Approximate Entropy-Based Epileptic EEG Detection Using Artificial Neural Networks

Nonlinear System Identification of Neural Systems from Neurophysiological Signals

The human nervous system is one of the most complicated systems in nature. Complex nonlinear behaviours have been shown from the single neuron level to the system level. For decades, linear connectivity analysis methods, such as correlation, coherence and Granger causality, have been extensively used to assess the neural connectivities and input-output interconnections in neural systems. Recent studies indicate that these linear methods can only capture a certain amount of neural activities and functional relationships, and therefore cannot describe neural behaviours in a precise or complete way. In this review, we highlight recent advances in nonlinear system identification of neural systems, corresponding time and frequency domain analysis, and novel neural connectivity measures based on nonlinear system identification techniques. We argue that nonlinear modelling and analysis are necessary to study neuronal processing and signal transfer in neural systems quantitatively. These approaches can hopefully provide new insights to advance our understanding of neurophysiological mechanisms underlying neural functions. These nonlinear approaches also have the potential to produce sensitive biomarkers to facilitate the development of precision diagnostic tools for evaluating neurological disorders and the effects of targeted intervention.

Multifuse multilayer multikernel RVFLN+ of process modes decomposition and approximate entropy data from iEEG/sEEG signals for epileptic seizure recognition

In this paper, the extracted features using variational mode decomposition (VMD) and approximate entropy (ApEn) privileged information of the input EEG signals are combined with multilayer multikernel random vector functional link network plus (MMRVFLN+) classifier to recognize the epileptic seizure epochs efficaciously. In our experiment Bonn University single-channel intracranial electroencephalogram (iEEG) and Children's Hospital Boston-Massachusetts Institute of Technology (CHB-MIT) multichannel scalp EEG (sEEG) recordings are considered to evaluate the efficacy of the proposed method. The VMD is applied on chaotic, non-stationary, nonlinear, and complex EEG signal to decompose it into three band-limited intrinsic mode functions (BLIMFs). The Hilbert transform (HT) is applied on BLIMFs to extract informative spectral and temporal features. The ApEn is computed from the raw EEG signals as the privileged information and given to the multi-hidden layer structure to obtain the most discriminative compressed form. The scatter plots show the distinct nature of compressed privileged ApEn information among the seizure pattern classes. The linear as well as nonlinear mapping, local and global kernel function, high-learning speed, less computationally complex MMRVFLN+ classifier is proposed to recognize the seizure events accurately by importing the efficacious features with ApEn as the input. The advanced signal processing algorithm i.e., Hilbert Huang transform (HHT) with ApEn and MMRVFLN+ are combined to compare the performance with the proposed VMDHTApEn-MMRVFLN+ method. The proposed method has remarkable recognition ability, superior classification accuracy, and excellent overall performance as compared to other methods. The digital architecture of the multifuse MMRVFLN+ is developed and implemented on a high-speed reconfigurable FPGA hardware platform to validate the effectiveness of the proposed method. The superior classification accuracy, the negligible false positive rate per hour (FPR/h), simplicity, feasibility, robustness, and practicability of the proposed method validate its ability to recognize the epileptic seizure epochs automatically.

A Review on Machine Learning for EEG Signal Processing in Bioengineering

Electroencephalography (EEG) has been a staple method for identifying certain health conditions in patients since its discovery. Due to the many different types of classifiers available to use, the analysis methods are also equally numerous. In this review, we will be examining specifically machine learning methods that have been developed for EEG analysis with bioengineering applications. We reviewed literature from 1988 to 2018 to capture previous and current classification methods for EEG in multiple applications. From this information, we are able to determine the overall effectiveness of each machine learning method as well as the key characteristics. We have found that all the primary methods used in machine learning have been applied in some form in EEG classification. This ranges from Naive-Bayes to Decision Tree/Random Forest, to Support Vector Machine (SVM). Supervised learning methods are on average of higher accuracy than their unsupervised counterparts. This includes SVM and KNN. While each of the methods individually is limited in their accuracy in their respective applications, there is hope that the combination of methods when implemented properly has a higher overall classification accuracy. This paper provides a comprehensive overview of Machine Learning applications used in EEG analysis. It also gives an overview of each of the methods and general applications that each is best suited to.

