Automatic Analysis and Recognition of the Auditory Brainstem Response Signals

One of the most important challenges in the contemporary audiology is the early detection and diagnosis of hearing impairments in newborn children. In practice such an objective can be achieved only by application of objective methods. The most important is the study of auditory brainstem response signals (ABR). Unfortunately for that method the prospects for automation of the examination are not very promising. It is easy to elaborate an algorithm for automated acquisition and stimulation, it is however much more difficult to construct an algorithm for automated analysis of the results. The objective of the project is the construction of a unified acquisition technique for ABR signals and elaboration of a processing method capable of their automated analysis. Furthermore the automation of the analysis of ABR signals is oriented towards the detection of wave V in the ABR signals. For that task automated classification of ABR signals is proposed, with application of artificial neural networks. In the final stage the combination of the present research topic with remote access to the database it will be possible to create a diagnostic advisory system.