Professional Documents
Culture Documents
Summary
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
Outline
Motivation Source types in EEG based BCI Automatic Feature Selection Learning Spatial Features Feature selection as Model Selection Spectral/Temporal Filtering
kyb-logo
mc-logo
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
Current BCI use learning in two distinct phases, 1. Feature Extraction where we attempt to extract features which lead to good classier performance, 2. Classication usually a simple linear classier, (SVM, LDA, Gaussian), because Once we have good features the classier doesnt really matter
kyb-logo mc-logo
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
Current BCI use learning in two distinct phases, 1. Feature Extraction where we attempt to extract features which lead to good classier performance, using,
prior-knowledge, the 7-30Hz band for ERDs maximising r-scores, maximising independence (ICA) maximising the ratios of the class variances (CSP)
2. Classication usually a simple linear classier, (SVM, LDA, Gaussian), because Once we have good features the classier kyb-logo doesnt really matter
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
mc-logo
MPI Tbingen
Motivation
Summary
Current BCI use learning in two distinct phases, 1. Feature Extraction where we attempt to extract features which lead to good classier performance, 2. Classication usually a simple linear classier, (SVM, LDA, Gaussian), because Once we have good features the classier doesnt really matter
kyb-logo mc-logo
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
A Better approach
1. Combine the feature extraction and classier learning 2. Choose features which optimise the classiers objective We show how to learn spatio-spectro-temporal feature extractors for classifying ERDs using the max-margin criterion1
kyb-logo 1 We have also successfully applied this approach to LR and GP classiers and MRP/P300 temporal signals)
mc-logo
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
A Better approach
1. Combine the feature extraction and classier learning 2. Choose features which optimise the classiers objective We show how to learn spatio-spectro-temporal feature extractors for classifying ERDs using the max-margin criterion1
kyb-logo 1 We have also successfully applied this approach to LR and GP classiers and MRP/P300 temporal signals)
mc-logo
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
A Better approach
1. Combine the feature extraction and classier learning 2. Choose features which optimise the classiers objective We show how to learn spatio-spectro-temporal feature extractors for classifying ERDs using the max-margin criterion1
kyb-logo 1 We have also successfully applied this approach to LR and GP classiers and MRP/P300 temporal signals)
mc-logo
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
Raw data is dxT time-series for N trials ROC-ogram : time vs. frequency vs. ROC score for each channel allows us to identify where the discriminative information lies
kyb-logo
mc-logo
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
kyb-logo
mc-logo
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
kyb-logo
mc-logo
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
kyb-logo
mc-logo
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
kyb-logo
mc-logo
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
kyb-logo
mc-logo
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
kyb-logo
mc-logo
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
kyb-logo
mc-logo
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
Start by showing how to learning spatial lters with the max-margin criteria, Then extend to learning spatial+spectral+temporal
kyb-logo
mc-logo
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
Spatial Filtering
Volume Conduction electrodes detect superposition of signals from all over the brain X = AS Spatial ltering undoes this superposition to re-focus on discriminative signals y = fs X This is a Blind Source Separation (BSS) problem many algorithms available to solve this problem In BCI commonly use a fast, supervised method called kyb-logo Common Spatial Patterns [Koles 1990]
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
mc-logo
MPI Tbingen
Motivation
Summary
Spatial Filtering
Volume Conduction electrodes detect superposition of signals from all over the brain X = AS Spatial ltering undoes this superposition to re-focus on discriminative signals y = fs X This is a Blind Source Separation (BSS) problem many algorithms available to solve this problem In BCI commonly use a fast, supervised method called kyb-logo Common Spatial Patterns [Koles 1990]
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
mc-logo
MPI Tbingen
Motivation
Summary
Spatial Filtering
Volume Conduction electrodes detect superposition of signals from all over the brain X = AS Spatial ltering undoes this superposition to re-focus on discriminative signals y = fs X This is a Blind Source Separation (BSS) problem many algorithms available to solve this problem In BCI commonly use a fast, supervised method called kyb-logo Common Spatial Patterns [Koles 1990]
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
mc-logo
MPI Tbingen
Motivation
Summary
for non-linear classication we can simply replace xi with an explicit feature mapping (xi ) this is how we include the feature extraction into the kyb-logo classication objective
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
mc-logo
MPI Tbingen
Motivation
Summary
3. Optimise this objective, treating s parameters as additional optimisation variables kyb-logo Note Unconstrained optimisation, solve for w, b, Fs directly using CG
mc-logo
MPI Tbingen
Motivation
Summary
3. Optimise this objective, treating s parameters as additional optimisation variables kyb-logo Note Unconstrained optimisation, solve for w, b, Fs directly using CG
mc-logo
MPI Tbingen
Motivation
Summary
3. Optimise this objective, treating s parameters as additional optimisation variables kyb-logo Note Unconstrained optimisation, solve for w, b, Fs directly using CG
mc-logo
MPI Tbingen
Motivation
Summary
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
Filter regularisation
The lters, Fs , Ff , Ft are unconstrained so may overt We have prior knowledge about the lters shape, e.g.
