연속적 데이터 처리 심층신경망을 이용한 12 lead 심전도 파라미터의 자동 획득

김지운,박성민,최성욱,Kim, Ji Woon,Park, Sung Min,Choi, Seong Wook 대한의용생체공학회 2020 의공학회지 Vol.41 No.2

The deep neural networks (DNN) that can replicate the behavior of the human expert who recognizes the characteristics of ECG waveform have been developed and studied to analyze ECG. However, although the existing DNNs can not provide the explanations for their decisions, those trials have attempted to determine whether patients have certain diseases or not and those decisions could not be accepted because of the absence of relating theoretical basis. In addition, these DNNs required a lot of training data to obtain sufficient accuracy in spite of the difficulty in the acquisition of relating clinical data. In this study, a small-sized continuous data processing DNN (C-DNN) was suggested to determine the simple characteristics of ECG wave that were not required additional explanations about its decisions and the C-DNN can be easily trained with small training data. Although it can analyze small input data that was selected in narrow region on whole ECG, it can continuously scan all ECG data and find important points such as start and end points of P, QRS and T waves within a short time. The star and end points of ECG waves determined by the C-DNNs were compared with the results performed by human experts to estimate the accuracies of the C-DNNs. The C-DNN has 150 inputs, 51 outputs, two hidden layers and one output layer. To find the start and end points, two C-DNNs were trained through deep learning technology and applied to a parameter acquisition algorithms. 12 lead ECG data measured in four patients and obtained through PhysioNet was processed to make training data by human experts. The accuracy of the C-DNNs were evaluated with extra data that were not used at deep learning by comparing the results between C-DNNs and human experts. The averages of the time differences between the C-DNNs and experts were 0.1 msec and 13.5 msec respectively and those standard deviations were 17.6 msec and 15.7 msec. The final step combining the results of C-DNN through the waveforms of 12 leads was successfully determined all 33 waves without error that the time differences of human experts decision were over 20 msec. The reliable decision of the ECG wave's start and end points benefits the acquisition of accurate ECG parameters such as the wave lengths, amplitudes and intervals of P, QRS and T waves.

헤어살롱의 디자이너특성이 고객만족에 미치는 영향

김지운 ( Ji-woon Kim ),김은혜 ( Eun-hye Kim ),김희은 ( Hee-eun Kim ) 한국미용예술경영학회 2015 미용예술경영연구 Vol.9 No.1

This study is to find out the effect of hairdresser’s characteristic that clients' satisfaction. And reason of the clients’ satisfaction and preference after provision of informaion. Looking at the impact of customer satisfaction on the hairdresser's characteristics were influenced by same pattern when the main cause of the service is increased as career satisfaction. Treatment satisfaction were able to see the relationship of decreasing satisfaction increased more informative. In addition, this technology increases the more self-satisfaction were related to increased satisfaction. Namely, Hairdresser's technology and services are, of course, and Advertising, appearance, information, etc. This affects customer satisfaction. Therefore, If improve your marketing and service training, based on the findings on the characteristics of a hairdresser Customer Satisfaction is thought to be able to grow through customer satisfaction.

Web과 멀티데이타베이스 시스템의 CORBA 기반 연동

김지운(Ji-Woon Kim),문강식(Kang-Sik Moon),김수웅(Su-Woong Kim),이전영(Jeon-Young Lee) 한국정보과학회 1997 한국정보과학회 학술발표논문집 Vol.1997 No.2

광용적맥파(PPG)의 심층신경망(DNN) 분석을 통한 원격의료 데이터의 신뢰성 평가

김지운(Ji Woon Kim),박성민(Sung Min Park),최성욱(Seong Wook Choi) 대한기계학회 2021 大韓機械學會論文集B Vol.45 No.5

