Using sequential floating forward selection algorithm to detect epileptic seizure in EEG signals

Epileptic seizures detection is largely based on analysis of Electroencephalogram signals. The ambulatory EEG recordings generate very lengthy data which require a skilled and careful analysis. This tedious procedure necessitates the use of automated systems for epileptic seizure detection. This paper proposes one such automated epileptic seizure detection technique based on Probabilistic Neural Network (PNN) by using a time frequency domain characteristics of EEG signal called Approximate Entropy(ApEn). Our method consists of EEG data collection, feature extraction and classification. EEG data from normal and epileptic subjects was collected, digitized and then fed into the PNN. For feature extraction, the wavelet coefficients are derived using Discrete Wavelet Transformation. For the feature selection stage a new methodology is proposed, which is, comparing the ApEn values of wavelet coefficients of different EEG data. The experimental results portray that this proposed approach efficiently detects the presence of epileptic seizures in EEG signals and showed a reasonable accuracy.

Epileptic seizure is a neurological condition caused by short and unexpectedly occurring electrical disruptions in the brain. It is estimated that roughly 60 million individuals worldwide have had an epileptic seizure. Experiencing an epileptic seizure can have serious consequences for the patient. Automatic seizure detection on electroencephalogram (EEG) recordings is essential due to the irregular and unpredictable nature of seizures. By thoroughly analyzing EEG records, neurophysiologists can discover important information and patterns, and proper and timely treatments can be provided for the patients. This research presents a novel machine learning-based approach for detecting epileptic seizures in EEG signals. A public EEG dataset from the University of Bonn was used to validate the approach. Meaningful statistical features were extracted from the original data using discrete wavelet transform analysis, then the relevant features were selected using feature selection based on the binary particle swarm optimizer. This facilitated the reduction of 75% data dimensionality and 47% computational time, which eventually sped up the classification process. After having been selected, relevant features were used to train different machine learning models, then hyperparameter optimization was utilized to further enhance the models' performance. The results achieved up to 98.4% accuracy and showed that the proposed method was very effective and practical in detecting seizure presence in EEG signals. In clinical applications, this method could help relieve the suffering of epilepsy patients and alleviate the workload of neurologists.

A novel approach based on wavelet analysis and arithmetic coding for automated detection and diagnosis of epileptic seizure in EEG signals using machine learning techniques

Preprocessing and signal enhancement methods can be applied to improve quality of signal detection in the presence of background noise. This article concerns the novel preprocessing techniques for enhancement of EEG signals and background noise suppression during epileptic seizure by using Independent Component Analysis (ICA) and Novelty Filtering which employs an artificial neural network performing autoassociative task. ICA is used for removing biological artifacts and noise from EEG signals and stabilizing its probabilistic behavior. At the next stage Novelty Filtering technique has been used to suppress background EEG activities and improvement of signal-to-noise ratio for the detection and identification of epileptic seizure. A novelty filter consist of neural networks of retinotopic topology having a one-to-one correspondence between input and output units to perform autoassociative mappings. Filtering effect is obtained by subtracting the network output from the input vectors. The results show that novelty filtering combined with ICA is a powerful preprocessing tool for the detection and enhancement of epileptic seizure activity in the nonstationary EEG signals.KeywordsNovelty FilteringAutoassociative Neural NetworksIndependent Component analysisEpileptic SeizureEEG Signals

Detecting epileptic seizures from EEG signals allows for earlier and more accurate diagnosis of patients with epilepsy. This study evaluates the performance of three traditional machine learning (ML) models: support vector machines (SVM), random forests (RF), and K-nearest neighbors (KNN) for the binary classification of EEG segments with or without seizures. The CHB-MIT database was used, without preprocessing, to mimic a real clinical setting. Linear temporal features were extracted in three configurations: 9 widely cited features, 21 novel features, and a combination of all 30 features. The results show that RF is the most robust and reliable classifier; with 30 features, it achieved 96.75% precision, 94.30% accuracy, 91.71% recall, 94.14% F1 score, and 96.88% specificity. These findings emphasize the importance of proper feature selection and suggest new possibilities for improving the accuracy of traditional ML models in detecting epileptic seizures from EEG signals.