Electroencephalographic Correlates and Predictors of Treatment Outcome in OCD: A Brief Narrative Review

Electroencephalography (EEG) measures the brain's electrical activity with high temporal resolution. In comparison to neuroimaging modalities such as MRI or PET, EEG is relatively cheap, non-invasive, portable, and simple to administer, making it an attractive tool for clinical deployment. Despite this, studies utilizing EEG to investigate obsessive-compulsive disorder (OCD) are relatively sparse. This contrasts with a robust literature using other brain imaging methodologies. The present review examines studies that have used EEG to examine predictors and correlates of response in OCD and draws tentative conclusions that may guide much needed future work. Key findings include a limited literature base; few studies have attempted to predict clinical change from EEG signals, and they are confounded by the effects of both pharmacotherapy and psychotherapy. The most robust literature, consisting of several studies, has examined event-related potentials, including the P300, which several studies have reported to be abnormal at baseline in OCD and to normalize with treatment; but even here the literature is quite heterogeneous, and more work is needed. With more robust research, we suggest that the relatively low cost and convenience of EEG, especially in comparison to fMRI and PET, make it well-suited to the development of feasible personalized treatment algorithms.

Empirical Mode Decomposition Based Multi-Modal Activity Recognition

This paper aims to develop an activity recognition algorithm to allow parents to monitor their children at home after school. A common method used to analyze electroencephalograms is to use infinite impulse response filters to decompose the electroencephalograms into various brain wave components. However, nonlinear phase distortions will be introduced by these filters. To address this issue, this paper applies empirical mode decomposition to decompose the electroencephalograms into various intrinsic mode functions and categorize them into four groups. In addition, common features used to analyze electroencephalograms are energy and entropy. However, because there are only two features, the available information is limited. To address this issue, this paper extracts 11 different physical quantities from each group of intrinsic mode functions, and these are employed as the features. Finally, this paper uses the random forest to perform activity recognition. It is worth noting that the conventional approach for performing activity recognition is based on a single type of signal, which limits the recognition performance. In this paper, a multi-modal system based on electroencephalograms, image sequences, and motion signals is used for activity recognition. The numerical simulation results show that the percentage accuracies based on three types of signal are higher than those based on two types of signal or the individual signals. This demonstrates the advantages of using the multi-modal approach for activity recognition. In addition, our proposed empirical mode decomposition-based method outperforms the conventional filtering-based method. This demonstrates the advantages of using the nonlinear and adaptive time frequency approach for activity recognition.

Localization of the epileptogenic zone based on ictal stereo-electroencephalogram: Brain network and single-channel signal feature analysis

Accurate localization of the epileptogenic zone (EZ) is crucial for refractory focal epilepsy patients to achieve freedom from seizures following epilepsy surgery. In this study, ictal stereo-electroencephalography data from 35 patients with refractory focal epilepsy were analyzed. Effective networks based on partial directed coherence were analyzed, and a gray level co-occurrence matrix was applied to extract the time-varying features of the in-degree. These features, combined with the single-channel signal time-frequency features, including approximate entropy and line length, were used to localize the EZ based on a cluster algorithm. For all seizure-free patients (n = 23), the proposed method was effective in identifying the clinical-EZ-contacts and clinical-EZ-blocks, with an F1-score of 62.47 % and 72.18 %, respectively. The sensitivity was 96.00 % for the clinical-EZ-block identification, which provided the information for the decision-making of clinicians, prompting clinicians to focus on the identified EZ-blocks and their nearby contacts. The agreement between the EZ identified by the proposed method and the clinical-EZ was worse for non-seizure-free patients (n = 12) than for seizure-free patients. Furthermore, our method provided better results than using only brain network or single-channel signal features. This suggests that combining these complementary features can facilitate more accurate localization of the EZ.

Non-Gaussianity Detection of EEG Signals Based on a Multivariate Scale Mixture Model for Diagnosis of Epileptic Seizures

OBJECTIVE

The detection of epileptic seizures from scalp electroencephalogram (EEG) signals can facilitate early diagnosis and treatment. Previous studies suggested that the Gaussianity of EEG distributions changes depending on the presence or absence of seizures; however, no general EEG signal models can explain such changes in distributions within a unified scheme.

METHODS

This article describes the formulation of a stochastic EEG model based on a multivariate scale mixture distribution that can represent changes in non-Gaussianity caused by stochastic fluctuations in EEG. In addition, we propose an EEG analysis method by combining the model with a filter bank and introduce a feature representing the non-Gaussianity latent in each EEG frequency band.

