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

The studies implemented with Electroencephalogram (EEG) signals are progressing very rapidly and brain computer interfaces (BCI) and disease determinations are carried out at certain success rates thanks to new methods developed in this field. The effective use of these signals, especially in disease detection, is very important in terms of both time and cost. Currently, in general, EEG studies are used in addition to conventional methods as well as deep learning networks that have recently achieved great success. The most important reason for this is that in conventional methods, increasing classification accuracy is based on too many human efforts as EEG is being processed, obtaining the features is the most important step. This stage is based on both the time-consuming and the investigation of many feature methods. Therefore, there is a need for methods that do not require human effort in this area and can learn the features themselves. Based on that, two-dimensional (2D) frequency-time scalograms were obtained in this study by applying Continuous Wavelet Transform to EEG records containing five different classes. Convolutional Neural Network structure was used to learn the properties of these scalogram images and the classification performance of the structure was compared with the studies in the literature. In order to compare the performance of the proposed method, the data set of the University of Bonn was used. The data set consists of five EEG records containing healthy and epilepsy disease which are labeled as A, B, C, D, and E. In the study, A-E and B-E data sets were classified as 99.50%, A-D and B-D data sets were classified as 100% in binary classifications, A-D-E data sets were 99.00% in triple classification, A-C-D-E data sets were 90.50%, B-C-D-E data sets were 91.50% in quaternary classification, and A-B-C-D-E data sets were in the fifth class classification with an accuracy of 93.60%.

show abstract

“…Ten-fold cross validation procedures were performed. They found the normal and seizure EEG signal to be 98.00% classification accuracy [15].…”

Section: Introductionmentioning

confidence: 99%

Epilepsy Detection by Using Scalogram Based Convolutional Neural Network from EEG Signals

2019

View full text Add to dashboard Cite

show abstract

“…Mappings between the frequency and time spaces are utilized generally as a part of signal investigation and handling. The strategies in time-frequency domain uses Fast Fourier change (FFT), wavelet transform (WT) 43 , Tunable-Q Wavelet Transform 40 , short time Fourier transform (STFT), wavelet entropy 29 , wavelet energy function 30 , multi domain wavelet threshold 44 , harmonic wavelet packet transform 36 , Stockwell transform 38 , ensemble empirical mode decomposition 37 , Multivariate Empirical Mode Decomposition 14 , Bootstrap Aggregating 45 , visibility graph 2,27 , Cohen class kernel functions 33 and other entropy based methods 17 . Since, Fourier strategies may not be suitablefor non-stationary signal or stationary signals with short-lived segments.…”

Section: Eeg Signal Classification Methodsmentioning

confidence: 99%

“…For instance, the issue with binary classification involves the separation of classes into two category, for example, the target and non-target classes. Classification algorithms rely mostly on labelled output, where the learning is supervised or unsupervised based on statistical or non-statistical data.The supervised classification algorithms foreseescategorical labels as: support vector machine (SVM) [26][27][28][29][30][31][32][33][34][35] , Global modular PCA with SVM [36][37][38][39][40][41] , linear discriminant analysis (LDA), Naive Bayes, decision trees, K-nearest-neighbour (kNN), logistic regression, neural networks, Kernel estimation, linear regression, Kalman filters, Gaussian process regression, fractional linear prediction 2 etc. The aim of these algorithms is to amplify the precision of testing over testing dataset and hence, the supervised algorithms are used mostly in classifying the EEG signals.…”

Section: Eeg Signal Classificationmentioning

confidence: 99%

Review on diverse approaches used for epileptic seizure detection using EEG signals

