• The Journal of Bigdata
• /
• v.2 no.2
• /
• pp.67-74
• /
• 2017

The use of Bigdata plays an important role in all areas of society. Especially in the health care field, the role of Bigdata is very considerable because it deals with people's life and health. However, the interest and awareness of quality control of medical data is markedly low. Because the low-quality medical Bigdata leads to national loss and public health impairment, quality control of medical Bigdata is needed. The purpose of this research is to present the direction of medical Bigdata quality management by examining literature and cases of domestic and foreign medical Bigdata quality management practices. In addition, as a case of medical Bigdata quality control in the Y medical institution in Korea, activities of a Bigdata quality management TFT and results of a survey conducted for major data users in the hospital were presented.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2022.10a
• /
• pp.29-29
• /
• 2022

• ETRI Journal
• /
• v.43 no.5
• /
• pp.835-855
• /
• 2021

With the recent increase in data disclosure, the Comprehensive Knowledge Archive Network (CKAN), which is an open-source data distribution platform, is drawing much attention. CKAN is used together with additional extensions, such as Datastore and Datapusher for data management and Harvest and DCAT for data collection. This study derives the problems of CKAN itself and Harvest Extension. First, CKAN causes two problems of data inconsistency and storage space waste for data deletion. Second, Harvest Extension causes three additional problems, namely source deletion that deletes only sources without deleting data themselves, job stop that cannot delete job during data collection, and service interruption that cannot provide service, even if data exist. Based on these observations, we propose herein an improved CKAN that provides a new deletion function solving data inconsistency and storage space waste problems. In addition, we present an improved Harvest Extension solving three problems of the legacy Harvest Extension. We verify the correctness and the usefulness of the improved CKAN and Harvest Extension functions through actual implementation and extensive experiments.

• Journal of Korea Artificial Intelligence Association
• /
• v.1 no.1
• /
• pp.17-21
• /
• 2023

The primary objective of this research is to utilize machine learning models to analyze factors tailored to each dataset for predicting mental health conditions. The study aims to develop appropriate models based on specific datasets, with the goal of accurately predicting mental health states through the analysis of distinct factors present in each dataset. This approach seeks to design more effective strategies for the prevention and intervention of depression, enhancing the quality of mental health services by providing personalized services tailored to individual circumstances. Overall, the research endeavors to advance the development of personalized mental health prediction models through data-driven factor analysis, contributing to the improvement of mental health services on an individualized basis.

• Journal of IKEEE
• /
• v.24 no.3
• /
• pp.766-776
• /
• 2020

Recently, as interest in machine learning (ML) has increased and research using ML has become active, it is becoming more important to find an optimal hyperparameter combination for various ML models. In this paper, among various hyperparameters, we focused on ML optimizers, and measured and compared the performance of major optimizers using various datasets. In particular, we compared the performance of nine optimizers ranging from SGD, which is the most basic, to Momentum, NAG, AdaGrad, RMSProp, AdaDelta, Adam, AdaMax, and Nadam, using the MNIST, CIFAR-10, IRIS, TITANIC, and Boston Housing Price datasets. Experimental results showed that when Adam or Nadam was used, the loss of various ML models decreased most rapidly and their F1 score was also increased. Meanwhile, AdaMax showed a lot of instability during training and AdaDelta showed slower convergence speed and lower performance than other optimizers.

• Korean Journal of Artificial Intelligence
• /
• v.10 no.2
• /
• pp.7-11
• /
• 2022

OLED displays cannot be used permanently due to burn-in or generation of dark spots due to degradation. Therefore, the time when the display can operate normally is very important. It is close to impossible to physically measure the time when the display operates normally. Therefore, the time that works normally should be predicted in a way other than a physical way. Therefore, if you do computer simulations based on artificial intelligence, you can increase the accuracy of prediction by saving time and continuous learning. Therefore, if we do computer simulations based on artificial intelligence, we can increase the accuracy of prediction by saving time and continuous learning. In this paper, a dataset in the form of development from generation to diffusion of dark spots, which is one of the causes related to the life of OLED, was generated by applying the finite element method. The dark spots were generated in nine conditions, such as 0.1 to 2.0 ㎛ with the size of pinholes, the number was 10 to 100, and 50% with water content. The learning data created in this way may be a criterion for generating an artificial intelligence-based dataset.

