Analysis of brain activity to methamphetamine stimulus using electroencephalography technology with Naive Bayes algorithm

Abstract

The increasing use of methamphetamine among young generations has led to significant alterations in brain function, affecting both behavior and mental health. However, scientific understanding of the neural activity changes induced by methamphetamine remains limited. This study aims to analyze brainwave patterns using electroencephalography (EEG) and classify addiction response levels through the Naive Bayes algorithm. The experimental procedure involved presenting each subject with visual stimuli related to methamphetamine while recording their brain activity using EEG for three minutes. The extracted EEG features were then analyzed with the Naive Bayes classifier. The results demonstrated a classification accuracy of 97.9%. The proposed method successfully categorized brain activity patterns into five levels of response: non-addicted, mildly addicted, moderately active, addicted, and highly addicted. These findings indicate that the Naive Bayes algorithm is effective in distinguishing subtle variations in brainwave patterns associated with different levels of methamphetamine addiction response.