Application of convolutional neural networks for EEG signals classification in brain-computer interfaces

Abstract

Brain-Computer Interfaces (BCI) has been subject of great attention for its potential applications in a myriad of contexts, for example, in assistive, rehabilitation and entertainment technologies. Significant advances, like collecting data with non-invasive methods by means of electroencephalograms (EEG), motivates the study and development of this promising interface. However, the broad variability of patterns observed in users of BCI, and its application in increasing sophisticated contexts, makes its use a very challenging problem. In this sense, this research project aims at applying Artificial Neural Networks for improvement of BCI systems, making them more efficient and robust. More specifically, we will focus on Convolutional Neural Networks, an Artificial Neural Network for Deep Learning with great potential for multidimensional data processing, like images and videos. In order to explore the full potential of this structure, a number of types of EEG patterns mappings will be used for building an input profile for the Neural Network.