Electroencephalogram (EEG)-based systems to monitor driver fatigue: a review
View/ Open
Date
2022-03Author
Muhammad Shafiq, Ibrahim
Seri Rahayu, Kamat
Syamimi, Shamsuddin
Metadata
Show full item recordAbstract
An efficient system that is capable to detect driver fatigue is urgently needed to help
avoid road crashes. Recently, there has been an increase of interest in the application of
electroencephalogram (EEG) to detect driver fatigue. Feature extraction and signal
classification are the most critical steps in the EEG signal analysis. A reliable method for
feature extraction is important to obtain robust signal classification. Meanwhile, a
robust algorithm for signal classification will accurately classify the feature to a
particular class. This paper concisely reviews the pros and cons of the existing techniques
for feature extraction and signal classification and its fatigue detection accuracy
performance. The integration of combined entropy (feature extraction) with support
vector machine (SVM) and random forest (classifier) gives the best fatigue detection
accuracy of 98.7% and 97.5% respectively. The outcomes from this study will guide
future researchers in choosing a suitable technique for feature extraction and signal
classification for EEG data processing and shed light on directions for future research
and development of driver fatigue countermeasures.