دانشگاه علم و صنعت ایران، دانشکده مهندسی راه آهن
عنوان مقاله [English]
One of the major issues in railways is passenger train delays and this matter in railway has a lot of reasons; so predicting passenger train delay is a very difficult task. The aim of this paper is to present an artificial neural network based model with high accuracy to predict the delay of passenger trains in the Islamic Republic of Iran railway. In the proposed model we use tree different methods to define inputs including normalized real number, binary coding, and binary set encoding inputs. To find an appropriate structure for proposed neural network model, three different strategies, called quick, dynamic, and multiple, are investigated. In this research, the registered data of passenger train delays in Iranian railway from 1383 to the end of 1387 year is used. To eliminate any inconsistent and noisy data which always companion with real world data set, a comprehensive preprocessing on this data set is done. To get more knowledge about data we sketch some graphs such as seasonal average of delays, monthly average of delays, and total delay since 1383 to 1387 per year. To prevent models from over fitting with data specifications, according to cross validation, we divide existing passenger train delays data set into three subsets called training set, validation set and testing set, respectively. To evaluate the proposed model, we compare the result of three different data input methods and three different structures with each other and also with some common prediction methods such as decision tree and multinomial logistic regression. In comparison different neural networks we consider training time, accuracy of neural network on testing data set and network size and to compare neural networks with other well-known prediction methods we consider training time and accuracy of neural network on testing data set. To do a fair comparison among all models we sketch a time-accuracy graph. The results revealed that the proposed model has higher accuracy.