RESULTS

We applied the proposed method to multichannel EEG data from twenty patients with focal epilepsy. The results showed a significant increase in the proposed feature during epileptic seizures, particularly in the high-frequency band. The feature calculated in the high-frequency band allowed highly accurate classification of seizure and non-seizure segments [area under the receiver operating characteristic curve (AUC) = 0.881] using only a simple threshold.

CONCLUSION

This article proposed a multivariate scale mixture distribution-based stochastic EEG model capable of representing non-Gaussianity associated with epileptic seizures. Experiments using simulated and real EEG data demonstrated the validity of the model and its applicability to epileptic seizure detection.

SIGNIFICANCE

The stochastic fluctuations of EEG quantified by the proposed model can help detect epileptic seizures with high accuracy.

Regularization of Deep Neural Networks for EEG Seizure Detection to Mitigate Overfitting

Seizure detection is a major goal for simplifying the workflow of clinicians working on EEG records. Current algorithms can only detect seizures effectively for patients already presented to the classifier. These algorithms are hard to generalize outside the initial training set without proper regularization and fail to capture seizures from the larger population. We proposed a data processing pipeline for seizure detection on an intra-patient dataset from the world's largest public EEG seizure corpus. We created spatially and session invariant features by forcing our networks to rely less on exact combinations of channels and signal amplitudes, but instead to learn dependencies towards seizure detection. For comparison, the baseline results without any additional regularization on a deep learning model achieved an F1 score of 0.544. By using random rearrangements of channels on each minibatch to force the network to generalize to other combinations of channels, we increased the F1 score to 0.629. By using random rescale of the data within a small range, we further increased the F1 score to 0.651 for our best model. Additionally, we applied adversarial multi-task learning and achieved similar results. We observed that session and patient specific dependencies were causing overfitting of deep neural networks, and the most overfitting models learnt features specific only to the EEG data presented. Thus, we created networks with regularization that the deep learning did not learn patient and session-specific features. We are the first to use random rearrangement, random rescale, and adversarial multitask learning to regularize intra-patient seizure detection and have increased sensitivity to 0.86 comparing to baseline study.

Identification of epilepsy from intracranial EEG signals by using different neural network models

In this work, a framework is provided for identifying intracranial electroencephalography (iEEG) seizures based on discrete wavelet transform (DWT) analysis of iEEG signals using forward propagation and feedback neural networks. The performance of 5 different data sets combination classifications is studied using the probabilistic neural network (PNN), learning vector quantization neural network (LVQ) and Elman neural network (ENN). Different feature combinations serve as the input vectors of the classifiers to obtain the best outcomes. It has been found that PNN has less running time and provides better classification accuracy (CA) than ENN and LVQ classifiers for all 5 classification problems. It is worth noticing that the CA for the C-D classification task, which shows the status of pre-ictal versus post-ictal, has been greatly improved, and reached 83.13%. Hence, the epilepsy iEEG signals pattern recognition based on DWT statistical features using the PNN classifier is more suitable for forming a reliable, automatic classification system in order to assist doctors in diagnosis.

EEG Channel-Selection Method for Epileptic-Seizure Classification Based on Multi-Objective Optimization

We present a multi-objective optimization method for electroencephalographic (EEG) channel selection based on the non-dominated sorting genetic algorithm (NSGA) for epileptic-seizure classification. We tested the method on EEG data of 24 patients from the CHB-MIT public dataset. The procedure starts by decomposing the EEG data from each channel into different frequency bands using the empirical mode decomposition (EMD) or the discrete wavelet transform (DWT), and then for each sub-band four features are extracted; two energy values and two fractal dimension values. The obtained feature vectors are then iteratively tested for solving two unconstrained objectives by NSGA-II or NSGA-III; to maximize classification accuracy and to reduce the number of EEG channels required for epileptic seizure classification. Our results have shown accuracies of up to 1.00 with only one EEG channel. Interestingly, when using all the EEG channels available, lower accuracies were achieved compared to the case when EEG channels were selected by NSGA-II or NSGA-III; i.e., in patient 19 we obtained an accuracy of 0.95 using all the channels and 0.975 using only two channels selected by NSGA-III. The results obtained are encouraging and it has been shown that it is possible to classify epileptic seizures using a few electrodes, which provide evidence for the future development of portable EEG seizure detection devices.

