The main goal of the proposed research is to develop an algorithm capable of classifying a test subject’s caffeine level as “no caffeine”, “normal caffeine”, or “above average caffeine” intake, and through that process, analyze caffeine’s influence on alpha, beta, and gamma oscillations, as well as heart rate, memory, and attention.
The project takes inspiration from the study ‘Automated Detection of Caffeinated Coffee-Induced Short-Term Effects on ECG Signals Using EMD, DWT, and WPD, where several machine learning models (linear regression, naive Bayes, random forest, gradient-boosted tree, support vector machine, and others) were implemented to classify caffeine levels based on EEG signals. The best result achieved was 78 % classification accuracy by using gradient boosting model.