• 제목/요약/키워드: Residual variance Estimation

검색결과 31건 처리시간 0.021초

상태벡터 모형에 의한 서울지역의 강우예측 (Rainfall Prediction of Seoul Area by the State-Vector Model)

  • 주철
    • 물과 미래
    • /
    • 제28권5호
    • /
    • pp.219-233
    • /
    • 1995
  • 강우의 평균과 분산이 시 공간적으로 변하는 비정상 다변량 모형을 강우모형으로 선정하였다. 그리고 강우모형의 상태 및 매개변수의 추정을 위해 비정상 대변량 모형의 잔차항에 Kalman Filter 순환추정 알고리즘을 적용하여 강우예측모형 시스템을 구성하였다. 그후 반응시간이 짧은 도시지역에 설치된 T/M 강우관측소에 입력되는 매 시간(10분간격) 강우자료를 사용하여 호우개수방법에 의한 비정상(Non-stationary) 평균과 분산의 추정 그리고 호우속도 추정을 통한 정규잔차 공분산을 추정하여 다수의 지점들 및 선행시간들의 실시간 다변량 단기 강우예측 (On-line, Real-time, Multivariate Short-term, Rainfall Prediction)을 하였다. 강우예측시스템 모형에 의한 결과와 비정상 변량 모형에 의한 강우모의 결과가 잘 일치하였다. 그리고 예측정도를 측정하는 방법인 제곱 평균 제곱근 오차(RMSE)와 모형 효율성 계수(ME)를 분석한 결과, 강우 예측시간 즉 선행시간이 갈수록 제곱 평균 제곱근 오차가 커지고 모형 효율성 계수가 1로부터 점차 작아지는 것으로 보아 강우예측 정도가 떨어지는 것을 알 수 있었다. 또한 호우개수방법으로 구한 평균이 호우구조의 많은 부분을 차지하고 있음을 알 수 있었다.

  • PDF

해양모니터링 자료의 장기결측 보충 기법 (Long-gap Filling Method for the Coastal Monitoring Data)

  • 조홍연;이기섭;이욱재
    • 한국해안·해양공학회논문집
    • /
    • 제33권6호
    • /
    • pp.333-344
    • /
    • 2021
  • 해양모니터링 자료에서 빈번하게 발생하는 장기결측구간의 자료 보충기법을 제안한다. 제안하는 방법은 결측구간의 장기변동 추세 성분과 단기변동 잔차성분을 추정하여 조합하는 방식으로 결측구간의 미지 정보를 추정한다. 이 방법을 이용하여 울릉도 해상부이 자료의 수온 항목, 약 1개월 정도의 장기결측 구간의 자료를 보충하였으며, 부이에서 관측하는 자료 항목에 대해서도 결측 보충을 수행하였다. 보충된 자료는 항목에 따라 차이를 보이지만 변동양상이 적절하게 재현되는 것으로 파악되었다. 이 방법은 추세추정과 잔차 반영에 따른 편향오차와 분산오차가 발생하지만, 장기결측으로 인한 통계적인 측도 추정의 편향오차는 크게 절감하는 것으로 파악되었다. 결측보충 모형의 추정 RMS 오차의 평균과 90% 신뢰구간은 각각 0.93, 0.35~1.95 범위이다.

간편 간접추론 방식의 퍼지논리에 의한 확장 칼만필터의 성능 향상 (Performance Improvement of an Extended Kalman Filter Using Simplified Indirect Inference Method Fuzzy Logic)

  • 채창현
    • 한국기계가공학회지
    • /
    • 제15권2호
    • /
    • pp.131-138
    • /
    • 2016
  • In order to improve the performance of an extended Kalman filter, a simplified indirect inference method (SIIM) fuzzy logic system (FLS) is proposed. The proposed FLS is composed of two fuzzy input variables, four fuzzy rules and one fuzzy output. Two normalized fuzzy input variables are the variance between the trace of a prior and a posterior covariance matrix, and the residual error of a Kalman algorithm. One fuzzy output variable is the weighting factor to adjust for the Kalman gain. There is no need to decide the number and the membership function of input variables, because we employ the normalized monotone increasing/decreasing function. The single parameter to be determined is the magnitude of a universe of discourse in the output variable. The structure of the proposed FLS is simple and easy to apply to various nonlinear state estimation problems. The simulation results show that the proposed FLS has strong adaptability to estimate the states of the incoming/outgoing moving objects, and outperforms the conventional extended Kalman filter algorithm by providing solutions that are more accurate.

