Classification of EEG signals for epileptic seizures detection and eye states identification using Jacobi polynomial transforms-based measures of complexity and least-square support vector machine

Nkengfack, Laurent Chanel Djoufack; Tchiotsop, Daniel; Atangana, Romain; Louis-Door, Valérie

doi:10.1016/j.imu.2021.100536

Cited by 22 publications

(9 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nkengfack et al [13] discussed the detection and identification of seizure or seizure-free states by using EEG signals for epileptic patients. Discrete Legendre transforms (DLT) and discrete Chebyshev transform (DChT) have been suggested for extraction of beta and gamma rhythms of EEG signal that would be fed as an input to the least square support vector machine (LS-SVM) that is used for the classification process.…”

Section: Related Workmentioning

confidence: 99%

“…We have categorized various EEG signals and recognized various states of EEG signals as opposed to the methods used by others. [13] LS-SVM A -E 100 Samiee et al [15] DSTFT & MLP A -E 99.5 Peng et al [24] Stein kernel-based sparse representation A -E 99 Liu et al [1] Energy, ApEn with LPP, LS-SVM S -Z 98 Attia et al [3] Burg + SVM A -E 98 Ech-choudany et al [25] ANN A -E 100 Proposed model HPS classifier with PSO S -Z 100 Nkengfack et al [13] LS-SVM B -E 100 Samiee et al [15] DSTFT & MLP B -E 99.3 Peng et al [24] Stein kernel-based sparse representation B -E 98.3 Liu et al [1] Energy, ApEn with LPP, LS-SVM B -E ----Attia et al [3] Burg + SVM B -E 99 Ech-choudany et al [25] ANN B -E 100 Proposed model HPS classifier with PSO S -O 100 Nkengfack et al [13] LS-SVM C -E 100 Samiee et al [15] DSTFT & MLP C -E 98.5 Peng et al [24] Stein kernel-based sparse representation C -E 98.3 Liu et al [1] Energy, ApEn with LPP, LS-SVM C -E 99.5 Attia et al [3] Burg + SVM C -E 99 Ech-choudany et al [25] ANN C -E 100 Proposed model HPS classifier with PSO S -N 100 Nkengfack et al [13] LS-SVM D -E 100 Samiee et al [15] DSTFT & MLP D -E 94.9 Peng et al [24] Stein kernel-based sparse representation D -E 96.7 Liu et al [1] Energy, ApEn with LPP, LS-SVM D -E 98 Attia et al [3] Burg + SVM D -E 95 Ech-choudany et al […”

Section: Comparison With Other Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Health Electroencephalogram epileptic classification based on Hilbert probability similarity

Al-Hamzawi

Al‐Shammary

Hammadi

2023

IJECE

View full text Add to dashboard Cite

This paper has proposed a new classification method based on Hilbert probability similarity to detect epileptic seizures from electroencephalogram (EEG) signals. Hilbert similarity probability-based measure is exploited to measure the similarity between signals. The proposed system consisted of models based on Hilbert probability similarity (HPS) to predict the state for the specific EEG signal. Particle swarm optimization (PSO) has been employed for feature selection and extraction. Furthermore, the used dataset in this study is Bonn University's publicly available EEG dataset. Several metrics are calculated to assess the performance of the suggested systems such as accuracy, precision, recall, and F1-score. The experimental results show that the suggested model is an effective tool for classifying EEG signals, with an accuracy of up to 100% for two-class status.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Comparison With Other Modelsmentioning

confidence: 99%

Health Electroencephalogram epileptic classification based on Hilbert probability similarity

Al-Hamzawi

Al‐Shammary

Hammadi

2023

IJECE

View full text Add to dashboard Cite

show abstract

“…[2], [3]), epileptic seizure detection (e.g. [4], [5]), robotic control [6] as well as video gaming [7].…”

Section: Introductionmentioning

confidence: 99%

Improving Generalization of CNN-Based Motor-Imagery EEG Decoders via Dynamic Convolutions

