Microneedle Array Electrode-Based Wearable EMG System for Detection of Driver Drowsiness through Steering Wheel Grip

Abstract

Driver drowsiness is a major cause of fatal accidents throughout the world. Recently, some studies have investigated steering wheel grip force-based alternative methods for detecting driver drowsiness. In this study, a driver drowsiness detection system was developed by investigating the electromyography (EMG) signal of the muscles involved in steering wheel grip during driving. The EMG signal was measured from the forearm position of the driver during a one-hour interactive driving task. Additionally, the participant’s drowsiness level was also measured to investigate the relationship between muscle activity and driver’s drowsiness level. Frequency domain analysis was performed using the short-time Fourier transform (STFT) and spectrogram to assess the frequency response of the resultant signal. An EMG signal magnitude-based driver drowsiness detection and alertness algorithm is also proposed. The algorithm detects weak muscle activity by detecting the fall in EMG signal magnitude due to an increase in driver drowsiness. The previously presented microneedle electrode (MNE) was used to acquire the EMG signal and compared with the signal obtained using silver-silver chloride (Ag/AgCl) wet electrodes. The results indicated that during the driving task, participants’ drowsiness level increased while the activity of the muscles involved in steering wheel grip decreased concurrently over time. Frequency domain analysis showed that the frequency components shifted from the high to low-frequency spectrum during the one-hour driving task. The proposed algorithm showed good performance for the detection of low muscle activity in real time. MNE showed highly comparable results with dry Ag/AgCl electrodes, which confirm its use for EMG signal monitoring. The overall results indicate that the presented method has good potential to be used as a driver’s drowsiness detection and alertness system.

Sensitive Electrochemical Non-Enzymatic Detection of Glucose Based on Wireless Data Transmission

“…Several reports on microneedles (MNs) have been published in the past decade due to their attractive features such as being minimally invasive for painless sampling and micron-size dimensions limiting their penetration to the intradermal space, thanks to the MEMS fabrication technology [ 21 , 22 ]. To date, MNs have been used for transdermal drug delivery [ 23 ], insulin injection [ 24 ] and for sensing various analytes of clinical interest lactate [ 25 ], glucose [ 22 ], L-DOPA [ 26 ], glutamate [ 27 ] and cholesterol [ 28 ].…”

Driver Fatigue Detection Based on Residual Channel Attention Network and Head Pose Estimation

“…The eigenvector of A T A is (v w,i , i = 1, 2, 3). A is shown in Equation ( 6), and the remain three control points can be determined by Equation (7).…”

“…Physiological signal measurement methods are usually based on the driver's physiological signals, such as electroencephalogram (EEG [5]), electrooculogram (EOG [6]), and EMG [7]. The fatigue state can be evaluated by frequency domain analysis and linear classification based on EEG or EEG.…”

Trends and Future Prospects of the Drowsiness Detection and Estimation Technology

“…They also found that as the driver’s drowsiness level increased, the muscle activity for gripping the steering decreased with time while driving. In addition, the results of the frequency domain analysis revealed that the frequency components of the steering shifted from low frequency to high frequency in an hour’s driving [ 38 ]. In one case, the driver’s states were detected by electrodes attached to the steering [ 39 ] for sensing the vitals.…”