drowsiness analysis using common spatial pattern and extremelearning machine based on electroencephalogram signal

An alarm system has become essential to prevent someone from drowsiness while driving,considering the high incidence due to fatigue or drowsiness. this study offered an alternativeto overcome all the limitations provided by the conventional system to detect sleepiness basedon the driver’s brain electrical activity using wearable electroencephalogram (eeg), which islighter and easy to use. the eeg signals were collected using emotiv epoc + and then weredecomposed into narrowband frequency, such as delta, theta, alpha, and beta using dwt. therelative power, as the result of feature extraction, then were processed further by calculating itsvariance using the common spatial pattern (csp) method to optimize the accuracy of extremelearning machine (elm). comparison of relative power between awake and drowsy state showedthat during the drowsy state, theta‑wave, alpha‑wave, and beta‑wave were tend to be higher thanin the awake state. however, despite with the help of elm, the accuracy was not too high (below87%). the feature extraction which continued by calculating its variance using csp algorithmbefore classified by elm obtained a high accuracy, even with small amount of data training. thisshowed that csp combining with elm could be useful to shorten the time in training/calibrationsession, yet still, obtained high accuracy in classifying the awake state and drowsy state. theoverall average accuracy of testing ranged from 91.67% to 93.75%. this study could increase theability of eeg in detecting drowsiness that is important to prevent the risk caused by driving in adrowsy state.