MUMBAI, India, Oct. 5 -- Intellectual Property India has published a patent application (202641114576 A) filed by Amrita Vishwa Vidyapeetham on September 24, 2026, for System And Method For Electroencephalography-Based Semantic Assistive Communication Using Semantic Visual Representations.
Inventors include Arunkumar, Akash; A S, Krishnakanth; Najeeb, Mujeeb Rahman; and Surendran, Simi.
The application for the patent was published on October 02, 2026, under issue no. 40/2026.
Abstract: A system (100) and a method (400) for electroencephalography (EEG)-based assistive communication are disclosed. The system (100) includes an electroencephalography acquisition device (102), a memory (104) storing executable instructions and a semantic representation database (132), and a processor (108) configured to receive EEG signals, preprocess the EEG signals, generate a latent neural representation, transform the latent neural representation into a multimodal semantic embedding representing a communicative intent of a user, retrieve one or more semantic representations through similarity-based semantic matching, generate one or more semantic visual representations using a conditional diffusion-based image generation model, and present the generated semantic visual representations through a user interface as a communication output. The present disclosure provides reliable semantic interpretation of EEG signals, improved robustness against signal variability and noise, enhanced semantic consistency during visual representation generation, and compatibility with conventional EEG acquisition systems for assistive communication and neuro-rehabilitation applications.
Disclaimer: Curated by HT Syndication.
