Brain Robot Interface

Brain Robot Interface

1. BCI

   • EEG DAQ
     • 64 electrodes
     • Scan for bad electrodes
   • MVPC
     • Multivariate Pattern Classification. The system for learning to classify samples of EEG data
     • Training
       • Training the classifier on samples of data to recognize new samples with unknown class
     • Testing
       • Presenting samples of unknown class to the MVPC and see the performance, i.e. the accuracy of the classifier.
     • Gaussian Units
       • neural network with gaussian prototypes
     • SVM
       • Support Vector Machine, with kernel trick
     • LDA
       • Fisher's Linear Discriminant Analysis 
   • Pre-processing
     • Feature Selection
       • The Power Spectral Density is estimated within frequency bands and presented as features.
     • Spatial Filter
       • Surface Laplacian or fit to single dipole
     • Bandpass filter
       • 1-48Hz or narrower
       • "only HP-filter continuous data"
         • comment from Mike x Cohan's book neural ....

2. Report

3. Test Environment

4. Robot Control

   • Direct
   • Shared
   • Regularized
   • Robot Manoeuvering

Bilder und Dateien der Mindmap