MUMBAI, India, Sept. 28 -- Intellectual Property India has published a patent application (202641111296 A) filed by Vellore Institute Of Technology on September 16, 2026, for System And Method For Privacy-Preserving Federated Physiological Modeling Using Digital Twin Synthesis.
Inventors include R Sujatha; Mohammed Kaif K; Gowtham S; and Pravin G.
The application for the patent was published on September 25, 2026, under issue no. 39/2026.
Abstract: The present disclosure proposes a system (100) and method for privacy-preserving federated physiological modeling using dynamic digital twins for decentralized model training while protecting raw physiological data during local processing and model-update transmission. The system (100) comprises a computing device (102), at least one processor (104), a memory (106), a server (108), a network (110), physiological sensing devices (112), and a data buffer (114). The system (100) generates and continuously synchronizes a dynamic digital twin from physiological sensor data, generates synthetic training samples from the dynamic digital twin, and performs local federated training within a Trusted Execution Environment. An integrity verification module (124) generates a Zero-Knowledge Proof for verifying local training integrity. A resource management module (126) adapts processing according to device-resource conditions, and a monitoring module (128) performs predictive physiological simulations and generates local safety alerts.
Disclaimer: Curated by HT Syndication.
