With the increasing number of aging buildings, the importance of structural safety inspections has grown significantly. Traditional methods for inspecting welding defects, such as visual inspection and magnetic testing, rely heavily on human expertise, making them time-consuming, costly, and subjective. To address these limitations, thermographic technology has been introduced as a non-contact alternative, significantly reducing both time and cost. Furthermore, by incorporating AI, an objective and automated evaluation of welding defects can be achieved. In this study, we propose an AI-based thermographic approach for detecting welding defects. To validate the applicability of this method, a Mock-up Test was conducted. Specifically, 12 types of welding specimens with 4 welding part were prepared, generating a dataset of 6,500 thermographic images. Among 7 regression algorithms tested, RF and EXT were selected due to their superior performance. By ensemble learning these two models, we developed a robust welding defect measurement algorithm. To further verify its effectiveness, we applied the developed algorithm to 2 real projects, evaluating its applicability using 450 thermographic images. The results of this study demonstrate the feasibility of AI and thermographic technology in welding defect detection, highlighting its potential to enhance the efficiency and reliability of structural safety inspections in aging infrastructures.

최근 디지털 전환과 나노·광학 기술의 융합이 가속화되면서 화상(이미지·광학) 분야 연구가 증가하고 있다. 그럼에도 불구하고 국내 연구 흐름을 계량적으로 조망한 분석은 드문 실정이다 본 연구는 2014–2024년 11년간 한국화상학회지에 게재된 167편논문 초록을 대상으로 텍스트마이닝을 수행하여 국내 화상 연구의 흐름을 정량적으로 파악하였다. 분석은 불용어 제거·표제어 변환을 거친 키워드 전처리, 키 워드 빈도 분석, LDA 토픽 모델링과 의미망 분석을 통해 수행되었다. 연구는 크게 6개의 토픽(광학 코팅 및 성능 최적화, 나노 소재 기반 광학 장치 개발, 광학 특성 측정 및 분석 기술, 이미지 처리 및 디스플레이 기 술, 유기 고분자 기반 신소재 및 반응 연구, 기능성 재료 및 에너지 응용)으로 수행되었다. 각 토픽의 핵심 키 워드는 동시출현빈도 기반의 의미망 분석을 통해 핵심 키워드간 관계를 살펴보았다. 본 연구는 국내 화상 분 야의 세부 연구축과 성장 영역을 데이터 기반으로 제시하여 향후 연구 로드맵 수립에 기여한다.

Due to rapid spread of fireblight, the Rural Development Administration is supplying bactericides to farmers. However, research on inhibitory effects of main active ingredients in these bactericides on fireblight is lacking. Chlorophyll fluorescence analysis is a non-destructive method for analyzing the photosynthetic efficiency of plants, enabling time-series data analysis of pathogen progression and allowing for large-scale studies. Therefore, this study analyzed inhibitory effects of main active ingredients in bactericides on fireblight using chlorophyll fluorescence response analysis. Flowering pear trees (three-year-old ‘Shingo’ variety) were sprayed with control agents and fire blight pathogens on flowers. Chlorophyll fluorescence responses were then measured at seven-day intervals. Twenty-eight days after bactericide treatment, the fluorescence of the O-J transition stage in the untreated group was twice as high as in the average bactericide-treated group presumably due to inhibition of electron transport in the PSII donor side caused by pathogen infection, leading to leaf necrosis. Additionally, the electron transport efficiency (ET2o, RE1o) decreased, reducing the driving force of photosynthesis (DF total ABS) to 20% of the average bactericidetreated group, indicating chlorophyll damage and reduced photosynthetic capacity. In conclusion, chlorophyll fluorescence technology can be used to quantitatively evaluate the efficacy of fire blight control agents during the flowering period of pear trees.

This study was carried out to establish various physiological changes according to soil water stress and to compare the degree of water stress between two species of grapevines (‘Jinok’ as a new breeding cultivar and ‘Campbell Early’ as a control) using thermography. Soil water potentials were treated at -70, -30, and -5 kPa with waterlogging for 7 days. Regarding the photosynthetic rates (A) of the two cultivars, they showed an order of –30 kPA > -5 kPa > -70 kPa in order. With -70 kPa and waterlogging treatments, a decrease of photosynthetic rate was observed at 3 days after treatment, with a more significant decrease accumulating over time. At 7 days after treatment, photosynthetic rates of ‘Campbell Early’ (33.3, 45.6%) and ‘Jinok’ (56.6, 57.3%) grapes decreased compared to those with -30 kPa treatment. H2O2 and proline synthesis were the highest with the waterlogging treatment. In terms of proline synthesis, ‘Campbell Early’ had a relatively higher rate than ‘Jinok’. Leaf and stem water potential were the lowest with the -70 kPa treatment and the highest with the - 30 kPa treatment f or both cultivars. Crop water stress index (CWSI) showed the following order: waterlogging > -70 kPa > -5 kPa > -30 kPa, which was the opposite result of water vapor transfer (IG). As a result of correlation analysis between factors, photosynthetic rate showed negative correlations with the water potential of leaf and stem and crop water stress index but a positive correlation with the relative water content of leaves. Thus, tolerance to water stress of ‘Campbell Early’ was relatively stronger than that of ‘Jinok’ grape. It is possible to compare water stress using infrared imaging.

