期刊名称：IAENG International Journal of Computer Science
印刷版ISSN：1819-656X
电子版ISSN：1819-9224
出版年度：2019
卷号：46
期号：3
页码：384-394
出版社：IAENG - International Association of Engineers
摘要：This paper presents and discusses the challenge ofmode mixing when using the Empirical Mode Decomposition(EMD) to identify intrinsic modes from EEG signals usedfor neural activity reconstruction. The standard version ofthe EMD poses some challenges when decomposing signalshaving intermittency and close spectral proximity in theirbands. This is known as the Mode Mixing problem in EMD.Several approaches to solve the issue have been proposed inthe literature, but no single technique seems to be universallyeffective in preserving independent modes after the EMDdecomposition. This paper exposes the impact of mode mixingin the process of neural activity reconstruction and reports theresults of a performance comparison between a well knownstrategy, the Ensemble EMD (EEMD), and a new strategyproposed by the authors for mitigating the mode mixingproblem. The comparative evaluation shows a more accurateneural reconstruction when employing the strategy proposedby the authors, compared to the use of EEMD and its variantsfor neural activity reconstruction.
