Epileptic seizure detection using EEG signals and extreme gradient boosting

Vanabelle, Paul; Handschutter, Pierre De; Tahry, Riëm El; Benjellοun, Mohammed; Boukhebouze, Mohamed

doi:10.7555/jbr.33.20190016

Cited by 27 publications

(10 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our study, the regularization parameter ( C ) is set to 100 and gamma value is set to 0.0001. Gradient boosting classifier (GB) [ 39 ] is also an ensemble technique that is based on the assumption that many weak learners, when combined generate a stronger learning model. Rather than fitting a predictor to the data at each iteration, it fits a new predictor to the residual errors of the previous prediction.…”

Section: Methodsmentioning

confidence: 99%

Epileptic Seizure Detection Using a Hybrid 1D CNN-Machine Learning Approach from EEG Data

Hassan

Hussain

Qaisar

2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Electroencephalography (EEG) is a widely used technique for the detection of epileptic seizures. It can be recorded in a noninvasive manner to present the electrical activity of the brain. The visual inspection of nonlinear and highly complex EEG signals is both costly and time-consuming. Therefore, an effective automatic detection system is needed to assist in the long-term evaluation and treatment of patients. Traditional approaches based on machine learning require feature extraction, while deep learning approaches are time-consuming and require more layers for effective feature learning and processing of complex EEG waveforms. Deep learning-based approaches also have weak generalization ability. This paper proposes a solution based on the combination of convolution neural networks (CNN) and machine learning classifiers. It preprocesses the EEG signal using the Butterworth filter and performs feature extraction using CNN. From the extracted set of features, the approach selects only the relevant features using mutual information-based estimators to reduce the curse of dimensionality and improve classification accuracy. The selected features are then passed as input to different machine learning classifiers. The suggested solution is evaluated on the University of Bonn dataset and CHB-MIT datasets. Our model effectively predicts 2, 3, 4, and 5 classes with accuracy of 100%, 99%, 94.6%, and 94%, respectively, for the Bonn dataset and 98% for CHB-MIT datasets.

show abstract

Section: Methodsmentioning

confidence: 99%

Epileptic Seizure Detection Using a Hybrid 1D CNN-Machine Learning Approach from EEG Data

Hassan

Hussain

Qaisar

2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…The empirical mode decomposition (EMD) and a multilayer perceptron neural network (MLPNN) were accustomed to decompose a time phase graphical record into intrinsic mode functions (IMFs) on that autoregressive (AR) parameters were extracted, combined, and fed to the MLPNN classifier [23]. AN experiment doles out on an in public offered dataset [31][32], comprising traditional, interictal, and ictic graphical record signals achieved a classification accuracy of up to ninety-eight. smoothened pseudo-Wigner-Ville distribution gave 98.9% of accuracy [24].…”

Section: Related Workmentioning

confidence: 99%

Epileptic seizure endorsement technique using DWT power spectrum

2022

View full text Add to dashboard Cite

EEG signals play significant role in the study of mental disorders. Epilepsy is one of the major mental disorder and need significant technological support in the treatment. A method proposed here is an endorsement technique for epileptic seizures using electroencephalogram (EEG) signals captured using non-invasive method.The method uses power spectrum density and discrete wavelet transformation (DWT). The impact of power spectral analysis along with the usage of EEG characteristics in endorsement of epilepsy is addressed here. A publicly available EEG epileptic dataset is processed using FIR filters along with DWT. The power spectrum density and its average were compared with specific spectrum to get the results and were compared against the standard EEG signal frequency range. It is found that the usage of DWT is more accurate and reliable to process and classify the EEG data for epilepsy endorsement.

show abstract

“…Therefore, a lot of work is available for automatic seizure detection but very less work has been explored for the problem of multi-class classification of different epileptic seizure types, summarized as follows. Wijayanto et al (2019) performed 5-class seizure type classification by extracting the statistical features from the Empirical Mode Decomposition (EMD) components and used SVM to obtain accuracy, specificity, and recall of 95%, 98.75% and 95% respectively; (Roy et al, 2019) obtained correlation coefficient matrix after employing two pre-processing methods based on Fast Fourier Transform (FFT) and obtained the highest f1-score of 90.7% using K-Nearest Neighbours (KNN) for 7-class seizure type classification; (Saputro et al, 2019) achieved an accuracy, specificity and sensitivity of 91.4%, 97.83% and 90.25% respectively on a combination of MFCC and hjorth descriptor based features using SVM; and (Vanabelle et al, 2020) performed 2-class classification (focal vs. generalized) using a combination of 22 temporal and frequential features following the standard partitioning and Leave One Out Cross-Validation (LOOCV) methods with XGBoost to obtain classification results as f1-score, precision, specificity and recall of 33.60%-51.33%, 27.55%-40.01%, 73.04%-92.50% and 35.80%-78.72% respectively. Most of the authors have explored a variety of deep learning based architecture models for current multi-class classification problem.…”

Section: Related Workmentioning

confidence: 99%

EEG‐based automatic multi‐class classification of epileptic seizure types using recurrence plots

2021

View full text Add to dashboard Cite

There is an urgent need to develop an efficient system for accurate recognition of epileptic seizure type that could play a significant role in reducing the adversial effects of the disease. A lot of work is available for EEG based automatic seizure detection but very less attempts have been made towards the classification of variants of seizures. Moreover, none of the authors have included the EEG signals for myoclonic seizure type in their classification studies. Our study aims to propose the automatic machine learning based multi-class classification system for classifying six types of epileptic seizures (such as absence, focal non-specific, complex-partial, generalized, tonic-clonic and including myoclonic too) through the use of recurrence plots (RPs). In our study, we have collected 19-channel EEG data from a huge database of Temple University Hospital. Two classification modalities have been proposed depending upon the feature extraction approach followed for RPs-(a) Traditional approach using the recurrence quantification analysis (RQA) method;(b) Texture based approach using the hybrid method named as Unthresholded Recurrence Plot with Fractal Weighted Local Binary Pattern (URP-FWLBP), that has been proposed in our work using a combination of Unthresholded RPs (URPs) and Fractal Weighted Local Binary Pattern (FWLBP) method. Thereby, an indirect variant of support vector machine (one-vs-rest approach) has been used as the multi-class classifier in both the approaches. The performance of the proposed modalities has been validated using five-fold cross-validation method in the light of seven metrics-accuracy, sensitivity, specificity, Matthews correlation coefficient, geometric-mean, precision and f1-score. The experimental results show the effectiveness of the proposed system following hybrid URP-FWLBP method in performing multi-class epileptic seizure type classification with 100% efficiency, thereby outperforming the traditional RQA method based system as well the existing state-of-the-art systems.

show abstract

Epileptic seizure detection using EEG signals and extreme gradient boosting

Cited by 27 publications

References 26 publications

Epileptic Seizure Detection Using a Hybrid 1D CNN-Machine Learning Approach from EEG Data

Epileptic Seizure Detection Using a Hybrid 1D CNN-Machine Learning Approach from EEG Data

Epileptic seizure endorsement technique using DWT power spectrum

EEG‐based automatic multi‐class classification of epileptic seizure types using recurrence plots

Contact Info

Product

Resources

About