Epileptic Seizure Detection in EEGs Using Time–Frequency Analysis

Quantitative EEG biomarkers for epilepsy and their relation to chemical biomarkers

The electroencephalogram (EEG) is the most important method to diagnose epilepsy. In clinical settings, it is evaluated by experts who identify patterns visually. Quantitative EEG is the application of digital signal processing to clinical recordings in order to automatize diagnostic procedures, and to make patterns visible that are hidden to the human eye. The EEG is related to chemical biomarkers, as electrical activity is based on chemical signals. The most well-known chemical biomarkers are blood laboratory tests to identify seizures after they have happened. However, research on chemical biomarkers is much less extensive than research on quantitative EEG, and combined studies are rarely published, but highly warranted. Quantitative EEG is as old as the EEG itself, but still, the methods are not yet standard in clinical practice. The most evident application is an automation of manual work, but also a quantitative description and localization of interictal epileptiform events as well as seizures can reveal important hints for diagnosis and contribute to presurgical evaluation. In addition, the assessment of network characteristics and entropy measures were found to reveal important insights into epileptic brain activity. Application scenarios of quantitative EEG in epilepsy include seizure prediction, pharmaco-EEG, treatment monitoring, evaluation of cognition, and neurofeedback. The main challenges to quantitative EEG are poor reliability and poor generalizability of measures, as well as the need for individualization of procedures. A main hindrance for quantitative EEG to enter clinical routine is also that training is not yet part of standard curricula for clinical neurophysiologists.

GRP-DNet: A gray recurrence plot-based densely connected convolutional network for classification of epileptiform EEG

BACKGROUND

The classification of epileptiform electroencephalogram (EEG) signals has been treated as an important but challenging issue for realizing epileptic seizure detection. In this work, combing gray recurrence plot (GRP) and densely connected convolutional network (DenseNet), we developed a novel classification system named GRP-DNet to identify seizures and epilepsy from single-channel, long-term EEG signals.

NEW METHODS

The proposed GRP-DNet classification system includes three main modules: 1) input module takes an input long-term EEG signal and divides it into multiple short segments using a fixed-size non-overlapping sliding window (FNSW); 2) conversion module transforms short segments into GRPs and passes them to the DenseNet; 3) fusion and decision, the predicted label of each GRP is fused using a majority voting strategy to make the final decision.

RESULTS

Six different classification experiments were designed based on a publicly available benchmark database to evaluate the effectiveness of our system. Experimental results showed that the proposed GRP-DNet achieved an excellent classification accuracy of 100 % in each classification experiment, Furthermore, GRP-DNet gave excellent computational efficiency, which indicates its tremendous potential for developing an EEG-based online epilepsy diagnosis system.

COMPARISON WITH EXISTING METHODS

Our GRP-DNet system was superior to the existing competitive classification systems using the same database.

CONCLUSIONS

The GRP-DNet is a potentially powerful system for identifying and classifying EEG signals recorded from different brain states.

Auto-Weighted Multi-View Discriminative Metric Learning Method With Fisher Discriminative and Global Structure Constraints for Epilepsy EEG Signal Classification

Metric learning is a class of efficient algorithms for EEG signal classification problem. Usually, metric learning method deals with EEG signals in the single view space. To exploit the diversity and complementariness of different feature representations, a new auto-weighted multi-view discriminative metric learning method with Fisher discriminative and global structure constraints for epilepsy EEG signal classification called AMDML is proposed to promote the performance of EEG signal classification. On the one hand, AMDML exploits the multiple features of different views in the scheme of the multi-view feature representation. On the other hand, considering both the Fisher discriminative constraint and global structure constraint, AMDML learns the discriminative metric space, in which the intraclass EEG signals are compact and the interclass EEG signals are separable as much as possible. For better adjusting the weights of constraints and views, instead of manually adjusting, a closed form solution is proposed, which obtain the best values when achieving the optimal model. Experimental results on Bonn EEG dataset show AMDML achieves the satisfactory results.

An Intelligence EEG Signal Recognition Method via Noise Insensitive TSK Fuzzy System Based on Interclass Competitive Learning

Epilepsy is an abnormal function disease of movement, consciousness, and nerve caused by abnormal discharge of brain neurons in the brain. EEG is currently a very important tool in the process of epilepsy research. In this paper, a novel noise-insensitive Takagi-Sugeno-Kang (TSK) fuzzy system based on interclass competitive learning is proposed for EEG signal recognition. First, a possibilistic clustering in Bayesian framework with interclass competitive learning called PCB-ICL is presented to determine antecedent parameters of fuzzy rules. Inherited by the possibilistic c-means clustering, PCB-ICL is noise insensitive. PCB-ICL learns cluster centers of different classes in a competitive relationship. The obtained clustering centers are attracted by the samples of the same class and also excluded by the samples of other classes and pushed away from the heterogeneous data. PCB-ICL uses the Metropolis-Hastings method to obtain the optimal clustering results in an alternating iterative strategy. Thus, the learned antecedent parameters have high interpretability. To further promote the noise insensitivity of rules, the asymmetric expectile term and Ho-Kashyap procedure are adopted to learn the consequent parameters of rules. Based on the above ideas, a TSK fuzzy system is proposed and is called PCB-ICL-TSK. Comprehensive experiments on real-world EEG data reveal that the proposed fuzzy system achieves the robust and effective performance for EEG signal recognition.

