• 제목/요약/키워드: Early selection

검색결과 738건 처리시간 0.029초

랜덤 포리스트를 이용한 비제어 급성 출혈성 쇼크의 흰쥐에서의 생존 예측 (A Survival Prediction Model of Rats in Uncontrolled Acute Hemorrhagic Shock Using the Random Forest Classifier)

  • 최준열;김성권;구정모;김덕원
    • 대한의용생체공학회:의공학회지
    • /
    • 제33권3호
    • /
    • pp.148-154
    • /
    • 2012
  • Hemorrhagic shock is a primary cause of deaths resulting from injury in the world. Although many studies have tried to diagnose accurately hemorrhagic shock in the early stage, such attempts were not successful due to compensatory mechanisms of humans. The objective of this study was to construct a survival prediction model of rats in acute hemorrhagic shock using a random forest (RF) model. Heart rate (HR), mean arterial pressure (MAP), respiration rate (RR), lactate concentration (LC), and peripheral perfusion (PP) measured in rats were used as input variables for the RF model and its performance was compared with that of a logistic regression (LR) model. Before constructing the models, we performed 5-fold cross validation for RF variable selection, and forward stepwise variable selection for the LR model to examine which variables were important for the models. For the LR model, sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (ROC-AUC) were 0.83, 0.95, 0.88, and 0.96, respectively. For the RF models, sensitivity, specificity, accuracy, and AUC were 0.97, 0.95, 0.96, and 0.99, respectively. In conclusion, the RF model was superior to the LR model for survival prediction in the rat model.

SW영재학급 현황 분석을 통한 SW영재교육의 개선 방안 탐색 (A Study on the Improvement of SW Gifted Education through Analysis on the Current Situation of the SW Gifted Class)

  • 심재권;김용천;권대용
    • 정보교육학회논문지
    • /
    • 제21권6호
    • /
    • pp.711-721
    • /
    • 2017
  • SW교육의 중요성이 증가함에 따라 SW분야에 재능이 뛰어난 학생들을 조기에 발굴하여 SW인재로 양성하기 위한 SW영재교육의 필요성이 높아지고 있다. 이에 2016년 초중고 학생을 대상으로 하는 SW영재학급 30곳이 설치되어 SW영재교육을 시작하였다. 그러나 각각의 영재학급이 선발 방법, 교육과정, 환경 등의 조건들이 모두 달라서 일관성과 체계성을 갖기 어려운 상황이다. 따라서 기관에 따른 SW영재학급의 편차를 줄이고, 효과적인 SW영재교육 수행을 위해서는 현황 조사를 통한 문제점 분석과 개선방향 도출이 필요하다. 이에 본 연구에서는 모든 학급의 설치운영계획서와 현장 방문을 통해 SW영재학급의 교육과정, 환경, 선발 내용을 조사하여 현재 SW영재학급의 전반적인 현황 분석하였으며 이를 기반으로 한계점 및 문제점을 도출하고 개선 방향을 제안하였다.

Genetic and Phenotypic Evaluation of Milk and Fat Production Traits and Their Interrelationship in (Zebu×European) Crossbred Cattle Using Parent Group Mixed Model

  • Singh, D.;Yadav, A.S.;Dhaka, S.S.
    • Asian-Australasian Journal of Animal Sciences
    • /
    • 제16권9호
    • /
    • pp.1242-1246
    • /
    • 2003
  • Data pertained to 335 crossbred cows comprising of 1/2 Friesian (F) + 1/2 Hariana (H), 1/2 F + 1/4 Jersey (J) + 1/4 H, 1/2 F + 1/4 Brown Swiss (BS) + 1/4 H, 1/2 F + 1/4 Red Dane (R) + 1/4 H, FR (I) and FRH (I) genetic groups extending over a period of 21 years (1970-1990) maintained at Animal Farm of CCS HAU, Hisar. The averages for first lactation milk yield was $2,486.24{\pm}80.26kg$ and peak yield of first three lactation were $11.35{\pm}0.72kg$, $13.97{\pm}0.60kg$ and $16.02{\pm}0.42kg$, respectively. The lifetime milk production was observed as $11,305.16{\pm}1,004.52kg$ in crossbred cattle. The average first lactation fat yield was observed as $102.06{\pm}0.01kg$ and peak fat yield of first three lactation were $0.458{\pm}0.01$, $0.490{\pm}0.01$ and $0.500{\pm}0.02kg$, respectively. The lifetime fat production was estimated as $502.31{\pm}45.90kg$. LTMP and LTFP had reasonably good additive genetic variance which could be exploited either through mass selection/combined with family or pedigree selection. FLMY, peak yields and LTMP had significant positive phenotypic correlation with FLFY and LTFP and the correlation at the genetic level were also higher and positive for these traits. Finally, peak week milk yield of first lactation (PMY1) was the earliest available trait having desirable and significant correlation at phenotypic and positive at genetic level with FLFY, PFY1 and PFY2, PFY3 and LTFP and selection for this trait will help in early evaluation of sires and dams and will increase genetic advancement per unit of time.

