Karhunen-loeve transform for sleep spindle detection

Automatic detection of sleep and its analysis have significant applications in clinical and driver fatigue detection. The method proposed here is aimed at detecting sleep spindles which are hallmark of beginning stage of sleep. The method uses one-dimensional EEG signal to detect presence of spindles occurring in EEG signal with the help of Karhunen-Loeve transform. The transform represents sampled EEG signal in terms of a basis which carries transient characteristics of sleep spindle. Projecting an EEG signal onto the spindle basis generates transform coefficients whose magnitude will decide whether input contains spindle or not. This method is simple and very easy to execute with a sensitivity of 86.9% and specificity of 93.5%.