광용적맥파(PPG: photoplethysmography)는 측정이 용이하고 심폐기능과 관련된 정보를 제공하므로 원격의료에 자주 사용되지만, 동잡음에 취약하고 질환과 환자의 특징에 따라 다양한 파형이 나타나기 때문에 자동화된 알고리즘을 만들기 어려웠다. 최근, COVID19의 확산으로 원격진료가 활성화됨에 따라 PPG 신호를 자동분석하고 신뢰성이 높은 데이터를 선별하기 위한 심층신경망(DNN) 기술의 적용이 늘어나고 있다. 본 연구에서는 뇌의 LTP(long term potential) 현상을 재현한 DNN을 이용하여 PPG를 분석하고 이를 바탕으로 함께 측정한 SPO2(saturation pulse oxymetry)의 신뢰성을 평가하였다. LTP-DNN은 동잡음이 포함된 58개의 PPG 데이터를 분석하여 정상적으로 측정한 데이터를 선별할 수 있었으며, SPO2의 오류 또한 예측할 수 있었다. 움직이는 상황에서도 기존에 상용화된 SPO2 기기보다 정확한 HR을 제공하였으며 PPG 파형을 표준화함으로써 개인 간의 파형 차이를 비교할 수 있게 하였다. Photoplethysmography (PPG) is often used in telemedicine because it enables convenient measurement and provides data related to cardiopulmonary function. However PPG is difficult analyze using an automated algorithm because of its vulnerability to motion artefacts and the diversity of the waveforms according to the characteristics of individuals and diseases. Recently, as the use of telemedicine has become more frequent due to the outbreak of COVID19, the application of deep neural network (DNN) technology in the analysis of PPG and selection of reliable data has increased. In this study, PPG was analyzed using DNN techniques to reproduce the long-term potential (LTP) phenomenon in the brain. Moreover, the reliability of measuring saturation pulse oxymetry (SPO2) simultaneously was evaluated using the LTP-DNN. The LTP-DNN was able to evaluate faultless data by inspecting 58 PPG datasets, including 29 fault data, and could determine the possibility of failure in SPO2 measurement as well. Even in a moving situation, the LTP-DNN provides more accurate heartrate (HR) measurements than commercial SPO2 devices do. It can also be used to normalize the PPG waveform to identify waveform differences between individuals.

췌장 전이가 동반된 십이지장 선암

김지운(Ji Woon Kim),정만(Mann Jung),이영미(Young Mi Lee),류형선(Hyung Sun Ryeu),심승식(Seung Sig Sim),박창현(Chang Hyun Park),박찬웅(Chan Woong Park) 대한소화기학회 1993 대한소화기학회지 Vol.25 No.3

Primaty adenocarcinoma of the duodenum is a uncommon neoplasm, accounting for about 0.3% of all gastrointestinal cancers. Adenocarcinomas tend to metastasize to regional lymph nodes, liver and pancreas, Peritoneal carcinomatosis also occurs and is more common than wide spread metastasis to lungs or bones. But with increasing awareness of its modes of presentation and improved diagnostiic techiques, more cases should be recognized at an earlier stage in the course of the disease. We experienced a case of primary adenocarcinoma of the duodenum associated with pancreatic metastasis, and report it with a review of the literature.

우측 총장골동맥 혈전증이 초기 증상으로 발현된 막성 사구체신염

김지운 ( Ji Woon Kim ),박현정 ( Hyun Jung Park ),박지수 ( Ji Soo Park ),오지수 ( Ji Su Oh ),김조은 ( Jo Eun Kim ),오현주 ( Hyun Ju Oh ),김형종 ( Hyung Jong Kim ) 대한내과학회 2011 대한내과학회지 Vol.81 No.2

Most patients with nephrotic syndrome visit the hospital because of edema due to hypoalbuminemia induced by severe proteinuria. However, rare cases have reported arterial thrombosis as the main problem complicating nephrotic syndrome. Arterial thrombosis combined with nephrotic syndrome is rarer than venous thrombosis, and it usually develops during treatment with steroids or diuretics. Arterial thrombosis is rarely diagnosed as the initial sign of nephrotic syndrome. We report the case of a 38-year-old-woman with membranous glomerulonephritis presenting with right common iliac artery thrombosis as the initial sign. (Korean J Med 2011;81:257-261)

