Online Epilepsy Diagnosis Based on Analysis of EEG Signals by Hybrid Adaptive Filtering and Higher-order Crossings

This paper presents a novel epilepsy diagnosis algorithm based on analysis of EEG signals by hybrid adaptive filtering (HAF) and higher-order crossings (HOC). In this algorithm, HAF is developed to isolate the seizure and non-seizure EEG characteristics and facilitating the task of the feature vector extraction. Furthermore, HOC analysis is employed to select the effective feature from the HAF-filtered signals. The extracted features by HAF-HOC scheme can create maximum distinction between two classes. Finally, Quadratic Discriminant Analysis (QDA) and Mahalanobis Distance (MD) is used for classification and recognition of seizures through EEG signals. The proposed algorithm is implemented on CHB dataset and its performance has been evaluated for three measures. The results indicate that the algorithm can recognize the seizure with smaller delay and higher good detection rate that are important factors from a clinical viewpoint.