• Journal of Digital Contents Society
• /
• v.17 no.2
• /
• pp.97-103
• /
• 2016

This work introduces techniques experienced for the electrocardiogram(ECG) visual analysis, able to characterize the major parameters and events with clinical relevance for heart failure management and cardiovascular risk assessment. In particular, it includes approaches for ECG data visual processing such as the variable charts, graphs base on the complex MIT-BIH ECG database. Through the experienced this works of ECG database visualization, so many researcher more easily access the complex ECG database and can intuitionally understand the meanings via a variable ECG visualized data.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.3
• /
• pp.1-9
• /
• 2021

In this study, we evaluated the accuracy of deep learning-based tree species classification model trained by using high-resolution images. We selected five species classed, i.e., pine, birch, larch, korean pine, mongolian oak for classification. We created 5,000 datasets using high-resolution orthophoto and forest type map. CNN deep learning model is used to tree species classification. We divided training data, verification data, and test data by a 5:3:2 ratio of the datasets and used it for the learning and evaluation of the model. The overall accuracy of the model was 89%. The accuracy of each species were pine 95%, birch 89%, larch 80%, korean pine 86% and mongolian oak 98%.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.362-365
• /
• 2021

이 논문에서는 자연어로 구성된 수학 문장제 문제를 자동으로 풀이하기 위한 Transformer 기반의 생성 모델인 KoEPT를 제안한다. 수학 문장제 문제는 일상 상황을 수학적 형식으로 표현한 자연어 문제로, 문장제 문제 풀이 기술은 실생활에 응용 가능성이 많아 국내외에서 다양하게 연구된 바 있다. 한국어의 경우 지금까지의 연구는 문제를 유형으로 분류하여 풀이하는 기법들이 주로 시도되었으나, 이러한 기법은 다양한 수식을 포괄하여 분류 난도가 높은 데이터셋에 적용하기 어렵다는 한계가 있다. 본 논문은 이를 해결하기 위해 우선 현존하는 한국어 수학 문장제 문제 데이터셋인 CC, IL, ALG514의 분류 난도를 측정한 후 5겹 교차 검증 기법을 사용하여 KoEPT의 성능을 평가하였다. 평가에 사용된 한국어 데이터셋들에 대하여, KoEPT는 CC에서는 기존 최고 성능과 대등한 99.1%, IL과 ALG514에서 각각 89.3%, 80.5%로 새로운 최고 성능을 얻었다. 뿐만 아니라 평가 결과 KoEPT는 분류 난도가 높은 데이터셋에 대해 상대적으로 개선된 성능을 보였다.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.3
• /
• pp.749-761
• /
• 2016

The purpose of this study was to investigate the effects of emotional regulation between clinical practice stress and nursing professionalism in nursing students. Participants were 192 nursing students and data were collected from September to November, 2015. This study has shown that nursing professionalism is negatively associated with clinical practice stress (r=-.40, p<.001) and positively associated with emotional regulation (r=.55, p<.001). In addition, a negative correlation has been found significant between emotional regulation and clinical practice stress (r=-.20, p<.001). In a final model of hierarchial multiple regression, professor support (${\beta}=.19$, p<.01), satisfaction with nursing as a major (${\beta}=.14$, p<.05), clinical practice stress (${\beta}=-.19$, p<.01) and emotional regulation (${\beta}=.32$, p <.001) were associated with nursing professionalism. In this study, we also have shown that emotional regulation does not play a moderating role on the relationship between clinical practice stress and nursing professionalism. The results of this study suggests that, in order to improve nursing professionalism, it is important to promote support system, develop clinical-practice-stress-relief programs, and enhance emotional regulation training for nursing students.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.2
• /
• pp.38-46
• /
• 2011

3D motion analysis system which is currently widely used for walking analysis has limitations due to both necessity of wide space for many cameras for measurement, high cost, and complicated preparation procedure, which results in low accessability in use and application for clinical diagnosis. To resolve this problem, we developed 3-dimensional wireless ambulatory measurement system based on inertial sensor which can be easily applicable for clinical diagnosis for lower extremity deformity and developed system was evaluated by applying for 10 elderly people with diabetes mellitus. Developed system was composed of wireless ambulatory measurement module that consists of inertial measurement unit (IMU) which measures the gait characteristics, microcontroller which collects and precesses the inertial data, bluetooth device which transfers the measured data to PC and Window's application for storing and processing and analyzing received data. This system will utilize not only to measure lower extremity (foot) problem conveniently in clinical medicine but also to analyze 3D motion of human in other areas as sports science, rehabilitation.

