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

Abstract

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.

Supervised Machine Learning and Deep Learning Techniques for Epileptic Seizure Recognition Using EEG Signals—A Systematic Literature Review

“…It was claimed that the use of RP displayed high-performance results in exploiting the interclass variability. The brain-rhythmic recurrence map (BRRM) [ 97 ] and unthresholded RP with fractal weighted LBP (URP-FWLBP) methods [ 98 ] were presented as improved versions to offset the loss of dynamical information due to the binarization process of RP. In [ 97 ], EEG signals are decomposed into three sub-bands and then transformed into images.…”

“…The images are fed to a CNN-based architecture for classification. In [ 98 ], FD and LBP are combined to construct the images, followed by histogram analysis to extract feature values resembling the signals. Linear discernment analysis (LDA) was used for dimensionality reduction, and SVM was used for classification.…”

Automated knee osteoarthritis severity classification using three‐stage preprocessing method andVGG16architecture

“…The image dataset is multiclass and imbalanced in nature, therefore, apart from accuracy, we have evaluated the performance of our model using other metrics, too such as recall, precision, and f1‐score 65 . The performance metrics have been explained as follows:…”

Untitled

“…are used as feature extractor based on their energy compaction, using recurrence plots, based on dictionary learning and sparse representations, using Random forest (RF) classifier, using different layers of CNN, transfer learning, using deep batch normalization, using neural memory networks, etc. are tried out with different researcher using cleaned and raw data from different datasets [30][31][32][33][34][35][36][37][38][39][40][41][42]. Slowly real time clinical diagnostics is tried out [43].…”