Investigation of EEG signals generated using imagined speech for application in BCIs

• Grant number: 23/02705-3
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: May 01, 2023
• End date: April 30, 2024
• Field of knowledge: Physical Sciences and Mathematics - Physics
• Principal Investigator: Gabriela Castellano
• Grantee: Eduardo Abreu da Silva
• Host Institution: Instituto de Física Gleb Wataghin (IFGW). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Associated research grant: 13/07559-3 - BRAINN - The Brazilian Institute of Neuroscience and Neurotechnology, AP.CEPID

Abstract

Brain-Computer Interface (BCI) is a system that uses brain signals to manage external devices, without utilizing the natural outputs of the Central Nervous System, such as muscle control by peripheral nerves. These systems capture, process, and translate brain activity into commands that operate an application (for example, a keyboard, or a robotic arm). By providing a completely new output pathway, this technology has been exploited to assist and rehabilitate patients suffering from severe motor disabilities, such as victims of amyotrophic lateral sclerosis (ALS) and stroke, so that they can express themselves and interact with the environment. Electroencephalography (EEG) has been the most used technique in BCI systems to record brain activity. To generate the signals captured by the EEG, different strategies have been employed; one of them is the imagination of speech (IS, from inner speech). IS consists of the mental rehearsal of a verbal task without its actual execution, allowing, in theory, a BCI based on this paradigm to be controlled according to the user's wishes. However, the brain signals resulting from IS are highly variable and difficult to classify. This project aims to investigate the brain response of users during IS, analyzing an EEG signal database where healthy volunteers were asked to imagine speaking one of four words ("arriba", "abajo", "derecha", "izquierda"). The objective is to identify the patterns associated with this task, evaluating the relationship between the signals from different channels using functional connectivity. The project will be carried out within the framework of the "Brazilian Institute of Neuroscience and Neurotechnology" CEPID (BRAINN) of FAPESP.