Seizure Detection Algorithm Based on Multidimensional Covariance Matrix and Binary Harris Hawks Optimization With Cauchy–Gaussian Mutation
- 21 December 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (4) , 4596-4608
Abstract
This paper proposes a novel seizure detection algorithm based on multidimensional covariance matrix and hybrid mutation of binary Harris hawks optimizer. First, raw electroencephalography (EEG) signals are preprocessed using empirical mode decomposition (EMD) and discrete wavelet transform (DWT) to obtain several subband signals. Second, single-channel single-subband matrices (SCSS), single-channel multi-subband matrices (SCMS) and multi-channel single-subband matrices (MCSS), are constructed and transformed into covariance matrices. After computing the eigenvalues of each covariance matrix, statistical parameters which include mean, variance, and skewness are extracted to form a feature set. Then, binary Harris hawks optimization (BHHO) algorithm with Cauchy-Gaussian mutation (CGBHHO) is proposed to enhance global search capability and local search capability of BHHO algorithm to accomplish iterative feature selection. Finally, random forest (RF) classifier is employed for automatic seizure detection. The proposed method achieves favorable experimental results with a ten-fold cross-validation evaluation on CHB-MIT database. The results show that the accuracy (ACC), specificity (SPE), sensitivity (SEN), and F1 score (F1) of the method can reach 99.32%, 99.22%, 99.45% and 99.36%, respectively.Keywords
Funding Information
- National key research and development program (2021YFE0100100)
- National Natural Science Foundation of China (62301203)
- Fundamental Research Funds for the Provincial Universities of Zhejiang (GK239909299001-401)
- Joint Fund of Zhejiang Provincial Natural Science Foundation of China (LBY21H090001)
- NSFC-Zhejiang Integration Joint Fund (U1909209)
- National College Students' innovation and entrepreneurship training program (202210336043)
- Open Research Projects of Zhejiang Lab (2021MC0AB04)
This publication has 35 references indexed in Scilit:
- Real-time epilepsy seizure detection based on EEG using tunable-Q wavelet transform and convolutional neural networkBiomedical Signal Processing and Control, 2023
- Bio-inspired Red Fox-Sine cosine optimization for the feature selection of SSVEP-based EEG signals for BCI applicationsBiomedical Signal Processing and Control, 2022
- Seizure detection algorithm based on fusion of spatio-temporal network constructed with dispersion indexBiomedical Signal Processing and Control, 2022
- Cognitive load detection using circulant singular spectrum analysis and Binary Harris Hawks Optimization based feature selectionBiomedical Signal Processing and Control, 2022
- An EEG based real-time epilepsy seizure detection approach using discrete wavelet transform and machine learning methodsBiomedical Signal Processing and Control, 2022
- EEG-Based Seizure detection using linear graph convolution network with focal lossComputer Methods and Programs in Biomedicine, 2021
- Time–Frequency Statistical Features of Delta Band for Detection of Epileptic SeizuresWireless Personal Communications, 2021
- Boosted binary Harris hawks optimizer and feature selectionEngineering with Computers, 2020
- Epileptic seizure detection by combining robust‐principal component analysis and least square‐support vector machineInternational Journal of Imaging Systems and Technology, 2017
- Feature extraction and recognition of ictal EEG using EMD and SVMComputers in Biology and Medicine, 2013