• 경영과정보연구
• /
• 제34권1호
• /
• pp.179-190
• /
• 2015

본 연구는 지방자치단체에서는 관광 상품 판매를 통해 얻는 수익이 지역 주민들에게 환원될 수 있도록 관광 상품 중의하나인 자연환경을 상품화하고 있다(한영주, 이무용, 2001). 부산 송도해수욕장의 경우 1980년대 시설낙후로 철거된 케이블카를 복원하는 사업이 26년 만에 가시화되고 있으며, 지역의 관광 삼품으로 그 가치가 크며 이에 대한 수요예측이 필요하다고 할 수 있다. 연구결과 부산광역시만을 대상으로 할 경우 대략 550,684명에서 1,514,416명의 수요예측 범위를 가질 것으로 예상되며, 송도해수욕장의 특성을 반영한 부산, 울산, 경남으로 지역을 확장할 경우 1,013,740명에서 2,854,340명의 수요예측결과를 도출하였다. 본 연구는 수요예측이 가지는 한계점을 보완하고자 방문객 수요예측 시 방문의사율에 실제로 실현 가능한 예측치인 실현율(그루버지수, 자기확신 지수)을 통해서 송도해상케이블카 복원사업 이용객 추정을 하고 이에 대한 수요예측을 통해 사업의 진행에 있어 중요한 근거로 활용될 것이며, 향후 지속적인 관리를 위한 초기자료로서 그 역할을 할 것으로 기대된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권3호
• /
• pp.528-550
• /
• 2024

Warehousing demand prediction is an essential part of the supply chain, providing a fundamental basis for product manufacturing, replenishment, warehouse planning, etc. Existing forecasting methods cannot produce accurate forecasts since warehouse demand is affected by external factors such as holidays and seasons. Some aspects, such as consumer psychology and producer reputation, are challenging to quantify. The data can fluctuate widely or do not show obvious trend cycles. We introduce a new model for warehouse demand prediction called MAGRU, which stands for Multi-layer Attention with GRU. In the model, firstly, we perform the embedding operation on the input sequence to quantify the external influences; after that, we implement an encoder using GRU and the attention mechanism. The hidden state of GRU captures essential time series. In the decoder, we use attention again to select the key hidden states among all-time slices as the data to be fed into the GRU network. Experimental results show that this model has higher accuracy than RNN, LSTM, GRU, Prophet, XGboost, and DARNN. Using mean absolute error (MAE) and symmetric mean absolute percentage error(SMAPE) to evaluate the experimental results, MAGRU's MAE, RMSE, and SMAPE decreased by 7.65%, 10.03%, and 8.87% over GRU-LSTM, the current best model for solving this type of problem.

• 한국항해학회지
• /
• 제8권1호
• /
• pp.1-16
• /
• 1984

The economical property of a shipping enterprise, as well as other transportation industries, is determined by the difference between the freight earned and expense paid. This study can be regarded as a division of optimizing ship allocation to routes under the integrated port transport system. Fleet planning and scheduling require complicated allocations of cargoes to ships and ships to routes in order to optimize the given criterion function for a given forecast period. This paper deals with the optimum ship allocation problem minimizing the operating cost of ships in a shipping company. Optimum fleet operating for a shipping enterprise is very important, since the marine transportation is a form of large quantity transport requiring long-term period, and there is a strong possibility to bring about large amount of loss in operation resulting from a faulty ship allocation. Where there are more than one loading and discharging ports, and a variety of ship's ability in speed, capacity, operating cost etc., and when the amount of commodities to be transported between the ports has been determined, then the ship's schedule minimizing the operating cost while satisfying the transport demand within the predetermined period will be made up. First of all a formula of ship allocation problems will be established and then will be constructed to solve an example by the Integer Programming application after consideration of the ship's ability, supply and demand of commodity, amount of commodity to be transported, operating costs of each ship etc. This study will give good information on deciding intention for a ship oprator or owner to meet the computerization current with shiping management.