MUMBAI, India, Sept. 12 -- Intellectual Property India has published a patent application (202411012631 A) filed by Bennett University, Greater Noida, Uttar Pradesh, on Feb. 22, 2024, for 'machine learning for improving accuracy of brain-computer interface system.'
Inventor(s) include Prof. Arpit Bhardwaj; and Prof. Ajith Abraham.
The application for the patent was published on Sept. 12, under issue no. 37/2025.
According to the abstract released by the Intellectual Property India: "The disclosed system and method aim to improve the accuracy of a brain-computer interface (BCI) system. The system comprises modules for data acquisition, pre-processing, feature extraction, machine learning, output control, and feedback. Brain signals are collected using various sensors such as EEG, MEG, intracortical microelectrode arrays, or NIRS. Pre-processing techniques including spatial and temporal filtering, artifact removal, and signal amplification are applied. Relevant features are extracted from the pre-processed brain signals using methods like time-domain or frequency-domain analysis. Machine learning algorithms such as SVM, ANN, deep learning, decision trees, or ensemble methods classify and predict user intentions. Control commands are generated based on the classified intentions for devices like prosthetic limbs, robots, virtual reality environments, or computer systems. Real-time feedback is provided to the user, and the machine learning model is updated based on user performance, resulting in a more accurate and efficient BCI system. The method involves acquiring, pre-processing, extracting features, classifying, generating commands, providing feedback, and calibrating the system through training sessions."
Disclaimer: Curated by HT Syndication.
