Trends in extreme learning machines

Epilepsy can be detected using EEG signals.The entropy indicates the complexity of the EEG signal.Various entropies are used to diagnose epilepsy.Unique ranges for various entropies are proposed. Epilepsy is the neurological disorder of the brain which is difficult to diagnose visually using Electroencephalogram (EEG) signals. Hence, an automated detection of epilepsy using EEG signals will be a useful tool in medical field. The automation of epilepsy detection using signal processing techniques such as wavelet transform and entropies may optimise the performance of the system. Many algorithms have been developed to diagnose the presence of seizure in the EEG signals. The entropy is a nonlinear parameter that reflects the complexity of the EEG signal. Many entropies have been used to differentiate normal, interictal and ictal EEG signals. This paper discusses various entropies used for an automated diagnosis of epilepsy using EEG signals. We have presented unique ranges for various entropies used to differentiate normal, interictal, and ictal EEG signals and also ranked them depending on the ability to discrimination ability of three classes. These entropies can be used to classify the different stages of epilepsy and can also be used for other biomedical applications.

Application of entropies for automated diagnosis of epilepsy using EEG signals

We propose new features for classification of epileptic seizure EEG signals.Features were extracted from PSR of IMFs of EEG signals.We define ellipse area of 2D PSR and IQR of Euclidian distance of 3D PSR as features.LS-SVM classifier has been used for classification with the proposed features.Results were compared with other existing methods studied on the same EEG dataset. Epileptic seizure is the most common disorder of human brain, which is generally detected from electroencephalogram (EEG) signals. In this paper, we have proposed the new features based on the phase space representation (PSR) for classification of epileptic seizure and seizure-free EEG signals. The EEG signals are firstly decomposed using empirical mode decomposition (EMD) and phase space has been reconstructed for obtained intrinsic mode functions (IMFs). For the purpose of classification of epileptic seizure and seizure-free EEG signals, two-dimensional (2D) and three-dimensional (3D) PSRs have been used. New features based on the 2D and 3D PSRs of IMFs have been proposed for classification of epileptic seizure and seizure-free EEG signals. Two measures have been defined namely, 95% confidence ellipse area for 2D PSR and interquartile range (IQR) of the Euclidian distances for 3D PSR of IMFs of EEG signals. These measured parameters show significant difference between epileptic seizure and seizure-free EEG signals. The combination of these measured parameters for different IMFs has been utilized to form the feature set for classification of epileptic seizure EEG signals. Least squares support vector machine (LS-SVM) has been employed for classification of epileptic seizure and seizure-free EEG signals, and its classification performance has been evaluated using different kernels namely, radial basis function (RBF), Mexican hat wavelet and Morlet wavelet kernels. Simulation results with various performance parameters of classifier, have been included to show the effectiveness of the proposed method for classification of epileptic seizure and seizure-free EEG signals.

Classification of epileptic seizures in EEG signals based on phase space representation of intrinsic mode functions

The brain is a complex structure made up of interconnected neurons, and its electrical activities can be evaluated using electroencephalogram (EEG) signals. The characteristics of the brain area affected by partial epilepsy can be studied using focal and non-focal EEG signals. In this work, a method for the classification of focal and non-focal EEG signals is presented using entropy measures. These entropy measures can be useful in assessing the nonlinear interrelation and complexity of focal and non-focal EEG signals. These EEG signals are first decomposed using the empirical mode decomposition (EMD) method to extract intrinsic mode functions (IMFs). The entropy features, namely, average Shannon entropy (ShEnAvg), average Renyi’s entropy (RenEnAvg ), average approximate entropy (ApEnAvg), average sample entropy (SpEnAvg) and average phase entropies (S1Avg and S2Avg), are computed from different IMFs of focal and non-focal EEG signals. These entropies are used as the input feature set for the least squares support vector machine (LS-SVM) classifier to classify into focal and non-focal EEG signals. Experimental results show that our proposed method is able to differentiate the focal and non-focal EEG signals with an average classification accuracy of 87% correct.

https://www.mdpi.com/1099-4300/17/2/669/pdf

Application of Entropy Measures on Intrinsic Mode Functions for the Automated Identification of Focal Electroencephalogram Signals

Epileptic seizure detection using DWT based fuzzy approximate entropy and support vector machine

Epileptic EEG classification based on extreme learning machine and nonlinear features

Feature extraction and recognition of ictal EEG using EMD and SVM

In this work, we evaluated the differences between epileptic electroencephalogram (EEG) and interictal EEG by computing some non-linear features. Correlation dimension (CD) and Hurst exponent (H) were calculated for 100 segments of epileptic EEG and 100 segments of interictal EEG. A comparison was made between epileptic EEG and interictal EEG in those non-linear parameters. Results show that the mean values of CD are 2.64 for epileptic EEG and 4.55 for interictal EEG. We also calculated approximate entropy (ApEn) of those EEG signals. The mean values of ApEn are 0.90 for epileptic EEG and 4.55 for interictal EEG. The values of CD and ApEn of epileptic EEG are generally lower than those of interictal EEG, indicating less complexity of EEG signals during seizures. The mean values of Hurst exponent are 0.19 for epileptic EEG and 0.29 for interictal EEG. Hurst exponents for epileptic EEG and interictal EEG are both <0.5. This indicates that both epileptic and interictal EEGs show long-range anticorrelation. The value of Hurst exponent of epileptic EEG signals is lower than that of interictal EEG signals, showing that the degree of anticorrelation of epileptic EEG signals is larger than that of interictal EEG. Hence, the non-linear parameters such as CD and Hurst exponent can help interpret epileptic and interictal EEGs and their neurodynamics.

EEG non-linear feature extraction using correlation dimension and Hurst exponent.

Automatic detection and classification of electroencephalogram (EEG) epileptic activity aid diagnosis and relieve the heavy workload of doctors. This article presents a new EEG classification approach based on the extreme learning machine (ELM) and wavelet transform (WT). First, the WT is used to extract useful features when certain scales cover abnormal components of the EEG. Second, the ELM algorithm is used to train a single hidden layer of feedforward neural network (SLFN) features. Finally, the SLFN is tested with interictal and ictal EEGs. The experiments demonstrated that the proposed approach achieved a satisfactory classification rate of 99.25% for interictal and ictal EEGs.

http://journals.sagepub.com/doi/pdf/10.1177/1550059411435861

Dongmei Cai

Papers

Epileptic EEG classification based on extreme learning machine and nonlinear features

Feature extraction and recognition of ictal EEG using EMD and SVM

EEG non-linear feature extraction using correlation dimension and Hurst exponent.

EEG classification approach based on the extreme learning machine and wavelet transform.

EEG signal classification based on EMD and SVM