EEG signal based seizure detection focused on Hjorth parameters from tunable-Q wavelet sub-bands

Abstract

In recent years, automated seizure identification with electroencephalogram (EEG) signals has received considerable attention and appears to be an appropriate approach for diagnosis and treatment of the disease. This paper analyze the ability of Hjorth parameter for seizure detection using EEG signals. The tunable-Q wavelet transform (TQWT) is applied to decompose an EEG signal into various subbands at different levels. The Hjorth parameters namely activity, mobility, and complexity are studied over the decomposed components. The University of Bonn, Germany dataset is studied to validate the proposed method with including seizure, seizure-free, and normal categories of EEG signal. Classification findings show that the proposed technique with estimating the Hjorth parameters preserves efficiency and is appropriate for automated identification of epileptic seizures. In this work, very high classification accuracy is achieved in various set of combinations. The proposed technique is compared with state-of-the-art approaches available in the literature. © 2022