Estimation of Genetic Parameters for First Lactation Monthly Test-day Milk Yields using Random Regression Test Day Model in Karan Fries Cattle

  • Singh, Ajay;Singh, Avtar;Singh, Manvendra;Prakash, Ved;Ambhore, G.S.;Sahoo, S.K.;Dash, Soumya
    • Asian-Australasian Journal of Animal Sciences
    • /
    • 제29권6호
    • /
    • pp.775-781
    • /
    • 2016
  • A single trait linear mixed random regression test-day model was applied for the first time for analyzing the first lactation monthly test-day milk yield records in Karan Fries cattle. The test-day milk yield data was modeled using a random regression model (RRM) considering different order of Legendre polynomial for the additive genetic effect (4th order) and the permanent environmental effect (5th order). Data pertaining to 1,583 lactation records spread over a period of 30 years were recorded and analyzed in the study. The variance component, heritability and genetic correlations among test-day milk yields were estimated using RRM. RRM heritability estimates of test-day milk yield varied from 0.11 to 0.22 in different test-day records. The estimates of genetic correlations between different test-day milk yields ranged 0.01 (test-day 1 [TD-1] and TD-11) to 0.99 (TD-4 and TD-5). The magnitudes of genetic correlations between test-day milk yields decreased as the interval between test-days increased and adjacent test-day had higher correlations. Additive genetic and permanent environment variances were higher for test-day milk yields at both ends of lactation. The residual variance was observed to be lower than the permanent environment variance for all the test-day milk yields.

Estimation of genetic relationships between growth curve parameters in Guilan sheep

  • Hossein-Zadeh, Navid Ghavi
    • Journal of Animal Science and Technology
    • /
    • 제57권5호
    • /
    • pp.19.1-19.6
    • /
    • 2015
  • The objective of this study was to estimate variance components and genetic parameters for growth curve parameters in Guilan sheep. Studied traits were parameters of Brody growth model which included A (asymptotic mature weight), B (initial animal weight) and K (maturation rate). The data set and pedigree information used in this study were obtained from the Agricultural Organization of Guilan province (Rasht, Iran) and comprised 8647 growth curve records of lambs from birth to 240 days of age during 1994 to 2014. Marginal posterior distributions of parameters and variance components were estimated using TM program. The Gibbs sampler was run 300000 rounds and the first 60000 rounds were discarded as a burn-in period. Posterior mean estimates of direct heritabilities for A, B and K were 0.39, 0.23 and 0.039, respectively. Estimates of direct genetic correlation between growth curve parameters were 0.57, 0.03 and -0.01 between A-B, A-K and B-K, respectively. Estimates of direct genetic trends for A, B and K were positive and their corresponding values were $0.014{\pm}0.003$ (P < 0.001), $0.0012{\pm}0.0009$ (P > 0.05) and $0.000002{\pm}0.0001$ (P > 0.05), respectively. Residual correlations between growth curve parameters varied form -0.52 (between A-K) to 0.48 (between A-B). Also, phenotypic correlations between growth curve parameters varied form -0.49 (between A-K) to 0.47 (between A-B). The results of this study indicated that improvement of growth curve parameters of Guilan sheep seems feasible in selection programs. It is worthwhile to develop a selection strategy to obtain an appropriate shape of growth curve through changing genetically the parameters of growth model.

