Biometric authentication of ADHD individuals using signal processing and 1D-CNN approaches on frontal lobe eeg signals

This thesis explores the significance of biometric recognition systems in security applications and examines the limitations of traditional methods. Within the scope of cognitive biometrics, the utilization of biosignals derived from the nervous system is addressed. Specifically, electroencephalography (EEG) signals have emerged as a preferred choice for biometric recognition due to the affordability and user-friendliness of modern devices. However, current EEG-based systems face challenges related to ergonomic design and signal quality. This study investigates EEG-based biometric authentication methods in individuals with Attention Deficit Hyperactivity Disorder (ADHD). By utilizing EEG data collected from the frontal lobe of ADHD individuals, a biometric authentication model was developed through the application of signal processing and deep learning techniques. The results demonstrate the feasibility of using EEG signals for biometric authentication in individuals with ADHD. This work makes a significant contribution to the limited body of literature on biometric recognition in ADHD populations. For future research, the use of larger datasets and advanced devices is recommended to further enhance the reliability and applicability of EEG-based biometric systems.