Classification of epileptic seizures using wavelet packet log energy and norm entropies with recurrent Elman neural network classifier

Electroencephalogram shortly termed as EEG is considered as the fundamental segment for the assessment of the neural activities in the brain. In cognitive neuroscience domain, EEG-based assessment method is found to be superior due to its non-invasive ability to detect deep brain structure while exhibiting superior spatial resolutions. Especially for studying the neurodynamic behavior of epileptic seizures, EEG recordings reflect the neuronal activity of the brain and thus provide required clinical diagnostic information for the neurologist. This specific proposed study makes use of wavelet packet based log and norm entropies with a recurrent Elman neural network (REN) for the automated detection of epileptic seizures. Three conditions, normal, pre-ictal and epileptic EEG recordings were considered for the proposed study. An adaptive Weiner filter was initially applied to remove the power line noise of 50 Hz from raw EEG recordings. Raw EEGs were segmented into 1 s patterns to ensure stationarity of the signal. Then wavelet packet using Haar wavelet with a five level decomposition was introduced and two entropies, log and norm were estimated and were applied to REN classifier to perform binary classification. The non-linear Wilcoxon statistical test was applied to observe the variation in the features under these conditions. The effect of log energy entropy (without wavelets) was also studied. It was found from the simulation results that the wavelet packet log entropy with REN classifier yielded a classification accuracy of 99.70 % for normal-pre-ictal, 99.70 % for normal-epileptic and 99.85 % for pre-ictal-epileptic.

Detection of epileptic seizure in EEG signals using linear least squares preprocessing

An epileptic seizure is a transient event of abnormal excessive neuronal discharge in the brain. This unwanted event can be obstructed by detection of electrical changes in the brain that happen before the seizure takes place. The automatic detection of seizures is necessary since the visual screening of EEG recordings is a time consuming task and requires experts to improve the diagnosis. Much of the prior research in detection of seizures has been developed based on artificial neural network, genetic programming, and wavelet transforms. Although the highest achieved accuracy for classification is 100%, there are drawbacks, such as the existence of unbalanced datasets and the lack of investigations in performances consistency. To address these, four linear least squares-based preprocessing models are proposed to extract key features of an EEG signal in order to detect seizures. The first two models are newly developed. The original signal (EEG) is approximated by a sinusoidal curve. Its amplitude is formed by a polynomial function and compared with the predeveloped spline function. Different statistical measures, namely classification accuracy, true positive and negative rates, false positive and negative rates and precision, are utilised to assess the performance of the proposed models. These metrics are derived from confusion matrices obtained from classifiers. Different classifiers are used over the original dataset and the set of extracted features. The proposed models significantly reduce the dimension of the classification problem and the computational time while the classification accuracy is improved in most cases. The first and third models are promising feature extraction methods with the classification accuracy of 100%. Logistic, LazyIB1, LazyIB5, and J48 are the best classifiers. Their true positive and negative rates are 1 while false positive and negative rates are 0 and the corresponding precision values are 1. Numerical results suggest that these models are robust and efficient for detecting epileptic seizure.

Using Fractal and Local Binary Pattern Features for Classification of ECOG Motor Imagery Tasks Obtained from the Right Brain Hemisphere

The feature extraction and classification of brain signal is very significant in brain–computer interface (BCI). In this study, we describe an algorithm for motor imagery (MI) classification of electrocorticogram (ECoG)-based BCI. The proposed approach employs multi-resolution fractal measures and local binary pattern (LBP) operators to form a combined feature for characterizing an ECoG epoch recording from the right hemisphere of the brain. A classifier is trained by using the gradient boosting in conjunction with ordinary least squares (OLS) method. The fractal intercept, lacunarity and LBP features are extracted to classify imagined movements of either the left small finger or the tongue. Experimental results on dataset I of BCI competition III demonstrate the superior performance of our method. The cross-validation accuracy and accuracy is 90.6% and 95%, respectively. Furthermore, the low computational burden of this method makes it a promising candidate for real-time BCI systems.

High-resolution melting combines with Bayes discriminant analysis: a novel hepatitis C virus genotyping method

Current hepatitis C virus (HCV) genotyping techniques are often highly technical, costly, or need improvements in sensitivity and specificity. These limitations indicate the need of novel methods for HCV genotyping. The present study aimed to develop a novel genotyping method combining high-resolution melting (HRM) analysis with Bayes discriminant analysis (BDA). Target gene fragment including 5'-untranslated and core region was selected. Four or five inner amplicons for every serum were amplified using nested PCR, HRM was used to determine the melting temperature of the amplicons, and HCV genotypes were then analyzed utilizing BDA. In initial genotyping (HCV genotypes were classified into 1b, 2a, 3a, 3b, and 6a), both the overall accuracy rate and the cross-validation accuracy rate were 92.6 %, external validation accuracy rate was 95.0 %. To enhance the accuracy rate of genotyping, HCV genotypes were firstly classified into 1b, 3a, 3b, and 2a-6a, followed by a supplementary genotyping for 2a-6a. Both the overall accuracy rate and the cross-validation accuracy rate reached 97.5 %, and external validation accuracy rate was 100 %. Comparing adjusted HRM genotyping with type-specific probe technique, the difference in accuracy rates was not significant. However, the limit of detection and cost were lower for HRM. Comparing with sequencing, the limit detection of HRM was the same as the former, but the cost of HRM was lower. Hence, HRM combined with BDA was a novel method that equipped with superior accuracy, high sensitivity, and lower cost and therefore could be a better technique for HCV genotyping.

