Authors: Tomasz Rogala Andrzej Brykalski
Publish Date: 2005/11/16
Volume: 8, Issue: 3, Pages: 238-246
Abstract
The paper discusses creating a waveletbased feature space for the classification of transient pattern electroretinograms PERGs—signals utilized in ophthalmology to evaluate the state of the retina Discrete wavelet transform DWT can provide compact signal description which is more accurate than timedomain data A procedure for the proper choice of transform parameters is proposed Both timedomain and wavelet features of these waveforms are visualized using principal components analysis Separability of feature spaces is compared using kmeans clustering algorithm The results suggest that PERG waveforms are better separable when represented by DWT coefficients of full timedomain signal than in traditional peakbased feature space
Keywords: