• 제목/요약/키워드: warning and prediction system

검색결과 100건 처리시간 0.032초

의료 빅데이터를 활용한 CRM 기반 건강예보모형 설계 (Design of Health Warning Model on the Basis of CRM by use of Health Big Data)

  • 이상원;신성윤
    • 한국정보통신학회논문지
    • /
    • 제20권8호
    • /
    • pp.1460-1465
    • /
    • 2016
  • 오늘날 많은 비용이 국가 의료보장체계의 유지를 위협하고 있다. 국가 질병 통제 및 방지 센터의 감사체계를 동반한 건강관리 역학성에 대한 연구에도 불구하고, 시간 한계, 표본 한계, 대상 질병 한계에 대한 제약이 여전히 존재하고 있다. 이러한 배경에서, 방대한 양의 전수 데이터를 활용하여, 많은 기술들이 건강의 선제적 예측이나 그 대상 질병을 확장하는 분야에 충분하게 적용되고 있다. 우리는 국민건강보험의 구조적 데이터와 소셜네트워크서비스의 비구조적 데이터를 활용하여 질병을 예측하는 모형을 설계하였다. 이 모형은 건강예보서비스를 제공함으로써, 국민건강을 증진시키고 사회적 혜택을 극대화할 수 있다. 또한, 빅데이터 분석에 근거하여, 건강보험비용의 갑작스러운 증가를 감소시키거나 적시적인 질병발생을 예측할 수도 있다. 관련된 의료 예측 사례를 살펴보았고, 제안된 모형의 검증을 위하여 시범과제를 통한 실험을 수행하였다.

Construction of Korean Space Weather Prediction Center: Magnetometer

  • Kim, Khan-Hyuk;Choi, Seong-Hwan;Cho, Kyung-Seok;Park, Young-Deuk;Choi, Kyu-Chul
    • 한국우주과학회:학술대회논문집(한국우주과학회보)
    • /
    • 한국우주과학회 2008년도 한국우주과학회보 제17권2호
    • /
    • pp.32.3-32.3
    • /
    • 2008
  • Solar and Space Weather Research Group in Korea Astronomy & Space Science Institute (KASI) has been funded for "Construction of Korean Space Weather Prediction Center" from Korean government. It has started since 2007 February and is planed as a 5-year project. The goal of this project is to develop a space weather warning and prediction system by the next solar maximum. KASI installed a magnetometer at Mt. Bohyun, which is about 200 km south-east apart from KASI, in 2007 September. After finishing test observations of the magnetometer for the period from September 2007 to January 2008, KASI has operated the magnetometer to monitor geomagnetic field variations associated with space weather effect. Ground-based magnetometers are critical for understanding geomagnetic disturbances in the near-Earth space environment, which are caused by solar wind variations. In this talk, we introduce science topics to be done with the data from KASI magnetometer and also discuss how they are related to space weather phenomena.

  • PDF

River streamflow prediction using a deep neural network: a case study on the Red River, Vietnam

  • Le, Xuan-Hien;Ho, Hung Viet;Lee, Giha
    • 농업과학연구
    • /
    • 제46권4호
    • /
    • pp.843-856
    • /
    • 2019
  • Real-time flood prediction has an important role in significantly reducing potential damage caused by floods for urban residential areas located downstream of river basins. This paper presents an effective approach for flood forecasting based on the construction of a deep neural network (DNN) model. In addition, this research depends closely on the open-source software library, TensorFlow, which was developed by Google for machine and deep learning applications and research. The proposed model was applied to forecast the flowrate one, two, and three days in advance at the Son Tay hydrological station on the Red River, Vietnam. The input data of the model was a series of discharge data observed at five gauge stations on the Red River system, without requiring rainfall data, water levels and topographic characteristics. The research results indicate that the DNN model achieved a high performance for flood forecasting even though only a modest amount of data is required. When forecasting one and two days in advance, the Nash-Sutcliffe Efficiency (NSE) reached 0.993 and 0.938, respectively. The findings of this study suggest that the DNN model can be used to construct a real-time flood warning system on the Red River and for other river basins in Vietnam.

기상조건별 비산먼지 관리체계 최적화 연구 (Optimization of Fugitive Dust Control System for Meteorological Conditions)

