선물시장의 시스템트레이딩에서 동적시간와핑 알고리즘을 이용한 최적매매빈도의 탐색 및 거래전략의 개발

이석준,오경주,Lee, Suk-Jun,Oh, Kyong-Joo 한국데이터정보과학회 2011 한국데이터정보과학회지 Vol.22 No.2

국내 정치적 사회적 경제적 요인 및 국제 정치 상황, 해외 경제 동향 등의 요인들을 비롯한 IMF이후의 금융시장 개방에 따른 외국투자자본의 유출입으로 인하여 한국 금융시장의 불확실성은 더욱 증가되었다. 특히 투자자들은 의사결정에 더 많은 혼돈을 겪게 되었고 투자 시 도움을 줄 수 있는 보다 유용한 도구들을 필요로 하게 되었다. 본 연구는 시스템 트레이딩을 이용하여 선물시장에서 거래 할 때 최적의 매매 타이밍을 알아보고 이에 적합한 전략을 알아보는 것이 목적이다. 패턴인식 알고리즘인 동적 시간 와핑 (DTW; Dynamic Time Warping) 알고리즘을 이용하여 빈도별 (10분, 30분, 60분, 일 별) 유사 패턴을 찾아내고 최적의 매매 타이밍을 분석한다. 이를 위해 주식시장의 대표적인 패턴들을 알아보고, 유사한 패턴을 보이는 기간을 DTW를 이용하여 빈도별로 분석한다. 유사한 패턴들의 검증을 위해 기술적 지표들의 개별 전략을 적용한 거래 시뮬레이션을 실시한다. 시뮬레이션 결과 대부분 30분 데이터에 적용된 전략들이 높은 수익률을 가져왔다. The aim of this study is to utilize system trading for making investment decisions and use technical analysis and Dynamic Time Warping (DTW) to determine similar patterns in the frequency of stock data and ascertain the optimal timing for trade. The study will examine some of the most common patterns in the futures market and use DTW in terms of their frequency (10, 30, 60 minutes, and daily) to discover similar patterns. The recognized similar patterns were verified by executing trade simulation after applying specific strategies to the technical indicators. The most profitable strategies among the set of strategies applied to common patterns were again applied to the similar patterns and the results from DTW pattern recognition were examined. The outcome produced useful information on determining the optimal timing for trade by using DTW pattern recognition through system trading, and by applying distinct strategies depending on data frequency.

체육전공 대학생의 자기효능감이 창의적 역량성 및 창업의지에 미치는 영향

이석준(Lee, Suk-Jun),이병관(Lee, Byung-Kwan) 한국관광레저학회 2018 관광레저연구 Vol.30 No.8

염증 반응과 수면 장애

이석준 ( Suk Jun Lee ),김진관 ( Jinkwan Kim ) 대한임상검사과학회 2015 대한임상검사과학회지(KJCLS) Vol.47 No.3

Sleep is not only an essential physiological function, but also serves important roles in promoting growth, maturation, and overall health of humans. There is increasing interest regarding the impact of sleep and its disorders on the regulation of inflammatory processes and end-organ morbidities, particularly in the context of metabolic and cardiovascular diseases (CVD) and their complications. Obstructive sleep apnea syndrome (OSAS) is an increasingly common health problem in children. In the last decade, the emergence of increasing obesity rates has further led to remarkable increases in the prevalence of OSAS, along with more prominent neurocognitive, behavioral, cardiovascular and metabolic morbidities. Although the underlying mechanisms leading to OSAS-induced morbidities are likely multifactorial and remain to be fully elucidated, activation of inflammatory pathways by OSAS has emerged as an important pathophysiological component of the end-organ injury associated with this disorder. To this effect, it would appear that OSAS could be viewed as a chronic, low-grade inflammatory disorder. Furthermore, the concurrent presence of obesity and OSAS poses a theoretically increased risk of OSAS-related complications. In this study, we will critically review the current state of research regarding the impact of insufficient and disrupted sleep and OSAS on the immune processes and inflammatory pathways that underlie childhood OSAS as a distinctive systemic inflammatory condition in children, and will explore potential interactions between OSAS and obesity.

