The Classification of Human and Cognitive Architecture Time Estimation Using Machine Learning Methods

Time perception which plays an important role in daily life, is a critical concept affecting a wide range of disciplines. Time perception is crucial in both computer science and cognitive psychology as it informs the design of human-centered systems and technologies, while also deepening our understanding of cognitive processes and individual differences in how humans experience and process time. Cognitive architectures that model human cognitive functions provide valuable insights into the mechanisms underlying time perception. It is assumed that cognitive architectures are effective in explaining the cognitive processes involved in perceiving and interpreting time. In this study, the data obtained by applying a designed time perception experiment to human participants and a cognitive architecture were classified with machine learning algorithms which are K-Nearest Neighbor, Naive Bayes, Decision Tree, Support Vector Machine, Random Forest. According to the classification results, the Random Forest classifier was the most successful algorithm to classify the Human and Model classes with an accuracy rate of 82.06%.