Use of EEG for Predicting Treatment Response to Transcranial Magnetic Stimulation in Obsessive Compulsive Disorder

Aim. In this study we assessed the predictive power of quantitative EEG (qEEG) for the treatment response to right frontal transcranial magnetic stimulation (TMS) in obsessive compulsive disorder (OCD) using a machine learning approach. Method. The study included 50 OCD patients (35 responsive to TMS, 15 nonresponsive) who were treated with right frontal low frequency stimulation and identified retrospectively from Uskudar Unversity, NPIstanbul Brain Hospital outpatient clinic. All patients were diagnosed with OCD according to the DSM-IV-TR and DSM-5 criteria. We first extracted pretreatment band powers for patients. To explore the prediction accuracy of pretreatment EEG, we employed machine learning methods using an artificial neural network model. Results. Among 4 EEG bands, theta power successfully discriminated responsive from nonresponsive patients. Responsive patients had more theta powers for all electrodes as compared to nonresponsive patients. Discussion. qEEG could be helpful before deciding about treatment strategy in OCD. The limitations of our study are moderate sample size and limited number of nonresponsive patients and that treatment response was defined by clinicians and not by using a formal symptom measurement scale. Future studies with larger samples and prospective design would show the role of qEEG in predicting TMS response better.

Multiband entropy-based feature-extraction method for automatic identification of epileptic focus based on high-frequency components in interictal iEEG

Presurgical investigations for categorizing focal patterns are crucial, leading to localization and surgical removal of the epileptic focus. This paper presents a machine learning approach using information theoretic features extracted from high-frequency subbands to detect the epileptic focus from interictal intracranial electroencephalogram (iEEG). It is known that high-frequency subbands (>80 Hz) include important biomarkers such as high-frequency oscillations (HFOs) for identifying epileptic focus commonly referred to as the seizure onset zone (SOZ). In this analysis, the multi-channel interictal iEEG signals were splitted into segments and each segment was decomposed into multiple high-frequency subbands. The different types of entropy were calculated for each of the subbands and the sparse linear discriminant analysis (sLDA) was applied to select the prominent entropy features. Due to the imbalance of SOZ and non-SOZ channels in iEEG data, the use of machine learning techniques is always tricky. To deal with the imbalanced learning problem, an adaptive synthetic oversampling approach (ADASYN) with radial basis function kernel-based SVM was used to detect the focal segments. Finally, the epileptic focus was identified based on detection of focal segments on SOZ and non-SOZ channels. Eight patients were examined to observe the efficiency of the automatic detector. The experimental results and statistical tests indicate that the proposed automatic detector can identify the epileptic focus accurately and efficiently.

Cross-database evaluation of EEG based epileptic seizures detection driven by adaptive median feature baseline correction

OBJECTIVE

In long-term electroencephalogram (EEG) signals, automated classification of epileptic seizures is desirable in diagnosing epilepsy patients, as it otherwise depends on visual inspection. To the best of the author's knowledge, existing studies have validated their algorithms using cross-validation on the same database and less number of attempts have been made to extend their work on other databases to test the generalization capability of the developed algorithms. In this study, we present the algorithm for cross-database evaluation for classification of epileptic seizures using five EEG databases collected from different centers. The cross-database framework helps when sufficient epileptic seizures EEG data are not available to build automated seizure detection model.

METHODS

Two features, namely successive decomposition index and matrix determinant were extracted at a segmentation length of 4 s (50% overlap). Then, adaptive median feature baseline correction (AM-FBC) was applied to overcome the inter-patient and inter-database variation in the feature distribution. The classification was performed using a support vector machine classifier with leave-one-database-out cross-validation. Different classification scenarios were considered using AM-FBC, smoothing of the train and test data, and post-processing of the classifier output.

RESULTS

Simulation results revealed the highest area under the curve-sensitivity-specificity-false detections (per hour) of 1-1-1-0.15, 0.89-0.99-0.82-2.5, 0.99-0.73-1-1, 0.95-0.97-0.85-1.7, 0.99-0.99-0.92-1.1 using the Ramaiah Medical College and Hospitals, Children's Hospital Boston-Massachusetts Institute of Technology, Temple University Hospital, Maastricht University Medical Centre, and University of Bonn databases respectively.

CONCLUSIONS

We observe that the AM-FBC plays a significant role in improving seizure detection results by overcoming inter-database variation of feature distribution.

SIGNIFICANCE

To the best of the author's knowledge, this is the first study reporting on the cross-database evaluation of classification of epileptic seizures and proven to be better generalization capability when evaluated using five databases and can contribute to accurate and robust detection of epileptic seizures in real-time.

