Abstract:
The study of sleep has become very essential to diagnose the brain disorders and analysis of brain activities these days. Electroencephalogram (EEG) is a medical imaging tool for diagnosing, monitoring, and managing neurological disorders. Therefore it is necessary to analyse the different sleep stages, & sleep transients like K-complexes. But due to the non stationary and non linear behaviour of brain signals, it is very difficult to detect the K-complexes manually. In this paper two automated detection approaches are discussed based on Wavelet decomposition (DWT) and Statistical k-means using mahalnobis distance. The performance of these methods is considerably efficient & is a hardware independent solution to the biomedical signal processing field.