نوع مقاله : علمی - پژوهشی
نویسندگان
1 استادیار، دانشکده عمران و محیط زیست، دانشگاه تربیت مدرس، تهران
2 دانشکده عمران و محیط زیست، دانشگاه تربیت مدرس، تهران
3 دانش آموخته کارشناسی ارشد، دانشکده عمران و محیط زیست، دانشگاه تربیت مدرس، تهران
4 دانش آموخته دوره دکتری دانشکده برق و مهندسی کامپیوتر، دانشگاه تربیت مدرس، تهران
چکیده
کلیدواژهها
موضوعات
عنوان مقاله [English]
نویسندگان [English]
In recent decades, increasing urban population, urbanization development and the lack of public transportation in response to increasing demand for inter-city trips have led to an increase in the use of private cars in Tehran. Therefore, changes in urban transport policies and efforts to develop and improve public transportation, especially the bus, are one of the most important strategies in the urban transport planning and require the necessary surveys to have a growth in share of public transportation. Studies show that planning for the optimal use of bus infrastructure and the use of solutions to increase the efficiency of this system in the world, requires information on infrastructure and bus lines demand. Accordingly, it is necessary to carry out studies to predict bus lines passenger demand in Tehran, for operational lines planning which are currently empirically carried out by the line manager and there is no planning based on the existing conditions for the future. Thus, this study predicts bus lines passenger demand for the short-term future, using AFC data (data recorded from smart credit card transactions for fares payment) and calibration of a suitable model. For this purpose, AFC information is firstly arranged for each bus line, then Sarima and neural network model (multi- layer perceptron) are calibrated based on. The model results show that the multi- layer perceptron model in terms of error indices in prediction of bus passenger demand is better than Sarima model and it is a more appropriate method for predicting short-term bus lines passenger demand.
کلیدواژهها [English]