MUMBAI, India, July 13 -- Intellectual Property India has published a patent application (202621059788 A) filed by Indian Institute Of Technology Gandhinagar on May 11, 2026, for System And Method For Channel-Agnostic Representation Learning From Electroencephalogram (eeg) Signals.
Inventors include Sharma, Anupam; Singh, Prajwal; Raman, Shanmuganathan; and Miyapuram, Krishna Prasad.
The application for the patent was published on July 10, 2026, under issue no. 28/2026.
Abstract: ABSTRACT SYSTEM AND METHOD FOR CHANNEL-AGNOSTIC REPRESENTATION LEARNING FROM ELECTROENCEPHALOGRAM (EEG) SIGNALS The present disclosure relates to a system (100) for channel-agnostic representation learning from electroencephalogram (EEG) signals (102). The system (100) receives EEG signals and comprises a spatial mapping module (106) configured to map electrode positions onto a predefined scalp topology, and a map generation module (108) comprising an interpolation engine (109) configured to generate two-dimensional topographical maps. A feature extraction module (110) processes the maps to extract spatio-temporal features, and an output generation module (112) generates classification or neural decoding outputs. An interpretability module (114) provides attribution-based analysis to identify contributing spatial regions. The system enables channel-agnostic processing, preserves spatial relationships, and improves generalization and interpretability.
Disclaimer: Curated by HT Syndication.
