• 제목/요약/키워드: Input Variables

검색결과 1,774건 처리시간 0.03초

기계학습을 이용한 벼 수발아율 예측 (Predicting the Pre-Harvest Sprouting Rate in Rice Using Machine Learning)

  • 반호영;정재혁;황운하;이현석;양서영;최명구;이충근;이지우;이채영;윤여태;한채민;신서호;이성태
    • 한국농림기상학회지
    • /
    • 제22권4호
    • /
    • pp.239-249
    • /
    • 2020
  • 본 연구는 자연 조건에서 쌀가루용 벼의 수발아율을 예측하기 위한 것으로 기계학습을 이용하여 기상요소들에 따른 수발아율을 간단히 예측할 수 있는 초기 시스템을 개발하기 위해 수행되었다. 이를 위하여 강원도, 충청북도, 경상북도에 위치한 6개 지역에서 쌀가루용 벼 3품종을 재배하였다. 수확 후 수발아율과 출수일을 조사하였으며, 각 지역의 종관기상대의 일평균 기온과 상대 습도, 그리고 강수량 정보를 이용하여 기계학습 모델 중 하나이며, 정확도가 높은 GBM 모델로 수발아율을 예측하였다. 2017년부터 2019년까지 강원과 충북, 그리고 경북의 6개 지역에서 쌀가루 용 벼 3품종에 대해 재배 실험을 수행하였다. 조사 항목은 출수일과 수발아율이었다. 기상자료는 동일한 지역명의 종관기상대를 이용하여 일 평균 기온 및 상대 습도, 그리고 강수량 자료를 수집하였다. 수발아율 예측을 위해 기계학습 모델인 Gradient Boosting Machine (GBM)을 이용하였으며, 학습 투입 변수로는 평균 기온과 상대 습도, 그리고 총 강수량이었다. 또한 수발아 피해 관련 기간을 설정하기 위해 출수 후 몇일 후부터 그 이후의 기간에 대한 실험도 수행하였다. 자료는 수발아 피해 관련 기간의 교정을 위한 training-set과 vali-set, 검증을 위한 test-set으로 구분하였다. training-set과 vali-set으로 교정한 결과, 출수 후 22일 후부터 24일동안에서 가장 높은 score를 나타내었다. test-set으로 검증한 결과는 3.0%보다 낮은 구간에서 수발아율을 약간 높게 예측한 경향이 있었지만, 높은 예측력을 보였다(R2=0.76). 따라서, 기계학습을 이용하여 특정기간동안의 기상요소들로 수발아율을 간단하게 예측할 수 있을 것으로 예상된다. 본 연구의 결과를 종합해 볼 때, 기계학습을 이용하여 특정 기간 동안에 평균 기온과 상대 습도, 그리고 총 강수량으로 높은 수발아율 예측 성능을 보였으며, 이 시스템을 이용하여 일반 농가들을 대상으로 수발아에 관한 피해를 예방할 수 있는 조기 수발아 예측 시스템으로 이용가능 할 것으로 판단된다. 하지만 품종마다 휴면 정도 차이로 인한 수발아 관련 기간에 차이가 있으므로, 다른 쌀가루용 벼 품종에 대해서도 추가로 조사하고, 개별 품종으로 세분화하여 분석한다면 좀 더 정확도 높은 예측 시스템을 개발할 수 있을 것으로 판단된다.

우리나라 주변 바다의 산성화 현황과 영향 요인 분석 (A Review on Ocean Acidification and Factors Affecting It in Korean Waters)

  • 김태욱;김동선;박근하;고영호;모아라
    • 한국지구과학회지
    • /
    • 제43권1호
    • /
    • pp.91-109
    • /
    • 2022
  • 해양은 대기로 배출된 이산화탄소의 30% 가량을 흡수하여 대기 중 이산화탄소 농도를 감소시키는 역할을 하였으나, 이 때문에 해양의 pH와 탄산염 이온(CO32-)이 감소하는 해양산성화 현상을 겪고 있다. 본 논문에서는 황해 연안역의 신규 관측자료를 타 해역에서 획득된 기존 연구자료와 합쳐서 우리나라 주변 해역의 해양산성화 현황을 파악하고자 하였다. 우리나라 주변의 황해, 동해, 동중국해(남해 포함)는 대기 중 이산화탄소를 흡수하고 있으나, 외해 대부분의 해역에서 해양산성화의 지표인 아라고나이트 포화도가 1 이상인 것으로 나타났다. 남해 동부 연안역에서는 담수 공급으로 인한 희석과 성층 형성, 생물에 의한 유기물 생성과 분해가 표층과 저층의 계절적 해양산성화 변동에 큰 영향을 끼쳤다. 진해만은 빈산소화 현상, 광양만은 담수로 인한 희석으로 여름철 광범위한 해역에서 아라고나이트 포화도가 1 미만으로 감소하여, 탄산칼슘 패각(CaCO3 shell)을 가진 생물들에게 잠재적 위협이 될 것으로 보고되었다. 하지만 담수 유입이 많은 황해 연안역에서는 진해만과 광양만과 같이 뚜렷하고 광범위한 산성화는 발견되지 않았기 때문에, 연안역에서는 각 해역별 특성에 따라 해양산성화의 양상을 진단해야 할 필요가 있었다. 우리나라 동해 남서부 해역의 계절적 용승 현상 역시 해양산성화에 영향을 미칠 수 있다. 이런 계절적 요인과 더불어, 대기 중의 이산화탄소 및 산성물질이 해양으로 계속 유입되면서, 우리나라 바다의 아라고나이트 포화도가 지속적으로 감소할 것으로 예상된다. 따라서 해양산성화로부터 수산자원과 해양생태계를 보호하기 위해 향후 체계적인 해양산성화 모니터링을 강화해야 할 것이다.

