An automatic algorithm based on artificial neural network is applied in taxi target prediction

DOI

10.2991/icmea-17.2018.46How to use a DOI?

Keywords

multi-Layer Perceptron;neural networks;taxi destination; prediction

Abstract

This paper describe the solution to the ECML/PKDD discovery challenge on taxi destination prediction. The work consisted in predicting the destination of a taxi based on the beginning of its trajectory, represented as a variable-length sequence of GPS points, and diverse associated meta-information, such as the departure time, the driver id and client information. Contrary to most published approaches, this paper uses an almost fully automated approach based on neural networks. The architectures we tried use multi-layer perceptions, bidirectional recurrent neural networks and models inspired from recently introduced memory networks. Our approach could easily be adapted to other applications in which the goal is to predict a fixed-length output from a variable-length sequence.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zhaosheng Wang
AU  - Shiyu Li
PY  - 2018/02
DA  - 2018/02
TI  - An automatic algorithm based on artificial neural network is applied in taxi target prediction
BT  - Proceedings of the 4th Annual International Conference on Material Engineering and Application (ICMEA 2017)
PB  - Atlantis Press
SP  - 199
EP  - 201
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmea-17.2018.46
DO  - 10.2991/icmea-17.2018.46
ID  - Wang2018/02
ER  -