MUMBAI, India, Nov. 2 -- Intellectual Property India has published a patent application (202641126784 A) filed by M M Asha; Dr. G. Asha; Dr. Y. Sreeraman; Dr. D. Jagadeesan; Dr. Thanga Prasath S; Ms. Sreekanth Nimitha; and Joshitha Gopal Krishna on October 24, 2026, for Quantum-Ai Enabled Multi-Agent Healthcare Monitoring And Emergency Response Device.
Inventors include M M Asha; Dr. G. Asha; Dr. Y. Sreeraman; Dr. D. Jagadeesan; Dr. Thanga Prasath S; Ms. Sreekanth Nimitha; and Joshitha Gopal Krishna.
The application for the patent was published on October 30, 2026, under issue no. 44/2026.
Abstract: The present invention relates to a cloud-based federated learning system for communication-efficient distributed model training. The system enables multiple client devices to collaboratively train a global machine learning model without sharing raw data, thereby preserving data privacy. The invention introduces a reinforcement learning-based adaptive client selection mechanism that evaluates device-specific parameters including computational capability, network bandwidth, communication latency, dataset characteristics, and energy availability. Based on these parameters, an optimization engine dynamically selects an optimal subset of client devices for each training round. The proposed system reduces communication overhead, improves resource utilization, and accelerates model convergence. The system supports both synchronous and asynchronous training modes and is suitable for large-scale distributed environments such as mobile networks, Internet of Things (IoT) systems, and edge computing platforms.
Disclaimer: Curated by HT Syndication.