Baskar

Karthikeyan

2018

Bangladesh J Med Sci

View full text Add to dashboard Cite

Epileptic seizure detection is a common diagnosis practiced by the expert clinicians through direct visual observation from the electroencephalography (EEG) signal. This detection by the expert clinicians is considered sensitive to bias and time consuming. Further, it suffers from various problems like unsustainability in larger dataset processing and low power detection. Hence, many computerized detection approaches are highly preferred to eliminate the aforementioned problems and to expedite the research in epilepsy seizure detection for aiding the medical professionals. Many such automated epilepsy diagnosis framework has been designed by various researches, which is made to operate in a single or in a combined manner with other domains. This study reviews different approaches, which is been designed to aid the human diagnosis using new avenues that explains the causes of epilepsy and seizures. Further, this study summarizes various methods used previously to analyze the epilepsy and seizures based on its state of art approach. Also, investigations are carried out in terms of performance evaluation to find the best suitable epileptic seizure detection technique in the application of Neuro-informatics.Bangladesh Journal of Medical Science Vol.17(4) 2018 p.526-531

show abstract

“…However, there are some problems with the EMD method, of which the main one is mode mixing. Complementary ensemble empirical mode decomposition (CEEMD) can effectively restrain the mode mixing of EMD at a certain level [ 23 , 24 , 25 ]. Based on the above considerations, we proposed a new algorithm which combines CEEMD with permutation entropy (PE) [ 26 ] to effectively improve the complexity of the digital chaotic sequence.…”

Section: Introductionmentioning

confidence: 99%

A Novel Algorithm to Improve Digital Chaotic Sequence Complexity through CCEMD and PE

Fan

Xie

Ding

2018

Entropy

View full text Add to dashboard Cite

In this paper, a three-dimensional chaotic system with a hidden attractor is introduced. The complex dynamic behaviors of the system are analyzed with a Poincaré cross section, and the equilibria and initial value sensitivity are analyzed by the method of numerical simulation. Further, we designed a new algorithm based on complementary ensemble empirical mode decomposition (CEEMD) and permutation entropy (PE) that can effectively enhance digital chaotic sequence complexity. In addition, an image encryption experiment was performed with post-processing of the chaotic binary sequences by the new algorithm. The experimental results show good performance of the chaotic binary sequence.Empirical mode decomposition (EMD) in digital signal processing has been extensively applied in nonlinear signal processing [15][16][17][18]. EMD was first proposed by Huang et al. [19][20][21]. It is an effective tool for analyzing nonlinear and non-stationary signals. The EMD method is closely related to the corresponding Hilbert transform method. Through the decomposition of nonlinear and non-stationary signals, a series of intrinsic mode functions (IMFs) are obtained, which makes each IMF a stable signal for narrowband [22]. The IMFs play a crucial role in the analysis of non-stationary or nonlinear signals. However, there are some problems with the EMD method, of which the main one is mode mixing. Complementary ensemble empirical mode decomposition (CEEMD) can effectively restrain the mode mixing of EMD at a certain level [23][24][25]. Based on the above considerations, we proposed a new algorithm which combines CEEMD with permutation entropy (PE) [26] to effectively improve the complexity of the digital chaotic sequence.The rest of this paper is organized as follows: Section 2 describes a hidden chaos attractor with no equilibria. The dynamic characteristics of a complex chaotic system are studied by means of numerical simulation and theoretical analysis. Section 3 proposes a new algorithm to improve the complexity of the digital chaotic sequence. Section 4 considers image encryption with post-processing of the chaotic binary sequences by the algorithm outlined in Section 3. The security of the encrypted image is analyzed through key sensitivity, information entropy, and histogram analysis. Section 5 summarizes the discussions of this paper. The Characteristic Analysis of a Chaotic SystemIn this section, a system can be expressed as the following set of differential equations:where a, b, c are real parameters. When a = 2, b = 0.35, c = 1 and the initial value is (−1.6, 0.82, 1.9), the system displays a single-scroll chaotic system [27]. Different projections of the chaotic attractor for this system are shown in Figure 1.

show abstract

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

Cited by 42 publications

References 34 publications

Epilepsy Detection by Using Scalogram Based Convolutional Neural Network from EEG Signals

Epilepsy Detection by Using Scalogram Based Convolutional Neural Network from EEG Signals

Review on diverse approaches used for epileptic seizure detection using EEG signals

A Novel Algorithm to Improve Digital Chaotic Sequence Complexity through CCEMD and PE

Contact Info

Product

Resources

About