MUMBAI, India, July 13 -- Intellectual Property India has published a patent application (202641068379 A) filed by Vellore Institute Of Technology on May 27, 2026, for System And Method For Noise-Conditioned Wavelet-Temporal-Graph Fusion For Explainable Multi-Class Ecg Arrhythmia Analysis.
Inventors include Deepa; Sandeep S; Pasala Hem Chand Reddy; and Parakoti Karthik Kumar.
The application for the patent was published on July 10, 2026, under issue no. 28/2026.
Abstract: The present disclosure proposes a system (100) capable of classifying multiple arrhythmia categories from segmented ECG beats or short ECG signal windows using a unified multi-branch analytical framework. The system (100) comprises a computing device (102) having a processor (104) and a memory (106) for storing one or more machine-readable instructions executable by the processor (104). The processor (104) is configured to execute plurality of modules (108) for explainable multi-class classification under variable signal conditions. The plurality of modules (108) comprises an acquisition and pre-processing module (110), a wavelet-based multi- resolution feature extraction module (112), a temporal rhythm modeling module (114), a graph-based relational reasoning module (116), a noise-quality estimation module (118), a noise-conditioned adaptive fusion module (120), a classification module (122), and an explainability and confidence reporting module (124). The proposed system (100) is configured to estimate signal quality and noise characteristics including artifact presence, baseline instability, and waveform reliability.
Disclaimer: Curated by HT Syndication.