  • 김현구
    • 한국대기환경학회지
    • /
    • 제21권6호
    • /
    • pp.573-583
    • /
    • 2005
  • Fugitive dust, which is emitted in the ambient air without first passing through a stack or duct designed to control flow, is frequently generated by means of wind erosion from storage yards at Pohang Steel Wokrs. The size distribution of fugitive dust is mostly in the range of coarse particulate which is deposited as soon as emitted and less harm to human health; however $20\%$ of fugitive dust contains PM 10 known as one of most harmful airborne pollutant. Consequently, effective control and reduction of fugitive dust is strongly requested by the local society, but it is not easy so far because the generation and dispersion of fugitive dust highly depends on meteorological conditions, and it being occurred for irregularity. This research presented a fugitive dust control system for each meteorological condition by providing statistical prediction data obtained from a statistical analysis on the probability of generating the threshold velocity at which the fugitive dust begins to occur, and the frequency occurring by season and by time of the wind direction that can generate atmospheric pollution when the dispersed dust spreads to adjacent residential areas. The research also built a fugitive dust detection system which monitors the weather conditions surrounding storage yards and the changes in air quality on a real-time basis and issues a warning message by identifying a situation where the fugitive dust disperses outside the site boundary line so that appropriate measures can be taken on a timely basis. Furthermore, in respect to the spraying of water to prevent the generation of fugitive dust from the storage piles at the storage yard, an advanced statistical meteorological analysis on the weather conditions in Pohang area and a case study of fugitive dust dispersion toward outside of working field during $2002\∼2003$ were carried out in order to decide an optimal water-spraying time and the number of spraying that can prevent the origin of fugitive dust emission. The results of this research are expected to create extremely significant effects in improving surrounding environment through actual reduction of the fugitive dust produced from the storage yard of Pohang Steel Works by providing a high-tech warning system capable of constantly monitoring the leakage of fugitive dust and water-spray guidance that can maximize the water-spraying effects.

Hazard prediction of coal and gas outburst based on fisher discriminant analysis

  • Chen, Liang;Wang, Enyuan;Feng, Junjun;Wang, Xiaoran;Li, Xuelong
    • Geomechanics and Engineering
    • /
    • 제13권5호
    • /
    • pp.861-879
    • /
    • 2017
  • Coal and gas outburst is a serious dynamic disaster that occurs during coal mining and threatens the lives of coal miners. Currently, coal and gas outburst is commonly predicted using single indicator and its critical value. However, single indicator is unable to fully reflect all of the factors impacting outburst risk and has poor prediction accuracy. Therefore, a more accurate prediction method is necessary. In this work, we first analyzed on-site impacting factors and precursors of coal and gas outburst; then, we constructed a Fisher discriminant analysis (FDA) index system using the gas adsorption index of drilling cutting ${\Delta}h_2$, the drilling cutting weight S, the initial velocity of gas emission from borehole q, the thickness of soft coal h, and the maximum ratio of post-blasting gas emission peak to pre-blasting gas emission $B_{max}$; finally, we studied an FDA-based multiple indicators discriminant model of coal and gas outburst, and applied the discriminant model to predict coal and gas outburst. The results showed that the discriminant model has 100% prediction accuracy, even when some conventional indexes are lower than the warning criteria. The FDA method has a broad application prospects in coal and gas outburst prediction.

발아시기 정밀추정에 의한 포도 만상해 경보방법 개선 (Phonology and Minimum Temperature as Dual Determinants of Late Frost Risk at Vineyards)

  • 정재은;윤진일
    • 한국농림기상학회지
    • /
    • 제8권1호
    • /
    • pp.28-35
    • /
    • 2006
  • 근년에 자주 나타나고 있는 봄철 과원의 서리피해는 관측된 기온이 비슷한 지역일지라도 개화 혹은 발아 단계의 과원에서 집중되고 있어 효율적인 상해 경보시스템 운영을 위해서는 발아기 혹은 만개기의 정확한 예측이 필요하다. 품종별 모수가 알려져 있는 포도 거봉, Campbell Early를 대상으로 생물계절모형을 적용하여 발아기를 추정하고 최저기온 예상치와 함께 늦서리 위험도 추정방법을 제시하였다. 이 방법은 발아 이후에 최저기온이 영하로 내려가면 상해가 발생한다고 가정하는데, 추정값의 오차범위를 고려한 발아일 이후 일 최저기온이 $-1.5^{\circ}C$ 이하로 떨어지면 경보(Warning), ${\pm}1.5^{\circ}C$ 사이면 주의보(Watch)를 발령한다. 이 방법을 2004년과 2005년 4월 경기 안성의 포도원에 적용하여 결과의 신뢰도를 확인하였다. 같은 방법으로 1971-2000평년의 기후조건에서 예상되는 안성지역의 포도 늦서리피해 위험지역을 30 m의 고해상도 전자기후도로 표현하였다. 안성시 전역을 30 m 격자점으로 표현하면 총 608,585개로 구성되는데, 평년의 포도 상해위험지역 판정결과 거봉은 1,059지역이, Campbell Early는 2,788지역이 주의지대로 예상된다.

IoT 센서와 AI 카메라를 융합한 급경사지 상태 분석 시스템 개발 (Development of a Slope Condition Analysis System using IoT Sensors and AI Camera)

