El profesor Dr. Laurent Bougrainque (Nancy-university (France)Cortex project, INRIA Nancy - Grand Est) realizó una estadía en el Departamento de Ingeniería Biomédica coordinada por el profesor Rodrigo Salas, durante la tercera semana de Abril. El día 18 de Abril realizó una charla titulada: "Brain-Computer Interfaces".
Brain-computer interface (BCI) system is a potentially powerful newcommunication and control option for those with severe motor disabilities. BCIsystem translates brain-activity into commands for a computer or other devices.In other words, a BCI allows users to act on their environment by using onlybrain-activity. The success of this approach depends on close and productiveinteraction of scientists, engineers, and clinicians from many differentdisciplines and requires recognition and attention to a number of crucialissues.Electroencephalography (EEG) is the most studied potential non-invasiveinterface, mainly due to its fine temporal resolution, ease to use, portabilityand low set-up cost. Unfortunately, non-invasive implants produce poor signalresolution because the skull dampens signals, dispersing and blurring theelectromagnetic waves created by the neurons. Although the waves can still bedetected it is more difficult to determine the area of the brain that createdthem or the actions of individual neurons. But as well as the technology'ssusceptibility to noise, another substantial barrier to using EEG as abrain-computer interface is the extensive training required before users canwork the technology. Patterns of P300 waves are generated involuntarily(stimulus-feedback) when people see something they recognize and may allow BCIsto decode categories of thoughts without training patients first. To achievethis challenge we are using a single-trial ERP estimation based on unsupervisedalgorithms.
