• Journal of Medicine and Life Science
• /
• v.20 no.3
• /
• pp.115-125
• /
• 2023

Arteriovenous fistula flow dysfunction is the leading cause of vascular access thrombosis and loss in patients undergoing hemodialysis. However, data regarding the influence of access flow rate measurements on the long-term outcomes of access are limited. This study aims to identify accesses at a high risk of thrombosis and loss among patients undergoing hemodialysis by measuring the access flow rate and exploring an optimal threshold value for predicting future access thrombosis. We enrolled 220 patients with arteriovenous fistula undergoing hemodialysis. The primary outcome was the occurrence of access thrombosis. Access flow rates were measured monthly using the ultrasound dilution method and were averaged using all measurements from patients with patent access. In patients experienced access thrombosis, those immediately before the thrombosis were selected. Using these data, we calculated the access flow rate threshold for thrombosis occurrence by analyzing the receiver operating characteristic curve, and the patients were divided into two groups according to whether access flow rates were higher or lower than 400 mL/min. During a median follow-up period of 3.1 years, 4,510 access flows were measured (median measurements per patient, 33 times; interquartile range, 11-54). A total of 65 access thromboses and 19 abandonments were observed. Access thrombosis and loss were higher in the lowflow group than in the high-flow group. This study revealed that low access flow rates are strongly associated with access thrombosis occurrence and subsequent loss of arteriovenous fistulas in patients undergoing hemodialysis.

• Electronics and Telecommunications Trends
• /
• v.39 no.4
• /
• pp.42-53
• /
• 2024

Mathematical modeling is the process of representing physical phenomena using equations, and it often describes various scientific phenomena through differential equations. Numerical analysis, which is capable of approximating solutions to partial differential equations representing physical phenomena, is widely utilized. However, in high-dimensional or nonlinear systems, computational costs can substantially increase, leading to potential numerical instability or convergence issues. Recently, Physics-Informed Neural Networks (PINNs) have emerged as an alternative approach. A PINN leverages physical laws even with limited data to provide highly reliable predictive performance and can address the convergence issues and high computational costs associated with numerical analysis. This paper analyzes the weak signals, research trends, patent trends, and case studies of PINNs. On the basis of this analysis, it proposes directions for the development of PINN techniques in the agricultural field. In particular, the application of PINNs in agriculture is expected to be more effective than in other industries because of their ability to reflect real-time changes in biological processes. While the technology readiness level of PINNs remains low, the potential for model training with minimal data and real-time prediction capabilities suggests that PINNs could replace traditional numerical analysis models. It is anticipated that the research and industrial applications of PINN will develop at an increasing pace while focusing on addressing the complexity of mathematical models in agriculture, mathematical modeling and the application of various biological processes; securing key patents related to PINNs; and standardizing PINN technology in the field of agriculture.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.9
• /
• pp.37-44
• /
• 2020

AI technology has developed in the form of decision support technology in law, patent, finance and national defense and is applied to disease diagnosis and legal judgment. To search real-time information with Deep Learning, Big data Analysis and Deep Learning Algorithm are required. In this paper, we try to predict the entrance rate to high-ranking universities using a Deep Learning model, RNN(Recurrent Neural Network). First, we analyzed the current status of private academies in administrative districts and the number of students by age in administrative districts, and established a socially accepted hypothesis that students residing in areas with a high educational fever have a high rate of enrollment in high-ranking universities. This is to verify based on the data analyzed using the predicted hypothesis and the government's public data. The predictive model uses data from 2015 to 2017 to learn to predict the top enrollment rate, and the trained model predicts the top enrollment rate in 2018. A prediction experiment was performed using RNN, a Deep Learning model, for the high-ranking enrollment rate in the special education zone. In this paper, we define the correlation between the high-ranking enrollment rate by analyzing the household income and the participation rate of private education about the current status of private institutes in regions with high education fever and the effect on the number of students by age.

• The Journal of the Korea Contents Association
• /
• v.8 no.1
• /
• pp.68-74
• /
• 2008

Application areas of Knowledge Discovery in Database(KDD) have been expanded to many R&D management processes including technology trends analysis, forecasting and evaluation etc. Established research field such as informetrics (or scientometrics) has utilized techniques or methods of KDD. Various systems have been developed to support works of analyzing large-scale R&D related databases such as patent DB or bibliographic DB by a few researchers or institutions. But extant systems have some problems for korean users to use. Their prices is not moderate, korean language processing is impossible, and user's demands not reflected. To solve these problems, Korea Institute of Science and Technology Information(KISTI) developed stand-alone type information analysis system named as KnowledgeMatrix. KnowledgeMatrix system offer various functions to analyze retrieved data set from databases. KnowledgeMatrix's main operation unit is composed of user-defined lists and matrix generation, cluster analysis, visualization, data pre-processing. Matrix generation unit help extract information items which will be analyzed, and calculate occurrence, co-occurrence, proximity of the items. Cluster analysis unit enable matrix data to be clustered by hierarchical or non-hierarchical clustering methods and present tree-type structure of clustered data. Visualization unit offer various methods such as chart, FDP, strategic diagram and PFNet. Data pre-processing unit consists of data import editor, string editor, thesaurus editor, grouping method, field-refining methods and sub-dataset generation methods. KnowledgeMatrix show better performances and offer more various functions than extant systems.