Bernese와 TGO에 의한 국내 GPS 상시관측소 자료처리 결과 분석

김지운(Kim, Ji Woon),권재현(Kwon, Jay Hyoun),이지선(Lee, Ji Sun) 한국측량학회 2008 한국측량학회지 Vol.26 No.6

역사적 건물의 가치와 보존개념의 재해석에 관한 연구-소비시대의 장소성 연구를 중심으로-

김지운(Kim. Ji woon),구영민(Koo. Young min) 대한건축학회 2004 대한건축학회 학술발표대회 논문집 - 계획계/구조계 Vol.24 No.1

The purpose of study is to investigate and reevaluate historical buildings and their related site in the city, with regard to the place marketing strategy, to explore assured methodologies of conservation through case study, and to review the conditions in which such historic buildings and sites can coexist with other urban constituents. The argument is focused in how such historical urban constituents can create pragmatic value rather than remain as relics alienated from the city space.<br/>

AI 기술을 이용한 PPG 기반 원격의료 데이터의 신뢰성 평가

김지운(Ji Woon Kim),박성민(Sung Min Park),최성욱(Sung Wook Choi) 대한기계학회 2020 대한기계학회 춘추학술대회 Vol.2020 No.12

유아음악교육에 대한 교수내용지식, 교수효능감과 교사의 태도 간의 구조분석

김지운(Ji-Woon Kim) 한국산학기술학회 2018 한국산학기술학회논문지 Vol.19 No.1

본 연구는 유아 교사의 음악교육을 위한 음악교수내용지식과 음악교수효능감, 음악교육에 대한 교사의 태도 사이에 관계를 실증적으로 검증 하고자 하였으며, 검증을 위해 유아교육기관에 근무하는 유아 교사 132명을 대상으로 수집된 자료를 분석하였다. 통계적 분석은 SPSS와 AMOS를 사용하여 구조방정식모형분석을 하였다. 본 연구의 결과, 연구모형에 대한 적합도는 적절하였으며, 유아교사의 음악교수내용지식과 음악교수효능감, 음악교육에 대한 교사의 태도 변수 사이의 인과관계를 명확하게 확인하였다. 첫째, 유아 교사의 음악 교수내용지식은 음악교육에 대한 교사의 태도에 통계적으로 유의미한 영향을 미치는 것으로 나타났다. 둘째, 유아 교사의 음악 교수내용지식은 유아 교사의 음악교육에 대한 교수효능감에 통계적으로 유의미한 영향을 미치는 것으로 나타났다. 셋째, 유아 교사의 음악 교수내용지식은 음악교육에 대한 교사의 태도에 음악교수효능감을 매개로 간접적으로 영향을 미치는 것으로 나타났으며, 매개 효과는 부분매개 효과로 나타났다. 본 연구의 결과는 유아의 음악적 발달을 위한 유아 교사의 전문성 강화에 중요한 기초 자료로 활용될 수 있다. 특히, 유아 교사의 음악교수내용지식 변수가 유아들의 음악교육에서 매우 중요한 변수임을 확인할 수 있다. In this study, the Pedagogical Content Knowledge for childhood’s music education and Teacher’s Efficacy empirically examined the relationship between teachers" attitudes through structural equation model analysis. Data were collected for 132 infant teachers working for early childhood educational institutions for this study. Structural equation model analysis was performed using SPSS and AMOS. In this research, conformity to the research model was appropriate. Pedagogical content knowledge for childhood’s music education clearly confirmed the relationship between the teacher’s efficacy, the attitude variables of the teacher. The Pedagogical Content Knowledge for childhood’s music education proved to have a meaningful influence on the attitude of the teacher for music education. The Pedagogical Content Knowledge for childhood’s music education proved to have a meaningful influence on Teacher’s Efficacy for music education. The Pedagogical Content Knowledge for childhood’s music education has been found to influence the attitude of the teacher indirectly with the intermediation of Teacher’s Efficacy. The effect of the parameter was the effect of the partial parameters. The results of this study can be used as basic material important for strengthening the expertise of young children "s teachers for music development of young children. In particular, it was confirmed that the knowledge variable of the content of the music professor of an infant teacher is a very important variable in early childhood music education.