• Asian-Australasian Journal of Animal Sciences
• /
• v.24 no.8
• /
• pp.1031-1040
• /
• 2011

The objective of this study was to characterize factors influencing genetic improvement of dairy cattle for milk production at farm level. Data were accumulated from 305-day milk yields and pedigree information from 1,921 first-lactation dairy cows that calved from 1990 to 2007 on 161 farms in Central Thailand. Variance components were estimated using average information restricted maximum likelihood procedures. Animal breeding values were predicted by an animal model that contained herd-year-season, calving age, and regression additive genetic group as fixed effects, and cow and residual as random effects. Estimated breeding values from cows that calved in a particular month were used to estimate genetic trends for each individual farm. Within-farm genetic trends (b, regression coefficient of farm milk production per month) were used to classify farms into 3 groups: i) farms with negative genetic trend (b<-0.5 kg/mo), ii) farms with no genetic trend (-0.5 kg/$mo{\leq}b{\leq}0.5$ kg/mo), and iii) farms with positive genetic trend (b>0.5 kg/mo). Questionnaires were used to gather information from individual farmers on educational background, herd characteristics, farm management, decision making practices, and opinion on dairy farming. Farmer's responses to the questionnaire were used to test the association between these factors and farm groups using Fisher's exact test. Estimated genetic trend for the complete population was $0.29{\pm}1.02$ kg/year for cows. At farm level, most farms (40%) had positive genetic trend ($0.63{\pm}4.67$ to $230.79{\pm}166.63$ kg/mo) followed by farms with negative genetic trend (35%; $-173.68{\pm}39.63$ to $-0.62{\pm}2.57$ kg/mo) and those with no genetic trend (25%; $-0.52{\pm}3.52$ to $0.55{\pm}2.68$ kg/mo). Except for educational background (p<0.05), all other factors were not significantly associated with farm group.

• Asian-Australasian Journal of Animal Sciences
• /
• v.26 no.9
• /
• pp.1237-1246
• /
• 2013

The objective of this study was to estimate variance components and genetic parameters for lactation milk yield (LY), lactation length (LL), average milk yield per day (YD), initial milk yield (IY), peak milk yield (PY), days to peak (DP) and parameters (ln(a) and c) of the modified incomplete gamma function (MIG) in an Ethiopian multibreed dairy cattle population. The dataset was composed of 5,507 lactation records collected from 1,639 cows in three locations (Bako, Debre Zeit and Holetta) in Ethiopia from 1977 to 2010. Parameters for MIG were obtained from regression analysis of monthly test-day milk data on days in milk. The cows were purebred (Bos indicus) Boran (B) and Horro (H) and their crosses with different fractions of Friesian (F), Jersey (J) and Simmental (S). There were 23 breed groups (B, H, and their crossbreds with F, J, and S) in the population. Fixed and mixed models were used to analyse the data. The fixed model considered herd-year-season, parity and breed group as fixed effects, and residual as random. The single and two-traits mixed animal repeatability models, considered the fixed effects of herd-year-season and parity subclasses, breed as a function of cow H, F, J, and S breed fractions and general heterosis as a function of heterozygosity, and the random additive animal, permanent environment, and residual effects. For the analysis of LY, LL was added as a fixed covariate to all models. Variance components and genetic parameters were estimated using average information restricted maximum likelihood procedures. The results indicated that all traits were affected (p<0.001) by the considered fixed effects. High grade $B{\times}F$ cows (3/16B 13/16F) had the highest least squares means (LSM) for LY ($2,490{\pm}178.9kg$), IY ($10.5{\pm}0.8kg$), PY ($12.7{\pm}0.9kg$), YD ($7.6{\pm}0.55kg$) and LL ($361.4{\pm}31.2d$), while B cows had the lowest LSM values for these traits. The LSM of LY, IY, YD, and PY tended to increase from the first to the fifth parity. Single-trait analyses yielded low heritability ($0.03{\pm}0.03$ and $0.08{\pm}0.02$) and repeatability ($0.14{\pm}0.01$ to $0.24{\pm}0.02$) estimates for LL, DP and parameter c. Medium heritability ($0.21{\pm}0.03$ to $0.33{\pm}0.04$) and repeatability ($0.27{\pm}0.02$ to $0.53{\pm}0.01$) estimates were obtained for LY, IY, PY, YD and ln(a). Genetic correlations between LY, IY, PY, YD, ln(a), and LL ranged from 0.59 to 0.99. Spearman's rank correlations between sire estimated breeding values for LY, LL, IY, PY, YD, ln(a) and c were positive (0.67 to 0.99, p<0.001). These results suggested that selection for IY, PY, YD, or LY would genetically improve lactation milk yield in this Ethiopian dairy cattle population.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.239-251
• /
• 2019

