Muath Alali

Dr. Muath Alali


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 March 2025 in SN Computer Science
Verified
Journal Article
Closed access
PDF file
QBQusay Bsoul
Qusay Bsoul
FZFiras Hanna Zawaideh
Firas Hanna Zawaideh
BABasma S. Alqadi
Basma S. Alqadi
LALatifa Abdullah Almusfar
Latifa Abdullah Almusfar
Osamah IbrahimOsamah Ibrahim
Osamah Ibrahim
DSDiaa Salama
Diaa Salama

12 October 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
Chayut BunterngchitChayut Bunterngchit
Chayut Bunterngchit
LLaith H. Baniata
Laith H. Baniata
MBMohammad H. Baniata
Mohammad H. Baniata
JAJaffar Muneer Atwan
Jaffar Muneer Atwan
MAMuath Alali
Muath Alali
Sangwoo KangSangwoo Kang
Sangwoo Kang
Electroencephalography (EEG) records cortical activity with high temporal resolution without radiation and at low cost, which makes it a practical signal for automated screening of neurological disorders. Deep learning classifies EEG with high accuracy, but most models distinguish only two conditions and give no account of their decisions, which limits their use in screening and decision support. This paper presents SpectraXAI, an interpretable frequency-aware deep learning model that assigns resting-state EEG to four diagnostic categories: Alzheimer’s disease, Parkinson’s disease, schizophrenia, and healthy control. The model filters each EEG window into the delta, theta, alpha, beta, and gamma bands and processes every band in a separate convolutional branch with squeeze-and-excitation recalibration. Softmax-weighted band attention and temporal attention then combine the spectral and temporal evidence, and the same attention weights are intrinsic explanations of each prediction. Under a subject-disjoint evaluation protocol that prevents window leakage, the model reached 94.43% accuracy, 96.74% balanced accuracy, and 93.82% macro-F1 on 20,760 windows from 173 unseen subjects while using only 0.10 million parameters. An ablation study confirmed that the attention modules account for most of the improvement over a plain convolutional baseline. Attention weights, feature-attention heatmaps, Grad-CAM, and t-SNE embeddings trace each decision to specific frequency bands, time segments, and learned features, therefore the frequency structure that drives the accuracy also makes the predictions inspectable.