fa ارتعاشات Vibration, noise, Acoustic پژوهشي Research This paper presents the prediction of vehicle's velocity time series using neural networks. For this purpose, driving data is firstly collected in real world traffic conditions in the city of Tehran using advance vehicle location devices installed on private cars. A multi-layer perceptron network is then designed for driving time series forecasting. In addition, the results of this study are compared with the auto regressive (AR) method. The least root mean square error (RMSE) and median absolute percentage error (MDAPE) are utilized as two criteria for evaluation of predictions accuracy. The results demonstrate the effectiveness of the proposed approach for prediction of driving data time series. vehicle, velocity, time series, prediction, neural networks 21 28 http://ase.iust.ac.ir/browse.php?a_code=A-10-28-1&slc_lang=fa&sid=1 A. Fotouhi afotouhi@iust.ac.ir 18003194753284600530 18003194753284600530 Yes iust M. Montazeri montazeri@iust.ac.ir 18003194753284600531 18003194753284600531 No iust M. Jannatipour Mo_janatipoor@mecheng.iust.ac.ir 18003194753284600532 18003194753284600532 No iust