Eventos Anais de eventos
COBEM 2019
25th International Congress of Mechanical Engineering
EVALUATION OF PARAMETERS USED AS SYMPTOMS TO EEG ANALYSIS
Submission Author:
Julia Duarte , MG
Co-Authors:
Julia Duarte, Marcus Antonio Duarte
Presenter: Julia Duarte
doi://10.26678/ABCM.COBEM2019.COB2019-1956
Abstract
Electroencephalography (EEG) is the study of the graphical register of electric currents developed in the brain, performed by electrodes applied to the scalp, the brain surface, or even within the brain. The physics spend a large time in neurological exams analysis and most of all are not an anomaly. To assist the specialist, we want to we want to choose which statistical parameters (symptoms) best represent the brain signals, in order to classify them into signs with and without anomalies. To do this, an available database of Bern-Barcelona are used, which consists of signs with and without the presence of ictal (signal event caused by an epileptic seizure). The parameters used as symptoms were RMS Level, Peak Value, Peak to Peak Value, Asymmetry, Curtosis, Crest Factor, k4 estimator and k6 estimator, applied to signals that underwent signal treatments, such as filtering processes, envelope analysis, Continuous Wavelet Transform, Intrinsic Modes Functions in conjunction with K-NEO low frequency peak evaluation metrics, Hilbert-Huang transform and entropy calculation, resulting in 1180 possible symptoms. A qualitative, visual analysis was performed through the boxplot evaluation of 100 pairs of focal and non-focal signals. The most frequent parameters were RMS Value, Crest Factor and kurtosis, with 15, 14 and 10 occurrences respectively.
Keywords
epilepsy, focal and non-focal signals, Electroencephalography, Statistical parameters
