Early Detection of Drug Users from EEG Signals Using Decision Tree

The increasing cases of drug addiction require innovative approaches to understand its effects on the brain. This study used electroencephalography (EEG) signals to identify neurophysiological changes in drug users through the decision tree method, as a classification tool. EEGs from drug convicts were analyzed to distinguish brain activity patterns into five categories: very active, active, tend to be active, less active and inactive. The results showed an accuracy of 99.2% in classifying EEG activity patterns, indicating unique characteristics in drug users. These findings provide significant insights into drug-induced brain function changes, with potential applications in early diagnosis and rehabilitation strategies.