arrow
返回

Driver Identification Using Deep Generative Model With Limited Data

delete2023-05-01
delete3
PRE
AI
H
Hongyu Hu
J
Jiarui Liu
陈国迎 封面图
陈国迎 (Guoying Chen) *
Y
Yuting Zhao
Z
Zhenhai Gao
R
Rencheng Zheng
DOI:10.1109/TITS.2023.3240185delete
delete原文链接
delete分享
delete收藏
摘要

摘要

En 中文
The scarcity of driving data constrains the accuracy of deep learning (DL)-based driver identification methods in practical application scenarios. To address this issue, this study proposes a novel unsupervised deep generative model called the convolution condition variant autoencoder (CCVAE) for driving data augmentation. In CCVAE, aided by driver identification information, the condition variant autoencoder can learn the real driving data distribution of each driver through an unsupervised learning paradigm; and aiming for better feature representation ability, convolutional neural network and deconvolution are leveraged, respectively. Therefore, a large number of synthetic samples can be generated by the generative part of the CCVAE. We demonstrate the effectiveness of the CCVAE through extensive experimental analysis using a real dataset collected from a vehicular CAN bus; the improvement of the DL-based driver identification results is demonstrated using synthetic samples. For instance, when only using 2% of the original data, approximately 20% improvement is achieved in terms of four evaluation indicators for two commonly used DL-based driver identification methods, namely, 1-D CNN and LSTM. Furthermore, several comparable experiments with state-of-the-art deep generative methods reveal the superior performance of the proposed CCVAE with respect to identification results, synthetic data quality, and model computation time. Therefore, the proposed model accomplishes a breakthrough in driver identification with limited data and shows great potential in data-driven applications of intelligent vehicles.
Keyword:
Vehicles
Data models
Feature extraction
Convolutional neural networks
Computational modeling
Unsupervised learning
Training data
CAN bus data
driver identification
deep generative model
data augmentation
deep learning

期刊

IEEE Transactions on Intelligent Transportation Systems 封面图
IEEE Transactions on Intelligent Transportation Systems
IF:
8.4
论文数:
9.9K
被引数:
8.1W

机构

天津大学 封面图
天津大学
学者数:
6.5K
论文数: 1.8K
被引数: 4.5W
华北电力大学 封面图
华北电力大学
学者数:
2.1K
论文数: 563
被引数: 1.2W
吉林大学 封面图
吉林大学
学者数:
5.4K
论文数: 1.3K
被引数: 3.7W
学者 查看更多机构
引用论文

引用论文

err分享
err收藏
Fly Ash Constituent-Silica and Alumina Role in the Synthesis and Characterization of Cordierite Based Ceramics
err2018-12-11
err0
PREAI
errM. Senthil Kumar; M. Vanmathi; G. Senguttuvan; R. V. Mangalaraja; G. Sakthivel
err分享
err收藏
Adhesion of thin, dry block copolymer layers adsorbed on mica
err2002-05-01
err0
PREAI
errHiroshi Watanabe; Shigetomo Matsuyama; Yoshinori Mizutani; Tadao Kotaka
err分享
err收藏
err分享
err收藏
学者 查看更多内容