Abstract
Automated epileptic seizure detection is essential for advancing epilepsy diagnosis and assisting medical professionals. Automated seizure detection using Electroencephalogram signals has gained significant interest in recent past and appeared to be an expedient approach in both disease diagnosis and treatment. In this paper, a new methodology of automated epileptic seizure detection using Tunable Q-wavelet Transform (TQWT) based nonlinear feature extraction is presented. The Electroencephalogram dataset studied in present work includes trials from non-seizure, pre-seizure and seizure EEG activity. Proposed methodology is carried out in three methodological steps. In first step, Electroencephalogram activity is decomposed into optimum number of time–frequency sub-bands using TQWT. In second step, three nonlinear features viz. approximate entropy, Higuchi’s fractal dimension and Katz’s fractal dimension are estimated from decomposed sub-bands and four feature vectors are prepared. Classification of estimated feature vector is performed using two soft computing techniques viz. support vector machine and random forest tree classifier in the third step. Experimental results illustrate efficacy of estimated features in epilepsy detection task. Classification results demonstrate that proposed methodology of nonlinear feature estimation preserves efficiency and simplicity and is appropriate for epileptic seizure detection.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.