Exploring human epileptic activity at the single-neuron level

Today, localization of the seizure focus heavily relies on EEG monitoring (scalp or intracranial). However, current technology enables much finer resolutions. The activity of hundreds of single neurons in the human brain can now be simultaneously explored before, during, and after a seizure or in association with an interictal discharge. This technology opens up new horizons to understanding epilepsy at a completely new level. This review therefore begins with a brief description of the basis of the technology, the microelectrodes, and the setup for their implantation in patients with epilepsy. Using these electrodes, recent studies provide novel insights into both the time domain and firing patterns of epileptic activity of single neurons. In the time domain, seizure-related activity may occur even minutes before seizure onset (in its current, EEG-based definition). Seizure-related neuronal interactions exhibit complex heterogeneous dynamics. In the seizure-onset zone, changes in firing patterns correlate with cell loss; in the penumbra, neurons maintain their spike stereotypy during a seizure. Hence, investigation of the extracellular electrical activity is expected to provide a better understanding of the mechanisms underlying the disease; it may, in the future, serve for a more accurate localization of the seizure focus; and it may also be employed to predict the occurrence of seizures prior to their behavioral manifestation in order to administer automatic therapeutic interventions.

Seizure Prediction Using Undulated Global and Local Features

In this study, a seizure prediction method is proposed based on a patient-specific approach by extracting undulated global and local features of preictal/ictal and interictal periods of EEG signals. The proposed method consists of feature extraction, classification, and regularization. The undulated global feature is extracted using phase correlation between two consecutive epochs of EEG signals and an undulated local feature is extracted using the fluctuation and deviation of EEG signals within the epoch. These features are further used for classification of preictal/ictal and interictal EEG signals. A regularization technique is applied on the classified outputs for the reduction of false alarms and improvement of the overall prediction accuracy (PA). The experimental results confirm that the proposed method provides high PA (i.e., 95.4%) with low false positive per hour using intracranial EEG signals in different brain locations of 21 patients from a benchmark dataset. Combining global and local features enables the transition point to be determined between different types of signals with greater accuracy, resulting successful versus unsuccessful prediction of seizure. The theoretical contribution of this study may provide an opportunity for the development of a clinical device to predict forthcoming seizure in real time.

An Auditory-Tactile Visual Saccade-Independent P300 Brain–Computer Interface

Most P300 event-related potential (ERP)-based brain–computer interface (BCI) studies focus on gaze shift-dependent BCIs, which cannot be used by people who have lost voluntary eye movement. However, the performance of visual saccade-independent P300 BCIs is generally poor. To improve saccade-independent BCI performance, we propose a bimodal P300 BCI approach that simultaneously employs auditory and tactile stimuli. The proposed P300 BCI is a vision-independent system because no visual interaction is required of the user. Specifically, we designed a direction-congruent bimodal paradigm by randomly and simultaneously presenting auditory and tactile stimuli from the same direction. Furthermore, the channels and number of trials were tailored to each user to improve online performance. With 12 participants, the average online information transfer rate (ITR) of the bimodal approach improved by 45.43% and 51.05% over that attained, respectively, with the auditory and tactile approaches individually. Importantly, the average online ITR of the bimodal approach, including the break time between selections, reached 10.77 bits/min. These findings suggest that the proposed bimodal system holds promise as a practical visual saccade-independent P300 BCI.

An Improved Sparse Representation over Learned Dictionary Method for Seizure Detection

Automatic seizure detection has played an important role in the monitoring, diagnosis and treatment of epilepsy. In this paper, a patient specific method is proposed for seizure detection in the long-term intracranial electroencephalogram (EEG) recordings. This seizure detection method is based on sparse representation with online dictionary learning and elastic net constraint. The online learned dictionary could sparsely represent the testing samples more accurately, and the elastic net constraint which combines the 11-norm and 12-norm not only makes the coefficients sparse but also avoids over-fitting problem. First, the EEG signals are preprocessed using wavelet filtering and differential filtering, and the kernel function is applied to make the samples closer to linearly separable. Then the dictionaries of seizure and nonseizure are respectively learned from original ictal and interictal training samples with online dictionary optimization algorithm to compose the training dictionary. After that, the test samples are sparsely coded over the learned dictionary and the residuals associated with ictal and interictal sub-dictionary are calculated, respectively. Eventually, the test samples are classified as two distinct categories, seizure or nonseizure, by comparing the reconstructed residuals. The average segment-based sensitivity of 95.45%, specificity of 99.08%, and event-based sensitivity of 94.44% with false detection rate of 0.23/h and average latency of -5.14 s have been achieved with our proposed method.

