Summary
Objective:
Single trial evoked potentials (EP) are generally obscured by the much larger spontaneous
or background electroencephalogram (EEG). A novel method was developed to enhance
single trial EPs. The potential of this approach was explored using actual flash evoked
visual EPs.
Method:
The basic procedure is a variant of the adaptive filtering approach. At the core
of our method is a mathematical, but neurophysiologically-realistic, nonlinear model
of the cortical structures involved in generating EEG and EP activity. The model parameters
are adjusted by a genetic algorithm in such a way that the model output resembles
the actually observed pre-stimulus EEG activity. When post-stimulus EEG is passed
through the inverse model, enhancement of the single trial EP should, theoretically,
occur.
Results:
Evidence was found that, in case of visual evoked potentials obtained by flashing
light through closed eyelids, alpha activity continues to around 150 ms post-stimulus,
at which point a low frequency potential arises, cresting 100 ms later and disappearing
after another 100 ms or so. Also, it was found that an individual’s response varies
considerably from trial to trial.
Conclusion:
The inverse modeling approach presented here is effective at enhancing single trial
EP activity. One potential application is to distinguish trials that contain a response
from those that do not, which could result in improved ensemble averages.
Keywords
Evoked Potentials - Visual - Signal Processing - Computer Assisted - Nonlinear - Models
- Neural Networks - Algorithms
