Autoencoder Regularized Network For Driving Style Representation Learning
It addresses driver behavior analysis for applications like insurance or safety, but is incremental as it builds on autoencoder and supervised learning techniques.
The paper tackled learning driving style representations from GPS trip data by proposing ARNet and trip2vec, achieving an average estimation error of 0.68 drivers and at least 3% higher identification accuracy than existing methods.
In this paper, we study learning generalized driving style representations from automobile GPS trip data. We propose a novel Autoencoder Regularized deep neural Network (ARNet) and a trip encoding framework trip2vec to learn drivers' driving styles directly from GPS records, by combining supervised and unsupervised feature learning in a unified architecture. Experiments on a challenging driver number estimation problem and the driver identification problem show that ARNet can learn a good generalized driving style representation: It significantly outperforms existing methods and alternative architectures by reaching the least estimation error on average (0.68, less than one driver) and the highest identification accuracy (by at least 3% improvement) compared with traditional supervised learning methods.