International Journal of Electrical and Computer Engineering (IJECE) Vol. 12, No. 3, June 2022, pp. 2986~2995 ISSN: 2088-8708, DOI: 10.11591/ijece.v12i3.pp2986-2995  2986 Journal homepage: http://ijece.iaescore.com Modern drowsiness detection techniques: a review Sarah Saadoon Jasim 1 , Alia Karim Abdul Hassan 2 1 Department of Informatics Techniques, Technical College of Management-Baghdad, Middle Technical University, Baghdad, Iraq 2 Department of Computer Science, University of Technology, Baghdad, Iraq Article Info ABSTRACT Article history: Received Aug 4, 2021 Revised Nov 5, 2021 Accepted Nov 30, 2021 According to recent statistics, drowsiness, rather than alcohol, is now responsible for one-quarter of all automobile accidents. As a result, many monitoring systems have been created to reduce and prevent such accidents. However, despite the huge amount of state-of-the-art drowsiness detection systems, it is not clear which one is the most appropriate. The following points will be discussed in this paper: Initial consideration should be given to the many sorts of existing supervised detecting techniques that are now in use and grouped into four types of categories (behavioral, physiological, automobile and hybrid), Second, the supervised machine learning classifiers that are used for drowsiness detection will be described, followed by a discussion of the advantages and disadvantages of each technique that has been evaluated, and lastly the recommendation of a new strategy for detecting drowsiness. Keywords: Identification of fatigue classification Machine learning classifiers Optical image processing driver drowsiness sensors This is an open access article under the CC BY-SA license. Corresponding Author: Sarah Saadoon Jasim Department of Informatics Techniques, Technical college of Management-Baghdad, Middle Technical University Baghdad, Iraq Email: sara-sm@mtu.edu.iq 1. INTRODUCTION Drowsiness and fatigue are one of the significant factors that affect road safety and cause serious accidents, casualties, and economic losses [1]. According to national highway traffic safety administration (NHTSA) report in the United States, between 2011 and 2015 about 2.4% of 153,297 road accidents, more than 1.25 million deaths annually, and 20-50 million people injured or disabled are caused by drowsy driving; In addition to the high cost which can be reached to $518 billion. In India, according to Ministry of Road transport and highways transport research wing report, there were about 449,002 accidents out of this number of data 33.65% was the mortality rate in 2019. While in Europe, in 2019 the mortality rate was 19% due to road accident. Statistics predicts that annually about 76,000 injuries and 1,200 deaths can caused because of fatigue and drowsiness through driving. As a result, by 2030 road traffics will become the fifth cause of death. In air traffic, Drowsiness and fatigue become a serious issue. According to recent surveys, long flight and busy schedule of the pilots lead them to take a short snap or snooze through their flight. Therefore, airline industry must ensure that their crew is a wake periodically or it will be a major problem. There are numerous factors that contribute to driver’s fatigue such as: lack of rest, a long ride, wakefulness, consumption of alcohol, and mental stress. Those factors may lead to serious disaster if action does not take on time. Moreover, previous transportation system was not provided with tools or techniques to control those factors on roads [2]–[4]. Due to the dangerous accidents that fatigue poses on the roads, researchers developed different types of methods to detect driver’s drowsiness. Despite the large number of methods conducted in this field and the numerous technologies available for driver’s drowsiness detection, it is still unclear which one is the most