Adaptive denoising and multiscale detection of the V wave in brainstem auditory evoked potentials

This paper describes a wavelet-transform-based system for the V wave identi fication in brainstem auditory evoked potentials (BAEP). The system combine s signal denoising and rule-based localization modules. The signal denoisin g module has the potential of effective noise reduction after signal averag ing. It analyses adaptively the evolution of the wavelet transform maxima a cross scales. The singularities of the signal create wavelet maxima with di fferent properties from those of the induced noise. A non-linear filtering process implemented with a neural network extracts out the noise-induced ma xima. The filtered wavelet details are subsequently analysed by the rule-ba sed localization module for the automatic identification of the V wave. In the first phase, it implements a set of statistical observations as well as heuristic criteria used by human experts in order to classify the IV-V com plex. At the second phase, using a multiscale focusing algorithm, the IV an d V waves are positioned on the BAEP signal. Our experiments revealed that the system provides accurate results even for signals exhibiting unclear IV -V complexes.