• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.4
• /
• pp.365-384
• /
• 2024

The development of scanning technology is accelerating for safer and more efficient automated inspection than human-based inspection. Research on automatically detecting facility damage from images collected using computer vision technology is also increasing. The pixel size, quality, and quantity of an image can affect the performance of deep learning or image processing for automatic damage detection. This study is a basic to acquire high-quality raw image data and camera performance of a mobile tunnel scanning system for automatic detection of damage based on deep learning, and proposes a method to quantitatively evaluate image quality. A test chart was attached to a panel device capable of simulating a moving speed of 40 km/h, and an indoor test was performed using the international standard ISO 12233 method. Existing image quality evaluation methods were applied to evaluate the quality of images obtained in indoor experiments. It was determined that the shutter speed of the camera is closely related to the motion blur that occurs in the image. Modulation transfer function (MTF), one of the image quality evaluation method, can objectively evaluate image quality and was judged to be consistent with visual observation.

• Korean Chemical Engineering Research
• /
• v.62 no.3
• /
• pp.214-224
• /
• 2024

Valves play an essential role in a chemical plant such as regulating fluid flow and pressure. Therefore, optimal selection of the valve size and type is essential task. Valve size and type have been selected based on theoretical formulas about calculating valve sizing coefficient (Cv). However, this approach has limitations such as requiring expert knowledge and consuming substantial time and costs. Herein, this study developed a model for predicting valve sizes and types using machine learning. We developed models using four algorithms: ANN, Random Forest, XGBoost, and Catboost and model performances were evaluated using NRMSE & R² score for size prediction and F1 score for type prediction. Additionally, a case study was conducted to explore the impact of phases on valve selection, using four datasets: total fluids, liquids, gases, and steam. As a result of the study, for valve size prediction, total fluid, liquid, and gas dataset demonstrated the best performance with Catboost (Based on R², total: 0.99216, liquid: 0.98602, gas: 0.99300. Based on NRMSE, total: 0.04072, liquid: 0.04886, gas: 0.03619) and steam dataset showed the best performance with RandomForest (R²: 0.99028, NRMSE: 0.03493). For valve type prediction, Catboost outperformed all datasets with the highest F1 scores (total: 0.95766, liquids: 0.96264, gases: 0.95770, steam: 1.0000). In Engineering Procurement Construction industry, the proposed fluid-specific machine learning-based model is expected to guide the selection of suitable valves based on given process conditions and facilitate faster decision-making.

• The Journal of Korean Academy of Prosthodontics
• /
• v.62 no.3
• /
• pp.215-223
• /
• 2024

The patient in this case presented with a desire to have new dentures due to discomfort with existing ones. At the initial visit, all of teeth were missing except for the mandibular left second molar. As the patient was 65 years old, treatment with dentures and implant-supported prostheses was possible under the national health insurance system, and the patient opted for the mandibular denture using implant. Temporary prostheses were initially provided for patient adaptation, and following successful adaptation period, the treatment progressed. A maxillary complete denture and a mandibular implant-supported denture using two implants in the canines were fabricated. The mandibular denture is a Kennedy Class II removable partial denture which consists of a six-unit porcelain fused to metal fixed dental prostheses supported by the implant in the canines on both sides and left second molar serving as the abutments. Despite severe bone resorption and insufficient abutment teeth, the patient expressed satisfaction with the treatment results. In cases with economic and anatomical constraints affecting the feasibility of complete denture, implant-supported overdenture, and implant-supported fixed dental prostheses, an implant-assisted removable partial denture using implant surveyed crowns proves to be a viable and effective alternative treatment option. Nevertheless, the current dearth of scientifically rigorous studies underscores the necessity for meticulous regular check-up and occlusal assessment.