Automatic Seizure Detection using Fully Convolutional Nested LSTM

The automatic seizure detection system can effectively help doctors to monitor and diagnose epilepsy thus reducing their workload. Many outstanding studies have given good results in the two-class seizure detection problems, but most of them are based on hand-wrought feature extraction. This study proposes an end-to-end automatic seizure detection system based on deep learning, which does not require heavy preprocessing on the EEG data or feature engineering. The fully convolutional network with three convolution blocks is first used to learn the expressive seizure characteristics from EEG data. Then these robust EEG features pertinent to seizures are presented as an input to the Nested Long Short-Term Memory (NLSTM) model to explore the inherent temporal dependencies in EEG signals. Lastly, the high-level features obtained from the NLSTM model are fed into the softmax layer to output predicted labels. The proposed method yields an accuracy range of 98.44–100% in 10 different experiments based on the Bonn University database. A larger EEG database is then used to evaluate the performance of the proposed method in real-life situations. The average sensitivity of 97.47%, specificity of 96.17%, and false detection rate of 0.487 per hour are yielded. For CHB–MIT Scalp EEG database, the proposed model also achieves a segment-level sensitivity of 94.07% with a false detection rate of 0.66 per hour. The excellent results obtained on three different EEG databases demonstrate that the proposed method has good robustness and generalization power under ideal and real-life conditions.

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.

Complexity analysis and dynamic characteristics of EEG using MODWT based entropies for identification of seizure onset

In this paper, complexity analysis and dynamic characteristics of electroencephalogram (EEG) signal based on maximal overlap discrete wavelet transform (MODWT) has been exploited for the identification of seizure onset. Since wavelet-based studies were well suited for classification of normal and epileptic seizure EEG, we have applied MODWT which is an improved version of discrete wavelet transform (DWT). The selection of optimal wavelet sub-band and features plays a crucial role to understand the brain dynamics in epileptic patients. Therefore, we have investigated MODWT using four different wavelets, namely Haar, Coif4, Dmey, and Sym4 sub-bands until seven levels. Further, we have explored the potentials of six entropies, namely sigmoid, Shannon, wavelet, Renyi, Tsallis, and Steins unbiased risk estimator (SURE) entropies in each sub-band. The sigmoid entropy extracted from Haar wavelet in sub-band D4 showed the highest accuracy of 98.44% using support vector machine classifier for the EEG collected from Ramaiah Medical College and Hospitals (RMCH). Further, the highest accuracy of 100% and 94.51% was achieved for the University of Bonn (UBonn) and CHB-MIT databases respectively. The findings of the study showed that Haar and Dmey wavelets were found to be computationally economical and expensive respectively. Besides, in terms of dynamic characteristics, MODWT results revealed that the highest energy present in sub-bands D2, D3, and D4 and entropies in those respective sub-bands outperformed other entropies in terms of classification results for RMCH database. Similarly, using all the entropies, sub-bands D5 and D6 outperformed other sub-bands for UBonn and CHB-MIT databases respectively. In conclusion, the comparison results of MODWT outperformed DWT.

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.

Electrophysiological assessment of plant status outside a Faraday cage using supervised machine learning

Living organisms have evolved complex signaling networks to drive appropriate physiological processes in response to changing environmental conditions. Amongst them, electric signals are a universal method to rapidly transmit information. In animals, bioelectrical activity measurements in the heart or the brain provide information about health status. In plants, practical measurements of bioelectrical activity are in their infancy and transposition of technology used in human medicine could therefore, by analogy provide insight about the physiological status of plants. This paper reports on the development and testing of an innovative electrophysiological sensor that can be used in greenhouse production conditions, without a Faraday cage, enabling real-time electric signal measurements. The bioelectrical activity is modified in response to water stress conditions or to nycthemeral rhythm. Furthermore, the automatic classification of plant status using supervised machine learning allows detection of these physiological modifications. This sensor represents an efficient alternative agronomic tool at the service of producers for decision support or for taking preventive measures before initial visual symptoms of plant stress appear.

Complex network based models of ECoG signals for detection of induced epileptic seizures in rats

The automatic detection of seizures bears a considerable significance in epileptic diagnosis as it can efficiently lead to a considerable reduction of the workload of the medical staff. The present study aims at automatic detecting epileptic seizures in epileptic rats. To this end, seizures were induced in rats implementing the pentylenetetrazole model, with the electrocorticogram (ECoG) signals during, before and after the seizure periods being recorded. For this purpose, five algorithms for transforming time series into complex networks based on visibility graph (VG) algorithm were used. In this study, VG based methods were used for the first time to analyze ECoG signals in rats. Afterward, Standard measures in network science (graph properties) were made to examine the topological structure of these networks produced on the basis of ECoG signals. Then these measures were given to a classifier as input features so that the ECoG signals could be classified into seizure periods and seizure-free periods. Artificial Neural Network, considered a popular classifier, was used in this work. The experimental results showed that the method managed to detect epileptic seizure in rats with a high accuracy of 92.13%. Our proposed method was also applied to the recorded EEG signals from Bonn database to show the efficiency of the proposed method for human seizure detection.

