, flavourzyme, neutrase, and papain, and the antioxidant activities of the hydrolysates were evaluated. Subsequent analysis of the available amino group contents and sodium dodecyl sulfate-polyacrylamide gel electrophoresis patterns indicated a high degree of hydrolysis in TP after treatment with all the enzymes, except for papain. Based on the RC₅₀ values obtained from four different antioxidant analyses, all the hydrolysates exhibited similar antioxidant activity, except for the flavourzyme hydrolysate, which showed significantly higher scavenging activity against ABTS radicals and hydrogen peroxide than the other hydrolysates. These findings suggest that protein hydrolysates derived from TP hold promise as potential sources of natural antioxidants.

• Composites Research
• /
• v.37 no.1
• /
• pp.7-14
• /
• 2024

Due to the structural characteristic of a double roller, the double roller can have various deformation behaviors depending on a gap block design, even if dimensions and loading conditions for the double roller are the same. Based on this feature, we propose a strategy for designing the gap block of the carbon-fiber reinforced plastic (CFRP) double roller to minimize defects (e.g., sagging and wrinkling), which can be raised during the product conveying process, with the pursue of the lightweight design. In the suggested strategy, analysis cases are first selected by considering main design parameters and engineering tolerances of the gap block, and then deformation behaviors of these selected cases are extracted using the finite element method (FEM). Here, to obtain the optimal gap block parameters that satisfy the purpose of this study, deformation deviations in the contact area are calculated and compared using the extracted deformation behaviors. Note that the contact area in this work is located between the product and the roller. As a result, through the design method of the gap block proposed in this work, it is possible to construct the CFRP double roller that can significantly decrease the defects without changing the overall sizes of the roller. A detailed method is suggested herein, and the results are evaluated in a numerical way.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.411-417
• /
• 2024

In the event of a disaster, it is essential to establish a disaster recovery plan and disaster recovery system to minimize disruption to major IT infrastructure and provide continuous business services. In the process of building a disaster recovery system, data replication is a key element of data recovery to provide uninterrupted and continuous business services in the event of a disaster. The data replication method can be determined depending on the system configuration environment and disaster recovery goal level. In this paper, we present a method for determining a data replication method suitable for the configuration environment and disaster recovery target level when building a disaster recovery system. In addition, the replication method decision procedure is applied to build a disaster recovery system and analyze the construction results. After establishing the disaster recovery system, a test was conducted to determine whether the service was transferred to the disaster recovery center in a disaster situation and normal service was provided, and the results were analyzed. As a result, it was possible to systematically select the optimal data replication method during the disaster recovery system construction phase. The established disaster recovery system has an RTO of 3.7 hours for service conversion to the disaster recovery center to provide continuous business services, and the disaster recovery level, which was Tier 2, has been improved to the target level within 4 hours of RTO and RPO=0.

• Journal of Applied Biological Chemistry
• /
• v.66
• /
• pp.394-403
• /
• 2023

In the pursuit of sustainable and environmentally-friendly agricultural practices, we conducted an extensive study on the rhizosphere bacteria inhabiting soils that have been devoid of chemical fertilizers for an extended period exceeding 40 years. Through this investigation, we isolated a total of 80 species of plant growth-promoting rhizosphere bacteria and assessed their potential to enhance plant growth. Among these isolates, Burkholderia cepacia CD2 displayed remarkable plant growth-promoting activity, making it an optimal candidate for further analysis. Burkholderia cepacia CD2 exhibited a range of beneficial characteristics conducive to plant growth, including phosphate solubilization, siderophore production, denitrification, nitrate utilization, and urease activity. These attributes are well-known to positively influence the growth and development of plants. To validate the taxonomic classification of the strain, 16S rRNA gene sequencing confirmed its placement within the Burkholderia genus, providing further insights into its phylogenetic relationship. To delve deeper into the potential mechanisms underlying its plant growth-promoting properties, we sought to confirm the presence of specific genes associated with plant growth promotion in CD2. To achieve this, whole genome sequencing (WGS) was performed by Plasmidsaurus Inc. (USA) utilizing Oxford Nanopore technology (Abingdon, UK). The WGS analysis of the genome of CD2 revealed the existence of a subsystem function, which is thought to be a pivotal factor contributing to improved plant growth. Based on these findings, it can be concluded that Burkholderia cepacia CD2 has the potential to serve as a microbial fertilizer, offering a sustainable alternative to chemical fertilizers.