EXPLORING PSD AND MCL BASED DIFFERENTIATION OF ADHD AND MDD USING MULTILAYER PERCEPTRON

Date

2025-7-16

Author

İNAL, ERİS

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

3029
views

0
downloads

Cite This

This thesis investigates the potential of EEG-based features to distinguish between Attention Deficit Hyperactivity Disorder (ADHD) and Major Depressive Disorder (MDD), two conditions that often share overlapping symptoms and neurophysiological characteristics. Focusing on power spectral density (PSD) across frequency bands and mean curve length (MCL) as a complexity measure, the study applies multilayer perceptron (MLP) classifiers to a clinically diverse sample under both eyes open and eyes closed resting state conditions. Delta power emerged as the most informative feature, particularly in the eyes open condition, while MCL features provided weak classification performance. Permutation feature importance (PFI) analyses helped identify which EEG channels most influenced model decisions across conditions. When these importance scores were compared with cluster-corrected F-statistics that performed independently from the classifier, the overlap was limited. This framework offers a structured approach for evaluating EEG-based features in clinical group differentiation and supports future applications in larger or more targeted datasets.

Subject Keywords

Electroencephalogram, attention deficit hyperactivity disorder, major depressive disorder, multilayer perceptron, mean curve length

URI

https://hdl.handle.net/11511/115438

Collections

Graduate School of Informatics, Thesis