Open AccessPrediction of the Quantity of Boxed Meals Preparation by High-Speed Train Based on ELM
Author(s) -
Feifei Zhou,
Hao Yang,
Jiahe Wang,
Sun Xian,
Xu Wu
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1910/1/012027
Subject(s) - beijing , service (business) , training (meteorology) , computer science , artificial neural network , extreme learning machine , range (aeronautics) , generalization , train , transport engineering , operations research , artificial intelligence , engineering , meteorology , business , mathematics , marketing , mathematical analysis , physics , cartography , political science , law , china , geography , aerospace engineering
Meal service is an important part of the railway transportation service, and when preparing the number of boxed meals before departure, the train must meet the needs of the train passengers for self-catering and food service. The demand of meals avoids causing too much waste. Extreme learning machine has the characteristics of fast learning speed and generalization ability, and has a wide range of applications in neural network prediction, this paper from the train perspective, by applying and improving the ELM model and using some of the high-speed train data from the Beijing-Qingdao section for model training. A prediction error analysis was performed to verify the reasonableness and feasibility of the model for the prediction of boxed meals.