• Nutrition Research and Practice
• /
• v.16 no.5
• /
• pp.616-627
• /
• 2022

BACKGROUND/OBJECTIVES: Vitamin E is essential for health, and although vitamin E deficiency seems rare in humans, studies on estimates of dietary intake are lacking. This study aimed to estimate dietary vitamin E intake, evaluate dietary adequacy of vitamin E, and detail major food sources of vitamin E in the Korean population. SUBJECTS/METHODS: This study used data from the Korea National Health and Nutrition Examination Survey (KNHANES) 2016-2019. Individuals aged ≥ 1 year that participated in a nutrition survey (n = 28,418) were included. Dietary intake was assessed by 24-h recall and individual dietary vitamin E intake was estimated using a newly established vitamin E database. Dietary adequacy was evaluated by comparing dietary intake with adequate intake (AI) as defined by Korean Dietary Reference Intakes 2020. RESULTS: For all study subjects, mean daily total vitamin E intake was 7.00 mg α-tocopherol equivalents, which was 61.6% of AI. The proportion of individuals that consumed vitamin E at above the AI was 12.9%. Inadequate intake was observed more in females, older individuals, rural residents, and those with a low income. Mean daily intakes of tocopherol (α-, β-, γ-, and δ-forms) and tocotrienol were 6.02, 0.30, 6.19, 1.63, and 1.61 mg, respectively. The major food groups that contributed to total dietary vitamin E intake were grains (22.3%), seasonings (17.0%), vegetables (15.3%), and fish, and shellfish (7.4%). The top 5 individual food items that contributed to total vitamin E intake were baechu kimchi, red pepper powder, eggs, soybean oil, and rice. CONCLUSIONS: This study shows that mean dietary vitamin E intake by Koreans did not meet the reference adequate intake value. To better understand the status of vitamin E intake, further research is needed that considers intake from dietary supplements.

• Korean Journal of Animal Reproduction
• /
• v.18 no.2
• /
• pp.95-99
• /
• 1994

The purpose of the present study was to determine the in vivo effect of oxytocin antagonist-I(Al) on uterine oxytocin receptor number (Rn) and/or binding affinity (Kd) in the estrous rat. Anesthetized rats were given a bolus infusion of control or 5${\mu}\textrm{g}$ of AI and sacri-ficed 0.5 and 4 hours later. The uterine tissue was removed, trimmed and frozen. Membrane oxytocin receptors were isolated after homogenization of uterine tissue and differential ultracentrifugation. The oxytocin receptor assay was performed by saturation with cold oxytocin competion with a high specific activity oxytocin antagonist. Rn and Kds were determined by nonlinear curve fitting methods. No differences(p>0.05) between the AI and control treated animals in either oxytocin receptor number or binding affinity was detected in this study. These data suggest that the major mode of action of AI is via competitive inhibition at the uterine oxytocin receptor and not by altering receptor number or binding affinity.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.4
• /
• pp.227-233
• /
• 2021

Predictive maintenance has been one of important applications of data science technology that creates a predictive model by collecting numerous data related to management targeted equipment. It does not predict equipment failure with just one or two signs, but quantifies and models numerous symptoms and historical data of actual failure. Statistical methods were used a lot in the past as this predictive maintenance method, but recently, many machine learning-based methods have been proposed. Such proposed machine learning-based methods are preferable in that they show more accurate prediction performance. However, with the exception of some learning models such as decision tree-based models, it is very difficult to explicitly know the structure of learning models (Black-Box Model) and to explain to what extent certain attributes (features or variables) of the learning model affected the prediction results. To overcome this problem, a recently proposed study is an explainable artificial intelligence (AI). It is a methodology that makes it easy for users to understand and trust the results of machine learning-based learning models. In this paper, we propose an explainable AI method to further enhance the explanatory power of the existing learning model by targeting the previously proposedpredictive model [5] that learned data from a core facility (Hyper Compressor) of a domestic chemical plant that produces polyethylene. The ensemble prediction model, which is a black box model, wasconverted to a white box model using the Explainable AI. The proposed methodology explains the direction of control for the major features in the failure prediction results through the Explainable AI. Through this methodology, it is possible to flexibly replace the timing of maintenance of the machine and supply and demand of parts, and to improve the efficiency of the facility operation through proper pre-control.

• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.51-62
• /
• 2022

AI-based speed prediction studies have been conducted quite actively. However, while the importance of explainable AI is emerging, the study of interpreting and reasoning the AI-based speed predictions has not been carried out much. Therefore, in this paper, 'Explainable Deep Graph Neural Network (GNN)' is devised to analyze the speed prediction and assess the nearby road influence for reasoning the critical contributions to a given road situation. The model's output was explained by comparing the differences in output before and after masking the input values of the GNN model. Using TOPIS traffic speed data, we applied our GNN models for the major congested roads in Seoul. We verified our approach through a traffic flow simulation by adjusting the most influential nearby roads' speed and observing the congestion's relief on the road of interest accordingly. This is meaningful in that our approach can be applied to the transportation network and traffic flow can be improved by controlling specific nearby roads based on the inference results.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2008.05a
• /
• pp.29-32
• /
• 2008

The electron charging and degradation of anode phosphor layers are showed major problems in high electric field with anode electrode of field emission devices. An AI metal layer on the phosphor layer may get rid of these problems. This Hetero-metal-oxide phosphor layer are formed with the roughness of phosphor surface layer without interlayer and cannot be given rise to enhance the luminance efficiency. In order to enhance the brightness, an anode layer need to be flated between phosphor layer and AI metal layer in anode electrode. After optimizing the anode phosphor layer, an anode layer with AI metal and inter layer increased the brightness and luminescence efficiency 1.2 times more than only phosphor laver in anode.

• Electronics and Telecommunications Trends
• /
• v.36 no.2
• /
• pp.65-74
• /
• 2021

In this paper, we discussed the necessity and importance of introducing feature stores to establish a collaborative environment between data engineering work and data science work. We examined the technology trends of feature stores by analyzing the status of some major feature stores. Moreover, by introducing a feature store, we can reduce the cost of performing artificial intelligence (AI) projects and improve the performance and reliability of AI models and the convenience of model operation. The future task is to establish technical requirements for establishing a collaborative environment between data engineering work and data science work and develop a solution for providing a collaborative environment based on this.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.3
• /
• pp.177-192
• /
• 2023

The employment rate of university graduates has been decreasing significantly recently. With the advent of the Fourth Industrial Revolution, the demand for software employment has increased. It is necessary to analyze the factors for software employment of university graduates. This paper proposes explainable software employment model of university graduates using machine learning and explainable AI. The Graduates Occupational Mobility Survey(GOMS) provided by the Korea Employment Information Service is used. The employment model uses boosting machine learning. Then, performance evaluation is performed with four algorithms of boosting model. Moreover, it explains the factors affecting the employment using SHAP. The results indicates that the top 3 factors are major, employment goal setting semester, and vocational education and training.

• International Journal of Advanced Culture Technology
• /
• v.11 no.4
• /
• pp.417-422
• /
• 2023

AI blockchain technology, which is attracting attention as a core technology of the 4th Industrial Revolution, is a technology that can be used as an important means of innovation not only in the current gaming industry but also in various industrial fields. This paper extracts the platforms and types of blockchain games currently ranked within the top 100 on the blockchain app (DApp) sites State Of The DApps, DApp.com, and Dapp Rader and introduces the top games on major platforms. As a result of extracting platforms and types, the top games were mainly based on Ethereum, EOS, and Steam. However, the results showed that there are significantly more games based on the Ethereum platform, which are stable, easy to apply, and have a low barrier to entry due to the large number of users and DApps. We plan to improve awareness of blockchain games by studying the characteristics that only blockchain games have.

• Electronics and Telecommunications Trends
• /
• v.39 no.4
• /
• pp.82-92
• /
• 2024

This paper introduces the technological development trends in on-device SLMs (Small Language Models). Large Language Models (LLMs) based on the transformer model have gained global attention with the emergence of ChatGPT, providing detailed and sophisticated responses across various knowledge domains, thereby increasing their impact across society. While major global tech companies are continuously announcing new LLMs or enhancing their capabilities, the development of SLMs, which are lightweight versions of LLMs, is intensely progressing. SLMs have the advantage of being able to run as on-device AI on smartphones or edge devices with limited memory and computing resources, enabling their application in various fields from a commercialization perspective. This paper examines the technical features for developing SLMs, lightweight technologies, semiconductor technology development trends for on-device AI, and potential applications across various industries.

• Neonatal Medicine
• /
• v.18 no.2
• /
• pp.211-220
• /
• 2011

Purpose: Late-onset hypotension in preterm infants is not a rare condition. Late circulatory collapse due to adrenal insufficiency (AI) is one of the major causes of late-onset hypotension. We assessed the incidence and causes of late-onset hypotension. We also compared the clinical findings according to the presence of AI. Methods: In total, 244 preterm infants with a gestational age ${\leq}$32 weeks and who were admitted to the neonatal intensive care unit (NICU) of Seoul National University Boramae Hospital and Seoul National University Hospital from January 2009 to April 2011 were included. Clinical findings were analyzed retrospectively. Results: Forty-four infants (18%) suffered from late-onset hypotension. Hydrocortisone was administered to 30 infants (68.2%) and AI occurred in 16 infants (36.4%). Cesarean section, sepsis before hypotension, and gastrointestinal surgery were independently associated with late-onset hypotension. Intrauterine growth retardation (IUGR) was less frequent in the hydrocortisonetreated group than in infants not treated with hydrocortisone. The AI group had fewer IUGR infants, and the duration of hospitalization was shorter in the AI group than in infants who were not administered hydrocortisone. Blood pressure tended to normalize more quickly in the AI group, however, the difference was not significant. Conclusion: AI was a major cause of late-onset hypotension, and the use of hydrocortisone shortened the length of hospitalization.