• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.21-31
• /
• 2021

As the COVID-19 pandemic rapidly changes healthcare around the globe, the need for smart healthcare that allows for remote diagnosis is increasing. The current classification of respiratory diseases cost high and requires a face-to-face visit with a skilled medical professional, thus the pandemic significantly hinders monitoring and early diagnosis. Therefore, the ability to accurately classify and diagnose respiratory sound using deep learning-based AI models is essential to modern medicine as a remote alternative to the current stethoscope. In this study, we propose a deep learning-based respiratory sound classification model using data collected from medical experts. The sound data were preprocessed with BandPassFilter, and the relevant respiratory audio features were extracted with Log-Mel Spectrogram and Mel Frequency Cepstral Coefficient (MFCC). Subsequently, a Parallel CNN network model was trained on these two inputs using stacking ensemble techniques combined with various machine learning classifiers to efficiently classify and detect abnormal respiratory sounds with high accuracy. The model proposed in this paper classified abnormal respiratory sounds with an accuracy of 96.9%, which is approximately 6.1% higher than the classification accuracy of baseline model.

• Herbal Formula Science
• /
• v.30 no.2
• /
• pp.85-93
• /
• 2022

Objectives : This study investigated anti-inflammatory effects of Nardotidis seu Sulculii Concha water extract (NSCE) against restraint-induced stress. Methods : In vivo, NSCE was orally administered to male white mice at concentrations of 250 mg/kg and 500 mg/kg for 3 days, and then restraint-induced stress was induced for 6 hours. The level of liver damage was measured by serum aspartate aminotransferase (AST), alanine aminotransferase (ALT) and lactate dehydrogenase (LDH). The stress-related hormones such as cortisol and corticosterone were measured by ELISA assay. Also, western blot analysis was performed to detect expression of mitogen-activated protein kinase (MAPK) and cyclooxygenase-2 (COX-2) proteins. Pathological changes were observed by hematoxylin and eosin (H&E) staining of the liver tissue, and Immunohistochemical (IHC) staining was performed to examine liver inflammation through macrophage infiltration. Results : The AST, ALT, LDH and the stress related hormones such as cortisol and corticosterone were significantly decreased in the NSCE treated group compared with stress group. In histological analysis, H&E staining of liver tissues did not detect the hepatic injury or damage in all groups. As a result of IHC staining, it was confirmed that infiltration of macrophages was increased in the stress-induced group, but decreased in the group treated with NSCE. The COX-2 and MAPK proteins expression was significantly increased by restraint-induced stress, but these proteins were decreased in the NSCE treated group. Conclusions : These results suggest that NSCE has the anti-inflammatory activity in restraint-induced stress model, and it is believed that NSCE can be used for the prevention of liver inflammation.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.25 no.1
• /
• pp.77-100
• /
• 2022

In the era of low growth, many provincial cities are experiencing population decline and aging. Population decline phenomena such as reduction of productive manpower, reduction of finances, deterioration of quality of life, and collapse of the community base are occurring in a chain and are being pushed to the brink of extinction of the cities. This study aims to propose a methodology to objectively estimate the employment creation centers and setting the basic unit of industrial-centered zoning by applying spatial statistical techniques and GIS for the application of the compact city plan as an efficient spatial management policy in a city with a declining population. In details, based on reviewing previous studies on compact city, 'employment complex index(ECI)' were defined considering the number of workers, the number of settlers, and the area of development land, the employment creation center was estimated by applying the 'Local Moran's I' and 'Getis-Ord's Hot-Spot Analysis'. As a case study, changes in the four years of 2013, 2015, 2017, and 2019 were compared and analyzed for Changwon City. As a result, it was confirmed that the employment creation center is becoming compacted and polycentric, which is a significant result that reflects the actual situation well. This results provide the basic data for functional and institutional territorial governance for the regional revitalization platform, and provide meaningful information necessary for spatial policy decision-making, such as population reduction, regional gross domestic product, and public facility arrangement that can respond to energy savings, transportation plans, and medical and health plans.

