EEG of game players – detecting involvement with and without ICA preprocessing.
Share
Study at a glance
- Area
- Other research
- Study type
- Observational study
- Authors
- GÓRSKI P
- Journal
- PRZEGLĄD ELEKTROTECHNICZNY
- Year
- 2016
- Participants
- 6
- Population
- Adults
- Protocol
- EEG classification with ICA
- Equipment
- BrainMaster Discovery
Key findings
- ICA improved classification at 19, 7 and 3 channels
- Accuracy reached 0.91 with 19 channels after ICA
EEG was recorded from six players during Dota 2 game sessions to classify moments as engaging or boring. Cleaning the data with independent component analysis improved classification accuracy whether 19, 7 or only 3 channels were used.