A methodology to determine a tolerance parameter in the calculation of the entropy in abnormal EEG transients

In order to characterize abnormal behaviours related to epileptic seizures and other neurological disorders, in this paper it is described a methodology to find an optimum tolerance criterion r to estimate the entropy of abnormal transients with a duration of two seconds from electroencephalograms (EEG) recordings of patients diagnosed with partial epilepsy, attention deficit/hyperactivity disorder (ADHD), and conduct disorder (CD). The considered EEG signals come from patients with different ages diagnosed with these cerebral disorders. Approximate entropy (ApEn) and sampling entropy (SampEn) of the transients lead to the determination of an appropriate value for the parameter r. With the present approach it is possible to obtain an accurate identification of abnormal transients in EEG signals of small duration and reliable estimations of their entropies.