A Combined Wavelet And Neural Network Based Model For Classifying Depth Of Anaesthesia

This study aims to use combined wavelet and neural network model to extract electroencephalogram (EEG) signal features during anesthesia and classify them according to the Depth of Anaesthesia (DOA). EEG signals were selected according to their Bispectral Index (BIS) value during anaesthesia and were processed using Discrete Wavelet Transform (DWT). The dimensionality of the wavelet coefficient vectors were reduced by extracting key features from their distribution. Artificial Neural networks (ANN) were implemented using the extracted features of EEG signals as inputs and then classifying anesthetic depth as awake, light anesthesia, moderate anaesthesia, deep anesthesia and very deep anaesthesia. The proposed model will classify depth of anaesthesia accurately. (C) 2015 The Authors. Published by Elsevier B.V.