Recognizing seizure using Poincaré plot of EEG signals and graphical features in DWT domain

Abstract

Electroencephalography (EEG) signals are considered one of the oldest techniques for detecting disorders in medical signal processing. However, brain complexity and the non-stationary nature of EEG signals represent a challenge when applying this technique. The current paper proposes new geometrical features for classifi cation of seizure (S) and seizure-free (SF) EEG signals with respect to the Poincaré pattern of discrete wavelet transform (DWT) coeffi cients. DWT decomposes EEG signal to four levels, and thus Poincaré plot is shown for coeffi cients. Due to patterns of the Poincaré plot, novel geometrical features are computed from EEG signals. The computed features are involved in standard descriptors of 2-D projection (STD), summation of triangle area using consecutive points (STA), as well as summation of shortest distance from each point relative to the 45-degree line (SSHD), and summation of distance from each point relative to the coordinate center (SDTC). The proposed procedure leads to discriminate features between S and SF EEG signals. Thereafter, a binary particle swarm optimization (BPSO) is developed as an appropriate technique for feature selection. Finally, k-nearest neighbor (KNN) and support vector machine (SVM) classifi ers are used for classifying features in S and SF groups. By developing the proposed method, we have archived classifi cation accuracy of 99.3 % with respect to the proposed geometrical features. Accordingly, S and SF EEG signals have been classifi ed. Also, Poincaré plot of SF EEG signals has more regular geometrical shapes as compared to S group. As a fi nal remark, we notice that the Poincaré plot of coeffi cients in S EEG signals has occupied more space as compared to SF EEG signals (Tab. 3, Fig. 11, Ref. 57).

Resting-State EEG Connectivity at High-Frequency Bands and Attentional Performance Dysfunction in Stabilized Schizophrenia Patients

“…Recent research identified the underlying patterns of EEG signals of a seizure and a psychiatric phenotype (e.g., depression) by using a novel approach based on geometric features derived from the EEG signal shape of the second-order differential plot (SODP), e.g., standard descriptors, a summation of the angles between consecutive vectors, a summation of distances to coordinate, a summation of the triangle area using three successive points, etc. [63,64]. The suitable features were selected by utilizing binary particle swarm optimization (PSO) and were fed to support vector machine and k-nearest neighbor (KNN) classifiers for the identification of normal and depressed signals [63].…”

Data augmentation for invasive brain–computer interfaces based on stereo-electroencephalography (SEEG)

“…For example, the multiscale principal component analysis method can be used for noise removal [72,[83][84][85]. In addition, it is also possible to identify the existing variance by comparing the underlying patterns of EEG signals by looking at the graphical features of different subjects [86,87].…”

Measuring Connectivity in Linear Multivariate Processes With Penalized Regression Techniques

“…Geometrical features pertain to a collection of quantitative measurements or characteristics extracted from the geometric representation of data in two-or three-dimensional space. In the literature, these features have found utility in the analysis of various biosignals, including heart rate variability [74], electrocardiography [75], and EEG for the detection of different conditions such as depression [76] and seizures [77]. Previous studies have demonstrated that the incorporation of geometrical features can significantly boost classification accuracy, often by as much as 20%, when compared to features extracted from the time, frequency, or time-frequency domains.…”