• Journal of the Korea Convergence Society
• /
• v.11 no.9
• /
• pp.1-6
• /
• 2020

In this study, we propose an association inference model based on data bias optimization for road hazard detection. This is a mining model based on association analysis to collect user's personal characteristics and surrounding environment data and provide traffic accident prevention services. This creates transaction data composed of various context variables. Based on the generated information, a meaningful correlation of variables in each transaction is derived through correlation pattern analysis. Considering the bias of classified categorical data, pruning is performed with optimized support and reliability values. Based on the extracted high-level association rules, a risk detection model for personal characteristics and driving road conditions is provided to users. This enables traffic services that overcome the data bias problem and prevent potential road accidents by considering the association between data. In the performance evaluation, the proposed method is excellently evaluated as 0.778 in accuracy and 0.743 in the Kappa coefficient.

• Clinical and Experimental Pediatrics
• /
• v.64 no.10
• /
• pp.504-510
• /
• 2021

Population screening of newborns is an extremely important and informative diagnostic approach that allows early identification of babies who are predisposed to the development of a number of serious diseases. Some of these diseases are known and have effective treatment methods. Neonatal screening enables the early diagnosis and subsequent timely initiation of therapy. This helps to prevent serious complications and reduce the percentage of disability and deaths among newborns and young children. Primary immunodeficiency diseases and primary immunodeficiency syndrome (PIDS) are a heterogeneous group of diseases and conditions based on impaired immune system function associated with developmental defects and characterized by various combinations of recurrent infections, development of autoimmune and lymphoproliferative syndromes (genetic defects in apoptosis, gene mutation Fas receptor or ligand), granulomatous process, and malignant neoplasms. Most of these diseases manifest in infancy and lead to serious illness, disability, and high mortality rates. Until recently, it was impossible to identify children with PIDS before the onset of the first clinical symptoms, which are usually accompanied by complications in the form of severe coinfections of a viral-bacterial-fungal etiology. Modern advances in medical laboratory technology have allowed the identification of children with severe PIDS, manifested by T- and/or B-cell lymphopenia and other disorders of the immune system. This review discusses the main existing strategies and directions used in PIDS screening programs for newborns, including approaches to screening based on excision of T-cell receptors and kappa-recombination excision circles, as well as the potential role and place of next-generation sequencing technology to increase the diagnostic accuracy of these diseases.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.11
• /
• pp.626-634
• /
• 2018

This retrospective study investigates the accuracy of triage procedures for pediatric patients in emergency departments (EDs) using the Korean Triage and Acuity Scale (KTAS). The study includes 250 randomly selected initial nursing records and clinical outcomes of pediatric patients who visited one regional ED or a local ED from October 2016 to September 2017. The collected data were analyzed by a qualified expert to determine the true triage score. The accuracy of triage was defined as the agreement between the triage score of the emergency nurses (ENs) and the true triage score as determined by the expert. Based on expert comments, the cause of the triage error was analyzed and the KTAS score was compared with the discharge, length of stay (LOS), and medical cost. The results showed that the degree of agreement in the triage score between the experts and the ENs was excellent (weighted kappa=0.77). Among the causes of triage discordance, the most frequent was the incorrect application of vital signs to the KTAS algorithm criteria (n=13). Patients with high severity KTAS levels 1 and 2 were discharged less often (${\chi}=43.25$, p<0.001). There were significant differences in the length of stay (F=12.39, p<0.001) and cost (F=11.78, p<0.001) between KTAS scores when adjusting for age. The results of this study indicate that KTAS is highly accurate in EDs. Hence, the newly developed triage tool is becoming well established in Korea.

• Journal of the Korean Society of Radiology
• /
• v.13 no.1
• /
• pp.9-14
• /
• 2019

This study aimed to investigate the performance of the S-detect method in breast ultrasonography and to determine how to reduce unnecessary biopsy by comparing the results of the S-detect method and biopsy. Thirty patients who had undergone breast ultrasonography between August and October 2018 and were scheduled to undergo biopsy because of the presence of breast nodules were retrospectively analyzed. The McNemar test was performed to determine whether detection of a malignant breast mass significantly differed between the S-detect method and biopsy. The following results were obtained from the analysis of the S-detect method: sensitivity, 90.9%; specificity, 84.21%; validity, 86.66%; positive predictive value, 76.92%; and negative predictive value, 94.11%. Analysis of the degree of agreement between the S-detect method and biopsy revealed a kappa value as high as 0.724 (p < 0.05), exhibiting good agreement between the two methods. The S-detect method in breast ultrasonography is diagnostically valuable in terms of distinguishing between malignant and benign breast masses, and if used properly before breast biopsy, unnecessary biopsy can be reduced.

