• Journal of Internet Computing and Services
• /
• v.23 no.3
• /
• pp.35-45
• /
• 2022

Even in recent years, treatment of first-aid patients is still often delayed due to a shortage of medical resources in marginalized areas. Research on automating the analysis of medical data to solve the problems of inaccessibility for medical services and shortage of medical personnel is ongoing. Computer vision-based medical inspection automation requires a lot of cost in data collection and labeling for training purposes. These problems stand out in the works of classifying lesion that are rare, or pathological features and pathogenesis that are difficult to clearly define visually. Anomaly detection is attracting as a method that can significantly reduce the cost of data collection by adopting an unsupervised learning strategy. In this paper, we propose methods for detecting abnormal images on chest X-RAY images as follows based on existing anomaly detection techniques. (1) Normalize the brightness range of medical images resampled as optimal resolution. (2) Some feature vectors with high representative power are selected in set of patch features extracted as intermediate-level from lesion-free images. (3) Measure the difference from the feature vectors of lesion-free data selected based on the nearest neighbor search algorithm. The proposed system can simultaneously perform anomaly classification and localization for each image. In this paper, the anomaly detection performance of the proposed system for chest X-RAY images of PA projection is measured and presented by detailed conditions. We demonstrate effect of anomaly detection for medical images by showing 0.705 classification AUROC for random subset extracted from the PadChest dataset. The proposed system can be usefully used to improve the clinical diagnosis workflow of medical institutions, and can effectively support early diagnosis in medically poor area.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_2
• /
• pp.793-810
• /
• 2022

Synthetic Aperture Radar (SAR) is considered to be suitable for near real-time inundation monitoring. The distinctly different intensity between water and land makes it adequate for waterbody detection, but the intrinsic speckle noise and variable intensity of SAR images decrease the accuracy of waterbody detection. In this study, we suggest two modules, named 'morphology module' and 'edge-enhanced module', which are the combinations of pooling layers and convolutional layers, improving the accuracy of waterbody detection. The morphology module is composed of min-pooling layers and max-pooling layers, which shows the effect of morphological transformation. The edge-enhanced module is composed of convolution layers, which has the fixed weights of the traditional edge detection algorithm. After comparing the accuracy of various versions of each module for U-Net, we found that the optimal combination is the case that the morphology module of min-pooling and successive layers of min-pooling and max-pooling, and the edge-enhanced module of Scharr filter were the inputs of conv9. This morphologic and edge-enhanced U-Net improved the F1-score by 9.81% than the original U-Net. Qualitative inspection showed that our model has capability of detecting small-sized waterbody and detailed edge of water, which are the distinct advancement of the model presented in this research, compared to the original U-Net.

• Korean Journal of Clinical Laboratory Science
• /
• v.53 no.2
• /
• pp.143-150
• /
• 2021

The recent spread of novel and highly variant pathogenic viruses, including the coronavirus (SARS-CoV-2), has increased the demand for diagnostic testing for rapid confirmation. This has resulted in investigating the functional capability of each space, and preparing facility guidelines to secure the safety of medical technologists. During viral evaluations, there is a requirement of negative pressure facilities along with thread separation, during pre-treatment of samples and before nucleic acid amplification. Space composition therefore needs to be planned by considering unidirectional air flow. This classification of safety management facilities is designated as biosafety level 2, and personal protective equipment is placed accordingly. In case of handling dangerous materials, they need to be carried out of the biosafety cabinet, and sterilizers are required for suitable disposal of infectious agents. A common feature of domestic laboratories is maintenance of the sample pre-treatment space at a negative pressure of -2.5 Pa or less, and arranging separate pre-treatment and reagent preparation spaces during the test process. We believe that the data generated in this study is meaningful, and offers an efficient direction and detailed flow for separation of the inspection process and space functions. Moreover, this study introduces construction of the laboratory by applying the safety management standards.

• Journal of Conservation Science
• /
• v.37 no.6
• /
• pp.712-722
• /
• 2021

This study presents a method for conserving shamanistic spirits in Chiseonggwang Buddha. Scientific investigation has revealed that these spirits have been subject to degeneration as a result of severe exfoliation and pollution. The materials and preservation treatment techniques used in create these shamanistic spirits were identified through visual inspection and using appropriate scientific equipment. The different types of background paper, background material, and color pigments used in create the shamanistic spirits were analyzed using a colorimeter, stereoscopic microscope, and SEM-EDS techniques. The analysis revealed that the pulp paper was used as the background and synthetic fiber polyester as the background material. In addition, the study of the pigment revealed that the color components were all synthetic, except for red lead [Pb₃O₄] and oyster shell white [CaCO₃]. Moreover, it was confirmed that the green pigment, identified as emerald green [Cu(C₂H₃O₂)₂.3Cu(AsO₂)₂], was a major component of shamanistic spirits in the late 19^th century. The shamanistic spirits in Chiseonggwang Buddha were conserved by identifying raw materials and pigments through this detailed analysis.

