Brainloop

8. Direct Brain–Computer Communication
	8.3. Components of graz BCI   8.3.1. Parameter Estimation and Classification

One part of EEG-based brain–computer interfaces (BCI) is based on the recording and classification of circumscribed and transient EEG changes during different types of motor imagery such as, e.g., imagination of left-hand, right-hand, or foot movement.

Characteristic for the Graz BCI is that a classifier is set up in a learning session and updated after one or more sessions with online feedback using the procedure of "rapid prototyping."

As a result, a discrimination of two brain states (e.g., left- versus right-hand movement imagination) can be reached within only a few days of training. At this time, a tetraplegic patient is able to operate an EEG-based control of a hand orthosis with nearly 100% classification accuracy by mental imagination of specific motor commands.

8. Direct Brain–Computer Communication
	8.1. A short overview of EEG-based BCI systems 8.2. Neurophysiological considerations   8.2.1. Dynamics of Brain Oscillations 8.2.2. Motor Imagery 8.3. Components of graz BCI   8.3.1. Parameter Estimation and Classification   8.3.1.1. Band Power Estimates 8.3.1.2. Adaptive Autoregressive Model 8.3.1.3. Common Spatial Patterns 8.3.1.4. Hidden Markov Model 8.3.2. Hardware–Software Requirements
	8.4. Man–Machine Learning Dilemma (MMLD)
	8.5. Visual target stimulus modifying the EEG

---

Source: Motor Imagery and Direct Brain–Computer Communication, Gert Pfurtscheller and Christa Neuper