• Korean Journal of Agricultural and Forest Meteorology
• /
• v.21 no.2
• /
• pp.75-84
• /
• 2019

In this study, the random forest approach was used to predict the national mean rice yield of South Korea by using mean climatic factors at a national scale. A random forest model that used monthly climate variable and year as an important predictor in predicting crop yield. Annual yield change would be affected by technical improvement for crop management as well as climate. Year as prediction factor represent technical improvement. Thus, it is likely that the variables of importance identified for the random forest model could result in a large error in prediction of rice yield in practice. It was also found that elimination of the trend of yield data resulted in reasonable accuracy in prediction of yield using the random forest model. For example, yield prediction using the training set (data obtained from 1991 to 2005) had a relatively high degree of agreement statistics. Although the degree of agreement statistics for yield prediction for the test set (2006-2015) was not as good as those for the training set, the value of relative root mean square error (RRMSE) was less than 5%. In the variable importance plot, significant difference was noted in the importance of climate factors between the training and test sets. This difference could be attributed to the shifting of the transplanting date, which might have affected the growing season. This suggested that acceptable yield prediction could be achieved using random forest, when the data set included consistent planting or transplanting dates in the predicted area.

• Journal of Korean Institute of Industrial Engineers
• /
• v.40 no.5
• /
• pp.477-480
• /
• 2014

The single-period production inventory control problem under random yield is considered to analyze the impact of the yield characteristics on the firm's profit. We use the stochastic comparison as a main vehicle to compare the profits resulted under different random yields. Commonly used stochastic orderings are addressed with an analysis of their implications on the firm's profit. Moreover, a distribution-free bound on the profit is derived.

• Management Science and Financial Engineering
• /
• v.22 no.1
• /
• pp.1-4
• /
• 2016

We consider a two-tier supply chain with multiplicative random yield. We focus on the supply chain performance with respect to the control scheme of determining the production lot size. The profit loss due to distributed control is analyzed to give an insight for devising efficient supply contracts.

• Asian-Australasian Journal of Animal Sciences
• /
• v.19 no.7
• /
• pp.915-921
• /
• 2006

Various random regression models with different order of Legendre polynomials for permanent environmental and genetic effects were constructed to predict future milk yield of Holstein cows in Korea. A total of 257,908 test-day (TD) milk yield records from a total of 28,135 cows belonging to 1,090 herds were considered for estimating (co)variance of the random covariate coefficients using an expectation-maximization REML algorithm in an animal mixed model. The variances did not change much between the models, having different order of Legendre polynomial, but a decreasing trend was observed with increase in the order of Legendre polynomial in the model. The R-squared value of the model increased and the residual variance reduced with the increase in order of Legendre polynomial in the model. Therefore, a model with $5^{th}$ order of Legendre polynomial was considered for predicting future milk yield. For predicting the future milk yield of cows, 132,771 TD records from 28,135 cows were randomly selected from the above data by way of preceding partial TD record, and then future milk yields were estimated using incomplete records from each cow randomly retained. Results suggested that we could predict the next four months milk yield with an error deviation of 4 kg. The correlation of more than 70% between predicted and observed values was estimated for the next four months milk yield. Even using only 3 TD records of some cows, the average milk yield of Korean Holstein cows would be predicted with high accuracy if compared with observed milk yield. Persistency of each cow was estimated which might be useful for selecting the cows with higher persistency. The results of the present study suggested the use of a $5^{th}$ order Legendre polynomial to predict the future milk yield of each cow.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.17 no.2
• /
• pp.107-115
• /
• 1992

Many manufacturing processes involved in the fabrication and assembly of hightech components have highly variable yields that tend to complicate the production control. Under this random yield situation we develop a model to determine optimal input quantity, mean waiting time in the system and variance of waiting time in the system. An example which considers beta distribution as a yield distribution is given.