Multifractal Analysis and Relevance Vector Machine-Based Automatic Seizure Detection in Intracranial EEG

Automatic seizure detection technology is of great significance for long-term electroencephalogram (EEG) monitoring of epilepsy patients. The aim of this work is to develop a seizure detection system with high accuracy. The proposed system was mainly based on multifractal analysis, which describes the local singular behavior of fractal objects and characterizes the multifractal structure using a continuous spectrum. Compared with computing the single fractal dimension, multifractal analysis can provide a better description on the transient behavior of EEG fractal time series during the evolvement from interictal stage to seizures. Thus both interictal EEG and ictal EEG were analyzed by multifractal formalism and their differences in the multifractal features were used to distinguish the two class of EEG and detect seizures. In the proposed detection system, eight features (α0, αmin, αmax, Δα, f(α min ), f(α max ), Δf and R) were extracted from the multifractal spectrums of the preprocessed EEG to construct feature vectors. Subsequently, relevance vector machine (RVM) was applied for EEG patterns classification, and a series of post-processing operations were used to increase the accuracy and reduce false detections. Both epoch-based and event-based evaluation methods were performed to appraise the system's performance on the EEG recordings of 21 patients in the Freiburg database. The epoch-based sensitivity of 92.94% and specificity of 97.47% were achieved, and the proposed system obtained a sensitivity of 92.06% with a false detection rate of 0.34/h in event-based performance assessment.

Early Seizure Detection Algorithm Based on Intracranial EEG and Random Forest Classification

The goal of this study is to provide a seizure detection algorithm that is relatively simple to implement on a microcontroller, so it can be used for an implantable closed loop stimulation device. We propose a set of 11 simple time domain and power bands features, computed from one intracranial EEG contact located in the seizure onset zone. The classification of the features is performed using a random forest classifier. Depending on the training datasets and the optimization preferences, the performance of the algorithm were: 93.84% mean sensitivity (100% median sensitivity), 3.03 s mean (1.75 s median) detection delays and 0.33/h mean (0.07/h median) false detections per hour.

Kernel Collaborative Representation-Based Automatic Seizure Detection in Intracranial EEG

Automatic seizure detection is of great significance in the monitoring and diagnosis of epilepsy. In this study, a novel method is proposed for automatic seizure detection in intracranial electroencephalogram (iEEG) recordings based on kernel collaborative representation (KCR). Firstly, the EEG recordings are divided into 4s epochs, and then wavelet decomposition with five scales is performed. After that, detail signals at scales 3, 4 and 5 are selected to be sparsely coded over the training sets using KCR. In KCR, l2-minimization replaces l1-minimization and the sparse coefficients are computed with regularized least square (RLS), and a kernel function is utilized to improve the separability between seizure and nonseizure signals. The reconstructed residuals of each EEG epoch associated with seizure and nonseizure training samples are compared and EEG epochs are categorized as the class that minimizes the reconstructed residual. At last, a multi-decision rule is applied to obtain the final detection decision. In total, 595 h of iEEG recordings from 21 patients with 87 seizures are employed to evaluate the system. The average sensitivity of 94.41%, specificity of 96.97%, and false detection rate of 0.26/h are achieved. The seizure detection system based on KCR yields both a high sensitivity and a low false detection rate for long-term EEG.

Ngram-derived pattern recognition for the detection and prediction of epileptic seizures

This work presents a new method that combines symbol dynamics methodologies with an Ngram algorithm for the detection and prediction of epileptic seizures. The presented approach specifically applies Ngram-based pattern recognition, after data pre-processing, with similarity metrics, including the Hamming distance and Needlman-Wunsch algorithm, for identifying unique patterns within epochs of time. Pattern counts within each epoch are used as measures to determine seizure detection and prediction markers. Using 623 hours of intracranial electrocorticogram recordings from 21 patients containing a total of 87 seizures, the sensitivity and false prediction/detection rates of this method are quantified. Results are quantified using individual seizures within each case for training of thresholds and prediction time windows. The statistical significance of the predictive power is further investigated. We show that the method presented herein, has significant predictive power in up to 100% of temporal lobe cases, with sensitivities of up to 70-100% and low false predictions (dependant on training procedure). The cases of highest false predictions are found in the frontal origin with 0.31-0.61 false predictions per hour and with significance in 18 out of 21 cases. On average, a prediction sensitivity of 93.81% and false prediction rate of approximately 0.06 false predictions per hour are achieved in the best case scenario. This compares to previous work utilising the same data set that has shown sensitivities of up to 40-50% for a false prediction rate of less than 0.15/hour.