Dynamical complexity of human responses: a multivariate data-adaptive framework

Abstract: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.

Section: Effect Of Data Length On Multivariate Fuzzy Sample Entropymentioning

confidence: 99%

“…On the contrary, for MSampEn the increase in m does not reduce the number of the available delay vectors, as the composite multivariate embedded vectors are constructed in parallel, as pointed out in [18]. Nevertheless, a valid MSampEn estimate at higher m k requires a progressively higher number of samples.…”

Section: Sensitivity To the Embedding Dimensionmentioning

confidence: 99%

A Multivariate Multiscale Fuzzy Entropy Algorithm with Application to Uterine EMG Complexity Analysis

Ahmed

Chanwimalueang

Thayyil

et al. 2016

“…For data with 1000 samples, the shortest coarse-grained time series has a length of 100 samples. For this last case, the length of the coarse-grained time series will therefore be lower than 300, as recommended by others [8,18]. With a length of 100 samples, the results obtained with MGrcMSE should still be acceptable, as shown in [9].…”

Section: Results For Synthetic Signalsmentioning

confidence: 90%

“…Scales were lower than 40. Therefore, all the coarse-grained time series were longer than 300 samples, as recommended by others [8,18].…”

Section: Results For Synthetic Signalsmentioning

confidence: 99%

Multivariate Generalized Multiscale Entropy Analysis

Humeau-Heurtier

2016

Multiscale entropy (MSE) was introduced in the 2000s to quantify systems' complexity. MSE relies on (i) a coarse-graining procedure to derive a set of time series representing the system dynamics on different time scales; (ii) the computation of the sample entropy for each coarse-grained time series. A refined composite MSE (rcMSE)-based on the same steps as MSE-also exists. Compared to MSE, rcMSE increases the accuracy of entropy estimation and reduces the probability of inducing undefined entropy for short time series. The multivariate versions of MSE (MMSE) and rcMSE (MrcMSE) have also been introduced. In the coarse-graining step used in MSE, rcMSE, MMSE, and MrcMSE, the mean value is used to derive representations of the original data at different resolutions. A generalization of MSE was recently published, using the computation of different moments in the coarse-graining procedure. However, so far, this generalization only exists for univariate signals. We therefore herein propose an extension of this generalized MSE to multivariate data. The multivariate generalized algorithms of MMSE and MrcMSE presented herein (MGMSE and MGrcMSE, respectively) are first analyzed through the processing of synthetic signals. We reveal that MGrcMSE shows better performance than MGMSE for short multivariate data. We then study the performance of MGrcMSE on two sets of short multivariate electroencephalograms (EEG) available in the public domain. We report that MGrcMSE may show better performance than MrcMSE in distinguishing different types of multivariate EEG data. MGrcMSE could therefore supplement MMSE or MrcMSE in the processing of multivariate datasets.

“…MMSE evaluates dynamic relationship of multi-channel time series from the perspective of complexity, mutual correlation prediction and long-range correlation and exhibits the nonlinear internal coupling characteristic of multi-channel time series. MMSE has been used in complex physiologic time series and center of pressure signals analysis [18,19]. However, the sample entropy used in MMSE, as described above, often has mutations when the time series is not long enough.…”

Section: Introductionmentioning

confidence: 99%

A Refined Composite Multivariate Multiscale Fuzzy Entropy and Laplacian Score-Based Fault Diagnosis Method for Rolling Bearings

Zheng

Pan

et al. 2017

Abstract:The vibration signals of rolling bearings are often nonlinear and non-stationary. Multiscale entropy (MSE) has been widely applied to measure the complexity of nonlinear mechanical vibration signals, however, at present only the single channel vibration signals are used for fault diagnosis by many scholars. In this paper multiscale entropy in multivariate framework, i.e., multivariate multiscale entropy (MMSE) is introduced to machinery fault diagnosis to improve the efficiency of fault identification as much as possible through using multi-channel vibration information. MMSE evaluates the multivariate complexity of synchronous multi-channel data and is an effective method for measuring complexity and mutual nonlinear dynamic relationship, but its statistical stability is poor. Refined composite multivariate multiscale fuzzy entropy (RCMMFE) was developed to overcome the problems existing in MMSE and was compared with MSE, multiscale fuzzy entropy, MMSE and multivariate multiscale fuzzy entropy by analyzing simulation data. Finally, a new fault diagnosis method for rolling bearing was proposed based on RCMMFE for fault feature extraction, Laplacian score and particle swarm optimization support vector machine (PSO-SVM) for automatic fault mode identification. The proposed method was compared with the existing methods by analyzing experimental data analysis and the results indicate its effectiveness and superiority.