CCTV 영상 기반 강우강도 산정을 위한 실환경 실험 자료 중심 적정 강우 이미지 DB 구축 방법론 개발 (Rainfall image DB construction for rainfall intensity estimation from CCTV videos: focusing on experimental data in a climatic environment chamber)

  • 변종윤;전창현;김현준;이재준;박헌일;이진욱
    • 한국수자원학회논문집
    • /
    • 제56권6호
    • /
    • pp.403-417
    • /
    • 2023
  • 본 연구에서는 CCTV 영상 기반 강우강도 산정 시 필수적으로 요구되는 적정 강우 이미지 DB를 구축하기 위한 방법론을 개발하였다. 먼저, 실환경에서 불규칙적이고 높은 변동성을 보일 수 있는 변수들(바람으로 인한 빗줄기의 변동성, 녹화 환경에서 포함되는 움직이는 객체, 렌즈 위의 흐림 현상 등)에 대한 통제가 가능한 한국건설생활환경시험연구원 내 기후환경시험실에서 CCTV 영상 DB를 구축하였다. 서로 다른 5개의 실험 조건을 고려하여 이상적 환경에서 총 1,728개의 시나리오를 구성하였다. 본 연구에서는 1,920×1,080 사이즈의 30 fps (frame per second) 영상 36개에 대하여 프레임 분할을 진행하였으며, 총 97,200개의 이미지를 사용하였다. 이후, k-최근접 이웃 알고리즘을 기반으로 산정된 최종 배경과 각 이미지와의 차이를 계산하여 빗줄기 이미지를 분리하였다. 과적합 방지를 위해 각 이미지에 대한 평균 픽셀 값을 계산하고, 설정한 픽셀 임계치보다 큰 자료를 선별하였다. 180×180 사이즈로의 재구성을 위해서 관심영역을 설정하고 10 Pixel 단위로 이동을 진행하여 픽셀 변동성이 최대가 되는 영역을 산정하였다. 합성곱 신경망 모델의 훈련을 위해서 120×120 사이즈로 재변환하고 과적합 방지를 위해 이미지 증강 과정을 거쳤다. 그 결과, 이미지 기반 강우 강도 합성곱 신경망 모델을 통해 산정된 결과값과 우량계에서 취득된 강우자료가 전반적으로 유사한 양상을 보였으며, 모든 강우강도 실험 조건에 대해서 약 92%의 데이터의 PBIAS (percent bias)가 절댓값 범위 10% 이내에 해당하였다. 본 연구의 결과물과 전이학습 등의 방법을 연계하여 기존 실환경 CCTV의 한계점을 개선할 수 있을 것으로 기대된다.

수증기 연직 분포에 의한 GOCI-II 해색 산출물 오차 분석 (Analysis of Uncertainty in Ocean Color Products by Water Vapor Vertical Profile)