Single-Channel Non-Causal Speech Enhancement to Suppress Reverberation and Background Noise

  • Song, Myung-Suk;Kang, Hong-Goo
    • 한국음향학회지
    • /
    • 제31권8호
    • /
    • pp.487-506
    • /
    • 2012
  • This paper proposes a speech enhancement algorithm to improve the speech intelligibility by suppressing both reverberation and background noise. The algorithm adopts a non-causal single-channel minimum variance distortionless response (MVDR) filter to exploit an additional information that is included in the noisy-reverberant signals in subsequent frames. The noisy-reverberant signals are decomposed into the parts of the desired signal and the interference that is not correlated to the desired signal. Then, the filter equation is derived based on the MVDR criterion to minimize the residual interference without bringing speech distortion. The estimation of the correlation parameter, which plays an important role to determine the overall performance of the system, is mathematically derived based on the general statistical reverberation model. Furthermore, the practical implementation methods to estimate sub-parameters required to estimate the correlation parameter are developed. The efficiency of the proposed enhancement algorithm is verified by performance evaluation. From the results, the proposed algorithm achieves significant performance improvement in all studied conditions and shows the superiority especially for the severely noisy and strongly reverberant environment.

UHF 레이더를 이용한 대류 경계층 고도의 추정 (Estimation of the Convective Boundary Layer Height Using a UHF Radar)

  • 허복행;김경익
    • 대한원격탐사학회지
    • /
    • 제17권1호
    • /
    • pp.1-14
    • /
    • 2001
  • 굴절 지수 구조 매개 변수(refractive index structure parameter) $C_n^2$의 증가는 보통 가온위(virtual potential temperature) ${\theta}_v$와 혼합비(mixing ratio) q의 연직 기울기가 최대가 되는 고도에서 발생하며, 대류 경계층(convective boundary layer)의 고도를 추정하는데 있어서 매우 유용한 매개 변수로 사용된다. 이 연구에서는 대류 경계층 고도의 추정에 이용되는 $C_n^2$ 첨두의 발생 특성이 조사되었으며, 또한 UHF 레이더로 관측된 $C_n^2$와 연직 속도의 분산 ${\sigma}_w$ 자료를 이용하여 대류 경계층 고도를 객관적으로 추정하는 방법이 제시되었다. UHF 레이더의 $C_n^2$ 연직 분포에서 첨두는 대류 경계층의 정상부뿐만 아니라 잔류층의 정상부나 구름층에서도 발생하였다. 약한 태양 복사로 연직 혼합이 뚜렷하지 않은 경우에 대류 경계층 고도에 상응하는 $C_n^2$ 첨두는 레윈존데(rawinsonde) 관측 자료로부터 추정된 대류 경계층 고도보다 약간 낮았다. 반면에, 강한 태양 복사에 의해 연직 혼합이 강하고 유입대에서 ${\theta}_v$와 q의 연직 기울기가 매우 클 경우에 대류 경계층 고도에 상응하는 $C_n^2$ 첨두는 레윈존데 관측 자료로부터 추정된 대류 경계층 고도와 잘 일치하였다. $C_n^2$ 첨두의 고도를 대류 경계층 고도로 결정하는 최대 후방 산란 강도 방법(maximurn backscatter intensity method)은 $C_n^2$ 연직 분포에서 하나의 첨두가 있을 경우에는 오류 없이 대류 경계층 고도를 추정하였지만 대류 경계층 고도 위에 잔류층이나 구름층이 있을 경우에는 대류 경계층 고도를 잘못 추정하였다. 본 연구에서 새로이 제시된 방법은 UHF 레이더의 $C_n^2$${\sigma}_w$ 자료를 이용하여 대류 경계층 고도로부터 오는 $C_n^2$ 첨두를 잔류층이나 구름층으로부터 오는 $C_n^2$ 첨두로부터 구별하여 오류 없이 대류 경계층 고도를 추정하였다. 또한 이 방법은 대류 경계층 고도의 일반화 추정에 적용되었으며, 후방 산란 강도의 연직 분포에서 두개의 첨두가 존해할 경우에도 더욱 신뢰성 있고 안정되게 대류 경계층 고도를 실시간으로 추정하였다.

