Classification of Focal and Non-Focal EEG Signal using an Area of Octagon Method
R. Krishnaprasanna1, V. Vijayabaskar2
1R.Krishnaprasanna*, Research scholar, Department of ECE, sathyabama institute of science and technology, Chennai, Tamil Nadu, India.
2V. Vijayabaskar, Professor, Department of ETCE, sathyabama institute of science and technology, Chennai, Tamil Nadu, India.
Manuscript received on September 22, 2019. | Revised Manuscript received on October 20, 2019. | Manuscript published on October 30, 2019. | PP: 1832-1838 | Volume-9 Issue-1, October 2019 | Retrieval Number: A1450109119/2019©BEIESP | DOI: 10.35940/ijeat.A1450.109119
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Epilepsy, a neurological syndrome can be detected via the electroencephalogram (EEG) signal with the help of sensors placing in the human cranium. This article introduces a fresh method known as the Area of Octagon (AOO), used for Focal (F) and Non-Focal (NF) EEG Signal classification. Initially, both class signals are putrefied into many intrinsic mode functions (IMF) with the help of Empirical mode decomposition (EMD) algorithm. The AOO can be computed with the help of decomposed IMFs. The AOO is now used as an input feature set for the classifier. This research aims to discriminate the F and NF EEG measurements for the therapy resistance. The proposed method attained an average classification accuracy of 97.9% with Linear, polynomial and an RBF kernel.
Keywords: Area of octagon (AOO), Electroencephalogram (EEG), Empirical Mode Decomposition (EMD), Intrinsic Mode Function (IMF).