An Epilepsy Detection Method Using Multiview Clustering Algorithm and Deep Features

The automatic detection of epilepsy is essentially the classification of EEG signals of seizures and nonseizures, and its purpose is to distinguish the different characteristics of seizure brain electrical signals and normal brain electrical signals. In order to improve the effect of automatic detection, this study proposes a new classification method based on unsupervised multiview clustering results. In addition, considering the high-dimensional characteristics of the original data samples, a deep convolutional neural network (DCNN) is introduced to extract the sample features to obtain deep features. The deep feature reduces the sample dimension and increases the sample separability. The main steps of our proposed novel EEG detection method contain the following three steps: first, a multiview FCM clustering algorithm is introduced, and the training samples are used to train the center and weight of each view. Then, the class center and weight of each view obtained by training are used to calculate the view-weighted membership value of the new prediction sample. Finally, the classification label of the new prediction sample is obtained. Experimental results show that the proposed method can effectively detect seizures.

Graph Eigen Decomposition-Based Feature-Selection Method for Epileptic Seizure Detection Using Electroencephalography

Epileptic seizure is a sudden alteration of behavior owing to a temporary change in the electrical functioning of the brain. There is an urgent demand for an automatic epilepsy detection system using electroencephalography (EEG) for clinical application. In this paper, the EEG signal is divided into short time frames. Discrete wavelet transform is used to decompose each frame into a number of subbands. Different entropies as well as a group of features with which to characterize the spike events are extracted from each subband signal of an EEG frame. The features extracted from individual subbands are concatenated, yielding a high-dimensional feature vector. A discriminative subset of features is selected from the feature vector using a graph eigen decomposition (GED)-based approach. Thus, the reduced number of features obtained is effective for differentiating the underlying characteristics of EEG signals that indicate seizure events and those that indicate nonseizure events. The GED method ranks the features according to their contribution to correct classification. The selected features are used to classify seizure and nonseizure EEG signals using a feedforward neural network (FfNN). The performance of the proposed method is evaluated by conducting various experiments with a standard dataset obtained from the University of Bonn. The experimental results show that the proposed seizure-detection scheme achieves a classification accuracy of 99.55%, which is higher than that of state-of-the-art methods. The efficiency of FfNN is compared with linear discriminant analysis and support vector machine classifiers, which have classification accuracies of 98.72% and 99.39%, respectively. Hence, the proposed method is confirmed as a potential marker for EEG-based seizure detection.

Scalp electroencephalography (sEEG) based advanced prediction of epileptic seizure time and identification of epileptogenic region

Objectives Epilepsy is characterized by uncontrollable seizure during which consciousness of patient is disturbed. Prediction of the seizure in advance will increase the remedial possibilities for the patients suffering from epilepsy. An automated system for seizure prediction is important for seizure enactment, prevention of sudden unexpected deaths and to avoid seizure related injuries. Methods This paper proposes the prediction of an upcoming seizure by analyzing the 23 channel non-stationary EEG signal. EEG signal is divided into smaller segments to change it into quasi-stationary data using an overlapping moving window. Brain region is marked into four regions namely left hemisphere, right hemisphere, central region and temporal region to identify the epileptogenic region. The epileptogenic region shows significant variations during pre-ictal state in comparison to the other regions. So, seizure prediction is carried out by analyzing EEG signals from this region. Seizure prediction is proposed using features extracted from both time and frequency domain. Relative entropy and relative energy are extracted from wavelet transform and Pearson correlation coefficient is obtained from time domain EEG signal. Extracted features have been smoothened using moving average filter. First order derivative of relative features have been used to normalize the intervariability before deciding the threshold for marking the prediction of seizure. Results Isolated seizures where pre-ictal duration of more than 1 h is reported has been detected with an accuracy of 92.18% with precursory warning 18 min in advance and seizure confirmation 12 min in advance. An overall accuracy of 83.33% with false positive alarm rate of 0.01/h has been obtained for all seizure cases with average prediction time of 9.9 min.

