Journal
SENSORS
Volume 22, Issue 14, Pages -Publisher
MDPI
DOI: 10.3390/s22145380
Keywords
PERCLOS; drowsiness detection; sympathetic nervous index; parasympathetic nervous index; EEG
Funding
- Ministry of Science and Technology of Taiwan, R.O.C. [MOST 108-2218-E-005-017, MOST 110-2221-E-005-085]
Ask authors/readers for more resources
Accidents caused by fatigue are common, and a drowsiness detection system is proposed to assess the driver's condition using heart rate variability and eyelid closure percentage. The system utilizes an algorithm to accurately and reliably determine the driver's state, and incorporates a near-infrared webcam for non-contact measurement.
Accidents caused by fatigue occur frequently, and numerous scholars have devoted tremendous efforts to investigate methods to reduce accidents caused by fatigued driving. Accordingly, the assessment of the spirit status of the driver through the eyes blinking frequency and the measurement of physiological signals have emerged as effective methods. In this study, a drowsiness detection system is proposed to combine the detection of LF/HF ratio from heart rate variability (HRV) of photoplethysmographic imaging (PPGI) and percentage of eyelid closure over the pupil over time (PERCLOS), and to utilize the advantages of both methods to improve the accuracy and robustness of drowsiness detection. The proposed algorithm performs three functions, including LF/HF ratio from HRV status judgment, eye state detection, and drowsiness judgment. In addition, this study utilized a near-infrared webcam to obtain a facial image to achieve non-contact measurement, alleviate the inconvenience of using a contact wearable device, and for use in a dark environment. Furthermore, we selected the appropriate RGB channel under different light sources to obtain LF/HF ratio from HRV of PPGI. The main drowsiness judgment basis of the proposed drowsiness detection system is the use of algorithm to obtain sympathetic/parasympathetic nervous balance index and percentage of eyelid closure. In the experiment, there are 10 awake samples and 30 sleepy samples. The sensitivity is 88.9%, the specificity is 93.5%, the positive predictive value is 80%, and the system accuracy is 92.5%. In addition, an electroencephalography signal was used as a contrast to validate the reliability of the proposed method.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available