This study proposes a deep learning framework for driver identity identification by extracting information from the vehicular controller area network (CAN) bus signals. First, naturalistic driving data of 20 drivers were collected under a fixed testing route with different road types and different traffic conditions. Then, a one-dimensional convolutional neural network was constructed for driver identification, which consists of two convolutional-pooling layers, a fully connected layer, and a SoftMax layer. Model optimisation algorithms were applied to improve accuracy and speed up the training process. Also, the model parameters were optimised by evaluating their influences on the model results. Furthermore, the performance of the proposed algorithm was compared with that of the K-nearest neighbour, support vector machine, multi-layer perceptron, and long short-term memory model. The authors used the ${\bf Macro}\, {\bi F}_1$ score as an evaluation criterion and the identification score of the authors' proposed model reaches 99.10% under 20 testing subjects where the data time window size is one second and the sample data overlap is 80%. The results show that the model's performance is significantly better than the other algorithms, which can effectively identify driver identities with stability and robustness.
Driver identification using 1D convolutional neural networks with vehicular CAN signals
IET Intelligent Transport Systems ; 14 , 13 ; 1799-1809
2021-01-13
11 pages
Article (Journal)
Electronic Resource
English
convolutional neural nets , convolutional-pooling layers , learning (artificial intelligence) , one-dimensional convolutional neural network , fixed testing route , nearest neighbour methods , 1D convolutional neural networks , vehicular CAN signals , naturalistic driving data , SoftMax layer , convolution filters , data time window size , road types , driver information systems , fully connected layer nodes , vehicular controller area network bus signals , road safety , multilayer perceptron , driver identity identification , long short-term memory model , K-nearest neighbour , support vector machines , model parameters , identification score , model optimisation algorithms , driver identification , multilayer perceptrons , optimisation , controller area networks , deep learning framework , sample data overlap
Metadata by IET is licensed under CC BY 3.0
Driver identification using 1D convolutional neural networks with vehicular CAN signals
Wiley | 2020
|Driver Distraction Identification with an Ensemble of Convolutional Neural Networks
DOAJ | 2019
|On Generalizing Driver Gaze Zone Estimation Using Convolutional Neural Networks
British Library Conference Proceedings | 2017
|