“…Based on the literature study that has been conducted in 20 articles, it can be found out that the construction and development of behaviour-based automatic driver drowsiness detection have mostly been conducted using some of the methods such as Vander Lugt Correlator [5], Haar Cascade [6,12,17], Eye Aspect Ratio [11,12,18,22], and even machine learning methods [11] such as Support Vector Machine [11,13], Neural Networks [4,6,7,8,10,14,15,16,18,20,22]. Recurrent Neural Networks like Long Short Term Memory have also been used in some of the research [4,16,22].…”