• Journal of Service Research and Studies
• /
• v.13 no.3
• /
• pp.105-126
• /
• 2023

The domestic used car market continues to grow along with the used car online platform service. The used car online platform service discloses vehicle specifications, accident history, inspection history, and detailed options to service consumers. Most of the preceding studies were predictions of used car prices using vehicle specifications and some options for vehicles. As a result of the study, it was confirmed that there was a nonlinear relationship between used car prices and some specification variables. Accordingly, the researchers tried to solve the nonlinear problem by executing a Machine Learning model. In common, the Regression based Machine Learning model had the advantage of knowing the actual influence and direction of variables, but there was a disadvantage of low Cost Function figures compared to the Decision Tree based Machine Learning model. This study attempted to predict used car prices of six domestic brands by utilizing both vehicle specifications and vehicle options. Through this, we tried to collect the advantages of the two types of Machine Learning models. To this end, we sequentially conducted a regression based Machine Learning model and a decision tree based Machine Learning model. As a result of the analysis, the practical influence and direction of each brand variable, and the best tree based Machine Learning model were selected. The implications of this study are as follows. It will help buyers and sellers who use used car online platform services to predict approximate used car prices. And it is hoped that it will help solve the problem caused by information inequality among users of the used car online platform service.

• Journal of the Korea Institute of Building Construction
• /
• v.23 no.4
• /
• pp.417-428
• /
• 2023

The demolition of domestic infrastructures mirrors other significant construction initiatives in presenting a markedly high accident rate. A comprehensive investigation into the origins of such accidents is crucial for the prevention of future incidents. Upon detailed inspection, the causes of demolition construction accidents are multifarious, encompassing unsafe worker behavior, hazardous conditions, psychological and physical states, and site management deficiencies. While statistics relating to demolition construction accidents are consistently collated and reported, there exists an exigent need for a more foundational cause categorization system based on accident type. Drawing from Heinrich's Domino Theory, this study classifies the origins of accidents(unsafe behavior, unsafe conditions) and human errors(human factors) as per the type of accidents experienced during demolition construction. In this study, a three-step model of QFD-FMEA(Quality Function Deployment - Failure Mode Effect Analysis) is employed to systematically categorize accident causes according to the types of accidents that occur during demolition construction. The QFD-FMEA method offers a technique for cause classification at each stage of the demolition process, including direct causes(unsafe behavior, unsafe environment), and human errors(human factors) through a tri-stage process. The results of this accident cause classification can serve as safety knowledge and reference checklists for accident prevention efforts.

• Journal of Navigation and Port Research
• /
• v.47 no.3
• /
• pp.174-181
• /
• 2023

Five local governments along the Korea-Japan Sea (Jeju, Jeonnam, Gyeongnam, Busan, Ulsan) operate a joint countermeasure committee regarding the marine discharge of contaminated water from the Fukushima nuclear power plant by Japan's Tokyo Electric Power Plant. This study compared and analyzed citizen surveys, response strategies, and detailed action plans conducted by the Jeju Research Institute, Busan Research Institute, and Ulsan Research Institute as part of a study on countermeasures for the marine discharge of contaminated water from the Fukushima nuclear power plant in Japan. The purpose was to present basic data for the preparation of effective measures. As a result of the perception survey, all citizens of local governments showed a strong negative perception of marine discharge regardless of scientific research results, and it is expected that future fisheries and tourism industries will suffer great damage. In response strategies for each local government, building a control tower was found to be the most urgent task common to all local governments. It is judged that this is because it is necessary to break away from the organization-centered system and to respond to the function-centered system for effective response. In terms of response methods, while Jeju and Busan established response plans for each sector, Ulsan City focused on practical responses with step-by-step response measures according to the release time. In terms of content, the establishment of a marine product radiation inspection system and publicity to relieve public anxiety were important. As the marine discharge of contaminated water from the Fukushima nuclear power plant is scheduled to continue until 2030, strengthening the network for sharing research results and achievements among local government research institutes was deemed necessary.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.25 no.6
• /
• pp.479-493
• /
• 2023

