Feature Extraction and Evaluation for Driver Drowsiness Detection Based on Thermoregulation
Numerous reports state that drowsiness is one of the major factors affecting driving performance and resulting in traffic accidents. In the past, methods to detect driver drowsiness have been developed based on physiological, behavioral, and vehicular features. In this pilot study, we test the use o...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/17/3555 |
| _version_ | 1819039375775760384 |
|---|---|
| author | Jasper Gielen Jean-Marie Aerts |
| author_facet | Jasper Gielen Jean-Marie Aerts |
| author_sort | Jasper Gielen |
| collection | DOAJ |
| description | Numerous reports state that drowsiness is one of the major factors affecting driving performance and resulting in traffic accidents. In the past, methods to detect driver drowsiness have been developed based on physiological, behavioral, and vehicular features. In this pilot study, we test the use of a new set of features for detecting driver drowsiness based on physiological changes related to thermoregulation. Nineteen participants successfully performed a driving simulation, while the temperature of the nose (T<sub>nose</sub>) and wrist (T<sub>wrist</sub>) as well as the heart rate (HR) were monitored. On average, an initial increase in temperature followed by a gradual decrease was observed in drivers who experienced drowsiness. For non-drowsy drivers, no such trends were observed. In addition, HR decreased on average in both groups, yet the decrease in the drowsy group was more distinct. Next, a classification based on each of these variables resulted in an accuracy of 68.4%, 88.9%, and 70.6% for T<sub>nose</sub>, T<sub>wrist,</sub> and HR, respectively. Combining the information of all variables resulted in an accuracy of 89.5%, meaning that ultimately the state of 17 out of 19 drivers was detected correctly. Hence, we conclude that the use of physiological features related to thermoregulation shows potential for future research in this field. |
| first_indexed | 2024-12-21T08:52:13Z |
| format | Article |
| id | doaj.art-9a165d0e39ef48f7944b427b56b8a82b |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-21T08:52:13Z |
| publishDate | 2019-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-9a165d0e39ef48f7944b427b56b8a82b2022-12-21T19:09:38ZengMDPI AGApplied Sciences2076-34172019-08-01917355510.3390/app9173555app9173555Feature Extraction and Evaluation for Driver Drowsiness Detection Based on ThermoregulationJasper Gielen0Jean-Marie Aerts1Department of Biosystems, Division Animal and Human Health Engineering, M3-BIORES: Measure, Model & Manage of Bioresponses Laboratory, KU Leuven, Kasteelpark Arenberg 30, 3001 Heverlee, BelgiumDepartment of Biosystems, Division Animal and Human Health Engineering, M3-BIORES: Measure, Model & Manage of Bioresponses Laboratory, KU Leuven, Kasteelpark Arenberg 30, 3001 Heverlee, BelgiumNumerous reports state that drowsiness is one of the major factors affecting driving performance and resulting in traffic accidents. In the past, methods to detect driver drowsiness have been developed based on physiological, behavioral, and vehicular features. In this pilot study, we test the use of a new set of features for detecting driver drowsiness based on physiological changes related to thermoregulation. Nineteen participants successfully performed a driving simulation, while the temperature of the nose (T<sub>nose</sub>) and wrist (T<sub>wrist</sub>) as well as the heart rate (HR) were monitored. On average, an initial increase in temperature followed by a gradual decrease was observed in drivers who experienced drowsiness. For non-drowsy drivers, no such trends were observed. In addition, HR decreased on average in both groups, yet the decrease in the drowsy group was more distinct. Next, a classification based on each of these variables resulted in an accuracy of 68.4%, 88.9%, and 70.6% for T<sub>nose</sub>, T<sub>wrist,</sub> and HR, respectively. Combining the information of all variables resulted in an accuracy of 89.5%, meaning that ultimately the state of 17 out of 19 drivers was detected correctly. Hence, we conclude that the use of physiological features related to thermoregulation shows potential for future research in this field.https://www.mdpi.com/2076-3417/9/17/3555driver drowsinessthermoregulationdistal skin temperaturedecision tree |
| spellingShingle | Jasper Gielen Jean-Marie Aerts Feature Extraction and Evaluation for Driver Drowsiness Detection Based on Thermoregulation Applied Sciences driver drowsiness thermoregulation distal skin temperature decision tree |
| title | Feature Extraction and Evaluation for Driver Drowsiness Detection Based on Thermoregulation |
| title_full | Feature Extraction and Evaluation for Driver Drowsiness Detection Based on Thermoregulation |
| title_fullStr | Feature Extraction and Evaluation for Driver Drowsiness Detection Based on Thermoregulation |
| title_full_unstemmed | Feature Extraction and Evaluation for Driver Drowsiness Detection Based on Thermoregulation |
| title_short | Feature Extraction and Evaluation for Driver Drowsiness Detection Based on Thermoregulation |
| title_sort | feature extraction and evaluation for driver drowsiness detection based on thermoregulation |
| topic | driver drowsiness thermoregulation distal skin temperature decision tree |
| url | https://www.mdpi.com/2076-3417/9/17/3555 |
| work_keys_str_mv | AT jaspergielen featureextractionandevaluationfordriverdrowsinessdetectionbasedonthermoregulation AT jeanmarieaerts featureextractionandevaluationfordriverdrowsinessdetectionbasedonthermoregulation |