Use of evolutionary algorithms to select filters for evoked potential enhancement

Evoked potentials are electrical signals produced by the nervous system in response to a stimulus. In general these signals are noisy with a low signal to noise ratio. The aim was to investigate ways of extracting the evoked response within an evoked potential recording, achieving a similar signal to noise ratio as conventional averaging but with less repetitions per average. In this thesis, evolutionary algorithms were used in three ways to extract the evoked potentials from a noisy background. First, evolutionary algorithms selected the cut-off frequencies for a set of filters. A different filter or filter bank was produced for each data set. The noisy signal was passed through each filter in a bank of filters the filter bank output was a weighted sum of the individual filter outputs. The goal was to use three filters ideally one for each of the three regions (early, middle and late components), but the use of five filters was also investigated. Each signal was split into two time domains: the first 30ms of the signal and the region 30 to 400ms. Filter banks were then developed for these regions separately. Secondly, instead of using a single set of filters applied to the whole signal, different filters (or combinations of filters) were applied at different times. Evolutionary algorithms are used to select the duration of each filter, as well as the frequency parameters and weightings of the filters. Three filtering approaches were investigated. Finally, wavelets in conjunction with an evolutionary algorithm were used to select particular wavelets and wavelet parameters. A comparison of these methods with optimal filtering methods and averaging was made. Averages of 10 signals were found suitable, and time-varying techniques were found to perform better than applying one filter to the whole signal.