A Study on Facial Expression Change Detection Using Machine Learning Methods with Feature Selection Technique

Along with the fourth industrial revolution, research in biomedical engineering field is being actively conducted. Among these fields, brain–computer interface (BCI) research, which studies direct interaction between brain and external devices, spotlight. However, case of electroencephalograph (EEG) data measured through BCI, there are a huge number features, can lead to many difficulties analysis because complex relationships features. For this reason, on BCIs using EEG often insufficient. Therefore, study, we develop methodology for selecting features specific type BCI that predicts whether person correctly detects facial expression changes or not by classifying EEG-based We also investigate affect change detection. Various feature selection methods were used check influence each detection, best combination was selected several machine learning classification techniques. As result accuracy, 71% accuracy obtained XGBoost 52 topography confirmed major showing detection largely engages activity frontal regions.