Exploring Douglas-Peucker Algorithm in the Detection of Epileptic Seizure from Multicategory EEG Signals

Discovering the concealed patterns of Electroencephalogram (EEG) signals is a crucial part in efficient detection of epileptic seizures. This study develops a new scheme based on Douglas-Peucker algorithm (DP) and principal component analysis (PCA) for extraction of representative and discriminatory information from epileptic EEG data. As the multichannel EEG signals are highly correlated and are in large volumes, the DP algorithm is applied to extract the most representative samples from EEG data. The PCA is utilised to produce uncorrelated variables and to reduce the dimensionality of the DP samples for better recognition. To verify the robustness of the proposed method, four machine learning techniques, random forest classifier (RF), k-nearest neighbour algorithm (k-NN), support vector machine (SVM), and decision tree classifier (DT), are employed on the obtained features. Furthermore, we assess the performance of the proposed methods by comparing it with some recently reported algorithms. The experimental results show that the DP technique effectively extracts the representative samples from EEG signals compressing up to over 47% sample points of EEG signals. The results also indicate that the proposed feature method with the RF classifier achieves the best performance and yields 99.85% of the overall classification accuracy (OCA). The proposed method outperforms the most recently reported methods in terms of OCA in the same epileptic EEG database.

Entropy-Based Quantitative Electroencephalogram Analysis for Diagnosing Attention-Deficit Hyperactivity Disorder in Girls

Diagnosis of attention-deficit hyperactivity disorder (ADHD) is currently based on core symptoms or checklists; however, the inevitability of practitioner subjectivity leads to over- and underdiagnosis. Although the Federal Drug Administration has approved an elevated theta/beta ratio (TBR) of the electroencephalogram (EEG) band as a tool for assisting ADHD diagnosis, several studies have reported no significant differences of the TBR between ADHD and control subjects. This study detailed the development of a method based on approximate entropy (ApEn) analysis of EEG to compare ADHD and control groups. Differences between ADHD presentation in boys and girls indicate the necessity of separate investigations. This study enrolled 30 girls with ADHD and 30 age-matched controls. The results revealed significantly higher ApEn values in most brain areas in the control group than in the ADHD group. Compared with TBR-related feature descriptors, ApEn-related feature descriptors can produce the higher average true positive rate (0.846), average true negative rate (0.814), average accuracy (0.817), and average area under the receiver operating characteristic curve value (0.862). Therefore, compared with TBR, ApEn possessed the better potential for differentiating between girls with ADHD and controls.

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.

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.

Spectral entropy indicates electrophysiological and hemodynamic changes in drug-resistant epilepsy - A multimodal MREG study

Objective

Epilepsy causes measurable irregularity over a range of brain signal frequencies, as well as autonomic nervous system functions that modulate heart and respiratory rate variability. Imaging dynamic neuronal signals utilizing simultaneously acquired ultra-fast 10 Hz magnetic resonance encephalography (MREG), direct current electroencephalography (DC-EEG), and near-infrared spectroscopy (NIRS) can provide a more comprehensive picture of human brain function. Spectral entropy (SE) is a nonlinear method to summarize signal power irregularity over measured frequencies. SE was used as a joint measure to study whether spectral signal irregularity over a range of brain signal frequencies based on synchronous multimodal brain signals could provide new insights in the neural underpinnings of epileptiform activity.

Methods

Ten patients with focal drug-resistant epilepsy (DRE) and ten healthy controls (HC) were scanned with 10 Hz MREG sequence in combination with EEG, NIRS (measuring oxygenated, deoxygenated, and total hemoglobin: HbO, Hb, and HbT, respectively), and cardiorespiratory signals. After pre-processing, voxelwise SE_MREG was estimated from MREG data. Different neurophysiological and physiological subfrequency band signals were further estimated from MREG, DC-EEG, and NIRS: fullband (0–5 Hz, FB), near FB (0.08–5 Hz, NFB), brain pulsations in very-low (0.009–0.08 Hz, VLFP), respiratory (0.12–0.4 Hz, RFP), and cardiac (0.7–1.6 Hz, CFP) frequency bands. Global dynamic fluctuations in MREG and NIRS were analyzed in windows of 2 min with 50% overlap.

