MSBE Analysis with Frequency Spectra for Automated Identification of Epileptic Seizure
Hemlata Pal
Hemlata Pal*, School of Electronics, Devi Ahilya University, Indore, India.
Manuscript received on October 11, 2019. | Revised Manuscript received on 26 October, 2019. | Manuscript published on November 10, 2019. | PP: 5869-5874 | Volume-8 Issue-12, October 2019. | Retrieval Number: L32251081219/2019©BEIESP | DOI: 10.35940/ijitee.L3225.1081219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© 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: This study introduces a reliable automated seizure detection technique based on MSBE (Multi scale bubble entropy) and frequency spectral analysis. Method- This paper aims to develop a novel seizure detection technique that incorporates AM FM model for decomposition of EEG into different sub bands. In our approach, integrated feature set is constructed using multi scale bubble entropy analysis at each sub band and frequency spectral analysis at each electrode. Result-In this paper, an application of bubble entropy with different frequency parameter such as PPF and PSD is provided in order to access its stable and outstanding performance on epileptic seizer detection. The experimental results show that classification accuracy is improved with this algorithm. These finding suggest that extracted features can be used for treatment of epilepsy. Significance- This method provides greater stability and discriminative power, so this technique could be used to detect wider range of seizures.
Keywords: Epilepsy, EEG, Multi scale bubble entropy, Power spectral density, Seizure detection
Scope of the Article: Power Spectral Density