  • 이경상;배수정;이은경;안재현
    • 대한원격탐사학회지
    • /
    • 제39권6_2호
    • /
    • pp.1591-1604
    • /
    • 2023
  • 해색 원격탐사에서 대기 보정은 자료의 정확도와 신뢰성 확보를 위해 반드시 수행해야하는 과정으로 높은 정확도가 요구된다. 또한 최근 원격 탐사 커뮤니티에서는 위성 자료의 오차에 대한 요구 사항이 증가함에 따라 대기 보정의 보조 자료로 사용되는 기상 변수(오존량, 기압, 바람장, 층적분 수증기량[total precipitable water, TPW])의 오차에 의해 발생하는 원격 반사도(remote sensing reflectance, Rrs)의 오차에 대한 연구가 진행되고 있지만 오차 요인으로 알려진 수증기 프로파일의 변동성에 의한 Rrs의 오차에 대한 연구는 수행되지 않았다. 본 연구에서는 Second Simulation of a Satellite Signal Vector version 2.1 모의를 통해 GOCI-II 관측 영역 내의 수증기 프로파일의 변동성에 따른 수증기 투과도의 오차를 계산하고 이로 인해 발생하는 해색 산출물의 오차에 대해 분석하였다. Radiosonde 관측 수증기 프로파일은 그 형태가 복잡할 뿐만 아니라 지표 부근의 큰 변동성으로 인해 기존 GOCI-II 대기 보정에서 사용하고 있는 US standard 62 수증기 프로파일과의 차이가 최대 0.007만큼 발생하였다. 이로 인해 발생한 수증기 투과도의 차이는 GOCI-II 대기 보정에서 에어로졸 반사도 추정의 차이를 발생시키고, 결과적으로 모든 밴드에서 Rrs의 오차가 발생하였다. 하지만 412-555 nm 밴드에서 수증기 프로파일 차이로 인한 Rrs 오차는 요구 정확도보다 낮은 2% 미만으로 나타났으며, 다른 해색 산출물인 클로로필(chlorophyll-a) 농도, 용존 유기물, 총 부유물 농도에서도 유사한 오차를 보이고 있다. 본 연구의 결과는 대기 보정 및 해색 산출물의 정확도에 있어 수증기 프로파일의 차이의 영향이 적다는 것을 의미한다. 하지만 추후 연구에서 수증기 흡광 보정 시 수증기 프로파일의 변동성을 고려할 경우 보다 높은 수준의 Rrs 정확도 확보를 기대할 수 있다.

K-Means Clustering 기법과 원격탐사 자료를 활용한 탄소기반 글로벌 해양 생태구역 분류 (Classification of Carbon-Based Global Marine Eco-Provinces Using Remote Sensing Data and K-Means Clustering)

  • 김영준;배덕원;임정호;정시훈;추민기;한대현
    • 대한원격탐사학회지
    • /
    • 제39권5_3호
    • /
    • pp.1043-1060
    • /
    • 2023
  • 최근 기후변화의 가속화로 바다에 의한 탄소의 흡수 작용을 칭하는 '블루 카본(blue carbon)'에 대한 관심이 많아지고 있지만, 탄소 순환의 핵심이 되는 해양 생태계에 대한 우리의 이해는 아직 부족한 실정이다. 본 연구는 탄소 순환을 고려한 글로벌 해양 생태 권역(marine eco-province)을 k-means clustering 기법을 활용하여 분류·분석하였다. 지난 20년 간(2001-2020) 위성을 활용하여 생산된 Carbon-based Productivity Model (CbPM) 순 일차 생산량(Net primary production, NPP), particulate inorganic and organic carbon (PIC and POC), 위성 관측과 재분석모델을 결합하여 생산한 해수면 염분(sea surface salinity, SSS) 및 온도(sea surface temperature, SST) 총 다섯가지 자료를 활용하였다. 최적화 과정을 거쳐 총 9개의 생태권역을 도출하였으며, 각 권역의 공간분포와 특성을 분석하였다. 이 중 5개의 권역은 주로 대양의 특성을 반영하고, 4개의 권역은 연안 및 고위도 해역의 특성을 반영하는 것으로 나타났다. 또한, 기존에 알려진 해양 생태 권역과의 정성적 비교를 통하여 탄소순환을 고려한 해양 생태권역의 특징을 상세히 분석하였다. 마지막으로 과거 5년 단위(2001-2005, 2006-2010, 2011-2015, 2016-2020)로 생태 권역의 변화를 분석하였으며, 연안생태계의 빠른 변화와 특히 담수유입으로 인해 생산량이 높고 생태적으로 중요한 권역의 감소를 확인하였다. 이러한 연구 결과는 탄소 순환 및 기후변화를 고려한 해양 생태 권역 분류 및 연안 관리에 대한 중요한 참고자료로 활용 될 수 있으며, 기후 변화에 취약한 지역에 대한 체계적인 관리 지침 개발에 활용될 수 있다.

