• Journal of Digital Convergence
• /
• v.19 no.6
• /
• pp.251-258
• /
• 2021

In this paper, we proposed an encoder-decoder model utilizing residual learning to improve the accuracy of the U-Net-based semantic segmentation method. U-Net is a deep learning-based semantic segmentation method and is mainly used in applications such as autonomous vehicles and medical image analysis. The conventional U-Net occurs loss in feature compression process due to the shallow structure of the encoder. The loss of features causes a lack of context information necessary for classifying objects and has a problem of reducing segmentation accuracy. To improve this, The proposed method efficiently extracted context information through an encoder using residual learning, which is effective in preventing feature loss and gradient vanishing problems in the conventional U-Net. Furthermore, we reduced down-sampling operations in the encoder to reduce the loss of spatial information included in the feature maps. The proposed method showed an improved segmentation result of about 12% compared to the conventional U-Net in the Cityscapes dataset experiment.

• Journal of Platform Technology
• /
• v.8 no.3
• /
• pp.3-9
• /
• 2020

As the need for sharing for research purposes in the medical field increases, the use of a Common Data Model (CDM) is increasing. However, when sharing CDM data, there are some problems in that access control and personal information in the data are not protected. In this paper, in order to solve this problem, access to CDM data is controlled by using an encryption method in a blockchain network, and information of CDM data is recorded to enable tracking. In addition, IPFS was used to share a large amount of CDM data, and Celery was used to automate the sharing process. In other words, we propose a multi-channel automation system in which the information required for CDM data sharing is shared by a trust-based technology, a distributed file system, and a message queue for automation. This aims to solve the problem of access control and personal information protection in the data that occur in the process of sharing CDM data.

• Journal of agricultural medicine and community health
• /
• v.47 no.1
• /
• pp.1-13
• /
• 2022

Objectives: This study aimed to establish a linkage model involving regional responsible medical institutions after analyzing the existing conditions and deriving problems through qualitative analysis within the community care system. Methods: A total of 14 participants of this study were selected through the snowball sampling method, including 7 community care service providers and 7 service users. As for the research data, primary data were collected through interviews, and as a result of analyzing according to Aday&Anderson' model, a total of 5 catergories, 8 topics, and 22 sub theme were derived. Results: The problem derived from the interview is that division services are provided for each institution due to the absence of a key central institution of community care system, and users' commercial institutions is unclear. The second is the inconsistency between the needs and supply for community care, resulting in a possibility of delay in returning to the community after discharge. Based on these problems, it is necessary to unify it as an community care window of the Dong-community center. In addition, there is a need for public health centers to play an active role, and to establish a public-private joint system with the Health and Living Support Center to establish a model that can play a certain role. Conclusions: Therefore, based on the results of this study, it can be used as basic data when constructing community care model and applying it as an expanded model in the future.

• Journal of radiological science and technology
• /
• v.45 no.2
• /
• pp.111-116
• /
• 2022

In this study, the applicability of machine learning for the development of a simulator for general X-ray examination education is evaluated. To this end, k-nearest neighbor(kNN), support vector machine(SVM) and neural network(NN) classification models are analyzed to present the most suitable model by analyzing the results. Image data was obtained by taking 100 photos each corresponding to Posterior anterior(PA), Posterior anterior oblique(Obl), Lateral(Lat), Fan lateral(Fan lat). 70% of the acquired 400 image data were used as training sets for learning machine learning models and 30% were used as test sets for evaluation. and prediction model was constructed for right-handed PA, Obl, Lat, Fan lat image classification. Based on the data set, after constructing the classification model using the kNN, SVM, and NN models, each model was compared through an error matrix. As a result of the evaluation, the accuracy of kNN was 0.967 area under curve(AUC) was 0.993, and the accuracy of SVM was 0.992 AUC was 1.000. The accuracy of NN was 0.992 and AUC was 0.999, which was slightly lower in kNN, but all three models recorded high accuracy and AUC. In this study, right-handed PA, Obl, Lat, Fan lat images were classified and predicted using the machine learning classification models, kNN, SVM, and NN models. The prediction showed that SVM and NN were the same at 0.992, and AUC was similar at 1.000 and 0.999, indicating that both models showed high predictive power and were applicable to educational simulators.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.7
• /
• pp.57-64
• /
• 2022

In this paper, the definition and overview of digital health care that has emerged recently, core technology, and We would like to propose a plan to establish a next-generation information protection system that can protect digital healthcare devices and data from cyber attacks. Various vulnerabilities exist for digital healthcare devices and data, and cyber attacks are possible for those vulnerabilities. Through an attack on digital health care devices and information and communication networks, it can directly adversely affect human life and health, Since digital healthcare data contains sensitive and personal information, it is essential to safely protect it from cyber attacks. In the case of this proposal, for continuous safe management of data and cyber attacks on equipment and communication networks for digital health devices, It is expected to be able to respond more effectively and continuously through the establishment of the next-generation information protection system.