회전기계 결함신호 진단을 위한 신호처리 기술 개발 (Signal Processing Technology for Rotating Machinery Fault Signal Diagnosis)

  • 안병현;김용휘;이종명;이정훈;최병근
    • 한국소음진동공학회논문집
    • /
    • 제24권7호
    • /
    • pp.555-561
    • /
    • 2014
  • Acoustic Emission technique is widely applied to develop the early fault detection system, and the problem about a signal processing method for AE signal is mainly focused on. In the signal processing method, envelope analysis is a useful method to evaluate the bearing problems and wavelet transform is a powerful method to detect faults occurred on rotating machinery. However, exact method for AE signal is not developed yet for the rotating machinery diagnosis. Therefore, in this paper two methods which are processed by Hilbert transform and DET for feature extraction. In addition, we evaluate the classification performance with varying the parameter from 2 to 15 for feature selection DET, 0.01 to 1.0 for the RBF kernel function of SVR, and the proposed algorithm achieved 94 % classification of averaged accuracy with the parameter of the RBF 0.08, 12 feature selection.

Agrobacterium LBA4404에 의한 국화 ′Shuho-no-chikara′에 LEAFY유전자의 도입 (Introduction of LEAFY Gene to Chrysanthemum(Dendranthema x grandiflorum(Ramat.) Kitamura) ′Shuho-no-chikara′ Mediated by Agrobacterium LBA4404)

  • 한봉희;예병우;이숙이;이수영;신학기
    • Journal of Plant Biotechnology
    • /
    • 제30권4호
    • /
    • pp.335-339
    • /
    • 2003
  • pSK109를 포함하고 있는 Agrobacterium LBA4004을 통하여 국화 'Shuho-no-chikara'에 LEAFY 유전자을 도입하였다. 엽절편체의 생존율은 kanamycin 10mg/L가 첨가된 배지에서 생존율 약 22%, 절편체의 재분화율이 10%정도였다. 그러나 kanamycin 20mg/L가 첨가된 배지에서는 엽절편은 약 5%정도 생존하였으나 전혀 재분화가 나타나지 않았다. 따라서 kanamycin 10mg/L를 1차 선발배지로, 20mg/L를 2차 선발배지로 선발하였다. Agrobacterium LBA4404와 국화 엽절편체를 3일간 공동배양 하는 것이 형질전환에 효과적이었다. LEAFY유전자가 삽입된 pSK109 vector를 포함한 Agrobacterium LBA4404의 형질전환 효율은 2차 선발까지 약 2.8% 였으며, Southern blot한 결과 0.13%만이 형질 전환체로 확인되었다. 형질 전환체 한계통은 포장에서 약 1주일 정도 조기개화하였고 화형은 정상이었다.

Corrosion and Materials Selection for Bitumen with Heavy Naphthenic Acid in Canadian Oil Sands

  • Eun, Thomas Jung-Chul
    • Corrosion Science and Technology
    • /
    • 제7권6호
    • /
    • pp.350-361
    • /
    • 2008
  • Canada's oil sands contain one of the largest reserves of oil in the world. According to recent estimates, there are nearly 180 billion barrels of oil in the Canadian oil sands trapped in a complex mixture of sand, water and clay. More than 40 companies have been currently operating or developing oil sands facilities since the first production in 1967. The process of oil sands upgrading is similar with down stream refinery, but the corrosion environment in upgrading refinery is often more severe than in the refinery because of high chlorides, mineral contents, carbonic acid, heavy viscosity and fouling, higher naphthenic acid [$NA-R(CH_{2})nCOOH$], and greater sulfur contents. Naphthenic acid corrosion (NAC) which is one of the most critical corrosion issues in up & downstream refinery plants was observed for the first time in 1920's in refinery distillation processes of Rumania, Azerbaizan (Baku), Venezuela, and California. As a first API report, the 11th annual meeting stated sources and mechanism of NAC in early 1930's. API has been developing the risk base standards, such as API RP580, 571, and Publication 581 which are based on the worst NAC damage in the world since 2000. Nevertheless not only the NAC phenomena and control in Canadian sands oil process are not much widely known but also there are still no engineering guidances for the Canadian sands oil in API standards. This paper will give NAC phenomina and materials selection guidance against NA environment in Canadian oil sands upgrading processes.

