Automatic classification of Sleep Stages on a EEG signal by Artificial Neural Networks

Visual analysis of the physiological signals recorded at sleep time constitutes a heavy task for the clinician. In fact data quantity to be analyzed, generally corresponding to eight hours of recordings studied per 30s epochs, as well as the complexity of this analysis require a significant time. The objective of our work is to propose a tool for automatic analysis and decision-making based on artificial neural networks (ANN). In this paper, we present an outline of this tool and we propose to compare human and ANN performances on a simple case of vigilance states labeling. The first difficulty consists of the choice of representation for the physiological signals and in particular the electroencephalogram (EEG) which is regarded as the principal indicator of sleep stages. Once the representation is adopted, the following step is the design of the optimal ANN by a training and validation process on data set of a healthy adult. The results obtained, on average 76% of agreement between the expert and the ANN for six stages of vigilance, encourage us to look further into the study of these problems at the levels of modeling and design to improve the performances of our tool