P300 EEG detection

Where

Zine Research Lab, NIT Jaipur

Objective

EEG or Electroencephalogram refers to recordings of electrical activity in the brain. P300 is a unique signal elicited by the brain on receiving a specific stimulus. It is most commonly known for being used as a EEG based speller, where the user can, simply with his focus, spell a word. Our objective was to recognize P300 event related potential in raw EEG generated while a user experiences the P300 speller.

P300 Target Potential

Methodology

We applied signal processing based feature extraction, which was fed to a linear classifier ensemble. We experimented with the following significant types of features:

  1. Time-Series features
  2. Frequency-Series features
  3. Wavelet features
  4. Statistical and Experiment related features

and a few more… Finally since the EEG data consisted of a lot of data to work with, we ended up with a large variety and quantity of features to experiment with. To enable modular organization, fast code execution and stacked feature vectors we setup a framework which utilises caching, parallel computing and modularity.

Results

  1. Accuracy of 97% at ideal training interval.
  2. Complete framework for future research usage.

Publication

Saatvik Shah,Anirudha Kumar and Rajesh Kumar. “A Robust framework for optimum feature extraction and recognition of P300 from raw EEG.” Neural Computing and Applications, 2015(Under Review) URL

Code@Github

Framework Block Diagram