The need for safety management has arisen due to the increasing number of years of operated underground structures, such as tunnels and utility tunnels, and accidents caused by those aging infrastructures. However, in the case of privately managed underground utility ducts, there is a lack of detailed guidelines for facility safety and maintenance, resulting in inadequate safety management. Furthermore, the absence of basic design information and the limited space for safety assessments make applying currently used non-destructive testing methods challenging. Therefore, this study suggests non-destructive inspection methods using ultrasonic and impact-echo techniques to assess the quality of underground structures. Thickness, presence of rebars, depth of rebars, and the presence and depth of internal defects are assessed to provide fundamental data for the safety assessment of box-type general underground structures. To validate the proposed methodology, different conditions of concrete specimens are designed and cured to simulate actual field conditions. Applying ultrasonic and impact signals and collecting data through multi-channel accelerometers determine the thickness of the simulated specimens, the depth of embedded rebar, and the extent of defects. The predicted results are well agreed upon compared with actual measurements. The proposed methodology is expected to contribute to developing safety diagnostic methods applicable to general underground structures in practical field conditions.

• Journal of Service Research and Studies
• /
• v.14 no.1
• /
• pp.27-43
• /
• 2024

The market share of online platform services in the used car market continues to expand. And The used car online platform service provides service users with specifications of vehicles, accident history, inspection details, detailed options, and prices of used cars. SUV vehicle type's share in the domestic automobile market will be more than 50% in 2023, Sales of Hybrid vehicle type are doubled compared to last year. And these vehicle types are also gaining popularity in the used car market. Prior research has proposed a used car price prediction model by executing a Machine Learning model for all vehicles or vehicles by brand. On the other hand, the popularity of SUV and Hybrid vehicles in the domestic market continues to rise, but It was difficult to find a study that proposed a used car price prediction model for these vehicle type. This study selects a used car price prediction model by vehicle type using vehicle specifications and options for Sedans, SUV, and Hybrid vehicles produced by domestic brands. Accordingly, after selecting feature through the Lasso regression model, which is a feature selection, the ensemble model was sequentially executed with the same sampling, and the best model by vehicle type was selected. As a result, the best model for all models was selected as the CBR model, and the contribution and direction of the features were confirmed by visualizing Tree SHAP Value for the best model for each model. The implications of this study are expected to propose a used car price prediction model by vehicle type to sales officials using online platform services, confirm the attribution and direction of features, and help solve problems caused by asymmetry fo information between them.

• Journal of Korean Home Economics Education Association
• /
• v.22 no.4
• /
• pp.91-107
• /
• 2010

The purpose of this study was to investigate what middle school Home Economics(HE) teachers perceive, practice and need for self-supervision at school related to HE. Questionnaires were sent by E-mail and 150 were collected. Descriptive statistics including frequency, percentage, average, standard deviation, t-test and ANOVA analysis were reported using SPSS/win 10.1. The results of this research were as follows: First, middle school HE teachers perceived that self-supervision at school was essential since it promoted self reflection of teachers themselves and improved professional skills. Furthermore, peer-coaching was highly preferred. Second, negative responses to the supervision of principal, vice-principal, and peer teachers overwhelmed positive answers. Information exchange among peer teachers was frequent, yet, approximately 22.6% of middle school HE teachers were still avoiding sharing information process for several reasons. About half of the teachers answered that all teachers needed to participate in this process. Third, they pointed out that self-supervision at school was not implemented well because of the lack of time due to the heavy work load, negative and passive attitude for the improvement of teaching-learning activities, administration-centered supervision that did not reflect teachers' opinion, and shortage of economical, and environmental support.. HE teachers perceived that peer teachers who were doing good practices were most helpful for the supervision. Also, they preferred self-evaluation at the end of the self-supervision at school. Forth, to improve self-supervision at school, there were very high demands for reduction of administrative work, additional time, fundamental philosophy toward HE education. Fifth, the purpose and detailed plans of self-supervision were recognized as the results that were democratically derived by the HE teachers. Sixth, class inspection and informal inspection were operated once in a year, and self-training was rarely operated. Peer coaching and self-coaching were operated occasionally. Self-coaching and peer coaching were reported as the most helpful types of supervision. In addition, HE teachers answered that supervision was helpful to teaching method followed by contents, evaluation, and philosophy of education.