서울시 공공자전거 시스템 운영에 관한 이용경험 및 개선사항 분석

이석준(Lee, Suk-Jun),김지태(Kim, Ji-Tae),권재윤(Kwon, Jae-Yoon) 한국체육과학회 2018 한국체육과학회지 Vol.27 No.6

The purpose of this study was to figure out the user experience and service improvement factors in Seoul city bike system by utilizing critical incidents technique which is the one of qualitative analysis methods. To attain the goal, 419 Seoul city bike system user in Seoul were studied using CIT method. The analysis of the data was produced based on the observation reliability of 3 independent researchers who has sport business and public management background. The results were as follows. First, according to the results of analyzing Seoul city bike system users’ positive experiences after use, convenient to use, accessibility, bicycle rental convenience, economics, and connectivity with other means of transportation. Second, according to the results of analyzing Seoul city bike system users’ negative experiences after use, accident risk, lack of bike roads, scarce publicity, applications and rental station, usage complexity, and broken bicycles. Lastly, according to the result of analyzing measures to improve the seoul city bike, realistic environmental infrastructure, rental station, about safety problem, bicycle functional aspect, application, and payment.

중·고등학교 태권도팀 주장의 리더십 유형과 스포츠 열정의 관계 분석

이석준(Lee, Suk-Jun) 한국체육과학회 2019 한국체육과학회지 Vol.28 No.4

The purpose of this study was to investigate the relationship between leadership type of Taekwondo team captain and sports enthusiasm. As of May 2019, the partiupants were selected in Taekwondo players from middle and high schools nationwide as a population. 397 Taekwondo players were sampled by convenience sampling method. The questionnaire used in the previous research was revised and supplemented according to the purpose of this study. The researcher and the research assistant directly visited the study school. Frequency analysis and correlation analysis were performed using SPSS 22.0, and AMOS 22.0 was used to validate the model "s fit and research hypothesis through confirmatory factor analysis and structural equation model analysis. The following conclusions were obtained. First, among the leadership types of Taekwondo team captain in middle and high school, transformative, transactional and charismatic leadership affected harmoay enthusiasm. Second, the transactional and charismatic leadership affected compilsion enthusiasm. This study could provide basic data on the role of Taekwondo team captain in the future.

java Based Magnetic Resonance User Interface의 Advanced Method for Accurate, Robust, and Efficient Spectral Fitting 분석방법의 관찰자 변동 요소

이석준(Suk Jun Lee),유승만(Seung Man Yu) 대한방사선과학회(구 대한방사선기술학회) 2016 방사선기술과학 Vol.39 No.2

본 연구에서는 MRS 정량적 분석 중 jMRUI AMARES방법의 관찰자의 의존적 원인 요소를 숙련자와 비숙련자의 측정을 통하여 파악하고 하였다. 실험용 10주령 수컷 쥐의 간 부분을 3T MRI 장치를 활용하여 point resolved spectroscopy 펄스시퀀스를 이용하여 자기공명분광 데이터를 획득하였다. 획득된 데이터는 기준 값으로 사용하기 위해서 LCModel software 이용하여 1.3 ppm의 메틸렌 양성자와 4.7 ppm의 물 분자 양성자의 정량 비를 계산하였다. 7명의 비숙련 관찰자는 jMRUI AMARES 방법으로 총 지질을 1, 2주 간격으로 측정한 후 측정된 값을 SPSS를 이용하여 interclass correlation coefficient를 시행하였다. 관찰자 사이 간 측정치의 일관성의 신뢰도 분석을 표현한 크논바 알파 계수는 0.1 미만으로 나타났다. 1주차 데이터 값과 2주차 데이터 값의 평균값은 0.096±0.038로 LCModel의 분석 값보다 0.048로 50% 높게 관찰되었다. jMRUI AMARES분석 방법이 LCModel과 동일한 결과를 얻기 위해서는 정확한 대사물질의 개요를 숙지하고 획득된 그래프의 형태를 잘 파악하여 잔존 대사물질를 최소화 하여야 한다. The purpose of this study was examined the measurement error factor on AMARES of jMRUI method for magnetic resonance spectroscopy (MRS) quantitative analysis by skilled and unskilled observer method and identified the reason of independent observers. The Point-resolved spectroscopy sequence was used to acquired magnetic resonance spectroscopy data of 10 weeks male Sprague-Dawley rat liver. The methylene protons ((-CH2-)n) of 1.3 ppm and water proton (H2O) of 4.7 ppm ratio was calculated by LCModel software for using the reference data. The seven unskilled observers were calculated total lipid (methylene/water) using the jMRUI AMARES technique twice every 1 week, and we conducted interclass correlation coefficient (ICC) statistical analysis by SPSS software. The inter-observer reliability (ICC) of Cronbach’s alpha value was less than 0.1. The average value of seven observer’s total lipid (0.096±0.038) was 50% higher than LCModel reference value. The jMRUI AMARES analysis method is need to minimize the presence of the residual metabolite by identified metabolite MRS profile in order to obtain the same results as the LCModel.