Contrast Media in Abdominal Computed Tomography: Optimization of Delivery Methods

  • Joon Koo Han;Byung Ihn Choi;Ah Young Kim;Soo Jung Kim
    • Korean Journal of Radiology
    • /
    • 제2권1호
    • /
    • pp.28-36
    • /
    • 2001
  • Objective: To provide a systematic overview of the effects of various parameters on contrast enhancement within the same population, an animal experiment as well as a computer-aided simulation study was performed. Materials and Methods: In an animal experiment, single-level dynamic CT through the liver was performed at 5-second intervals just after the injection of contrast medium for 3 minutes. Combinations of three different amounts (1, 2, 3 mL/kg), concentrations (150, 200, 300 mgI/mL), and injection rates (0.5, 1, 2 mL/sec) were used. The CT number of the aorta (A), portal vein (P) and liver (L) was measured in each image, and time-attenuation curves for A, P and L were thus obtained. The degree of maximum enhancement (Imax) and time to reach peak enhancement (Tmax) of A, P and L were determined, and times to equilibrium (Teq) were analyzed. In the computed-aided simulation model, a program based on the amount, flow, and diffusion coefficient of body fluid in various compartments of the human body was designed. The input variables were the concentrations, volumes and injection rates of the contrast media used. The program generated the time-attenuation curves of A, P and L, as well as liver-to-hepatocellular carcinoma (HCC) contrast curves. On each curve, we calculated and plotted the optimal temporal window (time period above the lower threshold, which in this experiment was 10 Hounsfield units), the total area under the curve above the lower threshold, and the area within the optimal range. Results: A. Animal Experiment: At a given concentration and injection rate, an increased volume of contrast medium led to increases in Imax A, P and L. In addition, Tmax A, P, L and Teq were prolonged in parallel with increases in injection time The time-attenuation curve shifted upward and to the right. For a given volume and injection rate, an increased concentration of contrast medium increased the degree of aortic, portal and hepatic enhancement, though Tmax A, P and L remained the same. The time-attenuation curve shifted upward. For a given volume and concentration of contrast medium, changes in the injection rate had a prominent effect on aortic enhancement, and that of the portal vein and hepatic parenchyma also showed some increase, though the effect was less prominent. A increased in the rate of contrast injection led to shifting of the time enhancement curve to the left and upward. B. Computer Simulation: At a faster injection rate, there was minimal change in the degree of hepatic attenuation, though the duration of the optimal temporal window decreased. The area between 10 and 30 HU was greatest when contrast media was delivered at a rate of 2 3 mL/sec. Although the total area under the curve increased in proportion to the injection rate, most of this increase was above the upper threshould and thus the temporal window was narrow and the optimal area decreased. Conclusion: Increases in volume, concentration and injection rate all resulted in improved arterial enhancement. If cost was disregarded, increasing the injection volume was the most reliable way of obtaining good quality enhancement. The optimal way of delivering a given amount of contrast medium can be calculated using a computer-based mathematical model.

  • PDF

가족계획과 모자보건 통합을 위한 조산원의 투입효과 분석 -서산지역의 개입연구 평가보고- (An Intervention Study on Integration of Family Planning and Maternal/Infant Care Services in Rural Korea)

