Publications

Kolmogorov-Arnold Networks for Alzheimer's Disease Detection using Multimodal Speech Analysis

IEEE EMBC 2026

Emiliano Garcia, Emad A. Mohammed

A frozen-encoder multimodal architecture with lightweight FKF classifier heads achieved 0.8556 ± 0.0382 macro-F1 and 0.9220 ± 0.0295 ROC-AUC using learned late fusion.

Analyzing Coronavirus Cough Sounds and Alzheimer's Speech with Deep Learning Models to Discover Common Patterns

Coming Soon

IEEE EMBC 2026

Emad A. Mohammed, Salma J. Ahmed, Emiliano Garcia Ochoa, Behrouz H. Far, Amir Sanati Nezhad

A shared 2D audio-analysis framework found representation-level proximity between Alzheimer's speech and COVID-19 cough samples; a weighted CNN ensemble reached 73% accuracy and 72% macro-F1 for AD detection.