A Multivariate Multiscale Fuzzy Entropy Algorithm with Application to Uterine EMG Complexity Analysis
| Autor: | Danilo P. Mandic, Theerasak Chanwimalueang, Mosabber Uddin Ahmed, Sudhin Thayyil |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2016 |
| Předmět: |
DYNAMICS
Multivariate statistics Computer science Fluids & Plasmas Physics Multidisciplinary TIME-SERIES General Physics and Astronomy Uterine electromyography lcsh:Astrophysics Short length TERM multivariate fuzzy entropy multiscale complexity uterine EMG 01 natural sciences DISEASE 010305 fluids & plasmas Structural complexity Multiscale entropy Fuzzy entropy 0103 physical sciences lcsh:QB460-466 RECORDINGS Entropy (information theory) 010306 general physics lcsh:Science 01 Mathematical Sciences Science & Technology 02 Physical Sciences Physics lcsh:QC1-999 Nonlinear system PRETERM DELIVERY Physical Sciences lcsh:Q Algorithm lcsh:Physics |
| Zdroj: | Entropy, Vol 19, Iss 1, p 2 (2016) Entropy; Volume 19; Issue 1; Pages: 2 |
| ISSN: | 1099-4300 |
| Popis: | The recently introduced multivariate multiscale entropy (MMSE) has been successfully used to quantify structural complexity in terms of nonlinear within- and cross-channel correlations as well as to reveal complex dynamical couplings and various degrees of synchronization over multiple scales in real-world multichannel data. However, the applicability of MMSE is limited by the coarse-graining process which defines scales, as it successively reduces the data length for each scale and thus yields inaccurate and undefined entropy estimates at higher scales and for short length data. To that cause, we propose the multivariate multiscale fuzzy entropy (MMFE) algorithm and demonstrate its superiority over the MMSE on both synthetic as well as real-world uterine electromyography (EMG) short duration signals. Based on MMFE features, an improvement in the classification accuracy of term-preterm deliveries was achieved, with a maximum area under the curve (AUC) value of 0.99. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|