  • 방숙;한성현;이정자;안문영;이인숙;김은실;김종호
    • Journal of Preventive Medicine and Public Health
    • /
    • 제20권1호
    • /
    • pp.165-203
    • /
    • 1987
  • This project was a service-cum-research effort with a quasi-experimental study design to examine the health benefits of an integrated Family Planning (FP)/Maternal & Child health (MCH) Service approach that provides crucial factors missing in the present on-going programs. The specific objectives were: 1) To test the effectiveness of trained nurse/midwives (MW) assigned as change agents in the Health Sub-Center (HSC) to bring about the changes in the eight FP/MCH indicators, namely; (i)FP/MCH contacts between field workers and their clients (ii) the use of effective FP methods, (iii) the inter-birth interval and/or open interval, (iv) prenatal care by medically qualified personnel, (v) medically supervised deliveries, (vi) the rate of induced abortion, (vii) maternal and infant morbidity, and (viii) preinatal & infant mortality. 2) To measure the integrative linkage (contacts) between MW & HSC workers and between HSC and clients. 3) To examine the organizational or administrative factors influencing integrative linkage between health workers. Study design; The above objectives called for quasi-experimental design setting up a study and control area with and without a midwife. An active intervention program (FP/MCH minimum 'package' program) was conducted for a 2 year period from June 1982-July 1984 in Seosan County and 'before and after' surveys were conducted to measure the change. Service input; This study was undertaken by the Soonchunhyang University in collaboration with WHO. After a baseline survery in 1981, trained nurses/midwives were introduced into two health sub-centers in a rural setting (Seosan county) for a 2 year period from 1982 to 1984. A major service input was the establishment of midwifery services in the existing health delivery system with emphasis on nurse/midwife's role as the link between health workers (nurse aids) and village health workers, and the referral of risk patients to the private physician (OBGY specialist). An evaluation survey was made in August 1984 to assess the effectiveness of this alternative integrated approach in the study areas in comparison with the control area which had normal government services. Method of evaluation; a. In this study, the primary objective was first to examine to what extent the FP/MCH package program brought about changes in the pre-determined eight indicators (outcome and impact measures) and the following relationship was first analyzed; b. Nevertheless, this project did not automatically accept the assumption that if two or more activities were integrated, the results would automatically be better than a non-integrated or categorical program. There is a need to assess the 'integration process' itself within the package program. The process of integration was measured in terms of interactive linkages, or the quantity & quality of contacts between workers & clients and among workers. Intergrative linkages were hypothesized to be influenced by organizational factors at the HSC clinic level including HSC goals, sltrurture, authority, leadership style, resources, and personal characteristics of HSC staff. The extent or degree of integration, as measured by the intensity of integrative linkages, was in turn presumed to influence programme performance. Thus as indicated diagrammatically below, organizational factors constituted the independent variables, integration as the intervening variable and programme performance with respect to family planning and health services as the dependent variable: Concerning organizational factors, however, due to the limited number of HSCs (2 in the study area and 3 in the control area), they were studied by participatory observation of an anthropologist who was independent of the project. In this observation, we examined whether the assumed integration process actually occurred or not. If not, what were the constraints in producing an effective integration process. Summary of Findings; A) Program effects and impact 1. Effects on FP use: During this 2 year action period, FP acceptance increased from 58% in 1981 to 78% in 1984 in both the study and control areas. This increase in both areas was mainly due to the new family planning campaign driven by the Government for the same study period. Therefore, there was no increment of FP acceptance rate due to additional input of MW to the on-going FP program. But in the study area, quality aspects of FP were somewhat improved, having a better continuation rate of IUDs & pills and more use of effective Contraceptive methods in comparison with the control area. 2. Effects of use of MCH services: Between the study and control areas, however, there was a significant difference in maternal and child health care. For example, the coverage of prenatal care was increased from 53% for 1981 birth cohort to 75% for 1984 birth cohort in the study area. In the control area, the same increased from 41% (1981) to 65% (1984). It is noteworthy that almost two thirds of the recent birth cohort received prenatal care even in the control area, indicating that there is a growing demand of MCH care as the size of family norm becomes smaller 3. There has been a substantive increase in delivery care by medical professions in the study area, with an annual increase rate of 10% due to midwives input in the study areas. The project had about two times greater effect on postnatal care (68% vs. 33%) at delivery care(45.2% vs. 26.1%). 4. The study area had better reproductive efficiency (wanted pregancies with FP practice & healthy live births survived by one year old) than the control area, especially among women under 30 (14.1% vs. 9.6%). The proportion of women who preferred the 1st trimester for their first prenatal care rose significantly in the study area as compared to the control area (24% vs 13%). B) Effects on Interactive Linkage 1. This project made a contribution in making several useful steps in the direction of service integration, namely; i) The health workers have become familiar with procedures on how to work together with each other (especially with a midwife) in carrying out their work in FP/MCH and, ii) The health workers have gotten a feeling of the usefulness of family health records (statistical integration) in identifying targets in their own work and their usefulness in caring for family health. 2. On the other hand, because of a lack of required organizational factors, complete linkage was not obtained as the project intended. i) In regards to the government health worker's activities in terms of home visiting there was not much difference between the study & control areas though the MW did more home visiting than Government health workers. ii) In assessing the service performance of MW & health workers, the midwives balanced their workload between 40% FP, 40% MCH & 20% other activities (mainly immunization). However, $85{\sim}90%$ of the services provided by the health workers were other than FP/MCH, mainly for immunizations such as the encephalitis campaign. In the control area, a similar pattern was observed. Over 75% of their service was other than FP/MCH. Therefore, the pattern shows the health workers are a long way from becoming multipurpose workers even though the government is pushing in this direction. 3. Villagers were much more likely to visit the health sub-center clinic in the study area than in the control area (58% vs.31%) and for more combined care (45% vs.23%). C) Organization factors (admistrative integrative issues) 1. When MW (new workers with higher qualification) were introduced to HSC, it was noted that there were conflicts between the existing HSC workers (Nurse aids with less qualification than MW) and the MW for the beginning period of the project. The cause of the conflict was studied by an anthropologist and it was pointed out that these functional integration problems stemmed from the structural inadequacies of the health subcenter organization as indicated below; i) There is still no general consensus about the objectives and goals of the project between the project staff and the existing health workers. ii) There is no formal linkage between the responsibility of each member's job in the health sub-center. iii) There is still little chance for midwives to play a catalytic role or to establish communicative networks between workers in order to link various knowledge and skills to provide better FP/MCH services in the health sub-center. 2. Based on the above findings the project recommended to the County Chief (who has power to control the administrative staff and the technical staff in his county) the following ; i) In order to solve the conflicts between the individual roles and functions in performing health care activities, there must be goals agreed upon by both. ii) The health sub·center must function as an autonomous organization to undertake the integration health project. In order to do that, it is necessary to support administrative considerations, and to establish a communication system for supervision and to control of the health sub-centers. iii) The administrative organization, tentatively, must be organized to bind the health worker's midwive's and director's jobs by an organic relationship in order to achieve the integrative system under the leadership of health sub-center director. After submitting this observation report, there has been better understanding from frequent meetings & communication between HW/MW in FP/MCH work as the program developed. Lessons learned from the Seosan Project (on issues of FP/MCH integration in Korea); 1) A majority or about 80% of the couples are now practicing FP. As indicated by the study, there is a growing demand from clients for the health system to provide more MCH services than FP in order to maintain the achieved small size of family through FP practice. It is fortunate to see that the government is now formulating a MCH policy for the year 2,000 and revising MCH laws and regulations to emphasize more MCH care for achieving a small size family through family planning practice. 2) Goal consensus in FP/MCH shouBd be made among the health workers It administrators, especially to emphasize the need of care of 'wanted' child. But there is a long way to go to realize the 'real' integration of FP into MCH in Korea, unless there is a structural integration FP/MCH because a categorical FP is still first priority to reduce the rate of population growth for economic reasons but not yet for health/welfare reasons in practice. 3) There should be more financial allocation: (i) a midwife should be made available to help to promote the MCH program and coordinate services, (in) there should be a health sub·center director who can provide leadership training for managing the integrated program. There is a need for 'organizational support', if the decision of integration is made to obtain benefit from both FP & MCH. In other words, costs should be paid equally to both FP/MCH. The integration slogan itself, without the commitment of paying such costs, is powerless to advocate it. 4) Need of management training for middle level health personnel is more acute as the Government has already constructed 90 MCH centers attached to the County Health Center but without adequate manpower, facilities, and guidelines for integrating the work of both FP and MCH. 5) The local government still considers these MCH centers only as delivery centers to take care only of those visiting maternity cases. The MCH center should be a center for the managment of all pregnancies occurring in the community and the promotion of FP with a systematic and effective linkage of resources available in the county such as i.e. Village Health Worker, Community Health Practitioner, Health Sub-center Physicians & Health workers, Doctors and Midwives in MCH center, OBGY Specialists in clinics & hospitals as practiced by the Seosan project at primary health care level.