Among all of the Machine Learning techniques used for classification tasks, Artificial Neural Networks (ANNs) have obtained much success in their applications. However, their development usually requires a manual effort from the human expert in which several parameter configurations (architectures, training parameters, etc) are tried. This paper proposes a new evolutionary method that evolves ANNs without any participation from the human expert. This system can be used to evolve feed-forward and recurrent ANNs. A real-world problem has been used to test the behaviour of this system: detection of epileptic seizures in EEG signals. A comparison of the results obtained using recurrent and feedforward ANNs to solve this problem is presented in this paper. This comparison shows the good accuracies obtained by this method (almost 100%). Moreover, these results show an important feature: the system tries to evolve simple ANNs, with a low number of neurons and connections (in many cases, the networks have only 1 hidden neuron).

Field-programmable gate arrays (FPGAs) are being extensively used for a wide range of digital applications due to their flexibility and reprogrammability. This paper presents a FPGA implementation of the second-order difference plot (SODP) technique which can be used for the classification of ictal and seizure-free electroencephalogram (EEG) signals. Empirical mode decomposition (EMD) can break down an EEG signal into simple oscillatory modes called intrinsic mode functions (IMFs). The hardware design developed takes a sampled IMF of an EEG signal as input and generates its SODP while simultaneously calculating the 95 percent confidence ellipse area of the SODP. The ellipse area can be used as a parameter for detecting epileptic seizures in EEG signals. The digital circuit was designed in the Vivado integrated development environment (IDE) using Verilog hardware description language (HDL) and a Xilinx Artix-7 xc7a100tcsg324 FPGA was used to verify operation of the physical implementation. The hardware was tested on EEG data made publicly available by the University of Bonn and the results were found to be consistent with MATLAB simulations.

Automated identification of epileptic seizures in EEG signals based on phase space representation and statistical features in the CEEMD domain

This paper analyzes the underlying complexity and non-linearity of electroencephalogram (EEG) signals by computing a novel multi-scale entropy measure for the classification of seizure, seizure-free and normal EEG signals. The quality factor (Q) based multi-scale entropy measure is proposed to compute the entropy of the EEG signal in different frequency-bands of interest. The Q -based entropy (QEn) is computed by decomposing the signal with the tunable-Q wavelet transform (TQWT) into the number of sub-bands and estimating K-nearest neighbor (K-NN) entropies from various sub-bands cumulatively. The optimal selection of Q and the redundancy parameter (R) of TQWT showed better robustness for entropy computation in the presence of high- and low-frequency components. The extracted features are fed to the support vector machine (SVM) classifier with the wrapper-based feature selection method. The proposed method has achieved accuracy of 100% in classifying normal (eyes-open and eyes-closed) and seizure EEG signals, 99.5% in classifying seizure-free EEG signals (from the hippocampal formation of the opposite hemisphere of the brain) from seizure EEG signals and 98% in classifying seizure-free EEG signals (from the epileptogenic zone) from seizure EEG signals, respectively, using the SVM classifier. We have also achieved classification accuracies of 99% and 98.6% in classifying seizure versus non-seizure EEG signals and the individual three classes, namely normal, seizure-free and seizure EEG signals, respectively. The performance measure of the proposed multi-scale entropy has been found to be comparable with the existing state of the art epileptic EEG signals classification methods studied using the same database.

Fisher proposes Fisher’s linear discriminant function (LDF) based on maximization of variance ratio. If data satisfies Fisher’s assumption, the same LDF is easily derived by variance-covariance matrix. If variance-covariance matrices of two classes are not same, quadratic discriminant function (QDF) is proposed. These discriminant functions have three problems. First, all discriminant functions except for Revised IP-OLDF can’t discriminate the cases xi on the discriminant hyper plane correctly (the unresolved problem of discriminant analysis). Only Revised IP-OLDF can solve this problem in theoretically. Second, LDF and QDF can’t recognize linear separable data in many cases, and the numbers of misclassifications (NMs) of these functions are usually higher than logistic regression that is used in many users. Third, these are not obtained if the values of some independent variable are constant, because inverse matrix can’t be calculated. JMP prepare the regularized discriminant function if QDF can’t analyze the difficult data. These facts mean that LDF and QDF shouldn’t be used for an important discrimination. On the contrary, Revised IP-OLDF based on Minimum Number of Misclassifications (MNM) criterion resolves these problems. In addition to this, means of error rates of Revised IP-OLDF are less than those of LDF and logistic regression and S-SVM by 100-fold cross validation in many cases.

