Deep learning for vehicle speed prediction

Citations of this article
Mendeley users who have this article in their library.


In this paper, a data driven approach, deep learning, for vehicle speed prediction is presented. Deep learning based on the deep neural network structure is applied to predict a future short-term speed with the collected dataset including the historical vehicle speed and its corresponding acceleration, steering information, location and driving date. The influence of the driving factors on the accuracy of vehicle speed prediction is analyzed. And four standard driving cycles are used to test the generalization ability of the proposed speed prediction method. The results show that when the training set is the information of the historical speed and the driving date, the prediction effect is the best, and RMSE is 1.5298. And the proposed prediction method has good generalization ability.




Yan, M., Li, M., He, H., & Peng, J. (2018). Deep learning for vehicle speed prediction. In Energy Procedia (Vol. 152, pp. 618–623). Elsevier Ltd.

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free