  • PDF

효과적인 입력변수 패턴 학습을 위한 시계열 그래프 기반 합성곱 신경망 모형: 주식시장 예측에의 응용 (A Time Series Graph based Convolutional Neural Network Model for Effective Input Variable Pattern Learning : Application to the Prediction of Stock Market)

  • 이모세;안현철
    • 지능정보연구
    • /
    • 제24권1호
    • /
    • pp.167-181
    • /
    • 2018
  • 지난 10여 년간 딥러닝(Deep Learning)은 다양한 기계학습 알고리즘 중에서 많은 주목을 받아 왔다. 특히 이미지를 인식하고 분류하는데 효과적인 알고리즘으로 알려져 있는 합성곱 신경망(Convolutional Neural Network, CNN)은 여러 분야의 분류 및 예측 문제에 널리 응용되고 있다. 본 연구에서는 기계학습 연구에서 가장 어려운 예측 문제 중 하나인 주식시장 예측에 합성곱 신경망을 적용하고자 한다. 구체적으로 본 연구에서는 그래프를 입력값으로 사용하여 주식시장의 방향(상승 또는 하락)을 예측하는 이진분류기로써 합성곱 신경망을 적용하였다. 이는 그래프를 보고 주가지수가 오를 것인지 내릴 것인지에 대해 경향을 예측하는 이른바 기술적 분석가를 모방하는 기계학습 알고리즘을 개발하는 과제라 할 수 있다. 본 연구는 크게 다음의 네 단계로 수행된다. 첫 번째 단계에서는 데이터 세트를 5일 단위로 나눈다. 두 번째 단계에서는 5일 단위로 나눈 데이터에 대하여 그래프를 만든다. 세 번째 단계에서는 이전 단계에서 생성된 그래프를 사용하여 학습용과 검증용 데이터 세트를 나누고 합성곱 신경망 분류기를 학습시킨다. 네 번째 단계에서는 검증용 데이터 세트를 사용하여 다른 분류 모형들과 성과를 비교한다. 제안한 모델의 유효성을 검증하기 위해 2009년 1월부터 2017년 2월까지의 약 8년간의 KOSPI200 데이터 2,026건의 실험 데이터를 사용하였다. 실험 데이터 세트는 CCI, 모멘텀, ROC 등 한국 주식시장에서 사용하는 대표적인 기술지표 12개로 구성되었다. 결과적으로 실험 데이터 세트에 합성곱 신경망 알고리즘을 적용하였을 때 로지스틱회귀모형, 단일계층신경망, SVM과 비교하여 제안모형인 CNN이 통계적으로 유의한 수준의 예측 정확도를 나타냈다.

