Postural time-series analysis using Empirical Mode Decomposition and second-order difference plots

Pachori, Ram Bilas; Hewson, David; Snoussi, Hichem; Duchêne, Jacques

doi:10.1109/icassp.2009.4959639

Cited by 26 publications

(12 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As an improvement of MSEn, intrinsic mode entropy (IMEn) [37] is proposed based on EMD, which computes complexity in high frequency scales of the signal, as well as being robust to dominating low-frequency components by combining the group of IMFs. The concept of multilevel filtering has been applied in the EMD domain [38] and in the flexible analytic wavelet transform (FAWT) [39] domain [40]. However, in some cases, the EMD method failed to extract low-energy components from the analyzed time series [41], and hence, low-energy components are absent in the time-frequency plane.…”

Section: Introductionmentioning

confidence: 99%

Tunable-Q Wavelet Transform Based Multiscale Entropy Measure for Automated Classification of Epileptic EEG Signals

et al. 2017

View full text Add to dashboard Cite

This paper analyzes the underlying complexity and non-linearity of electroencephalogram (EEG) signals by computing a novel multi-scale entropy measure for the classification of seizure, seizure-free and normal EEG signals. The quality factor (Q) based multi-scale entropy measure is proposed to compute the entropy of the EEG signal in different frequency-bands of interest. The Q -based entropy (QEn) is computed by decomposing the signal with the tunable-Q wavelet transform (TQWT) into the number of sub-bands and estimating K-nearest neighbor (K-NN) entropies from various sub-bands cumulatively. The optimal selection of Q and the redundancy parameter (R) of TQWT showed better robustness for entropy computation in the presence of high-and low-frequency components. The extracted features are fed to the support vector machine (SVM) classifier with the wrapper-based feature selection method. The proposed method has achieved accuracy of 100% in classifying normal (eyes-open and eyes-closed) and seizure EEG signals, 99.5% in classifying seizure-free EEG signals (from the hippocampal formation of the opposite hemisphere of the brain) from seizure EEG signals and 98% in classifying seizure-free EEG signals (from the epileptogenic zone) from seizure EEG signals, respectively, using the SVM classifier. We have also achieved classification accuracies of 99% and 98.6% in classifying seizure versus non-seizure EEG signals and the individual three classes, namely normal, seizure-free and seizure EEG signals, respectively. The performance measure of the proposed multi-scale entropy has been found to be comparable with the existing state of the art epileptic EEG signals classification methods studied using the same database.

show abstract

Section: Introductionmentioning

confidence: 99%

Tunable-Q Wavelet Transform Based Multiscale Entropy Measure for Automated Classification of Epileptic EEG Signals

et al. 2017

View full text Add to dashboard Cite

show abstract

“…28,29 Motivated by this technique, the second order difference plot was discovered and applied to analyze some physiological signals. 30,31 In this plot, Dx n þ 1 is plotted against Dx n (where D represents the standard first order difference) that means [x(n þ 2) -x(n þ 1)] is plotted against [x (n þ 1) À x(n)]. So this is basically a Poincaré plot of the first order differences that physically represents a plot of successive rates against each other and gives a graphical representation of the rate of variability.…”

Section: Second-order Difference Plotmentioning

confidence: 98%

Analysis of heart rate variability signal in meditation using second-order difference plot

Goswami

Tibarewala

Bhattacharya

2011

Journal of Applied Physics

View full text Add to dashboard Cite

In this article, the heart rate variability signal taken from subjects practising different types of meditations have been investigated to find the underlying similarity among them and how they differ from the non-meditative condition. Four different groups of subjects having different meditation techniques are involved. The data have been obtained from the Physionet and also collected with our own ECG machine. For data analysis, the second order difference plot is applied. Each of the plots obtained from the second order differences form a single cluster which is nearly elliptical in shape except for some outliers. In meditation, the axis of the elliptical cluster rotates anticlockwise from the cluster formed from the premeditation data, although the amount of rotation is not of the same extent in every case. This form study reveals definite and specific changes in the heart rate variability of the subjects during meditation. All the four groups of subjects followed different procedures but surprisingly the resulting physiological effect is the same to some extent. It indicates that there is some commonness among all the meditative techniques in spite of their apparent dissimilarity and it may be hoped that each of them leads to the same result as preached by the masters of meditation. The study shows that meditative state has a completely different physiology and that it can be achieved by any meditation technique we have observed. Possible use of this tool in clinical setting such as in stress management and in the treatment of hypertension is also mentioned.

show abstract

“…Due to the adaptive nature of the decomposition and suitability for analysis of non-linear and non-stationary signals without designing sets of basis functions, EMD has been studied in many areas such as fault diagnosis [32], speech processing [33], human posture control [34] and biomedical applications [35].…”

Section: Brief Overview Of Empirical Mode Decompositionmentioning

confidence: 99%

Empirical mode decomposition based dynamic error correction in SS covered 62.5/125µm optical fiber based distributed temperature sensor

Saxena

Raju

Arya

et al. 2015

Optics & Laser Technology

View full text Add to dashboard Cite

Postural time-series analysis using Empirical Mode Decomposition and second-order difference plots

Cited by 26 publications

References 10 publications

Tunable-Q Wavelet Transform Based Multiscale Entropy Measure for Automated Classification of Epileptic EEG Signals

Tunable-Q Wavelet Transform Based Multiscale Entropy Measure for Automated Classification of Epileptic EEG Signals

Analysis of heart rate variability signal in meditation using second-order difference plot

Empirical mode decomposition based dynamic error correction in SS covered 62.5/125µm optical fiber based distributed temperature sensor

Contact Info

Product

Resources

About