Electroencephalogram Signal Analysis for Impulsivity Detection in Drug User Using K- Nearest Neighbor

Sitanggang, Delima (Faculty of Science and Technology, Universitas Prima Indonesia, Medan, Indonesia)
Siahaan, Michael (Faculty of Science and Technology, Universitas Prima Indonesia, Medan, Indonesia)
Tampubolon, Mertfil (Faculty of Science and Technology, Universitas Prima Indonesia, Medan, Indonesia)
Ginting, Erdani Agustina (Faculty of Science and Technology, Universitas Prima Indonesia, Medan, Indonesia)
Turnip, Mardi (Faculty of Science and Technology, Universitas Prima Indonesia, Medan, Indonesia)

Zero : Jurnal Sains, Matematika, dan Terapan
Vol 9, No 2 (2025): Zero: Jurnal Sains Matematika dan Terapan

Drug abuse disrupts normal brain activity and contributes to recurrent impulsive behaviors. While various machine learning approaches have been investigated for analyzing brain signals, studies focusing on the use of the K-Nearest Neighbor (KNN) method for impulsivity detection in drug users remain limited. In this research, KNN was implemented to classify Electroencephalography (EEG) signals based on neuroelectric features that reflect impulsive tendencies. EEG recordings were collected from individuals with a history of drug use while performing cognitive tasks designed to trigger impulsive responses and were compared with recordings from a healthy control group. The classification results showed that KNN achieved an accuracy of 95% in identifying neural patterns associated with impulsivity. This work introduces a novel application of EEG analysis integrated with KNN for objective and precise detection of impulsivity in drug users. The findings highlight the potential of this approach to serve as a supportive tool in rehabilitation programs through reliable neuropsychological monitoring.