• 한국농공학회지
• /
• 제43권2호
• /
• pp.69-77
• /
• 2001

An artificial neural network model was developed to analyze and forecast daily steamflow flow a small watershed. Error Back propagation neural networks (EBPN) of daily rainfall and runoff data were found to have a high performance in simulating stremflow. The model adopts a gradient descent method where the momentum and adaptive learning rate concepts were employed to minimize local minima value problems and speed up the convergence of EBP method. The number of hidden nodes was optimized using Bayesian information criterion. The resulting optimal EBPN model for forecasting daily streamflow consists of three rainfall and four runoff data (Model34), and the best number of the hidden nodes were found to be 13. The proposed model simulates the daily streamflow satisfactorily by comparison compared to the observed data at the HS#3 watershed of the Baran watershed project, which is 391.8 ha and has relatively steep topography and complex land use.

• Communications for Statistical Applications and Methods
• /
• 제12권1호
• /
• pp.207-216
• /
• 2005

A binary segmentation procedure is a simple recursive approach to detect clusters and provide inferences for the study space when the shape of the clusters and the number of clusters are unknown. The procedure involves a sequence of nested hypothesis tests of a single cluster versus a pair of distinct clusters. The size and the shape of the clusters evolve as the procedure proceeds. The procedure allows for various growth clusters and for arbitrary baseline densities which govern the form of the hypothesis tests. A real tree data is used to highlight the procedure.

• 한국농공학회지
• /
• 제45권2호
• /
• pp.45-57
• /
• 2003

An artificial neural network model was developed to analyze and forecast Short-term river runoff from the Naju watershed, in Korea. Error back propagation neural networks (EBPN) of hourly rainfall and runoff data were found to have a high performance In forecasting runoff. The number of hidden nodes were optimized using total error and Bayesian information criterion. Model forecasts are very accurate (i.e., relative error is less than 3% and $R^2$is greater than 0.99) for calibration and verification data sets. Increasing the time horizon for application data sets, thus mating the model suitable for flood forecasting. decreases the accuracy of the model. The resulting optimal EBPN models for forecasting hourly runoff consists of ten rainfall and four runoff data(ANN0410 model) and ten rainfall and ten runoff data(ANN1010 model). Performances of the ANN0410 and ANN1010 models remain satisfactory up to 6 hours (i.e., $R^2$is greater than 0.92).

• 한국농공학회:학술대회논문집
• /
• 한국농공학회 2000년도 학술발표회 발표논문집
• /
• pp.384-389
• /
• 2000

A artificial neural network model was developed to analyze and forecast the flow fluctuation at small streams in the Balan watershed. Backpropagation neural networks were found to perform very well in forecasting daily streamflows. In order to deal with slow convergence and an appropriate structure, two algorithms were proposed for speeding up the convergence of the backpropagation method, and the Bayesian Information Criterion(BIC) was proposed for obtaining the optimal number of hidden nodes. From simulations using daily flows at the HS#3 watershed of the Balan Watershed Project, which is 412,5 ㏊ in size and relatively steep in landscape, it was found that those algorithms perform satisfactorily.

• 음성과학
• /
• 제8권4호
• /
• pp.59-72
• /
• 2001

In this paper, we experimented with speaker change detection that uses a statistical method for NOD (News On Demand) service. A specified speaker's change can find out content of each data in speech if analysed because it means change of data contents in news data. Speaker change detection acts as preprocessor that divide input speech by speaker. This is an important preprocessor phase for speaker tracking. We detected speaker change using GLR(generalized likelihood ratio) distance base division and BIC (Bayesian information criterion) base division among matrix method. An experiment verified speaker change point using BIC base division after divide by speaker unit using GLR distance base method first. In the experimental result, FAR (False Alarm Rate) was 63.29 in high noise environment and FAR was 54.28 in low noise environment in MDR (Missed Detection Rate) 15% neighborhood.

• Communications for Statistical Applications and Methods
• /
• 제15권3호
• /
• pp.429-440
• /
• 2008

In this paper, we develop the noninformative priors when the parameter of interest is the common coefficient of variation in two inverse Gaussian distributions. We want to develop the first and second order probability matching priors. But we prove that the second order probability matching prior does not exist. It turns out that the one-at-a-time and two group reference priors satisfy the first order matching criterion but Jeffreys' prior does not. The Bayesian credible intervals based on the one-at-a-time reference prior meet the frequentist target coverage probabilities much better than that of Jeffreys' prior. Some simulations are given.

• Asian-Australasian Journal of Animal Sciences
• /
• 제33권3호
• /
• pp.408-415
• /
• 2020

Objective: The aim of the paper was to compare the fit of data derived from daily automatic milking systems (AMS) and monthly test-day records with the use of lactation curves; data was analysed separately for primiparas and multiparas. Methods: The study was carried out on three Polish Holstein-Friesians (PHF) dairy herds. The farms were equipped with an automatic milking system which provided information on milking performance throughout lactation. Once a month cows were also subjected to test-day milkings (method A4). Most studies described in the literature are based on test-day data; therefore, we aimed to compare models based on both test-day and AMS data to determine which mathematical model (Wood or Wilmink) would be the better fit. Results: Results show that lactation curves constructed from data derived from the AMS were better adjusted to the actual milk yield (MY) data regardless of the lactation number and model. Also, we found that the Wilmink model may be a better fit for modelling the lactation curve of PHF cows milked by an AMS as it had the lowest values of Akaike information criterion, Bayesian information criterion, mean square error, the highest coefficient of determination values, and was more accurate in estimating MY than the Wood model. Although both models underestimated peak MY, mean, and total MY, the Wilmink model was closer to the real values. Conclusion: Models of lactation curves may have an economic impact and may be helpful in terms of herd management and decision-making as they assist in forecasting MY at any moment of lactation. Also, data obtained from modelling can help with monitoring milk performance of each cow, diet planning, as well as monitoring the health of the cow.

