Complexity Measures for Normal and Epileptic EEG Signals using ApEn, SampEn and SEN
There are numerous applications of EEG signal processing such as monitoring alertness, coma, and brain death, controlling an aesthesia, investigating epilepsy and locating seizure origin, testing epilepsy drug effects, monitoring the brain development, and investigating mental disorders; where data size is too long and requires long time to observe the data by clinician or neurologist. EEG signal processing techniques can be used effectively in such applications. The configuration of the signal waveform may contain valuable and useful information about the different state of the brain since biological signal is highly random in both time and frequency domain. Thus computerized analysis is necessary. Being a non-stationary signal, suitable analysis is essential for EEG to differentiate the normal EEG and epileptic seizures. The importance of entropy based features to recognize the normal EEGs, and ictal as well as interictal epileptic seizures. Three features, such as, Approximate entropy, Sample entropy, and Spectral entropy are used to take out the quantitative entropy features from the given EEG time series data of various time frames of 0.88s, and 1s .Average value of entropies for epileptic time series is less than non epileptic time series.