Epilepsy is one of the most prevalent neurological disorders affecting 70 million people worldwide. The present work is focused on designing an efficient algorithm for automatic seizure detection by using electroencephalogram (EEG) as a noninvasive procedure to record neuronal activities in the brain. EEG signals' underlying dynamics are extracted to differentiate healthy and seizure EEG signals. Shannon entropy, collision entropy, transfer entropy, conditional probability, and Hjorth parameter features are extracted from subbands of tunable Q wavelet transform. Efficient decomposition level for different feature vector is selected using the Kruskal-Wallis test to achieve good classification. Different features are combined using the discriminant correlation analysis fusion technique to form a single fused feature vector. The accuracy of the proposed approach is higher for Q=2 and J=10. Transfer entropy is observed to be significant for different class combinations. Proposed approach achieved 100% accuracy in classifying healthy-seizure EEG signal using simple and robust features and hidden Markov model with less computation time. The proposed approach efficiency is evaluated in classifying seizure and non-seizure surface EEG signals. The system has achieved 96.87% accuracy in classifying surface seizure and nonseizure EEG segments using efficient features extracted from different J level.

The stability of decision—Theoretic electrocardiographic classifiers based on the use of discretized features

In this study, seismic events in Northern and Central Egypt are inspected to discriminate quarry blasts from earthquakes. We examine a collection of 639 events in both time and frequency domains with local magnitudes of 1.5 ≤ ML ≤ 3.3 from the Egyptian Seismological Network’s seismic event catalogue between 2009 and 2015. The maximum S-wave to the maximum P-wave amplitude ratio, complexity (C), spectral ratio (Sr), and power of events (Pe) classifiers as well as two statistical approaches, linear discriminant function (LDF) and quadratic discriminant function (QDF), are used to distinguish between earthquakes and quarry blasts. The usage of the LDF and QDF forms did not result in any major differences in the discrimination. The results obtained by the LDF and QDF from (Pe-C) are the best of all approaches. The findings of all approaches were compared to get a final categorization for each event, and a decision was achieved when at least three of the four methods provided the same event category. In Northern Egypt, 243 earthquakes and 308 quarry blasts could be identified as final decisions, with two misclassified events, resulting in an overall success rate of 99.6%. In Central Egypt, 48 earthquakes and 36 quarry blasts were classified as a final decision, with two misclassified events, for an overall success percentage of 97.6%.

Hybrid metaheuristic algorithm enhanced support vector machine for epileptic seizure detection

An electroencephalogram (EEG) is utilized to assess activity in the brain and find various epileptic conditions of the brain. But, EEG signals are regularly corrupted with different types of physiological artifacts. Due to this reason, epileptic seizure detection and further analysis of the seizure information becomes challenging and leads to ambiguous decisions made by neuro-specialists. Hence, it is important to remove these EEG physiological artifacts in the pre-processing phase itself. This research paper discusses EEG physiological artifact removal based on multiresolutional analysis and thresholding. Multiresolutional analysis is employed using discrete wavelet transform (DWT). Using DWT, the signal containing the seizure information is separated in to two components namely, high frequency and low frequency. Threshold is applied to these separated frequency components to eliminate artifacts from the original EEG seizure signal. The outcome of the investigation proved that the proposed technique removes the physiological disturbances in the seizure EEG signal by retaining the significant seizure EEG data. The examination also investigates the performance of the wavelet function to remove physiological artifacts in terms of signal-to-noise ratio and cross relation coefficient. The analysis proves that the proposed technique is able to conserve seizure information by removing artifacts in the examined datasets which is then verified using a simulated noisy signal.KeywordsEEGMultiresolutionPhysiological artifacts seizureWavelet transform