Time-time analysis of electroencephalogram signals for epileptic seizure detection

Abstract

The detection and classification of epileptic seizures using the electroencphalogram (EEG) signals has been actively worked upon by the researchers from past few decades. This paper attempts a novel application of time-time transform for analysis of electroencephalogram time-series for epileptic seizure detection by transforming it into secondary time-limited local constituent time-series. This technique (TT-transform) of time-time representation of the EEG time series is derived from S-transform, i.e., Stockwell transform (an extension of the wavelets), a method that represents a non-stationary time series as a set of complex time-localised spectra. With the help of TT-transform, a more informative representation of the time features of EEG signals has been obtained, around a particular point on the time axis which has been seen to prove very effective in seizure detection. As the TT-transform is completely invertible, it indicates frequency filtering and signal to noise improvements in the time domain. Features obtained upon application of TT-transform on EEG time-series are classified using quadratic discriminant analysis and the correct classification rate obtained is 100%.