MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202541132865 A) filed by Dr. Udit Narayana Kar; Dr. Sambi Reddy Gottam; Dr. Asish Kumar Dalai; Vrishank Raina; Vishwanath Tiwari; Argha Saha; Priyanshu Upadhyay; and Raushan Shrivastwa, Amaravati, Andhra Pradesh, on Dec. 29, 2025, for 'swift medi link - system and method for real-time healthcare.'
Inventor(s) include Dr. Udit Narayana Kar; Dr. Sambi Reddy Gottam; Dr. Asish Kumar Dalai; Vrishank Raina; Vishwanath Tiwari; Argha Saha; Priyanshu Upadhyay; and Raushan Shrivastwa.
The application for the patent was published on Jan. 9, under issue no. 02/2026.
According to the abstract released by the Intellectual Property India: "The proposed invention introduces a drift-aware continual learning system designed for real-time IoT environmental and industrial monitoring using a lightweight TinyML-based multilayer perceptron integrated with Elastic Weight Consolidation (EWC). The system processes continuous sensor streams and identifies concept drift through adaptive statistical detection methods, enabling selective model updates only when necessary. By combining a compact neural network architecture with EWC's parameter-importance preservation, the invention mitigates catastrophic forgetting and ensures stable performance in non-stationary environments. The solution is optimized for resource-constrained microcontrollers, offering low latency inference, minimal energy consumption, and memory-efficient operation. It supports diverse IoT applications including air-quality assessment, industrial fault detection, and anomaly classification while enabling long-term autonomous adaptation. The invention enhances reliability, accuracy, and sustainability in IoT deployments, making it ideal for edge intelligence systems requiring continual learning under dynamic real-world conditions."
Disclaimer: Curated by HT Syndication.
