• 농촌계획
• /
• 제12권1호
• /
• pp.37-48
• /
• 2006

The objectives of this study were to develop an evaluation method of regional vulnerability to agricultural drought and to classify the vulnerability patterns. In order to test the method, 24 city or county areas of Gyeonggi-do were chose. First, statistic data and digital maps referred for agricultural drought were defined, and the input data of 31 items were set up from 5 categories: land use factor, water resource factor, climate factor, topographic and soil factor, and agricultural production foundation factor. Second, for simplification of the factors, principal component analysis was carried out, and eventually 4 principal components which explain about 80.8% of total variance were extracted. Each of the principal components was explained into the vulnerability components of scale factor, geographical factor, weather factor and agricultural production foundation factor. Next, DVIP (Drought Vulnerability Index for Paddy), was calculated using factor scores from principal components. Last, by means of statistical cluster analysis on the DVIP, the study area was classified as 5 patterns from A to E. The cluster A corresponds to the area where the agricultural industry is insignificant and the agricultural foundation is little equipped, and the cluster B includes typical agricultural areas where the cultivation areas are large but irrigation facilities are still insufficient. As for the cluster C, the corresponding areas are vulnerable to the climate change, and the D cluster applies to the area with extensive forests and high elevation farmlands. The last cluster I indicates the areas where the farmlands are small but most of them are irrigated as much.

• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.1-7
• /
• 2023

Demand prediction is an essential component of any business or supply chain. Large retailers need to keep track of tens of millions of items flows each day to ensure smooth operations and strong margins. The demand prediction is in the epicenter of this planning tornado. For business processes in retail companies that deal with a variety of products with short shelf life and foodstuffs, forecast accuracy is of the utmost importance due to the shifting demand pattern, which is impacted by an environment of dynamic and fast response. All sectors strive to produce the ideal quantity of goods at the ideal time, but for retailers, this issue is especially crucial as they also need to effectively manage perishable inventories. In light of this, this research aims to show how Machine Learning approaches can help with demand forecasting in retail and future sales predictions. This will be done in two steps. One by using historic data and another by using open data of weather conditions, fuel, Consumer Price Index (CPI), holidays, any specific events in that area etc. Several machine learning algorithms were applied and compared using the r-squared and mean absolute percentage error (MAPE) assessment metrics. The suggested method improves the effectiveness and quality of feature selection while using a small number of well-chosen features to increase demand prediction accuracy. The model is tested with a one-year weekly dataset after being trained with a two-year weekly dataset. The results show that the suggested expanded feature selection approach provides a very good MAPE range, a very respectable and encouraging value for anticipating retail demand in retail systems.

• International Journal of Computer Science & Network Security
• /
• 제23권8호
• /
• pp.210-216
• /
• 2023

Demand prediction is an essential component of any business or supply chain. Large retailers need to keep track of tens of millions of items flows each day to ensure smooth operations and strong margins. The demand prediction is in the epicenter of this planning tornado. For business processes in retail companies that deal with a variety of products with short shelf life and foodstuffs, forecast accuracy is of the utmost importance due to the shifting demand pattern, which is impacted by an environment of dynamic and fast response. All sectors strive to produce the ideal quantity of goods at the ideal time, but for retailers, this issue is especially crucial as they also need to effectively manage perishable inventories. In light of this, this research aims to show how Machine Learning approaches can help with demand forecasting in retail and future sales predictions. This will be done in two steps. One by using historic data and another by using open data of weather conditions, fuel, Consumer Price Index (CPI), holidays, any specific events in that area etc. Several machine learning algorithms were applied and compared using the r-squared and mean absolute percentage error (MAPE) assessment metrics. The suggested method improves the effectiveness and quality of feature selection while using a small number of well-chosen features to increase demand prediction accuracy. The model is tested with a one-year weekly dataset after being trained with a two-year weekly dataset. The results show that the suggested expanded feature selection approach provides a very good MAPE range, a very respectable and encouraging value for anticipating retail demand in retail systems.

