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.
Automated eyes-state classification from the EEG signals using nonlinear analysis tools is a new area of research. Based upon the theory of nonlinear analysis, recurrence plots (RPs) and recurrence quantification analysis (RQA) are of greater significance that help in understanding the chaotic and recurrence behavior of the dynamically occurring complex physiological signals. In our study, a novel method is proposed combining the RPs with the machine learning based algorithms for automated classification of EEG signals into eyes-open and eyes-close states. A huge dataset of 109 subjects has been acquired from the PhysioNet database. Each of the six RQA-based measures (recurrence rate, determinism, entropy, laminarity, trapping time, and longest vertical line)has been extracted from 64 EEG channels. Feature selection has been performed using genetic algorithm. The selected features have been averaged and combined to form a six-dimensional input vector which shows statistically significant differences (p < 0.01) between the two states. It is fed to different machine learning based algorithms such as logistic-regression, support vector machine, random forest, k-nearest neighbor, Gaussian naïve Bayes, and adaptive boosting. Logistic regression achieves the highest performance results in terms of accuracy, F1 score, precision, recall, and specificity of 97.27%, 97.17%, 98.26%, 96.36%, and 98.18%, respectively, with the least testing time of the model as 2.52 ms. Therefore, our method might be of greater significance in the development of the practical applications.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.