Journal of Electronics, Electromedical Engineering, and Medical Informatics
Vol 6 No 4 (2024): October

Unlocking Early Detection and Intervention Potential: Analyzing Visual Evoked Potentials (VEPs) in Adolescents/Teenagers with Narcotics Abuse Tendencies from the TelUnisba Neuropsychology EEG Dataset (TUNDA)

Wijayanto, Inung (Unknown)
Sulistyo, Tobias Mikha (Unknown)
Nur Pratama, Yohanes Juan (Unknown)
Safitri, Ayu Sekar (Unknown)
Rahmaniar, Thalita Dewi (Unknown)
Sa’idah, Sofia (Unknown)
Hadiyoso, Sugondo (Unknown)
Wibowo, Raiyan Adi (Unknown)
Kurnia Ismanto, Rima Ananda (Unknown)
Putri, Athaliqa Ananda (Unknown)
Khasanah, Andhita Nurul (Unknown)
Diliana, Faizza Haya (Unknown)
Azzahra, Salwa (Unknown)
Gadama, Melsan (Unknown)
Utami, Ayu Tuty (Unknown)



Article Info

Publish Date
16 Sep 2024

Abstract

Narcotics abuse has extensive negative impacts on individuals, families, and society, including physical harm to organs and mental health disorders. Addressing teenage narcotics problems requires collaborative efforts involving educational institutions, families, and psychologists. Currently, narcotics has increasingly targeted teenagers, becoming a serious issue that demands special attention in prevention and treatment. Handling narcotic problems at the adolescent level necessitates close collaboration among educational institutions, families, and the community, including psychologists. Emphasizing the importance of early detection and prevention, this study proposes a method to detect the possibility of narcotic abuse in adolescents using the Go/No-Go Association Task (GNAT) test designed by psychologists. The study introduced the TelUnisba Neuropsychology EEG Dataset (TUNDA), an open EEG dataset with data on the emotional and habitual aspects of drug abuse in Indonesia, classified into "normal" and "risk" by psychologists. The processed EEG signal is the visual evoked potential (VEP) within 1000 milliseconds following the visual stimulus onset. The data is classified as “slow” and “fast” based on respondent's responses using MobileNetV2 architecture. Results showed MobileNetV2 achieved the highest accuracy for both normal and risk categories, with accuracies of 0.86 and 0.85 respectively. This study obtained ethical clearance and received funding support from Telkom University and Universitas Islam Bandung, with technical assistance from the Smart Data Sensing Laboratory. The authors declare no conflicts of interest related to this study.

Copyrights © 2024






Journal Info

Abbrev

jeeemi

Publisher

Subject

Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering

Description

The Journal of Electronics, Electromedical Engineering, and Medical Informatics (JEEEMI) is a peer-reviewed open-access journal. The journal invites scientists and engineers throughout the world to exchange and disseminate theoretical and practice-oriented topics which covers three (3) majors areas ...