Utilizing HRV-Derived Respiration Measures for Driver Drowsiness Detection
This study aims to utilize heart rate variability (HRV) signals obtained with a wearable sensor for driver drowsiness detection. To this end, we investigated respiration characteristics derived from HRV signals based on the known fact that respiratory activity can be estimated from the high frequenc...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-06-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/8/6/669 |
| _version_ | 1798005535639863296 |
|---|---|
| author | Jinwoo Kim Miyoung Shin |
| author_facet | Jinwoo Kim Miyoung Shin |
| author_sort | Jinwoo Kim |
| collection | DOAJ |
| description | This study aims to utilize heart rate variability (HRV) signals obtained with a wearable sensor for driver drowsiness detection. To this end, we investigated respiration characteristics derived from HRV signals based on the known fact that respiratory activity can be estimated from the high frequency (HF) band of HRV signals. For drowsiness detection, many earlier works commonly used dominant respiration (DR) characteristics. However, in some situations where emphasized power in a power spectrum of HRV occurs at multi sub-frequency, the DR measures may possibly fail to capture overall respiration characteristics. To handle this problem, we propose two spectral indices, the weighted mean (WM) and the weighted standard deviation (WSD) of the HF band in the power spectrum. These indices are used to properly capture the overall shape of the respiratory activity shown through the HF band of the HRV power spectrum as an alternative to the DR measures. For experiments, we collected HRV data with an electrocardiogram device worn on the body under a virtual driving environment. The proposed indices somewhat clearly showed the tendency that respiratory frequency decreases and respiration regularity increases in drowsy states of all subjects, while existing DR measures hardly showed this. In addition, when the proposed indices are used alone or together with conventional HRV-related measures as input features for classification models, they showed the best performance in distinguishing drowsiness from wakefulness. |
| first_indexed | 2024-04-11T12:40:50Z |
| format | Article |
| id | doaj.art-463065f8480b4fcc8b61f01369b7c6e9 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-04-11T12:40:50Z |
| publishDate | 2019-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-463065f8480b4fcc8b61f01369b7c6e92022-12-22T04:23:29ZengMDPI AGElectronics2079-92922019-06-018666910.3390/electronics8060669electronics8060669Utilizing HRV-Derived Respiration Measures for Driver Drowsiness DetectionJinwoo Kim0Miyoung Shin1Bio-Intelligence & Data Mining Lab, School of Electronics Engineering, Kyungpook National University, Daegu 41566, KoreaBio-Intelligence & Data Mining Lab, School of Electronics Engineering, Kyungpook National University, Daegu 41566, KoreaThis study aims to utilize heart rate variability (HRV) signals obtained with a wearable sensor for driver drowsiness detection. To this end, we investigated respiration characteristics derived from HRV signals based on the known fact that respiratory activity can be estimated from the high frequency (HF) band of HRV signals. For drowsiness detection, many earlier works commonly used dominant respiration (DR) characteristics. However, in some situations where emphasized power in a power spectrum of HRV occurs at multi sub-frequency, the DR measures may possibly fail to capture overall respiration characteristics. To handle this problem, we propose two spectral indices, the weighted mean (WM) and the weighted standard deviation (WSD) of the HF band in the power spectrum. These indices are used to properly capture the overall shape of the respiratory activity shown through the HF band of the HRV power spectrum as an alternative to the DR measures. For experiments, we collected HRV data with an electrocardiogram device worn on the body under a virtual driving environment. The proposed indices somewhat clearly showed the tendency that respiratory frequency decreases and respiration regularity increases in drowsy states of all subjects, while existing DR measures hardly showed this. In addition, when the proposed indices are used alone or together with conventional HRV-related measures as input features for classification models, they showed the best performance in distinguishing drowsiness from wakefulness.https://www.mdpi.com/2079-9292/8/6/669driver drowsiness detectionwearable ECG devicerespiration characteristics |
| spellingShingle | Jinwoo Kim Miyoung Shin Utilizing HRV-Derived Respiration Measures for Driver Drowsiness Detection Electronics driver drowsiness detection wearable ECG device respiration characteristics |
| title | Utilizing HRV-Derived Respiration Measures for Driver Drowsiness Detection |
| title_full | Utilizing HRV-Derived Respiration Measures for Driver Drowsiness Detection |
| title_fullStr | Utilizing HRV-Derived Respiration Measures for Driver Drowsiness Detection |
| title_full_unstemmed | Utilizing HRV-Derived Respiration Measures for Driver Drowsiness Detection |
| title_short | Utilizing HRV-Derived Respiration Measures for Driver Drowsiness Detection |
| title_sort | utilizing hrv derived respiration measures for driver drowsiness detection |
| topic | driver drowsiness detection wearable ECG device respiration characteristics |
| url | https://www.mdpi.com/2079-9292/8/6/669 |
| work_keys_str_mv | AT jinwookim utilizinghrvderivedrespirationmeasuresfordriverdrowsinessdetection AT miyoungshin utilizinghrvderivedrespirationmeasuresfordriverdrowsinessdetection |