Classification of Psychological Disorders by Feature Ranking and Fusion using Gradient Boosting

Negative emotional regulation is a defining element of psychological disorders. Our goal was to create machine-learning model classify disorders based on negative emotions. EEG brainwave dataset displaying positive, negative, and neutral However, emotions are responsible for health. In this paper, research focused solely state characteristics which the divide-and-conquer approach has been applied feature extraction process. Features grouped into four equal subsets selection done each subset by ranking their importance determined Random Forest-Recursive Feature Elimination with Cross-validation (RF-RFECV) method. After ranking, fusion employed obtain new potential dataset. 10-fold cross-validation performed grid search created using set predetermined parameters that important achieving greatest possible accuracy. Experimental results demonstrated proposed achieved 97.71% accuracy in predicting