Brainloop

4. BCI - Brain–computer interfaces
	4.1. Definition and features of a BCI   4.1.3. The parts of a BCI   4.1.3.2. Signal processing: feature extraction

The digitized signals are then subjected to one or more of a variety of feature extraction procedures, such as:

1) spatial filtering
2) voltage amplitude measurements
3) spectral analyses
4) single-neuron separation.

This analysis extracts the signal features that encode the user’s messages or commands. BCIs can use signal features that are in the time domain (e.g. evoked potential amplitudes or neuronal firing rates) or the frequency domain (e.g. mu or beta rhythm amplitudes).

A BCI could conceivably use both time-domain and frequency-domain signal features, and might thereby improve performance.

In general, the signal features used in present-day BCIs reflect identifiable brain events like:

1) the firing of a specific cortical neuron
or
2) the synchronized and rhythmic synaptic activation in sensorimotor cortex that produces a mu rhythm.

4. BCI - Intro
	4.1. Definition and features of a BCI   4.1.1. Dependent and independent BCIs 4.1.2. BCI use is a skill 4.1.3. The parts of a BCI   4.1.3.1. Signal acquisition 4.1.3.2. Signal processing: feature extraction 4.1.3.3. Signal processing: the translation algorithm 4.1.3.4. The output device 4.1.3.5. The operating protocol 4.2. Present-day BCIs   4.2.1. Visual evoked potentials 4.2.2. Slow cortical potentials 4.2.3. P300 evoked potentials 4.2.4. Mu and beta rhythms   4.2.4.1. The Wadsworth BCI 4.2.4.2. The Graz BCI 4.2.5. Cortical neuronal action potentials 4.3. The future of BCI-based communication

---

Source: Brain–computer interfaces for communication and control, Clinical Neurophysiology 113 (2002) 767–791, Jonathan R. Wolpaw, Niels Birbaumer, Dennis J. McFarland, Gert Pfurtscheller, Theresa M. Vaughan