Machine-learning techniques for EEG data
In this chapter, we present an introductory overview of machine-learning techniques that can be used to recognize mental states from electroencephalogram (EEG) signals in brain-computer interfaces (BCIs). More particularly, we discuss how to extract relevant and robust information from noisy EEG signals. Due to the spatial properties of the EEG acquisition modality, learning robust spatial filters is a crucial step in the analysis of EEG signals. Optimal spatial filters will help us extract relevant and robust features, helping considerably the subsequent recognition of mental states. Also, a few classification algorithms are presented to assign this information into a mental state. Furthermore, particular care will be given on algorithms and techniques related to steady-state visual evoked potentials (SSVEPs) BCI and sensorimotor rhythms (SMRs) BCI systems. The overall objective of this chapter is to provide the reader with practical knowledge about how to analyze EEG signals.
Machine-learning techniques for EEG data, Page 1 of 2
< Previous page Next page > /docserver/preview/fulltext/books/ce/pbce129e/PBCE129E_ch7-1.gif /docserver/preview/fulltext/books/ce/pbce129e/PBCE129E_ch7-2.gif