Detecting Cognitive Distraction using Random Forest by Considering Eye Movement Type

2. Related Studies

Various research efforts have applied identification-based machine learning algorithms to detect cognitive distraction using eye movement data. In (Miyaji, Kawanaka, & Oguri, 2010), the Adaboost algorithm was applied to detect cognitive distraction in drivers using gaze angles and head rotation angles. In (Liu, Yang, Huang, & Lin, 2015) and (Liu, Yang, Huang, Yeo, & Lin, 2016), the Semi-Supervised Extreme Learning Machine algorithm was applied to detect distraction in drivers using eye and head movements. In (Liu, Yang, Huang, Lin, Klanner, Denk, & Rasshofer, 2015), the Cluster Regularized Extreme Learning Machine algorithm was applied to detect distraction in drivers using eye and head movements. However, classified eye movement types were not considered in these studies.