Analysis of statistical coefficients and autoregressive parameters over intrinsic mode functions (IMFs) for epileptic seizure detection

Epilepsy is a persistent neurological disorder impacting over 50 million people around the world. It is characterized by repeated seizures defined as brief episodes of involuntary movement that might entail the human body. Electroencephalography (EEG) signals are usually used for the detection of epileptic seizures. This paper introduces a new feature extraction method for the classification of seizure and seizure-free EEG time segments. The proposed method relies on the empirical mode decomposition (EMD), statistics and autoregressive (AR) parameters. The EMD method decomposes an EEG time segment into a finite set of intrinsic mode functions (IMFs) from which statistical coefficients and autoregressive parameters are computed. Nevertheless, the calculated features could be of high dimension as the number of IMFs increases, the Student's t-test and the Mann-Whitney U test were thus employed for features ranking in order to withdraw lower significant features. The obtained features have been used for the classification of seizure and seizure-free EEG signals by the application of a feed-forward multilayer perceptron neural network (MLPNN) classifier. Experimental results carried out on the EEG database provided by the University of Bonn, Germany, demonstrated the effectiveness of the proposed method which performance assessed by the classification accuracy (CA) is compared to other existing performances reported in the literature.

Modeling Hippocampal CA1 Gabaergic Synapses of Audiogenic Rats

Wistar Audiogenic Rats (WARs) are genetically susceptible to sound-induced seizures that start in the brainstem and, in response to repetitive stimulation, spread to limbic areas, such as hippocampus. Analysis of the distribution of interevent intervals of GABAergic inhibitory postsynaptic currents (IPSCs) in CA1 pyramidal cells showed a monoexponential trend in Wistar rats, suggestive of a homogeneous population of synapses, but a biexponential trend in WARs. Based on this, we hypothesize that there are two populations of GABAergic synaptic release sites in CA1 pyramidal neurons from WARs. To address this hypothesis, we used a well-established neuronal computational model of a CA1 pyramidal neuron previously developed to replicate physiological properties of these cells. Our simulations replicated the biexponential trend only when we decreased the release frequency of synaptic currents by a factor of six in at least 40% of distal synapses. Our results suggest that almost half of the GABAergic synapses of WARs have a drastically reduced spontaneous release frequency. The computational model was able to reproduce the temporal dynamics of GABAergic inhibition that could underlie susceptibility to the spread of seizures.

A Novel Deep Neural Network for Robust Detection of Seizures Using EEG Signals

The detection of recorded epileptic seizure activity in electroencephalogram (EEG) segments is crucial for the classification of seizures. Manual recognition is a time-consuming and laborious process that places a heavy burden on neurologists, and hence, the automatic identification of epilepsy has become an important issue. Traditional EEG recognition models largely depend on artificial experience and are of weak generalization ability. To break these limitations, we propose a novel one-dimensional deep neural network for robust detection of seizures, which composes of three convolutional blocks and three fully connected layers. Thereinto, each convolutional block consists of five types of layers: convolutional layer, batch normalization layer, nonlinear activation layer, dropout layer, and max-pooling layer. Model performance is evaluated on the University of Bonn dataset, which achieves the accuracy of 97.63%∼99.52% in the two-class classification problem, 96.73%∼98.06% in the three-class EEG classification problem, and 93.55% in classifying the complicated five-class problem.

Effects of physiological parameter evolution on the dynamics of tonic-clonic seizures

The temporal and spectral characteristics of tonic-clonic seizures are investigated using a neural field model of the corticothalamic system in the presence of a temporally varying connection strength between the cerebral cortex and thalamus. Increasing connection strength drives the system into ∼ 10 Hz seizure oscillations once a threshold is passed and a subcritical Hopf bifurcation occurs. In this study, the spectral and temporal characteristics of tonic-clonic seizures are explored as functions of the relevant properties of physiological connection strengths, such as maximum strength, time above threshold, and the ramp rate at which the strength increases or decreases. Analysis shows that the seizure onset time decreases with the maximum connection strength and time above threshold, but increases with the ramp rate. Seizure duration and offset time increase with maximum connection strength, time above threshold, and rate of change. Spectral analysis reveals that the power of nonlinear harmonics and the duration of the oscillations increase as the maximum connection strength and the time above threshold increase. A secondary limit cycle at ∼ 18 Hz, termed a saddle-cycle, is also seen during seizure onset and becomes more prominent and robust with increasing ramp rate. If the time above the threshold is too small, the system does not reach the 10 Hz limit cycle, and only exhibits 18 Hz saddle-cycle oscillations. It is also seen that the time to reach the saturated large amplitude limit-cycle seizure oscillation from both the instability threshold and from the end of the saddle-cycle oscillations is inversely proportional to the square root of the ramp rate.

