The purpose of this research project is to analyze the brainwave data collected from MUSE EEG headband and use machine learning techniques to select a small number of features and accurately predict the emotional state of an individual. The brainwave dataset records the reading of the MUSE EEG headband. Supervised machine learning techniques are designed and implemented on a brainwave dataset to predict positive, negative, and neutral emotional state. The classification algorithms: K-Nearest neighbors (KNN), Random Forest, and Artificial Neural Networks (ANN) are used in this research. Further, the dimensions of this dataset were also reduced without compromising the accuracy of the results using principal component analysis (PCA), SelectKBest, and ReliefF algorithms. The results were promising with 96.7% accuracy.
Seid, Bethlehem and Elgazzar, Heba, "Emotion Recognition Using Brainwave Datasets" (2021). 2021 Celebration of Student Scholarship - Oral Presentations. 60.