This study examined the machine learning-based approach allowing the recognition of human emotional states with the use of EEG signals. After a short introduction to the fundamentals of electroencephalography and neural oscillations, the two-dimensional valence-arousal Russell’s model of emotion was described. Next, we present the assumptions of the performed EEG experiment. Detail aspects of the data sanitization including preprocessing, feature extraction, and target variable creation were also given. At the modeling stage, we created several classification models to establish a benchmark ranking of the problem related to the recognition of human emotions. Such a methodological approach enabled us to confirm that it is possible to build machine learning solutions allowing to recognize and classify human emotions with very high accuracy of over 90%.
Autorzy
- mgr inż. Adrian Kastrau,
- inż. Michał Koronowski,
- mgr Mariusz Liksza,
- dr inż. Patryk Jasik link otwiera się w nowej karcie
Informacje dodatkowe
- Kategoria
- Publikacja monograficzna
- Typ
- rozdział, artykuł w książce - dziele zbiorowym /podręczniku w języku o zasięgu międzynarodowym
- Język
- angielski
- Rok wydania
- 2021