Epileptic Seizure Classification With Symmetric and Hybrid Bilinear Models

Epilepsy affects nearly [Formula: see text] of the global population, of which two thirds can be treated by anti-epileptic drugs and a much lower percentage by surgery. Diagnostic procedures for epilepsy and monitoring are highly specialized and labour-intensive. The accuracy of the diagnosis is also complicated by overlapping medical symptoms, varying levels of experience and inter-observer variability among clinical professions. This paper proposes a novel hybrid bilinear deep learning network with an application in the clinical procedures of epilepsy classification diagnosis, where the use of surface electroencephalogram (sEEG) and audiovisual monitoring is standard practice. Hybrid bilinear models based on two types of feature extractors, namely Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), are trained using Short-Time Fourier Transform (STFT) of one-second sEEG. In the proposed hybrid models, CNNs extract spatio-temporal patterns, while RNNs focus on the characteristics of temporal dynamics in relatively longer intervals given the same input data. Second-order features, based on interactions between these spatio-temporal features are further explored by bilinear pooling and used for epilepsy classification. Our proposed methods obtain an F1-score of [Formula: see text] on the Temple University Hospital Seizure Corpus and [Formula: see text] on the EPILEPSIAE dataset, comparing favourably to existing benchmarks for sEEG-based seizure type classification. The open-source implementation of this study is available at https://github.com/NeuroSyd/Epileptic-Seizure-Classification.

A Review of Algorithm & Hardware Design for AI-Based Biomedical Applications

This paper reviews the state of the arts and trends of the AI-Based biomedical processing algorithms and hardware. The algorithms and hardware for different biomedical applications such as ECG, EEG and hearing aid have been reviewed and discussed. For algorithm design, various widely used biomedical signal classification algorithms have been discussed including support vector machine (SVM), back propagation neural network (BPNN), convolutional neural networks (CNN), probabilistic neural networks (PNN), recurrent neural networks (RNN), Short-term Memory Network (LSTM), fuzzy neural network and etc. The pros and cons of the classification algorithms have been analyzed and compared in the context of application scenarios. The research trends of AI-Based biomedical processing algorithms and applications are also discussed. For hardware design, various AI-Based biomedical processors have been reviewed and discussed, including ECG classification processor, EEG classification processor, EMG classification processor and hearing aid processor. Various techniques on architecture and circuit level have been analyzed and compared. The research trends of the AI-Based biomedical processor have also been discussed.

Epileptic Seizure Detection Based on Stockwell Transform and Bidirectional Long Short-Term Memory

Automatic seizure detection plays a significant role in monitoring and diagnosis of epilepsy. This paper presents an efficient automatic seizure detection method based on Stockwell transform (S-transform) and bidirectional long short-term memory (BiLSTM) neural networks for intracranial EEG recordings. First, S-transform is applied to raw EEG segments, and the obtained matrix is grouped into time-frequency blocks as the inputs fed into BiLSTM for feature selecting and classification. Afterwards, postprocessing is adopted to improve detection performance, which includes moving average filter, threshold judgment, multichannel fusion, and collar technique. A total of 689 h intracranial EEG recordings from 20 patients are used for evaluation of the proposed system. Segment-based assessment results show that our system achieves a sensitivity of 98.09% and specificity of 98.69%. For the event-based evaluation, a sensitivity of 96.3% and a false detection rate of 0.24/h are yielded. The satisfactory results indicate that this seizure detection approach possess promising potential for clinical practice.

Detecting Epileptic Seizures in EEG Signals with Complementary Ensemble Empirical Mode Decomposition and Extreme Gradient Boosting

Epilepsy is a common nervous system disease that is characterized by recurrent seizures. An electroencephalogram (EEG) records neural activity, and it is commonly used for the diagnosis of epilepsy. To achieve accurate detection of epileptic seizures, an automatic detection approach of epileptic seizures, integrating complementary ensemble empirical mode decomposition (CEEMD) and extreme gradient boosting (XGBoost), named CEEMD-XGBoost, is proposed. Firstly, the decomposition method, CEEMD, which is capable of effectively reducing the influence of mode mixing and end effects, was utilized to divide raw EEG signals into a set of intrinsic mode functions (IMFs) and residues. Secondly, the multi-domain features were extracted from raw signals and the decomposed components, and they were further selected according to the importance scores of the extracted features. Finally, XGBoost was applied to develop the epileptic seizure detection model. Experiments were conducted on two benchmark epilepsy EEG datasets, named the Bonn dataset and the CHB-MIT (Children's Hospital Boston and Massachusetts Institute of Technology) dataset, to evaluate the performance of our proposed CEEMD-XGBoost. The extensive experimental results indicated that, compared with some previous EEG classification models, CEEMD-XGBoost can significantly enhance the detection performance of epileptic seizures in terms of sensitivity, specificity, and accuracy.

