Non-standard neural network architectures in the analysis of auditory brainstem response potentials

Neural networks can be useful in tasks connected with analysis of auditory brainstem response (ABR) potentials, which are derived functions of bioelectric processes taking place at the brain and auditory cortex level. However, some problems have been encountered with the detection of the presence or absence of wave V in the analysed ABR potential signal. Much better results are obtained when, in addition to the primary signal of the analysed ABR, evoked for a given intensity of the acoustic signal, a context signal is used. For specification of the task, an essential problem is the input of the context signal to the neural network analysing the ABR potential. In this paper, an attempt to solve the problem is been described, and several results are shown, obtained by application of non-standard architectures for the neural networks analysing the above-mentioned signals. The neural network's architecture has quite a great influence on the results of automated classification and recognition of ABR potentials. It shows that the search for applications of neural networks with atypical architectures is worthwhile, and it proves that it is possible to build a system based on neural networks for automatically detecting the presence of wave V (with satisfactory recognition reliability) in the ABR signal. This seems to be the most essential cognitive research result of this work.