MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202641076904 A) filed by Sr University on June 22, 2026, for An Adaptive Edge Ai Device For Real-Time Cardiac Monitoring.
Inventors include Shravanchandra G; and Dr. Santosh Kumar Henge.
The application for the patent was published on July 03, 2026, under issue no. 27/2026.
Abstract: AN ADAPTIVE EDGE AI DEVICE FOR REAL-TIME CARDIAC MONITORING The invention discloses an adaptive edge AI device for real-time cardiac monitoring that integrates multimodal sensing, adaptive inference, federated learning, and digital twin synchronization. The device acquires electrocardiogram (ECG), photoplethysmogram (PPG), and accelerometer signals through a multimodal sensor interface, with a pre-processing module suppressing motion artifacts. An inference engine supports two modes: a quantized convolutional neural network (CNN) for low-power operation and a CNN–long short-term memory (CNN–LSTM) for high- accuracy temporal analysis. A context-aware controller dynamically switches between inference modes based on patient risk, signal quality, and device energy state. A federated learning client enables collaborative model training with adaptive differential privacy and secure aggregation. A digital twin synchronization interface transmits compressed morphological and temporal descriptors of anomalies, reducing bandwidth while maintaining clinical relevance. The device achieves latency below 150 milliseconds and power consumption under 2 watts, making it suitable for continuous, secure, and efficient cardiac monitoring in wearable applications.
Disclaimer: Curated by HT Syndication.
