Real-time classification of attended source with EEG and EarEEG brain-computer interface
||Real-time classification of attended source with EEG and EarEEG brain-computer interface|
||Emina Alickovic <firstname.lastname@example.org>|
||2018-11-01 – 2023-11-01|
TITLE: Real-time classification of attended source with EEG and EarEEG brain-computer interface
In this project, we work developing new techniques grounded on the model-based learning (model fitting) to select the attended voice (AV) from multiple sound streams. This project has started in 2015, and we aim at running it for one year more. This project is a collaboration between Linkoping University and Eriksholm (Independent Research center of the hearing aid manufacturer Oticon). The long-term goal of this project would be to evaluate the developed techniques on hearing impaired subjects, and to develop objective measures to evaluate hearing aids and to develop a prosthesis that amplifies only AV. Here we focus on different modelling approaches applied on full-scalp EEG and wearable EEG (EarEEG) data. We aim at designing design models with high performances using advanced machine learning algorithms, what requires an extensive experimentation with data utilities ranging from data collection and storage (in huge volumes) to data analysis. It is computationally expensive to assess our model(s) on the standard laptops. To make the calculations for ONE sound stream of 120 minutes (40 trials, each 3 minutes long) and to process more than 1000 different combinations require approximately 150 hours of computing on an ordinary laptop. And we need to process a greater number of different combinations of shorter sounds and the same procedure needs to be repeated for 30 (or more) subjects that would therefore need our computers to run for several months. We need a faster turn-around time and therefore we are seeking this supercomputer opportunity. We have already used Super Computer for two years (November 2016- October 2018), and would like to continue using it for one additional year, to ensure having successful project completion.