• Journal of Industrial Convergence
• /
• v.22 no.7
• /
• pp.81-91
• /
• 2024

This study was conducted to determine the status of allergic diseases and mental health in adolescents, confirm the relationship between allergic diseases and mental health, and provide basic data for developing effective disease management measures for adolescents at the developmental stage. Secondary analysis was performed on the data from the 17^th Youth Health Behavior Online Survey, and complex sample descriptive statistics, cross-tabulation, and logistic regression analysis were performed using the SPSS 26.0 program. As a result of the study, those with one or more allergic diseases were 1.286 times more likely to have stress (B=1.286, p<.000), 1.289 times more likely to be depressed (B=1.289, p<.000), and 1.399 times more likely to have generalized anxiety disorder (B=1.399, p<.000) was highly likely to experience it. Additionally, factors affecting the mental health of adolescents with allergic diseases were gender, economic level, academic performance, drinking experience, and smoking experience. Stress and generalized anxiety disorder were more likely to be experienced by female students, if they had a lower economic level and academic performance, and if they drank alcohol or smoked. Male students were more likely to experience depression if their economic level and academic performance were higher, and if they did not drink alcohol or smoke. Based on these results, we hope to establish a practical approach by establishing effective strategies to manage allergic diseases in adolescents and the mental health conditions that may arise from them.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.4
• /
• pp.236-244
• /
• 2024

A representative problem in domestic chestnut industry is the high loss of flesh due to excessive knife peeling in order to increase the peeling rate, resulting in a decrease in production efficiency. In this study, a prediction model for weight loss rate of chestnut by stage of knife peeling process was developed as undergarment study to optimize conditions of the machine. 51 control conditions of the two-stage blade peeler used in the experiment were derived and repeated three times to obtain a total of 153 data. Machine learning(ML) models including artificial neural network (ANN) and random forest (RF) were implemented to predict the weight loss rate by chestnut peel stage (after 1st peeling, 2nd peeling, and after final discharge). The performance of the models were evaluated by calculating the values of coefficient of determination (R), normalized root mean square error (nRMSE), and mean absolute error (MAE). After all peeling stages, RF model have better prediction accuracy with higher R values and low prediction error with lower nRMSE and MAE values, compared to ANN model. The final selected RF prediction model showed excellent performance with insignificant error between the experimental and predicted values. As a result, the proposed model can be useful to set optimum condition of knife peeling for the purpose of minimizing the weight loss of domestic chestnut flesh with maximizing peeling rate.

• Journal of Wetlands Research
• /
• v.26 no.3
• /
• pp.254-265
• /
• 2024

This study was conducted to investigate the vascular flora of two outstanding forest wetlands(OFW) in Goheung-gun, Jeollanam-do, and to prepare an efficient management plan for forest wetlands through comparison with previous studies. Fieldwork was conducted seasonally from May to October 2023, The flora in the two OFW located in Goheung-gun, Jeollanam-do, consisted of 117 taxa such as 55 families, 92 genera, 108 species, 7 variants, 1 variety and 1 hybrid. The endemic plants were 4 taxa and rare plants were 7 taxa. Floristic target plants were V class 2 taxa, IV class 6 taxa, III class 8 taxa, II class 4 taxa and Iclass 21 taxa. Climate change adaptation plants were 10 taxa and naturalized plants was 1 taxa. Obligate wetland plants were 16 taxa, Facultative wetland plants 10 taxa and Facultative plant 4 taxa. OFW functioning a typical wetland ecosystem in Goheung-gun had been providing habitats for a variety of rare plants, such as the Habenaria radiata and Drosera rotundifolia. But those ecosystems would be suffering a critical disturbance such as human interference, the invasion of naturalized plants, and change of wetland function through landization for a short future. Therefore we suggest those OFWs should be designated as a Forest Genetic Resource Reserve in order to keep the ecosystems permanently and to manage them more soundly and efficiently.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.189-198
• /
• 2024