Statistical methods such as moving averages, Kalman filtering, exponential smoothing, regression analysis, and ARIMA (autoregressive integrated moving average) have been used for stock market predictions. However, these statistical methods have not produced superior performances. In recent years, machine learning techniques have been widely used in stock market predictions, including artificial neural network, SVM, and genetic algorithm. In particular, a case-based reasoning method, known as k-nearest neighbor is also widely used for stock price prediction. Case based reasoning retrieves several similar cases from previous cases when a new problem occurs, and combines the class labels of similar cases to create a classification for the new problem. However, case based reasoning has some problems. First, case based reasoning has a tendency to search for a fixed number of neighbors in the observation space and always selects the same number of neighbors rather than the best similar neighbors for the target case. So, case based reasoning may have to take into account more cases even when there are fewer cases applicable depending on the subject. Second, case based reasoning may select neighbors that are far away from the target case. Thus, case based reasoning does not guarantee an optimal pseudo-neighborhood for various target cases, and the predictability can be degraded due to a deviation from the desired similar neighbor. This paper examines how the size of learning data affects stock price predictability through k-nearest neighbor and compares the predictability of k-nearest neighbor with the random walk model according to the size of the learning data and the number of neighbors. In this study, Samsung electronics stock prices were predicted by dividing the learning dataset into two types. For the prediction of next day's closing price, we used four variables: opening value, daily high, daily low, and daily close. In the first experiment, data from January 1, 2000 to December 31, 2017 were used for the learning process. In the second experiment, data from January 1, 2015 to December 31, 2017 were used for the learning process. The test data is from January 1, 2018 to August 31, 2018 for both experiments. We compared the performance of k-NN with the random walk model using the two learning dataset. The mean absolute percentage error (MAPE) was 1.3497 for the random walk model and 1.3570 for the k-NN for the first experiment when the learning data was small. However, the mean absolute percentage error (MAPE) for the random walk model was 1.3497 and the k-NN was 1.2928 for the second experiment when the learning data was large. These results show that the prediction power when more learning data are used is higher than when less learning data are used. Also, this paper shows that k-NN generally produces a better predictive power than random walk model for larger learning datasets and does not when the learning dataset is relatively small. Future studies need to consider macroeconomic variables related to stock price forecasting including opening price, low price, high price, and closing price. Also, to produce better results, it is recommended that the k-nearest neighbor needs to find nearest neighbors using the second step filtering method considering fundamental economic variables as well as a sufficient amount of learning data.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.6
• /
• pp.1349-1360
• /
• 2017

This study was conducted to estimate the genetic parameters for common ketosis indicators (${\beta}$-hydroxybutyrate acid, BHBA; milk acetone), feed intake efficiency indicator (energy-corrected milk, ECM), and milk yield (MY) in Korean Holstein. A total of 75,072 monthly test-day records from 14,397 first parity cows were collected, between 2012 and 2016, from Korea animal improvement association enrolled farms. Variance components were estimated using a multiple trait random regression model. The heritability of BHBA and acetone levels ranged from 0.06 to 0.15 at different DIMs. The phenotypic and genetic correlations between BHBA and acetone were between 0.73 and 0.90, and between 0.93 and 0.98, respectively. The phenotypic correlation between BHBA and MY, between acetone and MY, between BHBA and ECM, and between acetone and ECM ranged from -0.18 to -0.05, -0.23 to -0.05, 0 to 0.10, and -0.09 to 0.01, respectively. Genetic correlation estimates between BHBA and MY, between acetone and MY, between BHBA and ECM, and between acetone and ECM also ranged from -0.55 to 0.05, -0.62 to -0.04, -0.10 to 0.11, and -0.20 to 0.00, respectively. We hope that these results would greatly assist in the improvement of ketosis disease in the local Holsteins.

• Journal of Preventive Medicine and Public Health
• /
• v.32 no.2
• /
• pp.177-182
• /
• 1999

Objectives: To reexamine the association between air pollution and daily mortality in Seoul, Korea using a method of meta-analysis with the data filed for 1991 through 1995. Methods: A separate Poisson regression analysis on each district within the metropolitan area of Seoul was conducted to regress daily death counts on levels of each ambient air pollutant, such as total suspended particulates (TSP), sulfur dioxide $(SO_2)$, and ozone $(O_3)$, controlling for variability in the weather condition. We calculated a weighted mean as a meta-analysis summary of the estimates and its standard error. Results: We found that the p value from each pollutant model to test the homogeneity assumption was small (p<0.01) because of the large disparity among district-specific estimates. Therefore, all results reported here were estimated from the random effect model. Using the weighted mean that we calculated, the mortality at a $100{\mu}g/m^3$ increment in a 3-day moving average of TSP levels was 1.034 (95% Cl 1.009-1.059). The mortality was estimated to increase 6% (95% Cl 3-10%) and 3% (95% Cl 0-6%) with each 50 ppb increase for 9-day moving average of SO2 and 1-hr maximum O3, respectively. Conclusions: Like most of air pollution epidemiologic studies, this meta-analysis cannot avoid fleeing from measurement misclassification since no personal measurement was taken. However, we can expect that a measurement bias be reduced in a district-specific estimate since a monitoring station is hefter representative cf air quality of the matched district. The similar results to those from the previous studios indicated existence of health effect of air pollution at current levels in many industrialized countries, including Korea.