홀스타인의 유생산형질에 대한 유전모수 추정 (Estimation of Genetic Parameters for Milk Production Traits in Holstein Dairy Cattle)

  • 조충일;조광현;최연호;최재관;최태정;박병호;이승수
    • Journal of Animal Science and Technology
    • /
    • 제55권1호
    • /
    • pp.7-11
    • /
    • 2013
  • 본 연구의 목적은 여러 산차를 이용한 모델을 사용하여 유전평가 분석을 하기위하여 3개의 유량생산 형질에 대한 (공)분산 성분을 추정하고자 하였다. 모수추정을 위한 자료는 2001년부터 2009년까지의 검정자료를 이용하였고 원시자료수는 1,416,589개이며 5개의 산차형질에 대해 각각 다른 형질로 가정하여 추정하였다. 동기그룹 내 10두 이하 및 씨수소의 딸소가 10두 미만인 개체는 삭제를 하였으며 305일 유량생산이 15,000 kg을 초과하는 비유개체에 대하여 사전 데이터 가공을 실시하였다. 혈통파일은 총292,382개의 혈통자료와 1,456두의 씨수소로 구성되어진 혈통자료가 연구에 사용되었다. Sire 모형은 herd-year-season의 동기그룹과 분만월령 그리고 혈통과 5산까지 상가적 유전효과들이 적용되었으며 VCE를 이용하여 유전 (공)분산이 추정되었다. 유전율과 유전상과 그리고 잔차상관은 R 패키지를 이용하여 계산하였다. 유량에 대한 산차간 유전 상관은 0.76에서 0.98였고, 유지방량은 0.79~0.10, 유단백질량은 0.75~1.00로 나타났다. 각 산차별 유량, 유지방량, 유단백질량은 상대적으로 낮은 유전력인 0.14~0.23, 0.13~0.20이 추정되었으며 산차에 가중치로 결합된 유전력은 각 형질에서 0.29, 0.28, 0.26로 나타났다. 본 연구에서 추정된 모수들은 국가단위 유전평가분석에 사용될 수 있을 것으로 판단된다.

Estimation of Genetic Parameters and Trends for Weaning-to-first Service Interval and Litter Traits in a Commercial Landrace-Large White Swine Population in Northern Thailand

  • Chansomboon, C.;Elzo, M.A.;Suwanasopee, T.;Koonawootrittriron, S.
    • Asian-Australasian Journal of Animal Sciences
    • /
    • 제23권5호
    • /
    • pp.543-555
    • /
    • 2010
  • The objectives of this research were the estimation of genetic parameters and trends for weaning-to-first service interval (WSI), and litter traits in a commercial swine population composed of Landrace (L), Large White (T), LT, and TL animals in Chiang Mai, Northern Thailand. The dataset contained 4,399 records of WSI, number of piglets born alive (NBA), litter weight of live piglets at birth (LBW), number of piglets at weaning (NPW), and litter weight at weaning (LWW). Variance and covariance components were estimated with REML using 2-trait analyses. An animal model was used for WSI and a sire-dam model for litter traits. Fixed effects were farrowing year-season, breed group of sow, breed group of boar (litter traits), parity, heterosis (litter traits), sow age, and lactation length (NPW and LWW). Random effects were boar (litter traits), sow, permanent environment, and residual. Heritabilities for direct genetic effects were low for WSI (0.04${\pm}$0.02) and litter traits (0.05${\pm}$0.02 to 0.06${\pm}$0.02). Most heritabilities for maternal litter trait effects were 20% to 50% lower than their direct counterparts. Repeatability for WSI was similar to its heritability. Repeatabilities for litter traits ranged from 0.15${\pm}$0.02 to 0.18${\pm}$F0.02. Direct genetic, permanent environment, and phenotypic correlations between WSI and litter traits were near zero. Direct genetic correlations among litter traits ranged from 0.56${\pm}$0.20 to 0.95${\pm}$0.05, except for near zero estimates between NBA and LWW, and LBW and LWW. Maternal, permanent environment, and phenotypic correlations among litter traits had similar patterns of values to direct genetic correlations. Boar genetic trends were small and significant only for NBA (-0.015${\pm}$0.005 piglets/yr, p<0.004). Sow genetic trends were small, negative, and significant (-0.036${\pm}$0.013 d/yr, p<0.01 for WSI; -0.017${\pm}$0.005 piglets/yr, p<0.007, for NBA; -0.015${\pm}$0.005 kg/yr, p<0.01, for LBW; -0.019${\pm}$0.008 piglets/yr, p<0.02, for NPW; and -0.022${\pm}$0.006 kg/yr, p<0.003, for LWW). Permanent environmental correlations were small, negative, and significant only for WSI (-0.028${\pm}$0.011 d/yr, p<0.02). Environmental trends were positive and significant only for litter traits (p<0.01 to p<0.0003). Selection based on predicted genetic values rather than phenotypes could be advantageous in this population. A single trait analysis could be used for WSI and a multiple trait analysis could be implemented for litter traits.

