Title :
Optimal features for pedestal peak validation of ABR signals
Author_Institution :
Dept. of Comput. Sci. & Appl. Math., Kuopio Univ., Finland
fDate :
31 Oct-3 Nov 1996
Abstract :
The pedestal peak method is very robust for Jewett peaks detection of auditory brainstem responses. The preliminary classification is the main task in order to ensure correct detection. The standard deviation of pedestal peak signal and normalized amplitude of the pedestal peak are practical features to classify the pedestal peak
Keywords :
FIR filters; auditory evoked potentials; feature extraction; medical signal processing; pattern classification; self-organising feature maps; ABR signals; FIR filtering; Jewett peaks detection; K-mean clustering; auditory brainstem responses; normalized amplitude; optimal features; pedestal peak validation; standard deviation; statistical classification; Computer science; Data mining; Delay; Materials testing; Mathematics; Microcomputers; Pattern recognition; Robustness; Signal generators; Signal processing;
Conference_Titel :
Engineering in Medicine and Biology Society, 1996. Bridging Disciplines for Biomedicine. Proceedings of the 18th Annual International Conference of the IEEE
Conference_Location :
Amsterdam
Print_ISBN :
0-7803-3811-1
DOI :
10.1109/IEMBS.1996.647539
