A Wavelet-Chaos Methodology for Analysis of EEGs and EEG Subbands to Detect Seizure and Epilepsy

Abstract

A wavelet-chaos methodology is presented for analysis of EEGs and delta, theta, alpha, beta, and gamma subbands of EEGs for detection of seizure and epilepsy. The nonlinear dynamics of the original EEGs are quantified in the form of the correlation dimension (CD, representing system complexity) and the largest Lyapunov exponent (LLE, representing system chaoticity). The new wavelet-based methodology isolates the changes in CD and LLE in specific subbands of the EEG. The methodology is applied to three different groups of EEG signals: 1) healthy subjects; 2) epileptic subjects during a seizure-free interval (interictal EEG); 3) epileptic subjects during a seizure (ictal EEG). The effectiveness of CD and LLE in differentiating between the three groups is investigated based on statistical significance of the differences. It is observed that while there may not be significant differences in the values of the parameters obtained from the original EEG, differences may be identified when the parameters are employed in conjunction with specific EEG subbands. Moreover, it is concluded that for the higher frequency beta and gamma subbands, the CD differentiates between the three groups, whereas for the lower frequency alpha subband, the LLE differentiates between the three groups.

Medical Big Data: Neurological Diseases Diagnosis Through Medical Data Analysis

“…Gular et al [31] proposed an idea of a study for the assessment of accuracy of recurrent neural networks (RNN) employing Lyapunov exponents in detection seizure in the EEG signals. For the detection of epilepsy and seizure, Adeli et al [32] developed a wavelet chaos methodology for analysis of EEGs and delta, theta, alpha, beta and gamma sub-bands of EEGs. Siuly et al [5] introduced a clustering technique-based LS-SVM for EEG signal classification.…”

EEG Signal Discrimination using Non-linear Dynamics in the EMD Domain S. M. Shafiul Alam,S. M. Shafiul Alam,Aurangozeb, and Syed TarekShahriar Abstract—An EMD-chaos based approach is proposed todiscriminate EEG signals corresponding to healthy persons,and epileptic patients during seizure-free intervals and seizureattacks. An electroencephalogram (EEG) is first empiricallydecomposed to intrinsic mode functions (IMFs). The nonlineardynamics of these IMFs are quantified in terms of the largestLyapunov expone

“…Hence, the sample length of each segment from each set is 173.61×23.6 ≈ 4097, and the corresponding maximum frequency content is 86.81 Hz. Since the frequency response of an EEG signal spans over 0~60 Hz [3], frequencies greater than 60 Hz are considered as noise and discarded by passing each signal through a 6 th order Butterworth filter having a cut-off frequency of 60 Hz. Fig.…”

“…where The optimum values of the lag and embedding dimension are determined using the algorithm of equidistant histogram box and Cao's method, respectively [3]. The phase space portrait corresponds to the dynamics of an attractor, confined to a sub-region of the system.…”

“…In [2], the modified Lempel-Ziv complexity is employed, but the analysis is carried out over only two EEG records, not enough to demonstrate its applicability on a wide scale. In [3], a combination of wavelet transform and chaos is used to classify healthy persons and epileptic patients with and without seizure attacks. However, the classifications are not consistent for different sub-bands and satisfactory performance is achieved for only one sub-band.…”

A Multistage System for Automatic Detection of Epileptic Spikes

“…Wavelets are well localized in both time and frequency domains; that is, the wavelet distribution shows good resolution at a given small timefrequency region. Nowadays, wavelet transform have been successfully applied to the analysis of EEG signals as in [30][31][32], for epileptic spike detection as in [3,[33][34][35] and seizure as in [36][37][38][39].…”