Comparison of different input modalities and network structures for deep learning-based seizure detection

The manual review of an electroencephalogram (EEG) for seizure detection is a laborious and error-prone process. Thus, automated seizure detection based on machine learning has been studied for decades. Recently, deep learning has been adopted in order to avoid manual feature extraction and selection. In the present study, we systematically compared the performance of different combinations of input modalities and network structures on a fixed window size and dataset to ascertain an optimal combination of input modalities and network structures. The raw time-series EEG, periodogram of the EEG, 2D images of short-time Fourier transform results, and 2D images of raw EEG waveforms were obtained from 5-s segments of intracranial EEGs recorded from a mouse model of epilepsy. A fully connected neural network (FCNN), recurrent neural network (RNN), and convolutional neural network (CNN) were implemented to classify the various inputs. The classification results for the test dataset showed that CNN performed better than FCNN and RNN, with the area under the curve (AUC) for the receiver operating characteristics curves ranging from 0.983 to 0.984, from 0.985 to 0.989, and from 0.989 to 0.993 for FCNN, RNN, and CNN, respectively. As for input modalities, 2D images of raw EEG waveforms yielded the best result with an AUC of 0.993. Thus, CNN can be the most suitable network structure for automated seizure detection when applied to the images of raw EEG waveforms, since CNN can effectively learn a general spatially-invariant representation of seizure patterns in 2D representations of raw EEG.

Deep learning approach to detect seizure using reconstructed phase space images

Epilepsy is a chronic neurological disorder that affects the function of the brain in people of all ages. It manifests in the electroencephalogram (EEG) signal which records the electrical activity of the brain. Various image processing, signal processing, and machine-learning based techniques are employed to analyze epilepsy, using spatial and temporal features. The nervous system that generates the EEG signal is considered nonlinear and the EEG signals exhibit chaotic behavior. In order to capture these nonlinear dynamics, we use reconstructed phase space (RPS) representation of the signal. Earlier studies have primarily addressed seizure detection as a binary classification (normal vs. ictal) problem and rarely as a ternary class (normal vs. interictal vs. ictal) problem. We employ transfer learning on a pre-trained deep neural network model and retrain it using RPS images of the EEG signal. The classification accuracy of the model for the binary classes is (98.5±1.5)% and (95±2)% for the ternary classes. The performance of the convolution neural network (CNN) model is better than the other existing statistical approach for all performance indicators such as accuracy, sensitivity, and specificity. The result of the proposed approach shows the prospect of employing RPS images with CNN for predicting epileptic seizures.

Classification of low-density EEG for epileptic seizures by energy and fractal features based on EMD

We are here to present a new method for the classification of epileptic seizures from electroencephalogram (EEG) signals. It consists of applying empirical mode decomposition (EMD) to extract the most relevant intrinsic mode functions (IMFs) and subsequent computation of the Teager and instantaneous energy, Higuchi and Petrosian fractal dimension, and detrended fluctuation analysis (DFA) for each IMF. We validated the method using a public dataset of 24 subjects with EEG signals from 22 channels and showed that it is possible to classify the epileptic seizures, even with segments of six seconds and a smaller number of channels (e.g., an accuracy of 0.93 using five channels). We were able to create a general machine-learning-based model to detect epileptic seizures of new subjects using epileptic-seizure data from various subjects, after reducing the number of instances, based on the k-means algorithm.

Regression analysis for detecting epileptic seizure with different feature extracting strategies

Due to the excitability of neurons in the brain, a neurological disorder is produced known as epilepsy. The brain activity of patients suffering from epilepsy is monitored through electroencephalography (EEG). The multivariate nature of features from time domain, frequency domain, complexity and wavelet entropy based, and the statistical features were extracted from healthy and epileptic subjects using the Bonn University database and seizure and non-seizure intervals using the CHB MIT database. The robust machine learning regression methods based on regression, support vector regression (SVR), regression tree (RT), ensemble regression, Gaussian process regression (GPR) were employed for detecting and predicting epileptic seizures. Performance was measured in terms of root mean square error (RMSE), squared error, mean square error (MSE) and mean absolute error (MAE). Moreover, detailed optimization was performed using a RT to predict the selected features from each feature category. A deeper analysis was conducted on features and tree regression methods where optimal RMSE and MSE results were obtained. The best optimal performance was obtained using the ensemble boosted regression tree (BRT) and exponential GPR with an RMSE of 0.47, an MSE (0.22), an R Square (RS) (0.25) and an MAE (0.30) using the Bonn University database and support vector machine (SVM) fine Gaussian with RMSE (0.63634), RS (0.03), MSE (0.40493) and MAE (0.31744); squared exponential GPR and rational quadratic GPR with an RMSE of 0.63841, an RS (0.03), an MSE (0.40757) and an MAE (0.3472) was obtained using the CHB MIT database. A further deeper analysis for the prediction of selected features was performed on an RT to compute the optimal feasible point, observed and estimated function values, function evaluation time, objective function evaluation time and overall elapsed time.

