Abstract
The detection of seizure onset and events using electroencephalogram (EEG) signals are important tasks in epilepsy research. The literature available on seizure detection has discussed the implementation of advanced signal processing algorithms using tools accessed over the cloud. However, seizure monitoring application needs near sensor processing due to privacy and latency issues. In this paper, a real time seizure detection system has been implemented using an embedded system. The proposed system is based on ensemble empirical mode decomposition (EEMD) and tunable-Q wavelet transform (TQWT) algorithms. The analysis and classification of non-stationary EEG signals require the wavelet transform with high Q-factor. However, direct use of TQWT increases the computational complexity of feature extraction from multivariate EEG signals. In this paper, the first step is to process the signal by using EEMD to obtain 8 intrinsic mode functions (IMFs). The Kraskov (KraEn), sample (SampEn), and permutation (PermEn) entropy features of IMFs are extracted and based on optimum values, and 4 IMFs are decomposed using TQWT. Secondly, centered correntropy (CenCorrEn) features of the 1st and 16th sub-band of TQWT have been used as classifier inputs. The performance of multilayer perceptron neural networks (MLPNN), least squares support vector machine (LSSVM), and random forest (RF) classifiers has been tested on the multichannel EEG data recorded from a local hospital. The RF classifier has produced the highest accuracy of 96.2% in classifying the signals. The proposed scheme has been employed in developing an embedded seizure detection system to assist neurologists in making seizure diagnostic decisions.
Highlights
Epilepsy is caused by irregular changes in neural activity[1]
Since we have considered 4 intrinsic mode functions (IMFs) from the Ensemble empirical mode decomposition (EEMD) step, a total of 16 sub-bands are produced by the tunable-Q wavelet transform (TQWT) step
Kraskov entropy (KraEn), permutation entropy (PermEn), sample entropy (SampEn) were computed for the 8 IMFs
Summary
Epilepsy is caused by irregular changes in neural activity[1]. The recurrent impulsive seizure from intricate processes is related to numerous neurotransmitters in the cholinergic, glutamatergic and GABAergic system[2]. Non-epileptic deformities are characterized by variations in normal signals or by the manifestation of abnormal signals While these two types often coexist, separating them is conceptually useful and helps in diagnosis of focal epilepsy[6]. The signal feature computation and classification are major steps in computerized seizure detection[7]. The decomposition of EEG signal and computation of features is done separately in two steps, using either ensemble EMD (EEMD) or TQWT. Advantages of EEMD and TQWT are combined to extract optimum features in two stages to enhance the classification accuracy in a real time seizure detection system. Since we have considered 4 IMFs from the EEMD step, a total of 16 sub-bands are produced by the TQWT step The features from these sub-bands represent oscillatory behavior of decomposed signals. A comparison of the classification performance is presented for LSSVM and RF classifiers
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
