Tehran University of Medical Sciences

Science Communicator Platform

Stay connected! Follow us on X network (Twitter):
Share this content! On (X network) By
Detection of Drowsiness Using the Pulse Rate Variability of Finger Publisher



Heydari S1 ; Ayatollahi A1 ; Najafi A2 ; Poorjafari M3
Authors
Show Affiliations
Authors Affiliations
  1. 1. University of Science and Technology, Tehran, Iran
  2. 2. Occupational Sleep Research Center, Baharloo Hospital, Tehran University of Medical Sciences, P.O. Box 1339973111, Tehran, Iran
  3. 3. Highway and Transportation Engineering at Department of Civil Engineering, Iran University of Science and Technology, Tehran, Iran

Source: SN Computer Science Published:2022


Abstract

This paper proposes a new method for detecting a driver's drowsiness from changes in the pulse rate of a finger. Electroencephalographic (EEG) signals were received from a sample of ten individuals. The analysis of electroencephalographic signals is investigated and the activation of theta waves during the drowsiness interval is observed. Photoplethysmography signals were received from ten participants simultaneously with the EEG signal. Finger pulse data are analyzed and the features showing a significant change during drowsiness in the pulse rate variability (PRV) of the finger are further identified and extracted. The results indicate that the values and the average values of PRV increase before the point of sleep onset (SO). It is observed that the standard deviation of all PP intervals (SDNN) has a significant reduction during drowsiness. An increase in the values of RMSSD is also observed in the drowsiness interval. Besides, the ratio of low to high frequency (LF/HF) representing the balance of sympathetic and parasympathetic branches decreases in the vicinity of SO which indicates raised parasympathetic activity. The nonlinear analysis of the Poincare plot indicated the reduction of the SD1 parameter. The results indicate that the PRV method can be used for the detection of driver drowsiness. Finally, the presented method is considered in an intelligent steering wheel design as a feasible non-invasive procedure for the detection of driver drowsiness. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.