Using Two-Class Boosted Decision Trees to accurately detect eye movement and blinking using 14-channel EEG data.
This project focused on replicating the development of a **Two-Class Boosted Decision Tree** Machine Learning model to classify whether a patient's eyes are open or closed - solely based on their brain signals. Eye movement and blinking poses as a major obstacle towards truly intelligent Brain-Computer Interface development, as it hinders EEG data to be extracted to its full potential value. In general, any unnecessary signal peaks in brain signal data from movement is known as an artifact, and a major challenge in today's EEG signal processing field is to detect and remove these artifacts to guarantee the most meaningful insights from an EEG reading. a simple, robust, and highly accurate model was built using a drag-and-drop interface, and was shown to achieve superior accuracy to decades-old transformation and normalization formulas.