The increasing number of vehicles on the roads raises the risk of accidents and injuries and distracted driving has emerged as a major contributing factor to road incidents. Secondary distractions, such as smartphone usage, divert drivers’ attention from the road and significantly increase the chances of collisions. This paper presents a classifier algorithm designed to recognize secondary distracting factors during car driving, focusing on analysis through the use of smart glasses and driving simulator. The study involved a reference ride scenario and four distinct distracting factors introduced into the simulated driving scenarios. Eye and head movement data were acquired with the use of smart glasses and prepared using basic signal processing techniques. The algorithm developed employed a Random Forest model to classify the signals from smart glasses and accurately identify the presence of distracting factors during driving. The experimental results showcased the efficacy of the proposed algorithm, achieving an impressive 98% accuracy rate on the test set, thus demonstrating its potential for real-world implementation. This research contributes to advancing driver assistance systems by providing a robust and reliable tool for early detection of secondary distractions, ultimately helping to reduce the likelihood of accidents and promoting safer driving practices.