비대칭적 전이효과와 SVM을 이용한 변동성 매도전략의 수익성 개선 (Performance Improvement on Short Volatility Strategy with Asymmetric Spillover Effect and SVM)

  • 김선웅
    • 지능정보연구
    • /
    • 제26권1호
    • /
    • pp.119-133
    • /
    • 2020
  • Fama에 의하면 효율적 시장에서는 일시적으로 높은 수익을 얻을 수는 있지만 꾸준히 시장의 평균적인 수익을 초과하는 투자전략을 만드는 것은 불가능하다. 본 연구의 목적은 변동성의 장중 비대칭적 전이효과를 이용하는 변동성 매도전략을 기준으로 투자 성과를 추가적으로 개선하기 위하여 SVM을 활용하는 투자 전략을 제안하고 그 투자성과를 분석하고자 한다. 한국 시장에서 변동성의 비대칭적 전이효과는 미국 시장의 변동성이 상승한 날은 한국 시장의 아침 동시호가에 변동성 상승이 모두 반영되지만, 미국 시장의 변동성이 하락한 날은 한국 시장의 변동성이 아침 동시호가에서 뿐만 아니라 장 마감까지 계속해서 하락하는 이상현상을 말한다. 분석 자료는 2008년부터 2018년까지의 S&P 500, VIX, KOSPI 200, V-KOSPI 200 등의 일별 시가지수와 종가지수이다. 11년 동안의 분석 결과, 미국 시장의 변동성이 상승으로 마감한 날은 그 영향력이 한국 시장의 아침 동시호가 변동성에 모두 반영되지만, 미국 시장의 변동성이 하락으로 마감한 날은 그 영향력이 한국 시장의 아침 동시호가뿐만 아니라 오후 장 마감까지도 계속해서 유의적으로 영향을 미치고 있다. 시장이 효율적이라면 미국 시장의 전일 변동성 변화는 한국 시장의 아침 동시호가에 모두 반영되고 동시호가 이후에는 추가적인 영향력이 없어야 한다. 이러한 변동성의 장중 비정상적 전이 패턴을 이용하는 변동성 매도전략을 제안하였다. 미국 시장의 전날 변동성이 하락한 경우 한국 시장에서 아침 동시호가에 변동성을 매도하고 장 마감시에 포지션을 청산하는 변동성 데이트레이딩전략을 분석하였다. 연수익률은 120%, 위험지표인 MDD는 -41%, 위험과 수익을 고려한 성과지수인 Sharpe ratio는 0.27을 기록하고 있다. SVM 알고리즘을 이용해 변동성 데이트레이딩전략의 성과 개선을 시도하였다. 2008년부터 2014년까지의 입력자료를 이용하여 V-KOSPI 200 변동성지수의 시가-종가 변동 방향을 예측하고, 시가-종가 변동율이(-)로 예측되는 경우에만 변동성 매도포지션을 진입하였다. 거래비용을 고려하면 2015년부터 2018년까지 테스트기간의 연평균수익률은 123%로 기준 전략 69%보다 크게 높아지고, 위험지표인 MDD도 -41%에서 -29%로 낮아져, Sharpe ratio가 0.32로 개선되고 있다. 연도별로도 모두 수익을 기록하면서 안정적 수익구조를 보여주고 있고, 2015년을 제외하고는 투자 성과가 개선되고 있다.

계획된 간호 정보가 수면량에 미치는 영향에 관한 연구 -개심술 환자를 중심으로- (The Effect of Structured Information on the Sleep Amount of Patients Undergoing Open Heart Surgery)

