Classification of Drowsiness Levels Based on a Deep Spatio-Temporal Convolutional Bidirectional LSTM Network Using Electroencephalography Signals

• Published in: Brain Sciences Vol. 9; no. 12; p. 348
• Main Authors: Jeong, Ji-Hoon, Yu, Baek-Woon, Lee, Dae-Hyeok, Lee, Seong-Whan
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 29.11.2019; MDPI
• Subjects: Accuracy; Aircraft; Artificial intelligence; Brain research; brain-Computer Interface; Cameras; Classification; Deep learning; Drowsiness; drowsiness levels classification; EEG; Electrocardiography; Electrodes; electroencephalogram; Electroencephalography; Experiments; Fatigue; Heart rate; Hemoglobin; Interfaces; Long short-term memory; Machine learning; mental states; Neural networks; Physiology; Process controls; Sleep and wakefulness; Support vector machines; brain-Computer Interface; deep learning; drowsiness levels classification; electroencephalogram; mental states
• ISSN: 2076-3425; 2076-3425
• DOI: 10.3390/brainsci9120348

Non-invasive brain-computer interfaces (BCI) have been developed for recognizing human mental states with high accuracy and for decoding various types of mental conditions. In particular, accurately decoding a pilot’s mental state is a critical issue as more than 70% of aviation accidents are caused by human factors, such as fatigue or drowsiness. In this study, we report the classification of not only two mental states (i.e., alert and drowsy states) but also five drowsiness levels from electroencephalogram (EEG) signals. To the best of our knowledge, this approach is the first to classify drowsiness levels in detail using only EEG signals. We acquired EEG data from ten pilots in a simulated night flight environment. For accurate detection, we proposed a deep spatio-temporal convolutional bidirectional long short-term memory network (DSTCLN) model. We evaluated the classification performance using Karolinska sleepiness scale (KSS) values for two mental states and five drowsiness levels. The grand-averaged classification accuracies were 0.87 (±0.01) and 0.69 (±0.02), respectively. Hence, we demonstrated the feasibility of classifying five drowsiness levels with high accuracy using deep learning.