• KNOM Review
• /
• v.23 no.2
• /
• pp.18-28
• /
• 2020

With the development of the virtual community, the benefits that IT technology provides to people in fields such as healthcare, industry, communication, and culture are increasing, and the quality of life is also improving. Accordingly, there are various malicious attacks targeting the developed network environment. Firewalls and intrusion detection systems exist to detect these attacks in advance, but there is a limit to detecting malicious attacks that are evolving day by day. In order to solve this problem, intrusion detection research using machine learning is being actively conducted, but false positives and false negatives are occurring due to imbalance of the learning dataset. In this paper, a Random Oversampling method is used to solve the unbalance problem of the UNSW-NB15 dataset used for network intrusion detection. And through experiments, we compared and analyzed the accuracy, precision, recall, F1-score, training and prediction time, and hardware resource consumption of the models. Based on this study using the Random Oversampling method, we develop a more efficient network intrusion detection model study using other methods and high-performance models that can solve the unbalanced data problem.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.6
• /
• pp.609-618
• /
• 2021

The spread and damage of COVID-19 are putting significant pressure on the world, including Korea. Most countries place restrictions on movement and gathering to minimize contact between citizens and these policies have brought new changes to social patterns. This study generated traffic volume data on the scale of a road network using taxi movement data collected in the early stages of the COVID-19 third pandemic to analyze the impact of COVID-19 on movement patterns. After that, correlation analysis was performed with the data of confirmed cases in Daegu Metropolitan City and Local Moran's I was applied to analyze the effect of spatial characteristics. As a result, in terms of the overall road network, the number of confirmed cases showed a negative correlation with taxi driving and at least -0.615. It was confirmed that citizens' movement anxiety was reflected as the number of confirmed cases increased. The commercial and industrial areas in the center of the city confirmed the cold spot with a negative correlation and low-low local Mona's I. However, the road network around medical institutions such as hospitals and spaces with spatial characteristics such as residential complexes was high-high. In the future, this analysis could be used for preventive measures for policymakers due to COVID-19.

• Korean Journal of Veterinary Service
• /
• v.45 no.4
• /
• pp.325-330
• /
• 2022

Distichiasis is one of the diseases commonly encountered in companion animals, and these abnormal eyelashes cause corneal ulcers, continuous eye irritation, eye pain, glare, epiphora, foreign body sensation and can cause corneal opacity and vision loss in severe cases. In this study, an eyelash epilation needle for animals was developed and applied to a real case, and the results were observed. In a case of corneal ulcer caused by distichiasis of a 2-year-old Shih Tzu, a high-frequency surgical instrument for animals was converted into an electric epilation needle to attempt a procedure to destroy the eyelash hair follicles on the upper eyelid. A epilation needle was developed to have a diameter of 0.1 mm and a length of 4 mm at the end of the handle of DOCTANZ 400, an electrosurgical instrument for animals only. In the procedure, 2~3 mm of an epilation needle was inserted into the hair follicle, and 1 watt of electric power was applied to the hair follicle for about 5 sec. to carry out electrolysis until white bubbles were generated around the meibomian glands thereby destroying the hair follicle. As a result, no eyelashes grew any longer in the treated area indicating that the treatment was successful. It is hoped that the method developed in this study will be applied so that it will be widely used as a treatment method for distichiasis in companion animals that can be frequently seen hereafter.

• Resources Recycling
• /
• v.32 no.3
• /
• pp.3-8
• /
• 2023

This study discussed production, demand, and future prospects of rubidium, which is an alkali group metal that is highly reactive to various media and requires carefulness in handling, but no significant environmental hazard of rubidium has been reported yet. Rubidium is used in various fields such as optoelectronic equipment, biomedical, and chemical industries. Because of difficulty in production as well as limited demand, the transaction price of rubidium is relatively high, but its detail information such as market status and potential growth is uncertain. However, if the mass production of versatile ultra-high-performance equipment such as quantum computers and the necessity of rubidium use in the equipment are confirmed, there is a possibility that the rubidium market will expand in the future. Rubidium is often found together with lithium, beryllium, and cesium, and may be present in granite containing minerals such as lepidolite and pollucite, as well as in seawater and industrial waste. Several technologies such as acid leaching, roasting, solvent extraction, and adsorption are used to recover rubidium. The maximum recovery efficiency of the rubidium from the sources and the processing above is generally high, but, in many practices, rubidium is not the main recovery target, and therefore the actual recovery effects should depend on presence of other valuable components or impurities, together with recovery costs, energy consumption, environmental issues, etc. In conclusion, although the current production and consumption of rubidium are limited, with consideration of the possible market fluctuations according to the emergence of large-scale demand sources, etc., further investigations by related institutions should be necessary.