• Journal of Broadcast Engineering
• /
• v.27 no.2
• /
• pp.228-239
• /
• 2022

In this paper, we propose an unmanned vehicle scratch detection deep learning model for car sharing services. Conventional scratch detection models consist of two steps: 1) a deep learning module for scratch detection of images before and after rental, 2) a manual matching process for finding newly generated scratches. In order to build a fully automatic scratch detection model, we propose a one-step unmanned scratch detection deep learning model. The proposed model is implemented by applying transfer learning and fine-tuning to the deep learning model that detects changes in satellite images. In the proposed car sharing service, specular reflection greatly affects the scratch detection performance since the brightness of the gloss-treated automobile surface is anisotropic and a non-expert user takes a picture with a general camera. In order to reduce detection errors caused by specular reflected light, we propose a preprocessing process for removing specular reflection components. For data taken by mobile phone cameras, the proposed system can provide high matching performance subjectively and objectively. The scores for change detection metrics such as precision, recall, F1, and kappa are 67.90%, 74.56%, 71.08%, and 70.18%, respectively.

• Journal of the Korean Society of Radiology
• /
• v.16 no.6
• /
• pp.751-759
• /
• 2022

Currently, ultrasound examination for diagnostic ultrasound and health examination purposes is widely used, and it is showing an increasing trend due to the application of health insurance. However, the risk of ultrasound has not been clearly identified so far, and in this study, surface and deep temperature changes according to frequency and mode were measured by using a tissue mimicking phantom and TI and MI values were compared. A simulated phantom was manufactured by adding a small amount of kappa-caraginan powder with acoustic characteristics similar to that of the human body and potassium chloride for solidification, and the change of surface and depth temperature was measured using a surface thermometer and a probe thermometer. As a result, the convex probe using low frequency showed a higher temperature increase than the linear probe using high frequency, so there was a significant difference, and the temperature increase was the highest on the surface, and the depth of 1cm showed a temporary temperature increase, but there was no significant temperature change. There was no change in the deep temperature of 5 cm to 15 cm, and the TI and MI values did not change during the test time. Since only the surface temperature rose during the 15-minute test and there was no temperature change in the core, so it is not expected to show a temperature change that is harmful to the human body. However, it is thought that prolonged examination of one area may cause temperature rise, so it should be avoided.

• The Journal of Advanced Prosthodontics
• /
• v.14 no.4
• /
• pp.203-211
• /
• 2022

PURPOSE. The aim of this study was to introduce rating criteria to evaluate student performance in a newly developed, digital wax-up preclinical program for computer-aided design (CAD) of full-coverage crowns and preliminarily investigate the reliability and internal consistency of the rating system. MATERIALS AND METHODS. This study, conducted in 2017, enrolled 47 fifth-year dental students of Okayama University Dental School. Digital wax-up training included a fundamental practice using computer graphics (CG), multipurpose CAD software programs, and an advanced practice to execute a digital wax-up of the right mandibular second molar (#47). Each student's digital wax-up work (stereolithography data) was evaluated by two instructors using seven qualitative criteria. The total qualitative score (0-90) of the criteria was calculated. The total volumetric discrepancy between each student's digital wax-up work and a reference prepared by an instructor was automatically measured by the CAD software. The inter-rater reliability of each criterion was analyzed using a weighted kappa index. The relationship between the total volume discrepancy and the total qualitative score was analyzed using Spearman's correlation. RESULTS. The weighted kappa values for the seven qualitative criteria ranged from 0.62 - 0.93. The total qualitative score and the total volumetric discrepancy were negatively correlated (ρ = -0.27, P = .09, respectively); however, this was not statistically significant. CONCLUSION. The established qualitative criteria to evaluate students' work showed sufficiently high inter-rater reliability; however, the digitally measured volumetric discrepancy could not sufficiently predict the total qualitative score.

