Auditory brainstem responses (ABR), recorded from several subjects with normal hearing, were used to train several self-organizing networks (SON). The resultant self-organizing feature maps (SOFM), using intra-subject data, showed promising results with respect to classification of ABR into low, mid, high and no-response regions. Although initial training with averaged ABR was lengthy, wavelet preprocessing helped to reduce computational time while retaining the same promising results
Published in:
[Engineering in Medicine and Biology, 1999. 21st Annual Conference and the 1999 Annual Fall Meetring of the Biomedical Engineering Society] BMES/EMBS Conference, 1999. Proceedings of the First Joint
(Volume:1
)
Date of Conference: 1999