Driver Behavior and Intention Recognition Based on Wavelet Denoising and Bayesian Theory

Min Li, Wuhong Wang, Zhen Liu*, Mingjun Qiu, Dayi Qu

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

7 Citations (Scopus)

Abstract

Driver behavior and intention recognition affects traffic safety. Many scholars use the steering wheel angle, distance of the brake pedal, distance of the accelerator pedal, and turn signal as input data to identify driver behaviors and intentions. However, in terms of time, the acquisition of these parameters has a relative delay, which lengthens the identification time. Therefore, this study uses drivers’ EEG (electroencephalograph) data as input parameters to identify driver behaviors and intentions. The key to the driving intention recognition of EEG signals is to reduce their noise. Noise interference has a significant influence on EEG driving intention recognition. To substantially denoise EEG signals, this study selects wavelet transform theory and wavelet packet transform technology, collects the EEG signals during driving, uses the threshold noise reduction method on EEG signals to reduce noise, and achieves noise reduction through wavelet packet reconstruction. After the wavelet packet coefficients of EEG signals are obtained, the energy characteristics of the wavelet packet coefficients are extracted as input to the Bayesian theoretical model for driver behavior and intention recognition. Results show that the maximum recognition rate of the Bayesian theoretical model reaches 82.6%. Early driver behavior and intention recognition has important research significance for traffic safety and sustainable traffic development.

Original languageEnglish
Article number6901
JournalSustainability (Switzerland)
Volume14
Issue number11
DOIs
Publication statusPublished - 1 Jun 2022

Keywords

  • Bayesian theory
  • EEG signal
  • driving intention
  • noise reduction
  • sustainable transportation
  • wavelet transform theory

Fingerprint

Dive into the research topics of 'Driver Behavior and Intention Recognition Based on Wavelet Denoising and Bayesian Theory'. Together they form a unique fingerprint.

Cite this