Barmpas

Panagakis²,

Bakas³

et al. 2023

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

Deep Convolutional Neural Networks (CNNs) have recently demonstrated impressive results in electroencephalogram (EEG) decoding for several Brain-Computer Interface (BCI) paradigms, including Motor-Imagery (MI). However, neurophysiological processes underpinning EEG signals vary across subjects causing covariate shifts in data distributions and hence hindering the generalization of deep models across subjects. In this paper, we aim to address the challenge of inter-subject variability in MI. To this end, we employ causal reasoning to characterize all possible distribution shifts in the MI task and propose a dynamic convolution framework to account for shifts caused by the inter-subject variability. Using publicly available MI datasets, we demonstrate improved generalization performance (up to 5%) across subjects in various MI tasks for four well-established deep architectures.

show abstract

“…On the other hand, more efforts have been focused on the association of EEG rhythms extraction methods and entropy measures to discriminate F and NF EEG signals. Also, some of these discrimination systems do not relate the extracted rhythms to the ones defined in the literature in terms of spectral coefficients as shown by Djoufack et al [12][13]. In short, despite many techniques used, polynomial transforms are not yet associated with entropy measures for the purpose of F and NF EEG signals discrimination even if it is already shown that the physical interpretation of the spectral coefficients leads to a new issue for automatic diagnosis in epilepsy [12,13].…”

Section: Introductionmentioning

confidence: 99%

“…Also, some of these discrimination systems do not relate the extracted rhythms to the ones defined in the literature in terms of spectral coefficients as shown by Djoufack et al [12][13]. In short, despite many techniques used, polynomial transforms are not yet associated with entropy measures for the purpose of F and NF EEG signals discrimination even if it is already shown that the physical interpretation of the spectral coefficients leads to a new issue for automatic diagnosis in epilepsy [12,13]. In this impetus, this paper aims to develop Jacobi polynomial transforms (JPTs)-based entropy measures like approximate entropy (ApEn), sample entropy (SampEn), permutation entropy (PermEn), fuzzy entropy (FuzzyEn) and increment entropy (IncrEn) for F and NF EEG signals discrimination.…”

Section: Introductionmentioning

confidence: 99%

Jacobi Polynomial Transforms-Based Entropy Measures for Focal and Non-Focal EEG Signals Discrimination Using Kernel Machines

Nkengfack¹,

Tchiotsop²,

Atangana³

et al. 2021

CSSP

Self Cite

View full text Add to dashboard Cite

Electroencephalogram (EEG) remains the primary technique in the diagnosis and localization of partial epilepsy seizures. Despite the advent of modern neuroimaging techniques, the use of EEG signals for locating epilepsy-affected brain areas is still convenient. That is why during these last decades, several computer-aided detection (CAD) methodologies have been proposed to detect and discriminate focal (F) EEG signals, and hence locate epileptogenic foci. In this impetus, this paper applied Jacobi polynomial transforms (JPTs)-based entropy measures to analyze the complexity and discriminate the bivariate focal (F) and non-focal (NF) EEG signals. Jacobi polynomial transforms namely discrete Legendre transform (DLT) and discrete Chebyshev transform (DChT) are applied to separate F and NF EEG signals into their different rhythms. Furthermore, entropy measures like approximate entropy (ApEn), sample entropy (SampEn), permutation entropy (PermEn), fuzzy entropy (FuzzyEn) and increment entropy (IncrEn) are extracted. For direct discrimination between F and NF EEG signals, extracted entropies are combined to define different features vectors that are fed as inputs of two kernel machines namely the leastsquares support vector machine (LS-SVM) and simple multi-layer perceptron neural network (sMLPNN). Experimental results demonstrated that our methodology achieved the highest performance of 98.33% sensitivity, 98.00% specificity, and 98.17% accuracy in discriminating F and NF EEG signals with sMLPNN classifier. In addition, our methodology will be useful to clinicians in providing an accurate and objective paradigm for locating epilepsy-affected brain areas.

show abstract

Classification of EEG signals for epileptic seizures detection and eye states identification using Jacobi polynomial transforms-based measures of complexity and least-square support vector machine

Cited by 22 publications

References 29 publications

Health Electroencephalogram epileptic classification based on Hilbert probability similarity

Health Electroencephalogram epileptic classification based on Hilbert probability similarity

Improving Generalization of CNN-Based Motor-Imagery EEG Decoders via Dynamic Convolutions

Jacobi Polynomial Transforms-Based Entropy Measures for Focal and Non-Focal EEG Signals Discrimination Using Kernel Machines

Contact Info

Product

Resources

About