A review on the pattern detection methods for epilepsy seizure detection from EEG signals

Over several years, research had been conducted for the detection of epileptic seizures to support an automatic diagnosis system to comfort the clinicians' encumbrance. In this regard, a number of research papers have been published for the identification of epileptic seizures. A thorough review of all these papers is required. So, an attempt has been made to review on the pattern detection methods for epilepsy seizure detection from EEG signals. More than 150 research papers have been discussed to determine the techniques for detecting epileptic seizures. Further, the literature review confirms that the pattern recognition techniques required to detect epileptic seizures varies across the electroencephalogram (EEG) datasets of different conditions. This is mostly owing to the fact that EEG detected under different conditions have different characteristics. This consecutively necessitates the identification of the pattern recognition technique to efficiently differentiate EEG epileptic data from the EEG data of various conditions.

Applications of Higher Order Statistics in Electroencephalography Signal Processing: A Comprehensive Survey

Electroencephalography (EEG) is a noninvasive electrophysiological monitoring technique that records the electrical activities of the brain from the scalp using electrodes. EEG is not only an essential tool for diagnosing diseases and disorders affecting the brain, but also helps us to achieve a better understanding of brain's activities and structures. EEG recordings are weak, nonlinear, and nonstationary signals that contain various noise and artifacts. Therefore, for analyzing them, advanced signal processing techniques are required. Second order statistical features are usually sufficient for analyzing most basic signals. However, higher order statistical features possess characteristics that are missing in the second order; characteristics that can be highly beneficial for analysis of more complex signals, such as EEG. The primary goal of this article is to provide a comprehensive survey of the applications of higher order statistics or spectra (HOS) in EEG signal processing. Therefore, we start the survey with a summary of previous studies in EEG analysis followed by a brief mathematical description of HOS. Then, HOS related features and their applications in EEG analysis are presented. These applications are then grouped into three categories, each of which are further explored thoroughly with examples of prior studies. Finally, we provide some specific recommendations based on the literature survey and discuss possible future directions of this field.

Event-Related Potential Analysis of ADHD and Control Adults During a Sustained Attention Task

Background. Event-related potentials (ERPs) of attention deficit hyperactivity disorder (ADHD) population have been extensively studied using the time-domain representation of signals but time-frequency domain techniques are less explored. Although, adult ADHD is a proven disorder, most of the electrophysiological studies have focused only on children with ADHD. Methods. ERP data of 35 university students with ADHD and 35 control adults were recorded during visual continuous performance task (CPT). Gray level co-occurrence matrix-based texture features were extracted from time-frequency (t-f) images of event-related EEG epochs. Different ERP components measures, that is, amplitudes and latencies corresponding to N1, N2, and P3 components were also computed relative to standard and target stimuli. Results. Texture analysis has shown that the mean value of contrast, dissimilarity, and difference entropy is significantly reduced in adults with ADHD than in control adults. The mean correlation and homogeneity in adults with ADHD were significantly increased as compared with control adults. ERP components analysis has reported that adults with ADHD have reduced N1 amplitude to target stimuli, reduced N2 and P3 amplitude to both standard and target stimuli than controls. Conclusions. The differences in texture features obtained from t-f images of ERPs point toward altered information processing in adults with ADHD during a cognitive task. Findings of reduction in N1, N2, and P3 components highlight deficits of early sensory processing, stimulus categorization, and attentional resources, respectively, in adults with ADHD.

A strategy combining intrinsic time-scale decomposition and a feedforward neural network for automatic seizure detection

Epilepsy is a common neurological disorder which can occur in people of all ages globally. For the clinical treatment of epileptic patients, the detection of epileptic seizures is of great significance.

OBJECTIVE

Electroencephalography (EEG) is an essential component in the diagnosis of epileptic seizures, from which brain surgeons can detect important pathological information about patient epileptiform discharges. This paper focuses on adaptive seizure detection from EEG recordings. We propose a new feature extraction model based on an adaptive decomposition method, named intrinsic time-scale decomposition (ITD), which is suitable for analyzing non-linear and non-stationary data.

APPROACH

Firstly, using the ITD technique, every EEG recording is decomposed into several proper rotation components (PRCs). Secondly, the instantaneous amplitudes and frequencies of these PRCs can be calculated and then we extract their statistical indices. Furthermore, we combine all these statistical indices of the corresponding five PRCs as the feature vector of each EEG signal. Finally, these feature vectors are fed into a feedforward neural network (FNN) classifier for EEG classification. The whole process of feature extraction proposed in this paper only involves one parameter and the role of the ITD method is based on a piecewise linear function, which makes the computation of the model simple and fast. More useful information for classification can be obtained since we take advantage of both instantaneous amplitude and instantaneous frequency for feature extraction.

MAIN RESULTS

We consider the 17 classification problems which contain normal versus epileptic, non-seizure versus seizure and normal versus interictal versus ictal using a FNN classifier which only contains one hidden layer. Experimental results show that the proposed method can catch the discriminative features of EEG signals and obtain comparable results when compared with state-of-the-art detection methods.

