A computationally efficient automated seizure detection method based on the novel idea of multiscale spectral features. (September 2021)

• Record Type: Journal Article
• Authors: Sukriti, ; Chakraborty, Monisha; Mitra, Debjani
• Is Part Of: Biomedical signal processing and control. Volume 70(2021)
• Publication Date: 2021-09
• Subjects: Epileptic Seizure Detection -- Electroencephalogram (EEG) -- Coarse graining -- Spectral features -- Random Forest Classifier -- Hardware implementation; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.102990
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Multiscale spectral features (MSSFs) are introduced for seizure detection. Our method took only 0.01965 s to extract features from EEG & to identify its class. Three benchmark EEG databases are used to verify the performance of proposed method. In comparison with related works, our results are promising. Zynq UltraScale + MPSoC ZCU102 is utilized to implement proposed MSSFs. Abstract: In this work, we propose a novel feature extraction scheme called multiscale spectral features (MSSFs) for the design of an automated seizure detection system. The MSSFs are derived from multiscale power spectral density (MSPSD) of electroencephalogram (EEG) signals that characterize seizure activities. Firstly, three MSSFs are computed from MSPSD of EEG segments. Subsequently, Kruskal-Wallis test is conducted to verify the class discrimination abilities of the proposed MSSFs, and then extracted features are given to Random Forest (RF) classifier for the categorization of EEG segments. The performance of RF classifier is assessed on three benchmark EEG databases. We also evaluate the computational time required for MSSFs extraction from an EEG segment and compare it with the computational time required by the existing methodologies based on spectral features. We achieved promising classification performances in comparison with state-of-the-art seizure detection models. Besides, our proposed seizure detection system required only 0.01965 s to extract features from an EEG segment and to identify its class. The reduced computational time in comparison with related works manifest the supremacy of our proposed methodology. Furthermore, the MSSFs are implemented on Zynq UltraScale + MPSoC ZCU102 to exhibit the real-time seizure detection capabilities of the proposed method. The implementation results manifest that the proposed methodology can be incorporated as a portable seizure control device. Hence, this work may pave the way for the development of seizure detection algorithms that have high detection rates, reduced computational complexity and are hardware-friendly as well.