http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
이용건(Yong-Geon Lee),장재봉(Jae Bong Chang) 한국농식품정책학회 2016 농업경영정책연구 Vol.43 No.4
This paper analyzes and compares the economic impacts of fisheries using the input-output tables of Korea and Japan. Results reveal there is significant variation across two countries with production-induced effect of fishery sector in Korea increasing and larger than one in Japan. However, valueadded induced effect of fishery sector in Korea has been decreased and are smaller than one in Japan. We also find the effect of production costs in other sectors on fishery sector differs between two countries.
이용건 ( Yong Geon Lee ),박재홍 ( Jae Hong Park ) 한국축산경영학회 2011 농업경영정책연구 Vol.38 No.2
This study focuses on finding the way to increase management efficiency in order to establish the financial stability. The dairy farms are planned and practiced by dairy farmers, the management efficiency may depend much upon the management capacity of dairy farmers. In order to measure efficiency of the dairy farms and management capacity of farmers, this study analyzes the survey and the business log of 19 farms. The major findings are as follows. First, DEA model estimates operational efficiency: 0.917 overall technical efficiency, 0.979 pure technical efficiency and 0.937 scale efficiency. Second, by factor analysis, five possible factors which may regulate operational efficiency are selected: the capacity in execution, sanitation, planning, collecting information, and responsiveness. Third, Tobit analysis demonstrates that the capacities in execution, sanitation, planning, and collecting information have a positive effect on efficiency, but the capacity in responsiveness has a negative effect. Furthermore, large farming size, couple co-management and the existence of inheritors have the effects on efficiency.
이용건(Yong-Geon Lee),박기환(Ki-Hwan Park),황윤재(Yun-Jae Hwang),정민국(Min-Kook Jeong) 한국농식품정책학회 2021 농업경영정책연구 Vol.48 No.4
This paper aims to identify greenhouse gas cost and economic effects between regions of dairy industry. For this purpose, we distinguished regional types (production areas, self-supporting areas, consumption areas) using milk production and milk consumption. In addition, livestock manure and greenhouse gas emissions by type of regions were calculated based on the recently revised 2019 IPCC Guidelines to analyze Regional-Environmental Input-Output Analysis. According to the analysis, the cost of greenhouse gas in the dairy sector in 2015 was 3.05% of the value added. The economic ripple effect considering the greenhouse gas cost of the dairy industry in 2015 was 1.723 trillion won in the dairy sector and 5.23 trillion won in the dairy product sector. The dairy sector in the production area has an economic effect of 296.5 billion won in the consumption area.
이용건 ( Yong-geon Lee ),조석진 ( Suk-jin Cho ) 한국농식품정책학회 2014 농업경영정책연구 Vol.41 No.1
This study is to clarify the effects of dairy and related industries on economy as a whole and also give some insights into measures for development of dairy industry. For this, input-output analysis was performed adopting Ritz-Spaulding model and input-output tables of 1990, 2000 and 2010. The results obtained can be summed up as follows. First, production inducement effect of dairy and related industries amounts 20,465.6 billion won as of 2010. Second, value added inducement coefficients of dairy and related industries turned out very high ranging from 0.83 for dairy product to 0.55 for dairy machinery. In addition, the amount of value added inducement revealed upward trend over 1990 to 2010. Third, the value of production inducement per head of milk cow revealed 18,660 thousand won the highest among livestock. On the other hand, investment for dairy infrastructure, promotion for milk consumption and stabilization of feed price seems prerequisite for further growth of dairy and related sectors.
머신러닝 해석 기법을 이용한 전력 수요 예측 모델 해석
이용건(Yong-Geon Lee),오재영(Jae-Young Oh),김기백(Gibak Kim) 대한전기학회 2020 전기학회논문지 Vol.69 No.3
Artificial intelligence (AI) is getting popular and has been successfully applied to many applications. However, in many cases, AI is considered as a ‘black box’ which is hard to interpret. Recently, researchers have been attempting to explain AI systems and various explainable AI techniques have been developed. In this paper, we apply explainable AI techniques to interpret the load forecasting based on machine learning method. For load forecasting, we employ XGBoost which is decision tree based gradient boosting algorithm. The XGBoost based load forecasting approach was analyzed in terms of feature importance and partial dependence plot. The experimental results show that the performance can be improved by selecting features which were found to have high importance in the SHAP analysis.