Intellectual Property India Publishes Patent Application for 'A System And Method For Mental State Classification Using Single-Channel Eeg Signals In Minimalist Brain-Computer Interface Systems' Filed by Sr University

MUMBAI, India, May 1 -- Intellectual Property India has published a patent application (202641050100 A) filed by Sr University, Warangal, Telangana, on April 20, for 'a system and method for mental state classification using single-channel eeg signals in minimalist brain-computer interface systems.'

Inventor(s) include Padakanti Swapna; and Ravichander Janapati.

The application for the patent was published on May 1, under issue no. 18/2026.

According to the abstract released by the Intellectual Property India: "A robust deep learning framework for mental state classification using single-channel electroencephalography (EEG) signals, addressing the challenge of information scarcity in minimalist brain-computer interface (BCI) systems. Conventional EEG-based systems rely on multi-channel configurations, increasing complexity, cost, and limiting real-time usability. The proposed framework utilizes a single-channel EEG acquisition setup combined with advanced preprocessing techniques, including noise filtering, normalization, and signal segmentation, to enhance data quality. A hybrid deep learning architecture integrating convolutional neural networks and recurrent neural networks is employed to extract spatial and temporal features effectively. To overcome limited data availability, intelligent data augmentation and synthetic signal generation methods are incorporated, improving model robustness and generalization. The framework further integrates transfer learning to enhance adaptability across diverse users and environments. Optimized for real-time processing, the system ensures low latency and efficient performance on wearable and embedded devices. The proposed solution enables accurate classification of cognitive and emotional states such as stress, attention, and relaxation. Overall, the invention provides a scalable, cost-effective, and efficient approach for real-time mental state monitoring, advancing applications in healthcare, neurofeedback, and human-machine interaction."

Disclaimer: Curated by HT Syndication.