Data publikacji: 27 gru 2017
Zakres stron: 481 - 497
Otrzymano: 15 lut 2014
Przyjęty: 01 cze 2014
DOI: https://doi.org/10.21307/ijssis-2017-666
Słowa kluczowe
© 2014 Leong Wai Yie et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Sleep apnea is a growing sleep disorder issue and estimate to affect 7% of the adult population in Malaysia. In this study, the electrical activity of the brain is studied using Electroencephalogram (EEG). The data obtained was then decomposed using three methods; Empirical Mode Decomposition (EMD), Bivariate EMD and finally Ensemble EMD. The Index of Orthogonatility (IO) was obtained which shows EMD performed the most poorly, EEMD the best and Bivariate in between. The performance of EMD greatly improves when the number of samples was greatly decreased and very high peaks and more complex parts of the signal were excluded in the analysis. Segmentation was also conducted and the segmentation error revealed when an Event Related Potential (ERP) has happened which is when apnea occurred.