• International Journal of Computer Science & Network Security
• /
• v.23 no.8
• /
• 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.

• Journal of Korea Water Resources Association
• /
• v.47 no.12
• /
• pp.1145-1154
• /
• 2014

In recent years, as frequency and intensity of severe weather disasters such as flash flood have been increasing, providing accurate and prompt information to the public is very important and needs of user-friendly monitoring/warning system are growing. This paper introduces a method that re-produces radar observations as multimedia contents and applies reproduced data to mesh-up services. In addition, a accurate GIS matching technique to help to track the exact location going on serious atmospheric phenomena is presented. The proposed method create multimedia contents having structures such as two dimensional images, vector graphics or three dimensional volume data by re-producing various radar variables obtained from a weather radar. After then, the multimedia formatted weather radar data are matched with various detailed raster or vector GIS map platform. Results of simulation test with various scenarios indicate that the display system based on the proposed method can support for users to figure out easily and intuitively routes and degrees of risk of severe weather. We expect that this technique can also help for emergency manager to interpret radar observations properly and to forecast meteorological disasters more effectively.

• Atmosphere
• /
• v.20 no.3
• /
• pp.247-260
• /
• 2010

A recent dramatic increase of natural hazards in the Korean peninsular (KP) due to typhoons have raised necessities for the accurate typhoon prediction. Ieodo ocean research station (IORS) has been constructed in June 2003 at the open ocean where typhoons pass frequently, aiming to observe typhoons before the landfall to the KP and hence to improve the prediction skill. This paper investigates the importance of measurements at the IORS in the typhoon research and forecast. Analysis of the best track data in the N. W. Pacific shows that about one typhoon passes over the IORS per year on the average and 54% of the KP-landfall typhoons during 59 years (1950-2008) passed by the IORS within the range of the 150-km radius. The data observed during the event of typhoons reveals that the IORS can provide useful information for the typhoon prediction prior to the landfall (mainland: before 8-10 hrs, Jeju Island: before 4-6 hrs), which may contribute to improving the typhoon prediction skill and conducting the disaster prevention during the landfall. Since 2003, nine typhoons have influenced the IORS by strong winds above 17m/s. Among them, the typhoon Maemi (0314) was the strongest and brought the largest damages in Korea. The various oceanic and atmospheric observation data at the IORS suggest that the Maemi (0314) has kept the strong intensity until the landfall as passing over warm ocean currents, while the Ewiniar (0603) has weakened rapidly as passing over the Yellow Sea Bottom Cold Water (YSBCW), mainly due to the storm's self-induced surface cooling. It is revealed that the IORS is located in the best place for monitering the patterns of the warm currents and the YSBCW which varies in time and space.

• Environmental and Resource Economics Review
• /
• v.18 no.2
• /
• pp.279-309
• /
• 2009

Greenhouse gas emissions should be precisely forecast to reduce the emissions from industrial production processes. This study calculated the direct and indirect $CO_2$ emission intensities of 401 industries using the Input-Output tables 2003 and statistical data on the amount of energy use. This study had some limitations in drawing study findings because overseas data were used given the lack of domestic data. Other limiting factors included the oil distribution problems in the oil refinery sector, re-review of carbon neutral, and insufficient consideration of waste treatment. Nonetheless, this study is very meaningful since the direct and indirect $CO_2$ emission intensities of 401 industries were calculated. Specifically, this study considered from the zero-waste perspective the effects of waste, which attract interest worldwide since coke gas and gas from the steel industry are obtained as byproducts for the first time in Korea. According to the results of the analysis of $CO_2$ emission intensity per industry, typical industries whose indirect $CO_2$ emission intensity is high include crude steel making, Remicon, steel wire rods & track rail, cast iron, and iron reinforcing rods & bar steel. These industries produce products using the raw materials produced in the industrial sector whose $CO_2$ emission intensity is high. The representative industries whose direct $CO_2$ emission intensity is high include cement, pig iron, lime & plaster products, andcoal-based compounds. These industries extract raw ore from nature and refine them into raw materials that are useful in other industries. The findings in this study can be effectively used for the following case: estimation of target $CO_2$ emission reduction level reflecting each industrial sector's characteristics, calculation of potential emission reduction of each policy to reduce $CO_2$ emissions, identification of a firm's $CO_2$ emission level, and setting of the target level of emission reduction. Moreover, the findings in this study can be utilized widely in fields such as System of integrated Environmental and Economic Accounting(SEEA) and Material Flow Analysis(MFA) as the current topic of research in Korea.