Estimation of Genetic Parameters and Trends for Length of Productive Life and Lifetime Production Traits in a Commercial Landrace and Yorkshire Swine Population in Northern Thailand

  • Noppibool, Udomsak;Elzo, Mauricio A.;Koonawootrittriron, Skorn;Suwanasopee, Thanathip
    • Asian-Australasian Journal of Animal Sciences
    • /
    • 제29권9호
    • /
    • pp.1222-1228
    • /
    • 2016
  • The objective of this research was to estimate genetic parameters and trends for length of productive life (LPL), lifetime number of piglets born alive (LBA), lifetime number of piglets weaned (LPW), lifetime litter birth weight (LBW), and lifetime litter weaning weight (LWW) in a commercial swine farm in Northern Thailand. Data were gathered during a 24-year period from July 1989 to August 2013. A total of 3,109 phenotypic records from 2,271 Landrace (L) and 838 Yorkshire sows (Y) were analyzed. Variance and covariance components, heritabilities and correlations were estimated using an Average Information Restricted Maximum Likelihood (AIREML) procedure. The 5-trait animal model contained the fixed effects of first farrowing year-season, breed group, and age at first farrowing. Random effects were sow and residual. Estimates of heritabilities were medium for all five traits ($0.17{\pm}0.04$ for LPL and LBA to $0.20{\pm}0.04$ for LPW). Genetic correlations among these traits were high, positive, and favorable (p<0.05), ranging from $0.93{\pm}0.02$ (LPL-LWW) to $0.99{\pm}0.02$ (LPL-LPW). Sow genetic trends were non-significant for LPL and all lifetime production traits. Sire genetic trends were negative and significant for LPL ($-2.54{\pm}0.65d/yr$; p = 0.0007), LBA ($-0.12{\pm}0.04piglets/yr$; p = 0.0073), LPW ($-0.14{\pm}0.04piglets/yr$; p = 0.0037), LBW ($-0.13{\pm}0.06kg/yr$; p = 0.0487), and LWW ($-0.69{\pm}0.31kg/yr$; p = 0.0365). Dam genetic trends were positive, small and significant for all traits ($1.04{\pm}0.42d/yr$ for LPL, p = 0.0217; $0.16{\pm}0.03piglets/yr$ for LBA, p<0.0001; $0.12{\pm}0.03piglets/yr$ for LPW, p = 0.0002; $0.29{\pm}0.04kg/yr$ for LBW, p<0.0001 and $1.23{\pm}0.19kg/yr$ for LWW, p<0.0001). Thus, the selection program in this commercial herd managed to improve both LPL and lifetime productive traits in sires and dams. It was ineffective to improve LPL and lifetime productive traits in sows.