With the increasing number of aging buildings across Korea, emerging maintenance technologies have surged. One such technology is the non-contact detection of concrete cracks via thermal images. This study aims to develop a technique that can accurately predict the depth of a crack by analyzing the temperature difference between the crack part and the normal part in the thermal image of the concrete. The research obtained temperature data through thermal imaging experiments and constructed a big data set including outdoor variables such as air temperature, illumination, and humidity that can influence temperature differences. Based on the collected data, the team designed an algorithm for learning and predicting the crack depth using machine learning. Initially, standardized crack specimens were used in experiments, and the big data was updated by specimens similar to actual cracks. Finally, a crack depth prediction technology was implemented using five regression analysis algorithms for approximately 24,000 data points. To confirm the practicality of the development technique, crack simulators with various shapes were added to the study.

이번에 제시할 화상 사례 보고는 환자와 검사를 시행하는 방사선사의 부주의로 인한 화상 안전사고가 아니라 환자 가운 의 치수 구별을 하기 위하여 사용한 녹색 염료가 착색된 파이핑 라인에서 발생한 복부 부위 화상 안전사고에 대한 MRI 인공물 영상과 사례를 보고하고자 함이다. 화학 착색염료는 다양한 금속을 사용하여 만들어지고 주로 금속 염화물로 이루 어져 있으며 이번에 화상 사례로 발생한 녹색 염료는 열 전도성이 높은 구리와 크롬, 철 성분이 많이 함유된 염화물이 주로 사용되고 있다. 이러한 화상 안전사고를 막기 위해서는 염료의 성분에 대해서 알아보고 열 전도성이 없는 스펀지나 면으로 된 포 등을 피부와 환자 가운 사이에 끼워 간격을 두어야 할 것이다. 이번 화상 사례는 철저한 검사 전 선별 절차에도 불구 하고 화상 안전사고가 발생할 수 있음을 보여 주고 있으며 MRI 인공물 영상을 확인하여 조치하면 화상 안전사고를 미리 예방할 수 있는 정보로 가치가 있을 것으로 생각된다.

High-risk microbial pathogens are handled in a biosafety laboratory. After experiments, the pathogens may remain as contaminants. To safely manage a biosafety laboratory, disinfection of microbial contaminants is necessary. This study was carried out to evaluate the effect of UV-C irradiation for the disinfection of a high-risk plant pathogenic bacterium Erwinia amylovora in a laboratory setting. For the test, the bacterium (8.7 × 106 CFU/ml) was embedded on the surface of PDA and placed on the work surface in a biosafety cabinet (Class 2 Type A1), and on the three different surfaces of the laboratory bench, laboratory bench shelf, and the floor which were positioned in a straight line from the UV lamp installed in the ceiling of the biosafety laboratory (BSL 2 class). UV-C irradiation was administered for 10min, 30min, 1 hr, 2hr, 3 hr, and 4hr, respectively. The reduction rate of bacteria ranged from 95% to 99% in regard to 10 min irradiation, from 97% to 99% in regard to 30 min irradiation, from 99.8% to 99.9% in regard to 1 hr irradiation, and higher than 99.99% in regard to 2 hr irradiation. The bacterium was completely inactivated after 3 hr irradiation. A similar UV-C irradiation effect was obtained when the bacterium was placed at a distance of 1 m from the three different surface points. Bacterial reduction by UV-C irradiation was not significantly different among the three different surface points.

