Investigating driver fatigue versus alertness using the granger causality network

Wanzeng Kong, Weicheng Lin, Fabio Babiloni, Sanqing Hu, Gianluca Borghini

Research output: Contribution to journalArticlepeer-review


Driving fatigue has been identified as one of the main factors affecting drivers’ safety. The aim of this study was to analyze drivers’ different mental states, such as alertness and drowsiness, and find out a neurometric indicator able to detect drivers’ fatigue level in terms of brain networks. Twelve young, healthy subjects were recruited to take part in a driver fatigue experiment under different simulated driving conditions. The Electroencephalogram (EEG) signals of the subjects were recorded during the whole experiment and analyzed by using Granger-Causality-based brain effective networks. It was that the topology of the brain networks and the brain’s ability to integrate information changed when subjects shifted from the alert to the drowsy stage. In particular, there was a significant difference in terms of strength of Granger causality (GC) in the frequency domain and the properties of the brain effective network i.e., causal flow, global efficiency and characteristic path length between such conditions. Also, some changes were more significant over the frontal brain lobes for the alpha frequency band. These findings might be used to detect drivers’ fatigue levels, and as reference work for future studies.

Original languageEnglish
Pages (from-to)19181-19198
Number of pages18
JournalSensors (Switzerland)
Issue number8
Publication statusPublished - Aug 5 2015


  • Brain effective network
  • Driving fatigue
  • Eeg
  • Frequency domain
  • Granger causality

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Atomic and Molecular Physics, and Optics
  • Analytical Chemistry
  • Biochemistry


Dive into the research topics of 'Investigating driver fatigue versus alertness using the granger causality network'. Together they form a unique fingerprint.

Cite this