eduzhai > Applied Sciences > Engineering >

EEG Signal Classification using Variational Mode Decomposition

  • KanKan
  • (0) Download
  • 20210430
  • Save

... pages left unread,continue reading

Document pages: 8 pages

Abstract: Epilepsy affects about 1 of the population every year, and is characterizedby abnormal and sudden hyper-synchronous excitation of the neurons in thebrain. The electroencephalogram(EEG) is the most widely used method to recordbrain signals and diagnose epilepsy and seizure cases. In this paper we use themethod of Variational Mode Decomposition (VMD) in our analysis to classifyseizure seizure free signals. This technique uses variational non recursivemode decomposition, in comparison to other methods like Empirical Mode (EMD)and Hilbert-Huang transform which recursively decompose the signals, makingthem more susceptible to noise and sampling rate. VMD decomposes a signal intoits components which are called principal modes. In our analysis, 4 features ofthe decomposed signals namely Renyi Entropy, second order difference plot(SODP), fourth order difference plot(FODP) and average amplitude areinvestigated, both individually and using a ranking methodology considering all4 features at the same time. The SODP of decomposed signal modes is anelliptical structure. The 95 confidence ellipse area measured from the SODP ofthe decomposed signal modes has been used as a feature in order to discriminateseizure-free EEG signals from the epileptic seizure EEG signal. For theclassification, a Multilayer Perceptron(MLP) with back propagation algorithm asthe training method was used. A high percentage of accuracy was obtained whenthe features were used individually for classification and an even higherdegree of accuracy was obtained when the ranking methodology was used.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...