The study of time domain features of EMG signals for detecting driver’s drowsiness
Fatigue or drowsiness is one of the major causes of traffic accidents in Malaysia. Physiological signals such as EMG is a useful input to detect drowsiness in drivers. The time domain features are easy to compute and well researched in the field of EMG hand motion detection. The focus of this paper...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English English |
| Published: |
Springer Science and Business Media Deutschland GmbH
2022
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/42244/1/The%20study%20of%20time%20domain%20features%20of%20EMG%20signals.pdf http://umpir.ump.edu.my/id/eprint/42244/2/The%20study%20of%20time%20domain%20features%20of%20emg%20signals%20for%20detecting%20driver%E2%80%99s%20drowsiness_ABS.pdf http://umpir.ump.edu.my/id/eprint/42244/ https://doi.org/10.1007/978-981-33-4597-3_39 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Fatigue or drowsiness is one of the major causes of traffic accidents in Malaysia. Physiological signals such as EMG is a useful input to detect drowsiness in drivers. The time domain features are easy to compute and well researched in the field of EMG hand motion detection. The focus of this paper is to find the best set of time domain features to detect drowsiness in drivers’ EMG signal from biceps brachii muscle. This study analyzes the time domain features of EMG signals in detecting the drowsiness in drivers during a 2 h simulated driving session. Nine time-domain features are applied to all 15 samples and classified using six classifiers. The best single feature for the long duration signal is the mean absolute value slope (MAVS) with 80% accuracy using Naïve Bayes (NB) classifiers. All features combined gives the highest accuracy of 85% using linear discriminant analysis (LDA) classifier. |
|---|