  • 이소우
    • 대한간호학회지
    • /
    • 제12권2호
    • /
    • pp.1-26
    • /
    • 1982
  • The main purpose of this study was to test the effect of the structured information on the sleep amount of the patients undergoing open heart surgery. This study has specifically addressed to the Following two basic research questions: (1) Would the structed in formation influence in the reduction of sleep disturbance related to anxiety and Physical stress before and after the operation? and (2) that would be the effects of the structured information on the level of preoperative state anxiety, the hormonal change, and the degree of behavioral change in the patients undergoing an open heart surgery? A Quasi-experimental research was designed to answer these questions with one experimental group and one control group. Subjects in both groups were matched as closely as possible to avoid the effect of the differences inherent to the group characteristics, Baseline data were also. collected on both groups for 7 days prior to the experiment and found that subjects in both groups had comparable sleep patterns, trait anxiety, hormonal levels and behavioral level. A structured information as an experimental input was given to the subjects in the experimental group only. Data were collected and compared between the experimental group and the control group on the sleep amount of the consecutive pre and post operative days, on preoperative state anxiety level, and on hormonal and behavioral changes. To test the effectiveness of the structured information, two main hypotheses and three sub-hypotheses were formulated as follows; Main hypothesis 1: Experimental group which received structured information will have more sleep amount than control group without structured information in the night before the open heart surgery. Main hypothesis 2: Experimental group with structured information will have more sleep, amount than control group without structured information during the week following the open heart surgery Sub-hypothesis 1: Experimental group with structured information will be lower in the level of State anxiety than control group without structured information in the night before the open heart surgery. Sub-hypothesis 2 : Experimental group with structured information will have lower hormonal level than control group without stuctured information on the 5th day after the open heart surgery Sub-hypothesis 3: Experimental group with structured information will be lower in the behavioral change level than control group without structured information during the week after the open heart surgery. The research was conducted in a national university hospital in Seoul, Korea. The 53 Subjects who participated in the study were systematically divided into experimental group and control group which was decided by random sampling method. Among 53 subjects, 26 were placed in the experimental group and 27 in the control group. Instruments; (1) Structed information: Structured information as an independent variable was constructed by the researcher on the basis of Roy's adaptation model consisting of physiologic needs, self-concept, role function and interdependence needs as related to the sleep and of operational procedures. (2) Sleep amount measure: Sleep amount as main dependent variable was measured by trained nurses through observation on the basis of the established criteria, such as closed or open eyes, regular or irregular respiration, body movement, posture, responses to the light and question, facial expressions and self report after sleep. (3) State anxiety measure: State Anxiety as a sub-dependent variable was measured by Spi-elberger's STAI Anxiety scale, (4) Hormornal change measure: Hormone as a sub-dependent variable was measured by the cortisol level in plasma. (5) Behavior change measure: Behavior as a sub-dependent variable was measured by the Behavior and Mood Rating Scale by Wyatt. The data were collected over a period of four months, from June to October 1981, after the pretest period of two months. For the analysis of the data and test for the hypotheses, the t-test with mean differences and analysis of covariance was used. The result of the test for instruments show as follows: (1) STAI measurement for trait and state anxiety as analyzed by Cronbachs alpha coefficient analysis for item analysis and reliability showed the reliability level at r= .90 r= .91 respectively. (2) Behavior and Mood Rating Scale measurement was analyzed by means of Principal Component Analysis technique. Seven factors retained were anger, anxiety, hyperactivity, depression, bizarre behavior, suspicious behavior and emotional withdrawal. Cumulative percentage of each factor was 71.3%. The result of the test for hypotheses show as follows; (1) Main hypothesis, was not supported. The experimental group has 282 minutes of sleep as compared to the 255 minutes of sleep by the control group. Thus the sleep amount was higher in experimental group than in control group, however, the difference was not statistically significant at .05 level. (2) Main hypothesis 2 was not supported. The mean sleep amount of the experimental group and control group were 297 minutes and 278 minutes respectively Therefore, the experimental group had more sleep amount as compared to the control group, however, the difference was not statistically significant at .05 level. Thus, the main hypothesis 2 was not supported. (3) Sub-hypothesis 1 was not supported. The mean state anxiety of the experimental group and control group were 42.3, 43.9 in scores. Thus, the experimental group had slightly lower state anxiety level than control group, howe-ver, the difference was not statistically significant at .05 level. (4) Sub-hypothesis 2 was not supported. . The mean hormonal level of the experimental group and control group were 338 ㎍ and 440 ㎍ respectively. Thus, the experimental group showed decreased hormonal level than the control group, however, the difference was not statistically significant at .05 level. (5) Sub-hypothesis 3 was supported. The mean behavioral level of the experimental group and control group were 29.60 and 32.00 respectively in score. Thus, the experimental group showed lower behavioral change level than the control group. The difference was statistically significant at .05 level. In summary, the structured information did not influence the sleep amount, state anxiety or hormonal level of the subjects undergoing an open heart surgery at a statistically significant level, however, it showed a definite trends in their relationships, not least to mention its significant effect shown on behavioral change level. It can further be speculated that a great degree of individual differences in the variables such as sleep amount, state anxiety and fluctuation in hormonal level may partly be responsible for the statistical insensitivity to the experimentation.

  • PDF