Results

Right thalamus, cingulate gyrus, inferior frontal gyrus, and frontal pole showed significantly higher SE_MREG in DRE patients compared to HC. In DRE patients, SE of cortical Hb was significantly reduced in FB (p = .045), NFB (p = .017), and CFP (p = .038), while both HbO and HbT were significantly reduced in RFP (p = .038, p = .045, respectively). Dynamic SE of HbT was reduced in DRE patients in RFP during minutes 2 to 6. Fitting to the frontal MREG and NIRS results, DRE patients showed a significant increase in SE_EEG in FB in fronto-central and parieto-occipital regions, in VLFP in parieto-central region, accompanied with a significant decrease in RFP in frontal pole and parietal and occipital (O2, Oz) regions.

Conclusion

This is the first study to show altered spectral entropy from synchronous MREG, EEG, and NIRS in DRE patients. Higher SE_MREG in DRE patients in anterior cingulate gyrus together with SE_EEG and SE_NIRS results in 0.12–0.4 Hz can be linked to altered parasympathetic function and respiratory pulsations in the brain. Higher SE_MREG in thalamus in DRE patients is connected to disturbances in anatomical and functional connections in epilepsy. Findings suggest that spectral irregularity of both electrophysiological and hemodynamic signals are altered in specific way depending on the physiological frequency range.

•

Simultaneous imaging methods indicate spectral irregularity in neurovascular and electrophysiological brain pulsations in DRE.

•

Altered spectral entropy in EEG, NIRS and BOLD indicate dysfunctional brain pulsations in respiratory frequency in epilepsy.

•

Spectral irregularity (0-5 Hz) of BOLD in right thalamus supports previous structural and functional findings in epilepsy.

Automated Detection of Postictal Generalized EEG Suppression

Although there is no strict consensus, some studies have reported that Postictal generalized EEG suppression (PGES) is a potential electroencephalographic (EEG) biomarker for risk of sudden unexpected death in epilepsy (SUDEP). PGES is an epoch of EEG inactivity after a seizure, and the detection of PGES in clinical data is extremely difficult due to artifacts from breathing, movement and muscle activity that can adversely affect the quality of the recorded EEG data. Even clinical experts visually interpreting the EEG will have diverse opinions on the start and end of PGES for a given patient. The development of an automated EEG suppression detection tool can assist clinical personnel in the review and annotation of seizure files, and can also provide a standard for quantifying PGES in large patient cohorts, possibly leading to further clarification of the role of PGES as a biomarker of SUDEP risk. In this paper, we develop an automated system that can detect the start and end of PGES using frequency domain features in combination with boosting classification algorithms. The average power for different frequency ranges of EEG signals are extracted from the prefiltered recorded signal using the fast fourier transform and are used as the feature set for the classification algorithm. The underlying classifiers for the boosting algorithm are linear classifiers using a logistic regression model. The tool is developed using 12 seizures annotated by an expert then tested and evaluated on another 20 seizures that were annotated by 11 experts.

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.

Automated epileptic seizures detection using multi-features and multilayer perceptron neural network

Detection of epileptic seizure activities from long-term multi-channel electroencephalogram (EEG) signals plays a significant role in the timely treatment of the patients with epilepsy. Visual identification of epileptic seizure in long-term EEG is cumbersome and tedious for neurologists, which might also lead to human error. Therefore, an automated tool for accurate detection of seizures in a long-term multi-channel EEG is essential for the clinical diagnosis. This study proposes an algorithm using multi-features and multilayer perceptron neural network (MLPNN) classifier. After appropriate approval from the ethical committee, recordings of EEG data were collected from the Institute of Neurosciences, Ramaiah Memorial College and Hospital, Bengaluru. Initially, preprocessing was performed to remove the power-line noise and motion artifacts. Four features, namely power spectral density (Yule–Walker), entropy (Shannon and Renyi), and Teager energy, were extracted. The Wilcoxon rank-sum test and descriptive analysis ensure the suitability of the proposed features for pattern classification. Single and multi-features were fed to the MLPNN classifier to evaluate the performance of the study. The simulation results showed sensitivity, specificity, and false detection rate of 97.1%, 97.8%, and 1 h⁻¹, respectively, using multi-features. Further, the results indicate the proposed study is suitable for real-time seizure recognition from multi-channel EEG recording. The graphical user interface was developed in MATLAB to provide an automated biomarker for normal and epileptic EEG signals.