This study was conducted to obtain basic information for the use of the ATP fluorescence detection method in consideration of the most common and frequent contamination situation that occurs in laboratories dealing with fire blight causing bacterium, Erwinia amylovora. ATP luminescence measurements (Relative Light Unit, RLU) were tested against these pathogen cells (CFU/cm2) which were artificially introduced on the disinfected surface of a bench floor of a biosafety cabinet (Class 2 Type A1), on a part of the disinfected surface of a lab experimental bench, on a part of the disinfected floor, and on a part of the disinfected floor of an acryl chamber for bioaerosol studies in a biosafety laboratory (BSL 2 class) using two different ATP bioluminometers. RLU values were not much increased with the bacterial cells from 2.15 × 102/cm2 to 2.15 × 106/cm2. RLU values varied among the four different surfaces tested. RLU values measured from the same number of bacterial cells differed little between the two different ATP bioluminometers used for this study. RLU values obtained from bacterial cells higher than 2.15 × 107/cm2 indicated the presence of bacterial contamination on the four different surfaces tested. The R2 values obtained based on the correlation data for the RLU values in response to different E. amylovora cell numbers (CFU/ cm2) on the surfaces of the four test spots ranged from 0.9827 to 0.9999.

The use of heat exchangers in various applications such as chemical, air conditioning systems, fuel processing, and power industries is increasing. In order to improve the performance of the heat exchanger, the problem of bonding quality of the copper tube, which is a major member, is emerging. However, since the copper tube is in the form of a pipe, it is difficult to identify internal defects with external factors. In this study, a thermal imaging camera was used to develop and verify an algorithm for detecting defects in the brazing part, and in the process, the brazing performance characteristics were analyzed according to the electrode position, and finally, a learning model was developed and performance evaluation was performed. It was confirmed that the method of supplying heat to the base material and melting the filler metal through the heat transfer effect is more effective than supplying heat input to the filler metal in the bonding process of copper tubes through high-frequency induction heating brazing. Thermal image data was used to develop a defect discrimination model, and 80% of training data and 20% of test data were selected, and a neural network-based single-layer copper tube brazing defect discrimination model was developed through k-Flod cross-validation., the prediction accuracy of 95.2% was confirmed as a result of the error matrix analysis.

The most common symptoms of COVID-19 are high fever, cough, headache, and fever. These symptoms may vary from person to person, but checking for “fever” is the government’s most basic measure. To confirm this, many facilities use thermographic cameras. Since the previously developed thermographic camera measures body temperature one by one, it takes a lot of time to measure body temperature in places where many people enter and exit, such as multi-use facilities. In order to prevent malfunctions and errors and to prevent sensitive personal information collection, this research team attempted to develop a facial recognition thermographic camera. The purpose of this study is to compensate for the shortcomings of existing thermographic cameras with disaster safety IoT integrated solution products and to provide quarantine systems using advanced facial recognition technologies. In addition, the captured image information should be protected as personal sensitive information, and a recent leak to China occurred. In order to prevent another case of personal information leakage, it is urgent to develop a thermographic camera that reflects this part. The thermal imaging camera system based on facial recognition technology developed in this study received two patents and one application as of January 2022. In the COVID-19 infectious disease disaster, ‘quarantine’ is an essential element that must be done at the preventive stage. Therefore, we hope that this development will be useful in the quarantine management field.

The oral cavity is rich in blood flow, which can cause excessive bleeding. Excessive bleeding in oral cavity is rare, but if the cause of the bleeding is not found, the patient's life may be at risk. Therefore, in the case of excessive bleeding, the dentist should consider the cause and provide appropriate first treatment. Hydrofluoric acid is widely used as a material for pre-treatment of ceramics before oral restoration for prosthetics and conservative dentistry. Since hydrofluoric acid is very reactive, when it comes into contact with tissues, even very diluted 0.1% hydrofluoric acid can cause very painful 2-3 degree burns, which heal very slowly. Negative reactions and even deaths of hydrofluoric acid have been reported in other fields, but there are very few case reports of complications related to hydrofluoric acid in the dental field. In this article, we report a case of excessive gingival bleeding after restorative treatment and discuss the effects of hydrofluoric acid on oral soft tissues and blood vessels and its prevention

This study presents the estimation of crack depth by analyzing temperatures extracted from thermal images and environmental parameters such as air temperature, air humidity, illumination. The statistics of all acquired features and the correlation coefficient among thermal images and environmental parameters are presented. The concrete crack depths were predicted by four different machine learning models: Multi-Layer Perceptron (MLP), Random Forest (RF), Gradient Boosting (GB), and AdaBoost (AB). The machine learning algorithms are validated by the coefficient of determination, accuracy, and Mean Absolute Percentage Error (MAPE). The AB model had a great performance among the four models due to the non-linearity of features and weak learner aggregation with weights on misclassified data. The maximum depth 11 of the base estimator in the AB model is efficient with high performance with 97.6% of accuracy and 0.07% of MAPE. Feature importances, permutation importance, and partial dependence are analyzed in the AB model. The results show that the marginal effect of air humidity, crack depth, and crack temperature in order is higher than that of the others.