Neural-network based classification of laser-Doppler flowmetry signals

Laser Doppler flowmetry is the most advantageous technique for non-invasive patient monitoring. Based on the Doppler principle, signals corresponding to blood flow are generated, and metrics corresponding to healthy vs. patient samples are extracted. A neural-network based classifier for these metrics is proposed. The signals are initially filtered and transformed into the frequency domain through third-order correlation and bispectrum estimation. The pictorial representation of the correlations is subsequently routed into a neural network based multilayer perceptron classifier, which is described in detail. Finally, experimental results demonstrating the efficiency of the proposed scheme are presented.<<ETX>>