Enhancing erp-based brain-computer interfaces for practical applications: asynchrony, deep learning, and a novel bci platform

• Autores: Eduardo Santamaría Vázquez
• Directores de la Tesis: Roberto Hornero Sánchez (dir. tes.)
• Lectura: En la Universidad de Valladolid ( España ) en 2023
• Idioma: inglés
• Tribunal Calificador de la Tesis: José María Azorín Poveda (presid.), Jesús Poza Crespo (secret.), Ana Matrán Fernández (voc.)
• Programa de doctorado: Programa de Doctorado en Tecnologías de la Información y las Telecomunicaciones por la Universidad de Valladolid
• Materias:
  • Psicología
    • Psicología experimental
      • Actividad cerebral
• Enlaces
  • Tesis en acceso abierto en: UVADOC
• Resumen

  • Throughout history, humans have sought ways to break free from the constraints of the body and interact with the world directly through the mind. Brain-computer interfaces (BCIs) represent the realization of this long-standing ambition, allowing individuals to control external devices directly using their brain activity. BCIs measure brain activity using the electroencephalography (EEG), a technique that records the electrical activity of neurons using electrodes placed over the scalp. Then, the EEG is analyzed using signal processing methods to decode users' intentions and translate them into commands that can be used to control external devices. BCIs have great potential in various applications, such as assistive systems for people with motor impairments, augmenting human cognitive abilities, entertainment, and medicine. However, this technology currently faces a number limitations, including low reliability, lack of validation and unsuitable research tools that hinder rapid development of the field. This doctoral dissertation presents a compendium of four publications that propose different strategies to overcome these limitations and promote the development of BCI systems for practical applications, especially in an assistive context. The main topics that were addressed in this research work were the improvement of the asynchronous BCI control, the application of deep learning techniques to increase the accuracy and speed of this technology, and the development of a novel software ecosystem to accelerate BCI and cognitive neuroscience research.