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 3Oms of the signal and the region 30 to 400ms. Filter banks were then developed Ibr 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 1 0 signals were ibund suitable, and time-varying techniques were Ibund to perlbrm better than applying one filter to the whole signal

The nonlinear modeling capabilities of artificial neural networks (ANN’s) are renowned in the field of artificial intelligence (Al) for capturing knowledge that can be very difficult to understand otherwise. Their ability to be trained on representative data within a particular problem domain and generalise over a set of data make them efficient predictive models. One problem domain that contains complex data that would benefit from the predictive capabilities of ANN’s is that of optical emission spectra (OES). OES is an important diagnostic for monitoring plasma species within plasma processing. Normally, OES spectral interpretation requires significant prior expertise from a spectroscopist. One way of alleviating this intensive demand in order to quickly interpret OES spectra is to interpret the data using an intelligent pattern recognition technique like ANN’s. This thesis investigates and presents MLP ANN models that can successfully classify chemical species within OES spectral patterns. The primary contribution of the thesis is the creation of deployable ANN species models that can predict OES spectral line sizes directly from six controllable input process parameters; and the implementation of a novel rule extraction procedure to relate the real multi-output values of the spectral line sizes to individual input process parameters. Not only are the trained species models excellent in their predictive capability, but they also provide the foundation for extracting comprehensible rules. A secondary contribution made by this thesis is to present an adapted fuzzy rule extraction system that attaches a quantitative measure of confidence to individual rules. The most significant contribution to the field of Al that is generated from the work presented in the thesis is the fact that the rule extraction procedure utilises predictive ANN species models that employ real continuously valued multi-output data. This is an improvement on rule extraction from trained networks that normally focus on discrete binary outputs