PFT: A Novel Time-Frequency Decomposition of BOLD fMRI Signals for Autism Spectrum Disorder Detection

Diagnosing Autism spectrum disorder (ASD) is a challenging task for clinicians due to the inconsistencies in existing medical tests. The Internet of things (IoT) has been used several applications realize advancements healthcare industry. Using machine learning tandem IoT can enhance monitoring and detection ASD. To date, most ASD studies have relied primarily on operational connectivity structural metrics fMRI data processing while neglecting temporal dynamics components. Our research proposes Progressive Fourier Transform (PFT), novel time-frequency decomposition, together with Convolutional Neural Network (CNN), as preferred alternative available systems. We use Brain Imaging Data Exchange dataset model validation, demonstrating better results proposed PFT compared models, including an increase accuracy 96.7%. These show that technique capable analyzing rs-fMRI from different brain diseases same type.