• Journal of Convergence for Information Technology
• /
• v.12 no.2
• /
• pp.184-191
• /
• 2022

This study aims to provide basic information necessary to find an efficient management plan for patients using auto insurance. The analysis was conducted on the five-year auto insurance medical expenses review data registered in the health care bigdata Hub from 2016 to 2020. As a result of the analysis, the number one composition ratio of auto insurance inpatient treatment expenses was treatment and surgery fees for Certified tertiary hospitals, hospitalization fees for general hospitals, hospitals and clinics, and treatment and surgery fees for oriental medical institutions and dental hospitals. outpatient treatment expenses was doctor's fee for medical institution, treatment and surgery fees for oriental medical institutions and dental hospitals. The ratio of medication, anesthesia, and special equipment significantly affected the cost of inpatient. And the ratio of physical therapy significantly affected the cost of outpatient.

• The Journal of Bigdata
• /
• v.6 no.2
• /
• pp.99-108
• /
• 2021

Recently, unexpected and more advanced cyber medical treat attacks are on the rise. However, in responding to various patterns of cyber medical threat attack, rule-based security methodologies such as physical blocking and replacement of medical devices have the limitations such as lack of the man-power and high cost. As a way to solve the problems, the medical community is also paying attention to artificial intelligence technology that enables security threat detection and prediction by self-learning the past abnormal behaviors. In this study, there has collecting and learning the medical information data from integrated Medical-Information-Systems of the medical center and introduce the research methodology which is to develop the AI-based Net-Working Behavior Adaptive Information data. By doing this study, we will introduce all technological matters of rule-based security programs and discuss strategies to activate artificial intelligence technology in the medical information business with the various restrictions.

• The Journal of Bigdata
• /
• v.8 no.2
• /
• pp.109-123
• /
• 2023

This study investigates the impact of perceived risk, perceived deception, and negative emotional factors on consumer distrust, dissatisfaction, and boycott intentions towards both YouTubers and products that fail to adequately disclose paid advertisements, commonly referred to as "hidden advertisement." Conducted through an online survey, 306 YouTube viewers from South Korea participated in the study. The findings reveal several key insights. Firstly, perceived deception, perceived risk, and negative emotional factors are identified as contributors to increased consumer distrust and dissatisfaction. Secondly, both consumer distrust and dissatisfaction exhibit positive correlations with boycott intentions towards YouTubers and products. This research seeks to unravel the intricacies of online consumer boycott intentions and aims to elucidate the underlying reasons behind such actions. It is noteworthy that in this context, the ramifications of boycotts extend beyond influencers or YouTubers alone, impacting consumer distrust and dissatisfaction, thereby influencing boycott intentions towards the associated products and exerting a lasting impact on a company's branding efforts.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.51-62
• /
• 2021

In the field of medical artificial intelligence, there have been a lot of researches on disease prediction and classification algorithms that can help doctors judge, but relatively less interested in artificial intelligence that can help medical consumers acquire and judge information. The fact that more than 150,000 questions have been asked about which hospital to go over the past year in NAVER portal will be a testament to the need to provide medical information suitable for medical consumers. Therefore, in this study, we wanted to establish a classification model that classifies 8 medical subjects for symptom text directly described by patients which was collected from NAVER portal to help consumers choose appropriate medical subjects for their symptoms. In order to ensure the validity of the data involving patients' subject matter, we conducted similarity measurements between objective symptom text (typical symptoms by medical subjects organized by the Seoul Emergency Medical Information Center) and subjective symptoms (NAVER data). Similarity measurements demonstrated that if the two texts were symptoms of the same medical subject, they had relatively higher similarity than symptomatic texts from different medical subjects. Following the above procedure, the classification model was constructed using a ridge regression model for subjective symptom text that obtained validity, resulting in an accuracy of 0.73.