  • 이승주;정기연;이태훈;김영석
    • 한국지반신소재학회논문집
    • /
    • 제23권2호
    • /
    • pp.43-52
    • /
    • 2024
  • 최근 이상기후로 인한 급경사지 붕괴 위험이 증가되고 있으며, 급경사지 붕괴 위험의 사전 예측 및 경보 전파가 이루어지지 않아 인명과 재산 피해가 발생할 수 있다. 본 논문에서는 급경사지의 상태를 평가하기 위해 IoT 센서와 AI 기반 카메라를 융합한 급경사지 분석 시스템을 개발하였다. 시스템을 개발하기 위하여 급경사지 지반조건을 고려한 계측센서 하드웨어 및 펌웨어 설계, AI 기반 영상 분석 알고리즘 설계, 그리고 예·경보 솔루션 및 시스템 제작을 수행하였다. IoT 센서의 데이터와 AI 카메라 영상 분석을 통해 센서 데이터의 오차를 최소화하고, 데이터의 신뢰성을 향상시키고자 하였다. 또한 실제 급경사지에 적용하여 정확도(신뢰도)를 평가하였다. 그 결과, 센서 계측 오류는 0.1° 이내로 유지되었으며 계측 데이터의 전송률은 95%이상이었다. AI 기반의 영상 분석 시스템은 야간에도 부분 인식률 99%의 높은 성능을 나타내었다. 본 연구결과는 다양한 사회간접자본(SOC) 시설의 급경사지 상태 분석 및 스마트 유지관리 분야에도 적용할 수 있을 것으로 판단된다.

독성 감지를 위한 생물 조기 경보 시스템 (Biological Early Warning System for Toxicity Detection)

  • 김성용;권기용;이원돈
    • 한국정보통신학회논문지
    • /
    • 제14권9호
    • /
    • pp.1979-1986
    • /
    • 2010
  • 생물 조기 경보 시스템은 물속 생명체의 행동을 관찰하여 독성을 감지한다. 이 시스템은 분류기를 물의 독성의 유무와 정도를 판단하기 위해 사용한다. 이 분류기의 성능을 높이기 위해 적용할 수 있는 방법 중에 부스팅 알고리즘이 있다. 부스팅은 기본 분류기로는 예측 정확도가 낮았던 분류하기 어려운 사건에 집중할 수 있도록 다음 번 데이터에 해당 훈련 사건(event)들이 뽑힐 확률을 높여준다. 횟수가 진행될수록 분류기가 어려운 사건들을 집중적으로 고려하게 된다. 그 결과 분류하기 어려웠던 사건에 대한 예측 성능은 좋아지지만, 비교적 쉬운 훈련 사건들의 정보는 버려지는 단점이 있다. 본 논문에서는 이 같은 단점을 보완하기 위해 분류기에 확장된 데이터 표현을 위한 점진적 학습법의 적용을 제안한다. 확장된 데이터 표현의 가중치 변수를 사용하면 약하게 분류되는 사건 뿐 아니라 쉽게 분류되는 사건의 정보까지도 사용하여 분류기의 예측 정확도를 높일 수 있게 된다. 새로 적용된 알고리즘과 기존의 중요도 변수를 사용하지 않는 learn++를 비교하여 성능이 향상됨을 검증하였다.

Space Weather Monitoring System for Geostationary Satellites and Polar Routes

  • Baek, Ji-Hye;Lee, Jae-Jin;Choi, Seong-Hwan;Hwang, Jung-A;Hwang, Eun-Mi;Park, Young-Deuk
    • 천문학회보
    • /
    • 제36권2호
    • /
    • pp.101.2-101.2
    • /
    • 2011
  • We have developed solar and space weather monitoring system for space weather users since 2007 as a project named 'Construction of Korea Space Weather Prediction Center'. In this presentation we will introduce space weather monitoring system for Geostationary Satellites and Polar Routes. These were developed for satisfying demands of space weather user groups. 'Space Weather Monitoring System for Geostationary Satellites' displays integrated space weather information on geostationary orbit such as magnetopause location, nowcast and forecast of space weather, cosmic ray count rate, number of meteors and x-ray solar flux. This system is developed for space weather customers who are managing satellite systems or using satellite information. In addition, this system provides space weather warning by SMS in which short message is delivered to users' cell phones when space weather parameters reach a critical value. 'Space Weather Monitoring System for Polar Routes' was developed for the commercial airline companies operating polar routes. This provides D-region and polar cap absorption map, aurora and radiation particle distribution, nowcast and forecast of space weather, proton flux, Kp index and so on.

  • PDF

PTT를 이용한 자전거 운동 중 지속적인 혈압의 예측 (Continuous Blood Pressure Prediction Using PTT During Exercise)

  • 김철승;문기욱;권정훈;엄광문
    • 대한의용생체공학회:의공학회지
    • /
    • 제27권6호
    • /
    • pp.370-375
    • /
    • 2006
  • The purpose of this work is to predict the systolic blood pressure (BP) during exercise from pulse transit time (PTT) for warning of possible danger. PTT was calculated as the time between R-peak of ECG and the peak of differential photoplethysmograph (PPG). For the PTT-BP model, we used regress equations from previous studies and 3 kinds of new models combining linear and nonlinear regress equation. The model parameters were estimated with the data measured under low to middle intensity exercise, and then was tested with the data measured under high intensity exercise. Predicted BP values after high intensity exercise were compared with those measured by cuff-type sphygmomanometer. The results showed that the error between measured and predicted values were acceptable for the monitoring BP. We tested PTT-BP models 1 month after the identification without further calibration. Models could predict the BP and the errors between measured and predicted BP were about 5mmHg. The suggested system is expected to be helpful in recognizing any danger during exercise.