뉴럴네트워크(NEWFM)를 이용한 심근경색의 특징추출과 분류 (Feature selection and Classification of Heart attack Using NEWFM of Neural Network)

  • 윤희진
    • 한국인터넷방송통신학회논문지
    • /
    • 제19권5호
    • /
    • pp.151-155
    • /
    • 2019
  • 최근 심근경색은 중장년층의 돌연사의 80%로 밝혀졌다. 심근경색의 발병 원인은 복합적이고 갑자기 발생하게 되어 예방이나 건강검진을 하더라도 발병을 예측하기 어렵다. 따라서 빠른 진단과 적절한 치료가 가장 중요하다. 이 논문에서는 심근경색에 대한 정확하고 빠른 진단을 위해 가중퍼지소속함수를 이용한 신경망으로 정상과 비정상 분류에 대한 정확도를 나타내었다. 실험에 사용된 데이터는 14개의 특징과 303개의 샘플 데이터로 이루어진 UCI Machine Learning Repository에서 제공하는 데이터 사용하였다. 2개의 특징을 선택하여 제거하였다. 특징선택을 위한 알고리즘은 average of weight method를 사용하였다. 가중퍼지소속함수를 이용하여 심근경색을 정상과 비정상으로 분류(1-nomal, 2-abnormal)하였다. 실험 결과 정확도가 87.66%가 나왔다.

수열에너지 입지 선정을 위한 계층화분석법의 적용 (Application of analytic hierarchy process technique for selecting a hydrothermal energy site)

  • 안주현;박수완;오창현
    • 상하수도학회지
    • /
    • 제38권2호
    • /
    • pp.69-81
    • /
    • 2024
  • In this study, an evaluation system that can be used to evaluate the feasibility of developing and supplying hydrothermal energy for the operation of large-scale complex facilities was developed. To this end, this study derived factors to be considered when selecting a location for the use of hydrothermal energy using raw water from multi-purpose dams and regional water supply systems through literature survey and expert interviews. The evaluation indicators derived from this study are divided into four sectors: hydrothermal energy utilization factors, location factors, planning factors, and disaster safety factors, and are composed of 10 mid-level indicators and 34 detailed planning indicators. The relative importance of all factors was derived using the Analytic Hierarchy Process (AHP) technique, and the developed evaluation indicators and relative importance were applied to four multi-purpose dam regions in the country. As a result, it was found that in the development and use of hydrothermal energy utilizing regional raw water supply line the urban planning conditions of the supply site can have a greater impact on the location selection results than the hydrothermal energy development itself. Due to the characteristics of the evaluation indicators developed in this study and their nature as comprehensive indicators, it is believed that the results should be applied to determine the overall adequacy of site selection in the early stages of hydrothermal energy development. In the future, it is believed that it will be necessary to analyze the problems in supplying and operating hydrothermal energy using raw water from multi-purpose dams and regional water resources. Based on the analysis the evaluation system developed in this study is expected to be improved and supplemented.

Automatic Detection of Cow's Oestrus in Audio Surveillance System

  • Chung, Y.;Lee, J.;Oh, S.;Park, D.;Chang, H.H.;Kim, S.
    • Asian-Australasian Journal of Animal Sciences
    • /
    • 제26권7호
    • /
    • pp.1030-1037
    • /
    • 2013
  • Early detection of anomalies is an important issue in the management of group-housed livestock. In particular, failure to detect oestrus in a timely and accurate way can become a limiting factor in achieving efficient reproductive performance. Although a rich variety of methods has been introduced for the detection of oestrus, a more accurate and practical method is still required. In this paper, we propose an efficient data mining solution for the detection of oestrus, using the sound data of Korean native cows (Bos taurus coreanea). In this method, we extracted the mel frequency cepstrum coefficients from sound data with a feature dimension reduction, and use the support vector data description as an early anomaly detector. Our experimental results show that this method can be used to detect oestrus both economically (even a cheap microphone) and accurately (over 94% accuracy), either as a standalone solution or to complement known methods.

토끼 수정란에서 Green Fluorescent Protein 유전자의 발현 (Expression of Green Fluorescent Protein(GFP) Gene in Rabbit Embryos)

  • 강태영;윤희준;채영진;이항;이효종
    • 한국수정란이식학회지
    • /
    • 제14권1호
    • /
    • pp.1-8
    • /
    • 1999
  • The efficiency of transgenic livestock animal production may be improved by early selection of transgenci preimplantation embryos. To examine the possibility of GFP gene as a non-invasive marker for the early screening of transgenic embryo, the GFP gene was microinjected into rabbit zygotes and the later stages of preimplantation embryos were examined for the expression of GFP. The presence of injected DNA was detected by PCR analysis and the expression of GFP was detected by observing green fluorescence in embryos under a fluorescent microscope. Out of 108 GFP gene-injected rabbit zygotes, seventy three(67.6%) were fluorescence-positive. When 11 fluroresecence-positive blastocysts were analyzed for the presence of GFP gene by PCR, 6(54.5%) were positive, and all of the 8 flrouescence-negative blastocysts were also negative by PCR. The results indicate that the screening of transgene in rabbit embryos by PCR analysis and GFP detection could be a promising method for the preselection of transgenic embryos.

  • PDF