SIGNIFICANCE

Therefore, the proposed system has a great potential in real-time seizure detection and provides physicians with a real-time diagnostic aid in their practice.

Wavelet based deep learning approach for epilepsy detection

Electroencephalogram (EEG) signal contains vital details regarding electrical actions performed by the brain. Analysis of these signals is important for epilepsy detection. However, analysis of these signals can be tricky in nature and requires human expertise. The human factor can result in subjective and possible erroneous epilepsy detection. To tackle this problem, Machine Learning (ML) algorithms were introduced, to remove the human factor. However, this approach is counterintuitive in nature as it involves using complex features for epilepsy detection. Hence to tackle this problem we have introduced a wavelet based deep learning approach which eliminates the need of feature extraction and also performs significantly better on smaller datasets compared to the present state of the art ML algorithms. To test the robustness of our model we have performed a binary (2-way) and ternary (3-way) classification using our model. It is found that the model is much more accurate than the present state of the art models and since it uses deep learning it also eliminates the need of feature extraction.

Recognition of Multiclass Epileptic EEG Signals Based on Knowledge and Label Space Inductive Transfer

Electroencephalogram (EEG) signal recognition based on machine learning models is becoming more and more attractive in epilepsy detection. For multiclass epileptic EEG signal recognition tasks including the detection of epileptic EEG signals from different blends of different background data and epilepsy EEG data and the classification of different types of seizures, we may perhaps encounter two serious challenges: (1) a large amount of EEG signal data for training are not available and (2) the models for epileptic EEG signal recognition are often so complicated that they are not as easy to explain as a linear model. In this paper, we utilize the proposed transfer learning technique to circumvent the first challenge and then design a novel linear model to circumvent the second challenge. Concretely, we originally combine γ -LSR with transfer learning to propose a novel knowledge and label space inductive transfer learning model for multiclass EEG signal recognition. By transferring both knowledge and the proposed generalized label space from the source domain to the target domain, the proposed model achieves enhanced classification performance on the target domain without the use of kernel trick. In contrast to the other inductive transfer learning methods, the method uses the generalized linear model such that it becomes simpler and more interpretable. Experimental results indicate the effectiveness of the proposed method for multiclass epileptic EEG signal recognition.

Evaluation of time domain features using best feature subsets based on mutual information for detecting epilepsy

In this pattern recognition study of detecting epilepsy, the first time the authors have attempted to use time domain (TD) features such as waveform length (WL), number of zero-crossings (ZC) and number of slope sign changes (SSC) which are extracted from the discrete wavelet transform (DWT) for the detecting the epilepsy for University of Bonn datasets and real-time clinical data. The performance of these TD features is studied along with mean absolute value (MAV) which has been attempted by other researchers. The performance of the TD features derived from DWT is studied using naive Bayes (NB) and support vector machines (SVM) for five different datasets from University of Bonn with 14 different combinations datasets and 24 patients datasets from Christian Medical College and Hospital (CMCH), India database. Using feature selection and feature ranking based on the estimation of mutual information (MI), the significant features required for the classifier to get higher accuracy is obtained. Further, NB achieves 100% classification accuracy (CA) in distinguishing normal eyes open and epileptic dataset with top 4 ranked features and it gives 100% accuracy with top-ranked two features in using CMCH data.

A NOVEL APPROACH FOR EPILEPSY DETECTION USING TIME–FREQUENCY LOCALIZED BI-ORTHOGONAL WAVELET FILTER

Identification of seizure using electroencephalogram (EEG) signal is crucial to detect diseases like epilepsy. Manual epilepsy detection is time consuming and prone to errors. Various techniques have been developed to get quick and accurate results for epilepsy detection. We propose a novel approach to detect epileptic seizure using bi-orthogonal wavelet filters. The bi-orthogonal wavelet filters divide the EEG signal into different sub-bands. Then different features, i.e., Shannon entropy (ShEn), Renyi entropy (RenEn), fractal dimension (FD), energy and fuzzy entropy (FE) are extracted from the sub-bands. The [Formula: see text]-values of the features are used to evaluate the discriminating ability of the features. These features are given as input to the support vector machine (SVM). The EEG signals are then classified into the following classes: (i) normal versus seizure, (ii) seizure-free versus seizure, (iii) normal versus seizure-free versus seizure, and (iv) normal versus seizure-free. We have used two independent datasets: a public dataset for training and validation of the model, and a private dataset for evaluating the model’s performance. The ten-fold cross-validation method is used here to reduce the chances of over fitting. The SVM classifier yielded 100% accuracy in discriminating both seizure-free and normal patients for public dataset, and inter-ictal and ictal for private dataset. It also gave very good classification accuracies for the other classification problems for both the datasets. The proposed method is ready for the clinical trial to be tested with huge databases before the actual practical usage.