Research combining deep learning-based models and physical simulations is making important advances in the medical field. This extracts the necessary information from medical image data and enables fast and accurate prediction of deformation of the skeleton and soft tissue based on physical laws. This study proposes a system that integrates Neural Radiance Fields (NeRF), Position-Based Dynamics (PBD), and Parallel Resampling to generate 3D volume data, and deform and visualize them in real-time. NeRF uses 2D images and camera coordinates to produce high-resolution 3D volume data, while PBD enables real-time deformation and interaction through physics-based simulation. Parallel Resampling improves rendering efficiency by dividing the volume into tetrahedral meshes and utilizing GPU parallel processing. This system renders the deformed volume data using ray casting, leveraging GPU parallel processing for fast real-time visualization. Experimental results show that this system can generate and deform 3D data without expensive equipment, demonstrating potential applications in engineering, education, and medicine.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.27 no.3
• /
• pp.60-75
• /
• 2024

Research on health outcomes of environmental factors has been implemented by multiple and interacting factors, including environmental, socio-demographic, economic, and traffic aspects. There are still significant challenges and limitations in constructing databases for the connections between contributing factors and an integrated approach to environmental health research even though there has been a dramatic increase in data availability and incredible technological advance in data storage and processing. This study emphasizes the necessity of establishing a geospatial data pipeline to analyze the impact of environmental factors on health. It also highlights the difficulties and solutions related to the construction and utilization of a geospatial database. Key challenges include diverse data sources and formats, different spatio-temporal data structures, and coordinate system inconsistencies over time within the same geospatial data. To address these issues, a data pipeline was constructed with pre-processing and post-processing for the data, resulting in refined datasets that could be used for calculating geographic variables. In addition, an AWS-based relational database and shared platform were established to provide an efficient environment for data storage and analysis. Guidelines for each step of the process, including data management and analysis, were developed to enable future researchers to effectively use the data pipeline.

• Journal of Science Education
• /
• v.48 no.2
• /
• pp.91-100
• /
• 2024

The use of smart devices in science classes has brought about positive changes, such as increased student participation and more self-directed learning. Smart devices are increasingly being used in science classes, creating a need to develop lesson models that can stimulate students' interest and encourage active, self-directed learning in scientific inquiry and experimental activities. In smart education, smart devices and applications play a major role. However, in the "Mixture Separation" section of middle school science, chromatography focuses mainly on paper chromatography, which is not currently used in the field of actual research. This approach is not well-suited for students preparing for a new future society, and it is becoming obsolete due to curriculum revisions. Although chromatography can be used as an activity for career exploration, removing it is not convincing. The advantage of using thin-layer chromatography (TLC), which is employed in actual research, is that it is inexpensive and easy to use in classroom settings. In this study, we have developed a new, faster, and simpler analysis method for TLC that uses smart devices for both qualitative and quantitative analysis. We hope this method will enhance student engagement and facilitate small-scale learning by integrating smart devices into learning activities, making it a practical tool for actual school settings.

• Journal of Environmental Impact Assessment
• /
• v.33 no.4
• /
• pp.164-174
• /
• 2024

Recently, many offshore wind farm project plans and environmental impact assessments have been conducted in Korea. However, despite having different characteristics from onshore wind farm, there is a lack of alternative setting and evaluation methods suitable for this. Accordingly, this study attempted to derive implications for the alternative setting and evaluation method suitable for the domestic situation through overseas guideline and case analysis. Through the result of the analysis, it was possible to examine the process of the alternative setting and evaluation method for offshore wind farm, and through this, detailed considerations and methodology were found. Even overseas, the methodology for alternative setting and evaluation has not yet been clear, and the methodology used for onshore wind farm has been improved and developed. In Korea, it is necessary to prepare a system for setting and evaluating alternatives to such offshore wind farm projects, and research in various fields is required to carry out them reasonably and efficiently. For the successful promotion of domestic offshore wind farm projects, it is thought that continuous efforts to increase environmental and social acceptance are necessary along with the promotion of related research reflecting the implications derived from overseas cases.