Brain–Computer Interfaces - Index of

Digital Signal Processing and Machine Learning
Yuanqing Li, Kai Keng Ang, and Cuntai Guan
Any brain–computer interface (BCI) system must translate signals from the users
brain into messages or commands (see Fig. 1). Many signal processing and machine
learning techniques have been developed for this signal translation, and this chapter
reviews the most common ones. Although these techniques are often illustrated
using electroencephalography (EEG) signals in this chapter, they are also suitable
for other brain signals.
This chapter first introduces the architecture of BCI systems, followed by signal
processing and machine learning algorithms used in BCIs. The signal processing
sections address data acquisition, followed by preprocessing such as spatial and
temporal filtering. The machine learning text primarily discusses feature selection
and translation. This chapter also includes many references for the interested reader
on further details of these algorithms and explains step-by-step how the signal
processing and machine learning algorithms work in an example of a P300 BCI.
The text in this chapter is intended for those with some basic background in
signal processing, linear algebra and statistics. It is assumed that the reader understands
the concept of filtering, general eigenvalue decomposition, statistical mean
and variance.
1 Architecture of BCI systems
A brain–computer interface (BCI) allows a person to communicate or to control a
device such as a computer or prosthesis without using peripheral nerves and muscles.
The general architecture of a BCI system is shown in Fig. 1, which includes 4
stages of brain signal processing:
Data acquisition: Brain signals are first acquired using sensors. For example, the
electroencephalogram (EEG) measures signals acquired from electrodes placed on
the scalp, as shown in Fig. 1. These signals are then amplified and digitalized by
Y. Li (B)
School of Automation Science and Engineering, South China
University of Technology, Guangzhou, China, 510640
e-mail: auyqli@scut.edu.cn
B. Graimann et al. (eds.), Brain–Computer Interfaces, The Frontiers Collection,
DOI 10.1007/978-3-642-02091-9_17, C○ Springer-Verlag Berlin Heidelberg 2010
305