Detection Analysis of Epileptic EEG Using a Novel Random Forest Model Combined With Grid Search Optimization

In the automatic detection of epileptic seizures, the monitoring of critically ill patients with time varying EEG signals is an essential procedure in intensive care units. There is an increasing interest in using EEG analysis to detect seizure, and in this study we aim to get a better understanding of how to visualize the information in the EEG time-frequency feature, and design and train a novel random forest algorithm for EEG decoding, especially for multiple-levels of illness. Here, we propose an automatic detection framework for epileptic seizure based on multiple time-frequency analysis approaches; it involves a novel random forest model combined with grid search optimization. The short-time Fourier transformation visualizes seizure features after normalization. The dimensionality of features is reduced through principal component analysis before feeding them into the classification model. The training parameters are optimized using grid search optimization to improve detection performance and diagnostic accuracy by in the recognition of three different levels epileptic of conditions (healthy subjects, seizure-free intervals, seizure activity). Our proposed model was used to classify 500 samples of raw EEG data, and multiple cross-validations were adopted to boost the modeling accuracy. Experimental results were evaluated by an accuracy, a confusion matrix, a receiver operating characteristic curve, and an area under the curve. The evaluations indicated that our model achieved the more effective classification than some previous typical methods. Such a scheme for computer-assisted clinical diagnosis of seizures has a potential guiding significance, which not only relieves the suffering of patient with epilepsy to improve quality of life, but also helps neurologists reduce their workload.

Automated Recognition of Epileptic EEG States Using a Combination of Symlet Wavelet Processing, Gradient Boosting Machine, and Grid Search Optimizer

Automatic recognition methods for non-stationary electroencephalogram (EEG) data collected from EEG sensors play an essential role in neurological detection. The integrated approaches proposed in this study consist of Symlet wavelet processing, a gradient boosting machine, and a grid search optimizer for a three-class classification scheme for normal subjects, intermittent epilepsy, and continuous epilepsy. Fourth-order Symlet wavelets are adopted to decompose the EEG data into five frequencies sub-bands, such as gamma, beta, alpha, theta, and delta, whose statistical features were computed and used as classification features. The grid search optimizer is used to automatically find the optimal parameters for training the classifier. The classification accuracy of the gradient boosting machine was compared with that of a conventional support vector machine and a random forest classifier constructed according to previous descriptions. Multiple performance indices were used to evaluate the proposed classification scheme, which provided better classification accuracy and detection effectiveness than has been recently reported in other studies on three-class classification of EEG data.

Epilepsy detection from EEG signals: a review

Over many decades, research is being attempted for the detection of epileptic seizure to support for automatic diagnosis system to help clinicians from burdensome work. In this respect, an enormous number of research papers is published for identification of epileptic seizure. It is difficult to present a detailed review of all these literature. Therefore, in this paper, an attempt has been made to review the detection of an epileptic seizure. More than 100 research papers have been discussed to discern the techniques for detecting the epileptic seizure. Further, the literature survey shows that the pattern recognition required to detect epileptic seizure varies with different conditions of EEG datasets. This is mainly due to the fact that EEG detected under different conditions has different characteristics. This is, in turn, necessitates the identification of pattern recognition technique to effectively distinguish EEG epileptic data from a various condition of EEG data.

Short-Time Fourier Transform Based Spike Detection of Spontaneous Peripheral Nerve Activity

Peripheral nerve interfaces are designed to record neural activity from residual nerves in amputees. Reliable detection of neural events from these recordings dictate the performance of neuroprosthetic device control. Extraction of neural events from peripheral nerve recordings is challenging because of low signal to noise ratio (SNR), sparse spiking pattern and the presence of electromyographic signal contamination from the surrounding muscles. In this study, we developed a spike detection algorithm based on Short-time Fourier Transform (STFT) and compared its performance to simple thresholding technique using synthesized nerve recordings. To mimic peripheral nerve recordings and produce ground-truth for validation, a quasi-simulation framework is proposed to incrementally synthesize signals from physiological recordings. A detection threshold was optimized on the spectral features of simulated signals and performance evaluation was done using an independent simulated data set. Results show that the STFT based technique, compared to the simple thresholding, reduces the false detection rate even in recordings with moderately low SNR.

A Distributed Descriptor Characterizing Structural Irregularity of EEG Time Series for Epileptic Seizure Detection

This paper presents a novel descriptor aiming at anomaly detection in sequential data, like epileptic seizure detection with EEG time series. The descriptor is derived from the eigenvalue decomposition (EVD) of a Hankel-form data matrix generated from the raw time series. Simulation trials imply that the descriptor is capable of characterizing the structural aspect of a time series. In addition, we deploy the proposed descriptor as a feature extractor and apply it on Bonn Seizure Database which is widely used in seizure detection. The high accuracies on classification problems are comparable with the state-of-the-art so validate the effectiveness of our method.