Related Experiment Videos
How many people are able to operate an EEG-based brain-computer interface (BCI)?
C Guger1, G Edlinger, W Harkam
1Guger Technologies OEG, A-8020 Graz, Austria. office@gtec.at
Summary
Healthy individuals achieved over 60% accuracy in a brain-computer interface (BCI) study using imagined movements. This BCI field study demonstrated effective classification with two training sessions.
Area of Science:
- Neuroscience
- Biomedical Engineering
- Human-Computer Interaction
Background:
- Brain-computer interfaces (BCI) offer novel interaction methods.
- Field studies are crucial for evaluating BCI usability in real-world settings.
Purpose of the Study:
- To assess the feasibility and performance of a BCI system in a public exposition setting.
- To evaluate classification accuracy using two different signal processing methods.
Main Methods:
- Ninety-nine healthy participants underwent a two-session BCI investigation.
- Participants imagined right-hand or foot movements to control a horizontal bar.
- Electrodes recorded brain activity over motor cortex areas; adaptive autoregressive and band power models were used for classification.
Main Results:
- Approximately 93% of participants achieved over 60% classification accuracy.
- Performance was evaluated after two training sessions, with and without feedback.
- Both adaptive autoregressive and band power estimation methods were employed.
Conclusions:
- BCI systems can achieve high classification accuracy in healthy individuals after brief training.
- The study demonstrates the potential for BCI applications in public and diverse environments.
- Feasible BCI control was achieved through imagined motor imagery.