Sleep Stage Classification using Wavelet Transform and Neural Network

In this paper we present a new method to do automatic sleep stage classification. The algorithm consists of basically three modules. A wavelet packet transformation (WPT) is applied to 30 seconds long epochs of EEG recordings to provide localized time-frequency information, a feature generator which quantifies the information and reduce the data set size, and an artificial neural network for doing optimal classification. The classification results compared to those of a human expert reached a 70 to 80% of agreement.