Application of Higher Order Spectra to Identify Epileptic EEG

Abstract

Epilepsy is characterized by the spontaneous and seemingly unforeseeable occurrence of seizures, during which the perception or behavior of patients is disturbed. An automatic system that detects seizure onsets would allow patients or the people near them to take appropriate precautions, and could provide more insight into this phenomenon. Various methods have been proposed to predict the onset of seizures based on EEG recordings. The use of nonlinear features motivated by the higher order spectra (HOS) has been reported to be a promising approach to differentiate between normal, background (pre-ictal) and epileptic EEG signals. In this work, we made a comparative study of the performance of Gaussian mixture model (GMM) and Support Vector Machine (SVM) classifiers using the features derived from HOS and from the power spectrum. Results show that the selected HOS based features achieve 93.11% classification accuracy compared to 88.78% with features derived from the power spectrum for a GMM classifier. The SVM classifier achieves an improvement from 86.89% with features based on the power spectrum to 92.56% with features based on the bispectrum.

Effects of Speech Phonological Features during Passive Perception on Cortical Auditory Evoked Potential in Sensorineural Hearing Loss

“…Several non-linear methods presented by previous researchers including sample entropy (SampEnt), higher order spectra (HOS), fractal dimension (FD) and recurrent quantification analysis (RQA) provide a better and valuable mechanism for result interpretation (Acharya et al 2015(Acharya et al , 2011Chua et al 2011Chua et al , 2009. For the last two decades, more exploration was conducted using nonlinear dynamic method in giving potential understanding as this technique extracts hidden complexity in the time series brain signal (Lehnertz 2008;Mormann et al 2005Mormann et al , 2003.…”

“…According to Acharya et al (2013), higher order spectra (HOS) method is considered as one of powerful mechanisms to justify the presence of abnormalities, besides usefulness in the event of signal distortion due to Gaussian noise. This framework has been persistently used in the field to study epilepsy disorder (Chua et al 2011(Chua et al , 2009.…”

Detection of emotions in Parkinson's disease using higher order spectral features from brain's electrical activity

“…Several nonlinear features such as correlation dimension (CD), approximate entropy (AP), largest lyapunov exponent (LLE), higher order spectra (HOS) and Hurst exponent (H) have been used widely [34,35] to characterize the EEG signal. In general, any analysis technique that can detect and quantify some aspect of non-linear mechanisms, may better reflect the dynamics and the characteristics of the EEG signal, and provide more realistic information about the physiological and pathological state of the CNS, the phenomenon of non-linearity and deviations of the signal from [36].…”

“…In particular, the nonlinear analysis method is effectively applied to EEG signals to study the dynamics of the complex underlying behavior [31] and it is well known that the EEG signals exhibit significant non-linear behavior [32]. Non-linear analysis based on chaos theory helps in identifying the apparently irregular behaviors that were present in the system [33].Several nonlinear features such as correlation dimension (CD), approximate entropy (AP), largest lyapunov exponent (LLE), higher order spectra (HOS) and Hurst exponent (H) have been used widely [34,35] to characterize the EEG signal. In general, any analysis technique that can detect and quantify some aspect of non-linear mechanisms, may better reflect the dynamics and the characteristics of the EEG signal, and provide more realistic information about the physiological and pathological state of the CNS, the phenomenon of non-linearity and deviations of the signal from [36].…”

Avaliação da q-transformada de Fourier como ferramenta não linear de estudos de sinais biomédicos

“…É usado em análises da variabilidade da freqüência cardíaca (VFC) para estudar a influência do sistema nervoso autônomo (SNA) na regulação do sistema cardiovascular, e a sua relação com a mortalidade cardiovascular. para identificar sinais epilépticos e preictais através de gráficos de biespectro e bicoerência [11,12]. Dimensão de correlação (CD) para indicar disfunções cerebrais em pessoas que sofrem do mal de Alzheimer [13].…”