• 한국노년학
• /
• v.31 no.3
• /
• pp.527-538
• /
• 2011

The purpose of this investigation is to analyze the effect of employment and quality of employment of senior job training. The questionnaire administered to 576 senior job trainees(over 50 years old) and 28 training institute before and after job training to survey job training characteristics, training institute characteristics and trainee characteristics. The results were as follows : First, independence test(X2) revealed that occupational category, period of training, type of institution, training history, location, and trainee's education level had significant difference on employment. Second, The probability of employment was higher in new and well-equipped public institution than private or old public institution. Third, compared with the prior wage, the wage after training decreased. This result suggested that the unemployed senior can hardly be reemployed in prior level job. The result of analysis on the cases of increased wage after training revealed that the trainees who was women, had a little dependent family, a shorter unemployed period, and a higher prior wage showed higher wage than prior wage after training.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.67-76
• /
• 2023

Although deep learning models are making innovative achievements in the field of computer vision, the problem of vulnerability to adversarial examples continues to be raised. Adversarial examples are attack methods that inject fine noise into images to induce misclassification, which can pose a serious threat to the application of deep learning models in the real world. In this paper, we propose a model that detects adversarial examples using differences in predictive values between edge-learned classification models and underlying classification models. The simple process of extracting the edges of the objects and reflecting them in learning can increase the robustness of the classification model, and economical and efficient detection is possible by detecting adversarial examples through differences in predictions between models. In our experiments, the general model showed accuracy of {49.9%, 29.84%, 18.46%, 4.95%, 3.36%} for adversarial examples (eps={0.02, 0.05, 0.1, 0.2, 0.3}), whereas the Canny edge model showed accuracy of {82.58%, 65.96%, 46.71%, 24.94%, 13.41%} and other edge models showed a similar level of accuracy also, indicating that the edge model was more robust against adversarial examples. In addition, adversarial example detection using differences in predictions between models revealed detection rates of {85.47%, 84.64%, 91.44%, 95.47%, and 87.61%} for each epsilon-specific adversarial example. It is expected that this study will contribute to improving the reliability of deep learning models in related research and application industries such as medical, autonomous driving, security, and national defense.

• Journal of Service Research and Studies
• /
• v.13 no.4
• /
• pp.70-96
• /
• 2023

Recently, the high turnover rate of nursing staff and the problems caused by increased job stress have been highlighted as social issues, and the problem of 'Taeoom' in nursing organizations has received increasing attention. Therefore, the purpose of this study is to propose a solution to the Taeoom problem, including bullying in the nursing work environment, as there is an urgent need to find a solution to prevent and overcome this problem. For this purpose, based on the S-O-R framework and previous studies, job stress and turnover intention were derived as outcome variables of Taeoom and communication competence as an antecedent factor, and a research model was constructed with the expectation that mindfulness and social support would serve as moderating variables to help overcome this problem. Data were collected through a survey of 300 nurses who had experienced Taeoom within the past year, and the hypotheses were tested using a structural equation model. The results revealed that the higher the communication competence of nurses, the less they perceived the damage of Taeoom, and that the damage caused by Taeoom leads to turnover intention through high job stress. In addition, mindfulness and social support significantly attenuated the positive effects of burnout on job stress and job stress on turnover intention, respectively. The significance of this study is that it proposed an extended P-S-O-R framework by adding a prevention stage to the existing S-O-R framework, and further tested the moderating effects of mindfulness and social support variables. It is expected that the findings of this study will provide concrete guidelines to prevent and overcome the Taeoom problem that can be applied in practice.