• The Journal of Bigdata
• /
• v.6 no.2
• /
• pp.71-84
• /
• 2021

Since small and medium-sized enterprises fell short of the securement of technological competitiveness in the field of big data and artificial intelligence (AI) field-core technologies of the Fourth Industrial Revolution, it is important to strengthen the competitiveness of the overall industry through technology commercialization. In this study, we aimed to propose a priority related to technology transfer and commercialization for practical use of public research results. We utilized public research performance information, improving missing values of 6T classification by deep learning model with an ensemble method. Then, we conducted topic modeling to derive the converging fields of big data and AI. We classified the technology fields into four different segments in the technology portfolio based on technology activity and technology efficiency, estimating the potential of technology commercialization for those fields. We proposed a priority of technology commercialization for 10 detailed technology fields that require long-term investment. Through systematic analysis, active utilization of technology, and efficient technology transfer and commercialization can be promoted.

• Journal of Technology Innovation
• /
• v.23 no.3
• /
• pp.225-253
• /
• 2015

The standard is a nation's one of the most important industrial issues that improve the social and economic efficiency and also the basis of the industrial development and trade liberalization. This research analyzes the enactment and the utilization of Korean industrial standards(KS) of various industries. This paper examines Korean industries' KS utilization status based on the KS possession, enactments and inquiry records. First, we implement multidimensional scaling method to visualize and group the KS possession records and the nation's institutional issues. We develop several hypothesis to find the decision factors of how each group's KS possession status impacts on the standard enactment activities of similar industry sectors, and analyzes the data by implementing regression analysis. The results show that the capital intensity, R&D activities and sales revenues affect standardization activities. It suggests that the government should encourage companies with high capital intensity, sales revenues to lead the industry's standard activities, and link the policies with the industry's standard and patent related activities from R&D. Second, we analyze the impacts of each KS data's inquiry records, the year of enactments, the form and the industrial segment on the utilization status by implementing statistical analysis and decision tree method. The results show that the enactment year has significant impact on the KS utilization status and some KSs of specific form and industrial segment have high utilization records despite of short enactment history. Our study suggests that government should make policies to utilize the low-utilized KSs and also consider the utilization of standards during the enactment processes.

• Journal of the Korea Convergence Society
• /
• v.12 no.6
• /
• pp.233-239
• /
• 2021

Recently, the COVID-19 virus has caused people to stay indoors longer without going out. As a result of this, people's activity decreased sharply, and their weight gained. So people became more interested in health. Home training can be an alternative method to solve this problem. Accordingly, To find out the trends of home training, we collected articles from December 1, 2019, to November 30, 2020, using the news provided by BIG KINDS, a news analysis system. We analyzed frequency analysis, relational analysis according to weighting, and related word analysis with the program using the algorithm developed by BIG KINDS. In conclusion, first, it was found that home training is led by technology and the emergence of artificial intelligence. Second, it can be assumed that people mainly do home training using content and video services related to mobile carriers. Third, people had a high preference for Pilates in the sports category. It can be seen that the number of patent applications increased as the demand for exercise products related to Pilates increased. In the next study, we expect that this study will be used as primary data for various big data studies by supplementing the research methodology and conducting various analyses.

• Journal of Industrial Convergence
• /
• v.21 no.2
• /
• pp.133-138
• /
• 2023

Due to social phenomena such as rapid aging in Korea, nuclear familyization, single marriage, and low birth rate, the number of Companion animals and the number of households with Companion animals are increasing due to the increase in single-person households. In fact, one out of every four households has a pet, and the scale of the industry is expected to reach 6 trillion won in 2027. In particular, in a situation where the Companion animal cosmetics market is in the spotlight amid the diversification of the pet industry, there is a great lack of research on related research and industry development methods. Accordingly, this study attempted to search and analyze academic data, patented technologies, and the latest data related to pet cosmetics and provide them as basic data for the Companion animal cosmetics industry, and the results are as follows. Academic data included verification of the effectiveness of natural materials to improve the skin condition of dogs, analysis of the pet cosmetics industry, and research on ICT-converged pet cosmetics, and the industry was mainly cleaning cosmetics, with pet shampoo launches in Amorepacific, LG Household & Healthcare, and Aekyung. In the patented technology for pets, a patent has been registered for natural product material composition and formulation ratio for skin moisturizing, skin improvement, thinning, and inflammation symptom relief. As a result of this award, it was confirmed that research and development are still insufficient compared to the consumption demand of the pet cosmetics market, and it is believed that industry analysis and development research in related fields should be actively carried out.

• Journal of Digital Convergence
• /
• v.12 no.9
• /
• pp.335-341
• /
• 2014

Due to the expiration of the 3D printer's patent, the articles covering the market activation and bright prospects for the future industry are being released. What are the requirements for the 3D printer to become popular like a general printer? To get the answer, on-line survey was performed for the activation of 3D printer. As a result, tit is observed that he public prefers creative printer and figure, and prefers to use through pay or free download rather than designing digital blueprint, which is output data. For the activation and popularization of 3D printer, figure is familiar to the public who are frequently exposed to image media contents, and it also has motivation factor to use and purchase 3D printer. For distribution of digital blueprint of figure content, the preparation of related law and regulation and activation of online market would be of help for activation of 3D printer.

• Journal of Korea Technology Innovation Society
• /
• v.16 no.3
• /
• pp.754-783
• /
• 2013

This study aims to suggest an empirical approach for improving the reliability of the valuation method for the technology developed at universities by using the recent data of university technology transfer. The influencing factors, the internal capabilities of an university and the characteristics of technology area, on the outcome of university technology transfer were investigated for this study. The analysis shows that the technology area distribution of the outcome of technology transfer of each university can be classified into two type: IT and NT area oriented type, and BT and other area oriented type. The analysis also shows that the type of technology area distribution can act as a moderator in the positive relationship between each independent variables, the number of patent applications and the number of technology commercialization staff, and the outcome of technology transfer. Considering that the capability of technology development and that of technology spread are related directly or indirectly to all the technology valuation process, the analysis results imply that the reliability of the valuation method for university technology might be improved by using factors of the internal capabilities of an university and that of the characteristics of technology area.