MUMBAI, India, Oct. 5 -- Intellectual Property India has published a patent application (202641107525 A) filed by Cochin University Of Science And Technology Cusat on September 07, 2026, for Multimodal Artificial Intelligence-Based System For Early Detection Of Autism Spectrum Disorder And Its Method Thereof.
Inventors include Dr. Tinu Varghese; Dr. Sabu Mk; Dr. Soumya Sundaram; and Dr. Neena Shilen.
The application for the patent was published on October 02, 2026, under issue no. 40/2026.
Abstract: The present invention generally relates to a system and method for early detection of autism spectrum disorder (ASD). The system comprises a sensing node (102) to collect localized brain wave signals, tri-axial acceleration and gyroscopic motion signals, spatial gaze coordinates, and continuous electrocardiogram signals from a subject. A synchronization processing unit (104) temporally aligns these heterogeneous signals using a real-time clock to establish coherent signal streams. A feature extraction unit processes these streams to extract spectral density, motion periodicity, spatial fixation density, and cardiac metrics. A multimodal classification unit (108) concatenates these features into a unified multidimensional matrix, leveraging multiple classification processors and self-attention mechanisms to map spatial, temporal, and long-range inter-modal dependencies, and computing a unified classification probability score indicating neurodevelopmental markers. Additionally, an attribution generation processing unit (112) calculates proportional analytical contribution metrics for each signal type using gradient-based dependency weights to isolate physiological causality.
Disclaimer: Curated by HT Syndication.