• Korean Journal of Clinical Laboratory Science
• /
• v.48 no.4
• /
• pp.348-354
• /
• 2016

Data stored in hospital information systems has a great potential to improve adequacy assessment and quality management. Moreover, an establishment of a data warehouse has been known to improve quality management and to offer help to clinicians. This study constructed a data mart that can be used to analyze antibiotic usage as a part of systematic and effective data analysis of infection control information. Metadata was designed by using the XML DTD method after selecting components and evaluation measures for infection control. OLAP-a multidimensional analysis tool-for antibiotic usage analysis was developed by building a data mart through modeling. Experimental data were obtained from data on antibiotic usage at a university hospital in Cheonan area for one month in July of 1997. The major components of infection control metadata were antibiotic resistance information, antibiotic usage information, infection information, laboratory test information, patient information, and infection related costs. Among them, a data mart was constructed by designing a database to apply antibiotic usage information to a star schema. In addition, OLAP was demonstrated by calculating the statistics of antibiotic usage for one month. This study reports the development of a data mart on antibiotic usage for infection control through the implementation of XML and OLAP techniques. Building a conceptual, structured data mart would allow for a rapid delivery and diverse analysis of infection control information.

• Journal of Internet of Things and Convergence
• /
• v.6 no.2
• /
• pp.19-24
• /
• 2020

In the present study, using biological information of bacteria and biochemical information of chlorine dioxide gas, Gram-positive bacteria, e.g., Alloiococcus otitis, Erysipelothrix rhusiopathiae, Staphylococcus caprae, Staphylococcus lentus, and gram-negative bacteria, e.g., Acinetobacter baumannii complex, Aeromonas salmonicida, Brucella melitensis, Oligella ureolytica were used whether a plastic kit to release ClO₂ gas could inhibit their growth. Overall, chlorine dioxide gas showed about 99% inhibition of bacterial growth, with less than 10 CFU. However, it was found that Gram positive Alloiococcus otitis and Gram negative Aeromonas salmonicida had more than about 50 CFU. When comparing the results of experiments with several bacteria, it suggested that the concentration of chlorine dioxide gas would be at least 10 ppm to 400 ppm for the bacterial inhibition. The results of this study could be used as basic data to evaluate the clinical usefulness of chlorine dioxide gas. If this study helps with prior knowledge to help clinicians to recognize and prevent the presence of micro-organisms that cause infections in hospitals, it would be helpful for activities such as patient care as a convergence field. In the future, it is considered that the research results will be the basis for rapidly inhibiting the microbes infected with patients by utilizing data of the information of the microbes that are inhibited for chlorine dioxide gas.

• The KIPS Transactions:PartB
• /
• v.9B no.5
• /
• pp.625-634
• /
• 2002

In this paper, we conducted various experiments with Bayesian networks in order to analyze clinical data of infertility patients. With these experiments, we tried to find out inter-dependencies among important factors playing the key role in clinical pregnancy, and to compare 3 different kinds of Bayesian network classifiers (including NBN, BAN, GBN) in terms of classification performance. As a result of experiments, we found the fact that the most important features playing the key role in clinical pregnancy (Clin) are indication (IND), stimulation, age of female partner (FA), number of ova (ICT), and use of Wallace (ETM), and then discovered inter-dependencies among these features. And we made sure that BAN and GBN, which are more general Bayesian network classifiers permitting inter-dependencies among features, show higher performance than NBN. By comparing Bayesian classifiers based on probabilistic representation and reasoning with other classifiers such as decision trees and k-nearest neighbor methods, we found that the former show higher performance than the latter due to inherent characteristics of clinical domain. finally, we suggested a feature reduction method in which all features except only some ones within Markov blanket of the class node are removed, and investigated by experiments whether such feature reduction can increase the performance of Bayesian classifiers.

• The KIPS Transactions:PartD
• /
• v.15D no.5
• /
• pp.681-690
• /
• 2008

In proteomics research, the identification of differentially expressed proteins observed under specific conditions is one of key issues. There are several ways to detect the change of a specific protein's expression level such as statistical analysis and graphical visualization. However, it is quiet difficult to handle the spot information of an individual protein manually by these methods, because there are a considerable number of proteins in a tissue sample. In this paper, using database and data mining techniques, the application plan of OLAP data cube and Discovery-driven exploration is proposed. By using data cubes, it is possible to analyze the relationship between proteins and relevant clinical information as well as analyzing the differentially expressed proteins by disease. We propose the measure and exception indicators which are suitable to analyzing protein expression level changes are proposed. In addition, we proposed the reducing method of calculating InExp in Discovery-driven exploration. We also evaluate the utility and effectiveness of the data cube and Discovery-driven exploration in the lung cancer 2-DE gel image.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.293-297
• /
• 2009

This paper describes a real-time reliable measurement and analysis system for ubiquitous healthcare based on IEEE802.15.4 standard. In order to obtain and monitor physiological body signals continuously, wearable pulse oximeter is designed in wrist that could used to measure oxygen saturation of a patient unobtrusively. The measured data was transferred to a central PC or server by using wireless sensor nodes via a wireless sensor network for storage and analysis purposes. LabVIEW server program was designed to monitor and process the measured photoplethysmogram(PPG) to accelerated plethysmogram(APG) by appling second order derivatives in server PC. These experimental results demonstrate that APG can precisely describe the features of an individual's PPG and be used as estimation of vascular elasticity for blood circulation.