• Journal of Industrial Convergence
• /
• v.20 no.6
• /
• pp.7-15
• /
• 2022

Recently, due to the development of AI and big data technologies following the advent of the era of the 4th Industrial Revolution, the emerging metaverse industry is emerging as a new business, and in particular, from this point of view, this paper analyzes the history of metaverse and the pros and cons of "Geppetto", which is the most popular in the Korean metaverse market, and aims to give an appropriate direction for future development based on this. In order to carry out this study, we first used SWOT analysis techniques as an initial enterprise analysis method to examine the strengths and weaknesses, opportunities and threat requirements, and derive the status of each factor. Based on the factors in each of the subsequent derivatives, we wanted to explore the TOWS development strategy and present significant implications based on this.

• Journal of Family Resource Management and Policy Review
• /
• v.26 no.3
• /
• pp.19-34
• /
• 2022

There are growing concerns about debt insolvency among youth and low-income households. The deterioration in household debt quality among young people is due to a combination of sluggish employment, an increase in student loan burden and an increase in high-interest loans from the secondary financial sector. The purpose of this study was to explore the possibility of household debt default among young borrowers in Korea and to predict the factors affecting this possibility. This study utilized the 2021 Household Finance and Welfare Survey and used random forest algorithm to comprehensively analyze factors related to the possibility of default risk among young adults. This study presented the importance index and partial dependence charts of major determinants. This study found that the ratio of debt to assets(DTA), medical costs, household default risk index (HDRI), communication costs, and housing costs the focal independent variables.

• Informatization Policy
• /
• v.29 no.4
• /
• pp.43-66
• /
• 2022

With the development of artificial intelligence technology, competition for artificial intelligence technology patents around the world is intensifying. During the period 2000 ~ 2021, artificial intelligence technology patent applications at the US Patent and Trademark Office have been steadily increasing, and the growth rate has been steeper since the 2010s. As a result of analyzing Korea's artificial intelligence technology competitiveness through patent indices, it is evaluated that patent activity, impact, and marketability are superior in areas such as auditory intelligence and visual intelligence. However, compared to other countries, overall Korea's artificial intelligence technology patents are good in terms of activity and marketability, but somewhat inferior in technological impact. While noise canceling and voice recognition have recently decreased as topics for artificial intelligence, growth is expected in areas such as model learning optimization, smart sensors, and autonomous driving. In the case of Korea, efforts are required as there is a slight lack of patent applications in areas such as fraud detection/security and medical vision learning.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.251-258
• /
• 2022

This study aims to provide basic data for reinforcing the learning competency of paramedic students by analyzing the performance, importance, and demand for the major curriculum of them. The participants of the study was 217 students from the Department of Emergency medical technology from 3 universities in Chungnam, and the survey data collection period was from December 13 to December 24, 2021. As a result of the study, 'Education for Ambulance management', 'Education for maintaining professionalism after graduation', 'Education for In-hospital patient monitoring' are highly required by Borich need, and 'Education for medical oder from a doctor, Education for han dover to In-hospital medical staff', 'Education for non-traumatic emergency patient treatment', 'Education for In-hospital patient monitoring', and 'Education for In-hospital medical assistance' are the top priority areas of the LF model. It is judged that it is necessary to reinforce the curriculum corresponding to in order to strengthen the learning capabilities of paramedic students.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.6
• /
• pp.243-250
• /
• 2023

Chest X-ray is radiological examination for xeamining the lungs and haert, and is particularly widely used for diagnosing lung disease. Since the quality of these chest X-rays can affect the doctor's diagnosis, the process of evaluating the quality must necessarily go through. This process can involve the subjectivity of radiologists and is manual, so it takes a lot of time and csot. Therefore, in this paper, based on the chest X-ray quality assessment guidelines used in clinical settings, we propose a tool that automates the five quality assessments of artificial shadow, coverage, patient posture, inspiratory level, and permeability. The proposed tool reduces the time and cost required for quality judgment, and can be further utilized in the pre-processing process of selecting high-quality learning data for the development of a learning model for diagnosing chest lesions.