MUMBAI, India, April 17 -- Intellectual Property India has published a patent application (202641043726 A) filed by Sr University, Warangal, Telangana, on April 6, for 'advanced self-supervised deep learning architectures for robust artifact suppression in non-stationary eeg signals.'
Inventor(s) include Dr. B. Paulchamy; Dr. Sandip Bhattacharya; Mr. Abdul Hayum; Dr. A. Purushothaman; Mr. R. Karuppusamy; Dr. K. Mahedndrakan; and Dr. Sudip Bhattacharya.
The application for the patent was published on April 17, under issue no. 16/2026.
According to the abstract released by the Intellectual Property India: "The present invention relates to advanced self-supervised deep learning architectures for robust artifact suppression in non-stationary electroencephalogram (EEG) signals. The proposed system utilizes a self-supervised learning framework that learns meaningful representations directly from raw EEG data without requiring large labeled datasets. The architecture integrates signal preprocessing, feature extraction, and deep neural network models to detect and suppress artifacts caused by eye movements, muscle activity, motion disturbances, and power line interference. The system preserves essential neural information while improving the signal-to-noise ratio and overall quality of EEG recordings. The cleaned EEG signals can be utilized for various applications including brain-computer interface systems, neurological diagnosis, cognitive monitoring, and wearable brain sensing devices. The proposed framework improves adaptability across different subjects and recording environments and enables reliable EEG signal analysis under non-stationary conditions."
Disclaimer: Curated by HT Syndication.
