Tissue ischemia monitoring using impedance spectroscopy: evaluation of neural networks for ischemia estimation

摘要: Tissue impedance spectra and pH values, collected during ischemic episodes in human skeletal muscle, were used to train test Artificial Neural Networks (NN) for ischemia level estimation. The goal was determine the NN with optimal performance classifying their corresponding values when varying levels of noise introduced original signal. two linear associative memory NNs (Hebbian ADALINE) backpropagation (BP) evaluated using frequency range from 25 Hz-500 kHz as inputs outputs. Results indicate that a BP single hidden layer moderate numbers neurons is an solution authors' research.