• 대한의용생체공학회:의공학회지
• /
• 제22권5호
• /
• pp.439-448
• /
• 2001

이식형 양심실 보조 장치 (Biventricular Assist Device, BVAD)에서 판막이 닫힐 때 나는 소리의 특성과 판막의 물리적인 상태의 상관성을 고찰하였다. 본 연구에서 Bj rk Shiley Convexo Concave tilting disk 판막을 사용했으며, 모의 순환계와 양의 체내에서 동작하는 BVAD 에서 판막음을 측정하였다. 모의 순환계에서는 정상 판막. 기계적으로 손상된 판막. 모의 혈전이 형성된 판막의 3가지를 고려하였다. 양에 이식된 BVAD의 경우, 이식 후 1일부터 5일 동안 규칙적인 간격으로 판막음을 측정하였다. 측정된 신호의 스펙트럼 특성은 Multiple Signal Classification (MUSIC)을 이용하여 추정하였다. MUSIC의 최적 차수는 Bayesian Information Criterion (BIC)을 이용하여 계산하였다. 실험 결과, 판막의 기계적인 손상은 판막 폐쇄음의 주파수 스펙트럼 구조를 변화시키고 있으며, 혈전의 형성은 판막음 스펙트럼의 기본 구조는 유지하지만 피크 주파수와 에너지의 크기를 변화시키는 것으로 관찰되었다. 최대 에너지를 가지는 MSP (maximum spectral peak)는 정상 판막에서는 2 kHz에 위치하고 있으나 모의 혈전을 부탁한 판막에서는 3 kHz로 이동하였다. 손상된 판막은 7 kHz 부근에서 강한 피크 보이고 있다 실험 동물 내에서 판막에 혈전이 형성되어감에 따라 판막음은 저주파 성분 (〈 2kHz)이 상대적으로 크게 감소하였고, Ist 2nd. 3rd MSP 주파수는 약간씩 상승하였다. 또한 혈전이 형성되어 감에 따라 반복해서 측정된 판막음의 1st, 2nd. 3rd MSP 주파수의 변화 정도 및 BIC 차수는 감소하는 것으로 나타났다

• Asian-Australasian Journal of Animal Sciences
• /
• 제29권6호
• /
• pp.759-767
• /
• 2016

The aim of this study was to compare two random regression models (RRM) fitted by fourth ($RRM_4$) and fifth-order Legendre polynomials ($RRM_5$) with a lactation model (LM) for evaluating Holstein cattle in Brazil. Two datasets with the same animals were prepared for this study. To apply test-day RRM and LMs, 262,426 test day records and 30,228 lactation records covering 305 days were prepared, respectively. The lowest values of Akaike's information criterion, Bayesian information criterion, and estimates of the maximum of the likelihood function (-2LogL) were for $RRM_4$. Heritability for 305-day milk yield (305MY) was 0.23 ($RRM_4$), 0.24 ($RRM_5$), and 0.21 (LM). Heritability, additive genetic and permanent environmental variances of test days on days in milk was from 0.16 to 0.27, from 3.76 to 6.88 and from 11.12 to 20.21, respectively. Additive genetic correlations between test days ranged from 0.20 to 0.99. Permanent environmental correlations between test days were between 0.07 and 0.99. Standard deviations of average estimated breeding values (EBVs) for 305MY from $RRM_4$ and $RRM_5$ were from 11% to 30% higher for bulls and around 28% higher for cows than that in LM. Rank correlations between RRM EBVs and LM EBVs were between 0.86 to 0.96 for bulls and 0.80 to 0.87 for cows. Average percentage of gain in reliability of EBVs for 305-day yield increased from 4% to 17% for bulls and from 23% to 24% for cows when reliability of EBVs from RRM models was compared to those from LM model. Random regression model fitted by fourth order Legendre polynomials is recommended for genetic evaluations of Brazilian Holstein cattle because of the higher reliability in the estimation of breeding values.

• Animal Bioscience
• /
• 제34권2호
• /
• pp.163-171
• /
• 2021

Objective: Considering the importance of dairy farming and the negative effects of heat stress, more tolerant genotypes need to be identified. The objective of this study was to investigate the effect of heat stress via temperature-humidity index (THI) and diurnal temperature variation (DTV) in the genetic evaluations for daily milk yield of Holstein dairy cattle, using random regression models. Methods: The data comprised 94,549 test-day records of 11,294 first parity Holstein cows from Brazil, collected from 1997 to 2013, and bioclimatic data (THI and DTV) from 18 weather stations. Least square linear regression models were used to determine the THI and DTV thresholds for milk yield losses caused by heat stress. In addition to the standard model (SM, without bioclimatic variables), THI and DTV were combined in various ways and tested for different days, totaling 41 models. Results: The THI and DTV thresholds for milk yield losses was THI = 74 (-0.106 kg/d/THI) and DTV = 13 (-0.045 kg/d/DTV). The model that included THI and DTV as fixed effects, considering the two-day average, presented better fit (-2logL, Akaike information criterion, and Bayesian information criterion). The estimated breeding values (EBVs) and the reliabilities of the EBVs improved when using this model. Conclusion: Sires are re-ranking when heat stress indicators are included in the model. Genetic evaluation using the mean of two days of THI and DTV as fixed effect, improved EBVs and EBVs reliability.