Abstract: Mental fog, also known as confusion, is one of the main reasons for poor performance in the learning process or any type of daily task that involves and requires thinking. Detecting confusion in the human mind is a real time paradigm that appears to be more difficult and important tasks that can be applied to online education, driver fatigue detection, etc. The Random Forest model achieve a better performance compared to other machine learning approaches and shows a great robustness evaluated by cross validation. We can predict if a student is confused about 100% accuracy. In addition, we found that the most important characteristic for detecting brain confusion is the beta 2 and gamma 1 wave of the Electroencephalography (EEG) signal. Our results suggest that machine learning is a potentially powerful tool for modeling and understanding brain activity. This work could be beneficial to individuals, to Ministry of Health, patients with brain diseases and to any other organization that deals on human state of mind in terms of performance.
Keywords: EEG, Mental Fog, Random Forest Model, Electroencephalography (EEG)
| DOI: 10.17148/IJARCCE.2020.9137