spatial lters tend to be over the motor regions temporal and spectral lters should be smooth
Include this prior knowledge with quadratic regularisation on the lters, Jmm = w w +
i
+s Tr(Fs Rs Fs ) + f Tr(Ff Rf Ff ) + t Tr(Ft Rt Ft ) where, R(.) is a positive denite matrix encoding the prior kyb-logo knowledge
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space. mc-logo
MPI Tbingen
Motivation
Summary
Implementation issues
Optimising Jmm for all the lters directly, results in a stiff problem and very slow convergence Further, evaluating (X ; fs , ff , ft ) requires a costly FFT Coordinate descent on the lter types solves both these problems,
1. Spatial optimisation, where, s (X , fs ) = fs Xf ,t Xf ,t fs 2. Spectral optimisation, where (X ; ff ) = Xs,t Df2 Xs,t 3. Temporal optimisation, where t (X , ft ) = Xs,f Dt2 Xs,f 4. Repeat until convergence
Non-convex problem seed with good solution found by another method, e.g. CSP or prior knowledge. kyb-logo
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
mc-logo
MPI Tbingen
Motivation
Summary
MPI Tbingen
Motivation
Summary
MPI Tbingen
Motivation
Summary
MPI Tbingen
Motivation
Summary
MPI Tbingen
Motivation
Summary
MPI Tbingen
Motivation
Summary
MPI Tbingen
Motivation
Summary
MPI Tbingen
Motivation
Summary
Experimental analysis
We show binary classication error from 15 imagined movement subjects:
9 from BCI competitions (Comp 2:IIa, Comp 3:IVa,IVc) and 6 from an internal MPI dataset.
pre-processed by band-pass ltering to .545Hz Baseline performance is from CSP with 2 lters computed on the signal ltered to 7-27Hz. CSP solution used as the spatial lter seed, at seeds used for spectral and temporal lters
kyb-logo mc-logo
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
100 Training Points 200 Training Points Spatial General Improvement in performance; particularly for low numbers of data-points (when overtting is an issue) kyb-logo Huge improvement in a few cases
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
mc-logo
MPI Tbingen
Motivation
Summary
MPI Tbingen
Motivation
Summary
100 Training Points Spatial + Spectral + Temporal slight decrease for others
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
MPI Tbingen
Motivation
Summary
Summary
EEG BCI performance depends mainly on learning subject-specic feature extractors These can be learnt by direct optimisation of the classication objective (Max-margin) Results show signicant improvement over independent feature-extractor/classier learning (better in 12/15 cases)
Future work
Alternative objective functions SVM, LR and Gaussian Process objectives
implementated already.
Better priors particularly for the spatial lters, found by cross-subject learning? Other feature/signal types wavelets, MRPs, P300, etc. kyb-logo On-line feature learning
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space.
mc-logo
MPI Tbingen
Motivation
Summary
100 Training Points 200 Training Points learn a rank-1, i.e. 1-spatial + 1-temporal, approximation to the full svm weight vector this regularisation signicantly improves classication performance kyb-logo mc-logo and produces readily interpertable results..
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space. MPI Tbingen
Motivation
Summary
100 Training Points 200 Training Points learn a rank-1, i.e. 1-spatial + 1-temporal, approximation to the full svm weight vector this regularisation signicantly improves classication performance kyb-logo mc-logo and produces readily interpertable results..
Jason Farquhar, Jeremy Hill, Bernhard Schlkopf Learning optimal EEG features across time, frequency and space. MPI Tbingen
Motivation
Summary
temporally?
MPI Tbingen