• 농업생명과학연구
• /
• 제53권2호
• /
• pp.121-129
• /
• 2019

본 연구는 여름철 산란계의 더위 스트레스로 인한 생산성 저하에 영향을 미치는 열환경인자들 중 제어 요소를 결정하고 산란계의 생산성을 높일 수 있는 방안을 모색하기 위해 수행되었다. 경상남도에 위치한 산란계사에서 ISA Brown 품종의 산란계 48,451수를 공시하여 생산성 지표를 측정하였다. 또한 산란계사 내부에 온습도로거를 설치하여 건구온도와 상대습도를 여름이 시작되는 6월 19일부터 9월 7일까지 총 81일간 동안 측정하였다. 1일 평균온도, 1일 최고온도, 1일 최저온도, 1일 평균상대습도, 1일 최고상대습도, 1일 최저상대습도, 1일 평균THI, 1일 최고THI 그리고 1일 최저THI와 산란계의 생산성 지표 간의 상관관계를 분석하였다. 분석한 결과에 의하면, 1일 평균, 최고, 최저의 건구온도와 THI가 상승할수록 사료섭취량, 헨데이 산란율, 난중과 FCR은 낮아졌다(p<0.01). 반면, 음수량은 1일 평균, 최고, 최저의 건구온도와 THI가 상승할수록 증가하였다(p<0.001). 상대습도의 경우, 산란계의 생산성 지표에 대해 직접적인 상관관계를 가지지 않는 것으로 판단된다(p>0.05). 특이점으로는 폐사율의 경우, 1일 평균·최고 온도, THI와 1일 평균·최고·최저 상대습도와는 유의적인 상관관계를 가지지 않았지만, 1일 최저의 온도와 THI와는 상관관계를 갖는 것으로 분석되었다(p<0.05). 따라서, 여름철 산란계의 생산성을 향상시키기 위해서는 산란계사 내의 1일 평균, 최고, 최저의 건구온도와 THI를 가능한 낮추는 것이 필요하고, 특히 1일 최저온도를 산란계의 하한임계온도인 20℃에 근접하게 조성해주는 것이 유리할 것으로 판단된다.

• 농업과학연구
• /
• 제26권2호
• /
• pp.77-93
• /
• 1999

This study is aiming at identifying the foreward and backward lingkage effects of the farm land base development project. Korean Government has continuously carried out farmland base development projets including the integrated agricultural development projects. large and medium scale irrigation projects and the comprehensive development of the four big river basin including tidal land reclamation and estuary dam construction for the all weather farming since 1962. the starting year of the five year economic development plans. Consequently the irrigation rate of paddy fields in Korea reached to 75% in 1998 and to escalate the irrigation rate, the Government had procured heavy investment fund from IBRD. IMF and OECF etc. To cope with the agricultural problems like trade liberalization in accordance with WTO policy, the government has tried to solve such problems as new farmland base development policy, preservation of the farmland and expansion of farmland to meet self-sufficiency of foods in the future. Especially, farmland base development projects have been challanged to environmental and ecological problems in evaluating economic benefits and costs where the value of non-market goods have not been included in those. Up to data, in evaluating benefits and costs of the projects, farmland base development projects have been confined to direct incremental value of farm products and it's related costs. Therefore the projects'efficiency as a decision making criteria has shown the low level of economic efficiencies. In estimating economic efficiencies including Leontiefs input-output analysis of the projects could not be founded in Korea at present. Accordingly this study is aimed at achieving and identifying the following objectives. (1) To identify the problems related to the financial supports of the Government in implementing the proposed projects. (2) To estimated backward and foreward linkage effects of the proposed project from the view point of national economy as a whole. To achieve the objectives, Hwangrak benefited area with reservoir which is located in Seosan-haemi Disticts, Chungnam Province were selected as a case study. The main results of the study are summarized as follows : a. The present value of investment and O & M cost were amounted to 3,510million won and the present value of the value added in related industries was estimated at 5.913million won for the period of economic life of 70 years. b. The total discounted value of farm products in the concerned industries derived by the project was estimated at 10,495million won and the foreward and backward linkage effects of the project were amounted to 6,760 and 5,126million won respectively. c. The total number of employment opportunities derived from the related industries for the period of project life were 3,136 man/year. d. Farmland base development projects were showed that the backward linkage effects estimated by index of the sensitivity dispersion were larger than the forward linkage effect estimated by index of the power of dispersion. On the other hand, the forward linkage effect of rice production value during project life was larger than the backward linkage effect e. The rate of creation of new job opportunity by means of implementing civil engineering works were shown high in itself rather than any other fields. and the linkage effects of production of the project investment were mainly derived from the metal and non-metal fields. f. According to the industrial linkage effect analysis, farmland base development projects were identified economically feasible from the view point of national economy as a whole even though the economic efficiencies of the project was outstandingly decreased owing to delaying construction period and increasing project costs.