Spike detection using a multiresolution entropy based method

Correct interpretation of neural mechanisms depends on the accurate detection of neuronal activities, which become visible as spikes in the electrical activity of neurons. In the present work, a novel entropy based method is proposed for spike detection which employs the fact that transient spike events change the entropy level of the neural time series. In this regard, the time-dependent entropy method can be used for detecting spike times, where the entropy of a selected segment of a neural time series, using a sliding window approach, is calculated and the time of the events are highlighted by sharp peaks in the output of the time-dependent entropy method. It is shown that the length of the sliding window determines the resolution of the time series in entropy space, therefore, the calculation is performed with a different window length for obtaining a multiresolution transform. The final decision threshold for detecting spike events is applied to the point-wise product of the time dependent entropy calculations with different resolutions. The proposed detection method has been assessed using several simulated and real neural data sets. The results show that the proposed method detects spikes in their exact times while compared with other traditional methods, relatively lower false alarm rate is obtained.

Deception Decreases Brain Complexity

Extensive evidence suggests the feasibility of lie detection using electroencephalograms (EEGs). However, it is largely unknown whether there are any differences in the nonlinear features of EEGs between guilty and innocent subjects. In this study, we proposed a complexity-based method to distinguish lying from truth telling. A total of 35 participants were randomly divided into two groups, and their EEG signals were recorded with 14 electrodes. Averages for sequential sets of five trials were first calculated for the probe responses within each subject. Next, a common wavelet entropy (WE) measure and an improved one were used to quantify complexity from each five-trial average. The results show that for both measures, the WE values in the guilty subjects are statistically lower than those in the innocent subjects for most of the 14 electrodes. More importantly, using the improved measure, the difference in WE between the two groups of subjects significantly increases for 11 brain regions compared with the values from the common measure. Finally, the highest balanced classification accuracy, 89.64%, is achieved when using the combined WE feature vector in five brain regions from the sites of Pz, P3, C4, Cz, and C3. Our findings indicate that the lying task elicits a more ordered brain activity in some specific brain regions than the task of telling the truth. This study not only demonstrates that improved WE measurements could be a powerful quantitative index for detecting lying but also sheds light on the brain mechanisms underlying deceptive behaviors.

Automatic Seizure Detection Based on Nonlinear Dynamical Analysis of EEG Signals and Mutual Information

Introduction:

In this paper, nonlinear dynamical analysis based on Recurrence Quantification Analysis (RQA) is employed to characterize the nonlinear EEG dynamics. RQA can provide useful quantitative information on the regular, chaotic, or stochastic property of the underlying dynamics.

Methods:

We use the RQA-based measures as the quantitative features of the nonlinear EEG dynamics. Mutual Information (MI) was used to find the most relevant feature subset out of RQA-based features. The selected features were fed into an artificial neural network for grouping of EEG recordings to detect ictal, interictal, and healthy states. The performance of the proposed procedure was evaluated using a database for different classification cases.

Results:

The combination of five selected features based on MI achieved 100% accuracy, which demonstrates the superiority of the proposed method.

Conclusion:

The results showed that the nonlinear dynamical analysis based on Rcurrence Quantification Analysis (RQA) can be employed as a suitable approach for characterizing the nonlinear EEG dynamics and detecting the seizure.

A Hybrid Approach Based on Higher Order Spectra for Clinical Recognition of Seizure and Epilepsy Using Brain Activity

Introduction

This paper proposes a reliable and efficient technique to recognize different epilepsy states, including healthy, interictal, and ictal states, using Electroencephalogram (EEG) signals.

Methods

The proposed approach consists of pre-processing, feature extraction by higher order spectra, feature normalization, feature selection by genetic algorithm and ranking method, and classification by support vector machine with Gaussian and polynomial radial basis function kernels. The proposed approach is validated on a public benchmark dataset to compare it with previous studies.

Results

The results indicate that the combined use of above elements can effectively decipher the cognitive process of epilepsy and seizure recognition. There are several bispectrum and bicoherence peaks at every bi-frequency plane, which reveal the location of the quadratic phase coupling. The proposed approach can reach, in almost all of the experiments, up to 100% performance in terms of sensitivity, specificity, and accuracy.

Conclusion

Comparing between the obtained results and previous approaches approves the effectiveness of the proposed approach for seizure and epilepsy recognition.