Sharif Digital Repository

In this work we used the Liley EEG model as a dynamical model of EEG. Two parameters of the model which are candidates for change during an epileptic seizure are defined as new states in state space representation of this dynamical model. Then SIS particle filter is applied for estimating the defined states over time using the recorded epileptic EEG as the observation of the system. A method for fast numerical solution of the nonlinear coupled equation of the model is proposed. This model is used for tracking the dynamical properties of brain during epileptic seizure. Tracking the changes of these new defined states of the model have good information about the state transition of the model... 

Objective: Epileptic seizures are defined as manifest of excessive and hyper-synchronous activity of neurons in the cerebral cortex that cause frequent malfunction of the human central nervous system. Therefore, finding precursors and predictors of epileptic seizure is of utmost clinical relevance to reduce the epileptic seizure induced nervous system malfunction consequences. Researchers for this purpose may even guide us to a deep understanding of the seizure generating mechanisms. The goal of this paper is to predict epileptic seizures in epileptic rats. Methods: Seizures were induced in rats using pentylenetetrazole (PTZ) model. EEG signals in interictal, preictal, ictal and postictal... 

This work proposes a novel deep learning-based model for prediction of epileptic seizures using multichannel EEG signals. Multichannel images are first constructed by applying short-time Fourier transform (STFT) to Electroencephalography (EEG) signals. After a preprocessing step, a CNN-LSTM neural network is trained on the STFTs in order to capture the spectral, spatial and temporal features within and between the EEG segments and classify them as preictal or interictal stage. The proposed method achieves a sensitivity of 98.21%, a false prediction rate (FPR) of 0.13/h and a mean prediction time of 44.74 minutes on the CHB-MIT dataset. As the main contribution of this work, by using a... 

This study presents a new method for epilepsy detection based on autoregressive (AR) estimation of EEG signals. In this method, optimum order for AR model is determined by Bayesian Information Criterion (BIC) and then AR parameters of EEG signals (from EEG data set of epilepsy center of the University of Bonn, Germany) and their sub-bands (created with the help of wavelet decomposition) are extracted based on it. These parameters are used as a feature to classify the EEG signals into Healthy, Interictal (seizure free) and Ictal (during a seizure) groups using multilayer perceptron (MLP) classifier. Correct classification scores at the range of 91% to 96% reveals the potential of our approach... 

This study presents applying recurrence quantification analysis (RQA) on EEG recordings and their subbands: delta, theta, alpha, beta, and gamma for epileptic seizure detection. RQA is adopted since it does not require assumptions about stationarity, length of signal, and noise. The decomposition of the original EEG into its five constituent subbands helps better identification of the dynamical system of EEG signal. This leads to better classification of the database into three groups: Healthy subjects, epileptic subjects during a seizure-free interval (Interictal) and epileptic subjects during a seizure course (Ictal). The proposed algorithm is applied to an epileptic EEG dataset provided... 

Automatic detection of epileptic seizures can serve as a valuable clinical tool which involves a more objective and computationally efficient method for the analysis of EEG data in order to generate increasingly accurate and reliable results. Automatic seizure detection is also an important component of closed-loop responsive cortical stimulation systems. The goal of this study is to evaluate EEG-based features recently proposed for seizure detection to discover the optimum ones for a reliable seizure detection system. We extracted seizure detection features from intracranial EEG signals that were recorded during invasive pre-surgical epilepsy monitoring of people with drug resistant focal... 

Abnormalities in the topology of brain networks may be an important feature and etiological factor for psychogenic non-epileptic seizures (PNES). To explore this possibility, we applied a graph theoretical approach to functional networks based on resting state EEGs from 13 PNES patients and 13 age- and gender-matched controls. The networks were extracted from Laplacian-transformed time-series by a cross-correlation method. PNES patients showed close to normal local and global connectivity and small-world structure, estimated with clustering coefficient, modularity, global efficiency, and small-worldness metrics, respectively. Yet the number of PNES attacks per month correlated with a...