• Korean Journal of Remote Sensing
• /
• v.39 no.3
• /
• pp.269-282
• /
• 2023

The purpose of this study was to construct land cover maps using a deep learning model and to select the optimal deep learning model for land cover classification by adjusting the dataset such as input image size and Stride application. Two types of deep learning models, the U-net model and the DeeplabV3+ model with an Encoder-Decoder network, were utilized. Also, the combination of the two deep learning models, which is an Ensemble model, was used in this study. The dataset utilized RapidEye satellite images as input images and the label images used Raster images based on the six categories of the land use of Intergovernmental Panel on Climate Change as true value. This study focused on the problem of the quality improvement of the dataset to enhance the accuracy of deep learning model and constructed twelve land cover maps using the combination of three deep learning models (U-net, DeeplabV3+, and Ensemble), two input image sizes (64 × 64 pixel and 256 × 256 pixel), and two Stride application rates (50% and 100%). The evaluation of the accuracy of the label images and the deep learning-based land cover maps showed that the U-net and DeeplabV3+ models had high accuracy, with overall accuracy values of approximately 87.9% and 89.8%, and kappa coefficients of over 72%. In addition, applying the Ensemble and Stride to the deep learning models resulted in a maximum increase of approximately 3% in accuracy and an improvement in the issue of boundary inconsistency, which is a problem associated with Semantic Segmentation based deep learning models.

• Proceedings of the KSME Conference
• /
• 2007.05b
• /
• pp.2955-2960
• /
• 2007

To control the coating thickness of zinc in the process of continuous hot-dip galvanizing, it is known from early day that the gas wiping through an air knife system is the most effective because of the obtainable of uniformity of coating thickness, possibility of thin coating, working ability in high speed and simplicity of control. But, the gas wiping using in the galvanizing process brings about a problem of splashing from the strip edge for a certain high speed of coating. And, it is known that the problem of splashing is caused mainly by the existence of separation bubble at the neighbor of the strip surface. In theses connections, in the present study, we proposed two kinds of air knife systems having the same expansion rate of nozzle, and the jet structures and coating thicknesses from a conventional and new proposed nozzles are compared. In numerical analysis, the governing equations consisted of two-dimensional time dependent Navier-Stokes equations, standard ${\kappa}-{\varepsilon}$ turbulence model to solve turbulence stress and so on are employed. As a result, it is found that it had better to use the constant rate nozzle from the point view of the energy saving to obtain the same coating thickness. Also, to reduce the size of separation bubble and to enhance the cutting ability at the strip, it is recommendable to use an air knife having the constant expansion rate nozzle.

• Journal of Sasang Constitutional Medicine
• /
• v.18 no.1
• /
• pp.75-90
• /
• 2006

1. Objectives The Sasang Constitution has been studied in many parts and one of the most common inquiries is the self-reporting questionnaire. But the established investigation has the problem that the respondents are not fully aware of the questionnaires and answer them. To settle this problem, it's been made new questionnaires through two steps. 2. Methods At first step, the testers ate classified into Yangin(陽人) and Eumin(陰人). And then, Taeyangin is distinguished from Soyangin likewise Taeumin is told from Soeumin. It's called 'The Two Step Questionnaire for the Sasang Constitution Diagnosis(TS-QSCD)'. This new method is tested by 160 testers and Woosuk university students whose constitution ate confirmed to make clear clinical uses 3. Results and Conclusions Questionnaire Sasang Constitution corresponds with The Real Sasang Constitution at the rate of 71.87%. Only 5.63% has shown an error at the first step. Every experimenters by constitutions, the 56 objects of 74 Taeumin are confirmed the same as it is. It has 84.85% accuracy. The 27 objects of 32 Soeumin come to the same thing and it has 69.23% accuracy. Similarly, the 32 objects of 42 Soyangin come to the same conclusion and 72.73% accuracy high As the result, in comparison to the Real Constitution with the Constitution by questionnaires, the accord comes out Kappa Indices 0.6427866. This result is comparatively high. Chi-square Test can be shown statistical meaning as well.