Name
Title | ||
|---|---|---|
Weighted Sliding Empirical Mode Decomposition for Online Analysis of Biomedical Time Series. |
Abstract | ||
|---|---|---|
Biomedical signals are in general non-linear and non-stationary. in conjunction with a provides a fully adaptive and data-driven technique to extract . The latter represent a complete set of locally orthogonal basis functions to represent non-linear and non-stationary time series. Large scale biomedical time series necessitate an online analysis, which is presented in this contribution. It shortly reviews the technique of EMD and related algorithms, discusses the recently proposed weighted sliding EMD algorithm (wSEMD) and, additionally, proposes a more sophisticated implementation of the weighting process. As an application to biomedical signals we will show that wSEMD in combination with mutual information could be used to detect temporal correlations of arterial blood pressure and intracranial pressure monitored at a neurosurgical intensive care unit. We will demonstrate that the wSEMD technique renders itself much more flexible than the Fourier based method used in Faltermeier et al. (Acta Neurochir Suppl, 114, 35–38, ). |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1007/s11063-012-9270-9 | Neural Processing Letters |
Keywords | Field | DocType |
Empirical mode decomposition,Neuromonitoring,Online analysis | Weighting,Online analysis,Pattern recognition,Computer science,Orthogonal basis,Fourier transform,Mutual information,Artificial intelligence,Machine learning,Hilbert–Huang transform | Journal |
Volume | Issue | ISSN |
37 | 1 | 1370-4621 |
Citations | PageRank | References |
4 | 0.44 | 3 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Angela Zeiler | 1 | 8 | 2.24 |
| Rupert Faltermeier | 2 | 17 | 5.38 |
| Ana Maria Tomé | 3 | 163 | 30.42 |
| Carlos García Puntonet | 4 | 107 | 25.86 |
| Alexander Brawanski | 5 | 17 | 5.38 |
| Elmar Wolfgang Lang | 6 | 260 | 36.10 |