دانشگاه آزاد اسلامی واحد تهران جنوب

صفحه اصلی / نخستین همایش هوش مصنوعی و پژوهش های نوظهور: همگرایی انسان و سیستم های هوشمند

Using Deep Pyramid CNN for Early Detection of Alzheimer’s Disease

نویسندگان :

Saba Haji Molla Rabie¹ Sedigheh Ghofrani² Mahdi Eslami³ Hamideh Barghamadi⁴

1- دانشجوی دانشگاه آزاد اسلامی واحد تهران جنوب 2- دانشیار دانشگاه آزاد اسلامی واحد تهران جنوب 3- دانشگاه آزاد اسلامی واحد علوم و تحقیقات تهران 4- هیئت علمی دانشگاه آزاد اسلامی واحد تهران جنوب

کلمات کلیدی :

Empirical Wavelet Transform،Empirical Fourier Decomposition،Deep Pyramid Convolutional Neural Network،Alzheimer’s Disease

چکیده :

This study proposes a deep learning framework for early Alzheimer’s disease (AD) detection using EEG signals, leveraging a novel feature extraction method, Empirical Fourier Decomposition (EFD). EEG data from 100 subjects, including AD, mild cognitive impairment (MCI), and healthy controls (HC), were analyzed. Frequency-domain features extracted via EFD were compared with those from the Empirical Wavelet Transform (EWT). A 16-coefficient feature vector, based on prior research, was used, and data were augmented through an overlapping sliding window technique. Classification with a Deep Pyramid Convolutional Neural Network (DPCNN) achieved 98.29% accuracy, 98.28% sensitivity, and 99.14% specificity. Results demonstrate EFD’s effectiveness over EWT in capturing discriminative EEG patterns, highlighting its promise for early and accurate AD diagnosis.