• Journal of Korean Society for Quality Management
• /
• v.40 no.4
• /
• pp.441-452
• /
• 2012

Purpose: In this paper, we have considered a problem of newsvendor model in an environment of random yields in quality and customer balking behavior, in which only the mean and the variance of the demand are known. In practice, the distributional information of the demand is very limited and only the mean and variance are guessed by experience. In addition, due to the customers balking behavior occurring when the available inventory level decreases, the product's demand becomes a function of inventory level so that the classical newsvendor's optimal order quantity is no longer optimal. Methods: We have developed an optimal order quantity model that enables us to incorporate the random yield of a product and the customer balking information such as a threshold inventory level of balking and the corresponding probability of a sale during the balking. Results: We illustrated the concepts developed here through simple numerical examples and showed the robustness of our model in a various setting of parameters. Conclusion: This paper provides a useful analysis showing that our distribution-specific and distribution-free approach to the optimal order quantity in the newsboy model can act as an effective tools to match supply with demand for these product lines.

• Asian-Australasian Journal of Animal Sciences
• /
• v.30 no.10
• /
• pp.1382-1387
• /
• 2017

Objective: During the last decade, genetic evaluation of dairy cows using longitudinal data (test day milk yield or 305-day milk yield) using random regression method has been officially adopted in several countries. The objectives of this study were to estimate covariance functions for genetic and permanent environmental effects and to obtain genetic parameters of 305-day milk yield over seven parities. Methods: Data including 60,279 total 305-day milk yield of 17,309 Iranian Holstein dairy cows in 7 parities calved between 20 to 140 months between 2004 and 2011. Residual variances were modeled by homogeneous and step functions with 7 and 10 classes. Results: The results showed that a third order polynomial for additive genetic and permanent environmental effects plus a step function with 10 classes for the residual variance was the most adequate and parsimonious model to describe the covariance structure of the data. Heritability estimates obtained by this model varied from 0.17 to 0.28. The performance of this model was better than repeatability model. Moreover, 10 classes of residual variance produce the more accurate result than 7 classes or homogeneous residual effect. Conclusion: A quadratic Legendre polynomial for additive genetic and permanent environmental effects with 10 step function residual classes are sufficient to produce a parsimonious model that explained the change in 305-day milk yield over consecutive parities of Iranian Holstein cows.

• Journal of Korean Institute of Industrial Engineers
• /
• v.41 no.3
• /
• pp.324-329
• /
• 2015

Though the supplier diversification is considered as a vital tool to mitigate the risk due to supply chain disruptions, there are results which show the optimality of the sole sourcing. This paper further generalizes the results to show that the sole sourcing is optimal under very mild conditions. Discussion on why the sole sourcing is optimal is given with the insight on the value of supplier diversification.

• International Journal of Computer Science & Network Security
• /
• v.23 no.9
• /
• pp.17-28
• /
• 2023

Today Agriculture segment is a significant supporter of Indian economy as it represents 18% of India's Gross Domestic Product (GDP) and it gives work to half of the nation's work power. Farming segment are required to satisfy the expanding need of food because of increasing populace. Therefore, to cater the ever-increasing needs of people of nation yield prediction is done at prior. The farmers are also benefited from yield prediction as it will assist the farmers to predict the yield of crop prior to cultivating. There are various parameters that affect the yield of crop like rainfall, temperature, fertilizers, ph level and other atmospheric conditions. Thus, considering these factors the yield of crop is thus hard to predict and becomes a challenging task. Thus, motivated this work as in this work dataset of different states producing different crops in different seasons is prepared; which was further pre-processed and there after machine learning techniques Gradient Boosting Regressor, Random Forest Regressor, Decision Tree Regressor, Ridge Regression, Polynomial Regression, Linear Regression are applied and their results are compared using python programming.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.22 no.1
• /
• pp.51-58
• /
• 1997

In this paper, we propose a stochastic LP model for determining an optimal input quantity in a single-product multi-stage production system with random yields. Due to the random yields in our model, each stage of the production system can result in defective items, which can be re-processed or scrapped at certain costs. We assume that the random yield at each stage follows an independent discrete empirical distribution. Compared to dynamic programming models that prevail in the literature, our model can easily handle problems of larger sizes.