피트니스클럽 종사자의 직무 및 조직적합도가 직무몰입 및 서비스성과에 미치는 영향

이석준(Lee, Suk-Jun) 한국관광레저학회 2016 관광레저연구 Vol.28 No.1

3T 자기공명영상 Fast Spin Echo (FSE)와 Ultra Short Time Echo (UTE) 펄스 시퀀스에서 가돌리늄 조영제 희석농도와 신호강도 비교 –팬텀 연구

이석준(Suk-Jun Lee),유승만(Seung-Man Yu) 대한방사선과학회(구 대한방사선기술학회) 2015 방사선기술과학 Vol.38 No.3

본 연구에서는 가돌리늄 조영제를 다양한 몰농도로 희석하여 T1 효과를 나타내는 펄스 시퀀스 중 고속스핀에코와 에코타임이 극도로 짧은 ultra short time echo에서 최대 신호 강도 분포를 나타내는 조영제 희석 몰농도를 3.0T에서 각각 알아보고자 하였다. T1 조영제인 gadoxetic acid 와 완충용액으로는 증류수, 2% agarose gel을 이용하여 다양한 몰농도로 조영제 팬텀을 제작하였다. 팬텀 제작의 정확성을 측정하기 위해 T1 이완시간 측정의 표준방식인 2D inversion recovery spine-echo 펄스시퀀스를 이용하였으며 팬텀의 중간 부의 한 개의 관상면 영상을 획득하여 T1 이완 시간을 계산하였다. 스핀에코에서는 1-2 mmol/L 조영제 몰농도에서 가장 높은 신호를 나타냈으며, ultra short time echo에서는 7 mmol/L에서 가장 큰 신호를 나타냈다. ultra short time echo 펄스 시퀀스를 이용한 조영증강 효과를 보기 위해서는 고속스핀에코 기법 보다 2-3배의 조영제 농도가 목적 장기에 유지하여야 하며 이와 관련된 조영제량 및 투여 방법의 연구가 이루어져야 한다. side effect and high contrast imaging. We investigated alternation of signal intensity as a function of the modality of Gd-based contrast media on spin echo and ultra short time echo (UTE) of T1 effective pulse sequence at 3T MRI unit. Gadoxetic acid, which is a MRI T1 contrast medium, was used to manufacture an agarose phantom diluted in various molarities, and sterile water and agarose 2% were used as the buf-fer solution for the dilution. The gold standard T1 calculation was based on coronal single section imag-ing of the phantom mid-point with 2D Inversion recovery spine-echo pulse sequence MR imaging for test-ing of phantom accuracy. The 1-2mmol/L and 7mmol/L was shown the maximum signal intensity on spin echo and UTE respectively. We confirm the difference of contrast media concentration which was shown the maximum signal intensity depending on the T1 effective pulse sequence.

직무 및 조직적합도와 직업몰입, 직업변경의도와의 구조적 관계

이석준(Lee, Suk-Jun) 한국관광레저학회 2016 관광레저연구 Vol.28 No.2

딥러닝을 활용한 여드름 중증도 측정

이석준 ( Suk Jun Lee ),전종수 ( Jong Soo Jeon ),류재연 ( Jae Yeon Ryu ),송현정 ( Hyun Jeong Song ),조윤재 ( Yoon Jae Jo ),방철환 ( Chul Hwhan Bang ),박영민 ( Young Min Park ),이지현 ( Ji Hyun Lee ) 대한피부과학회 2018 대한피부과학회지 Vol.56 No.7

Background: Acne is a chronic inflammatory disease of the pilosebaceous unit, mainly on the face. It can have various clinical manifestations and should be appropriately treated based on the severity. In Korea, the 'Korea Acne Severity Rating System (KAGS)' is a standardized index to determine the severity of acne according to specific Korean characteristics. However, the actual use of the KAGS in clinical settings has been limited. Objective: We sought to analyze whether we could effectively measure acne severity using a deep learning algorithm, which is an image learning method. Methods: Acne severity was classified into three levels of mild, moderate, and severe based on the KAGS, and learning and verification were performed using the CNN (Convolutional Neural Network), a deep learning technique. Results: GoogLeNet's Inception-v3 algorithm showed the highest accuracy at 86.7%. Conclusion: This study confirmed that the use of a deep learning algorithm may facilitate the scoring of acne severity. (Korean J Dermatol 2018;56(7):421∼425)