Complex Empirical Mode Decomposition

Tanaka, Tomomi; Mandic, Danilo P.

doi:10.1109/lsp.2006.882107

Cited by 254 publications

(125 citation statements)

References 5 publications

Supporting

Mentioning

122

Contrasting

Unclassified

Order By: Relevance

“…There are methods that can be used to obtain band limited signals; one standard method is to use band pass filter to restrict the frequency range needed for the analysis. Alternatively, empirical mode decomposition (EMD) [4], or its extensions in complex domain [5] and multivariate domain [6] can be used to automatically decompose signals into a number of band limited signals before applying Hilbert Transform for phase extraction. After constructing the filter, verification on its correctness has to be made by comparing the similarity of the frequency characteristics of the constructed filter with those of the ideal one [3].…”

Section: A Step 1: Phase Analysis For Each Channel Of Eeg Datamentioning

confidence: 99%

Unconsciousness state identification using phase information extracted by Wavelet and Hilbert transform

Berthelot

Witon

2017

2017 22nd International Conference on Digital Signal Processing (DSP)

View full text Add to dashboard Cite

Abstract-This work aims to determine features for the distinction of coma and quasi brain death (QBD) consciousness states by implementing an algorithm for extracting phase information from EEG data using wavelet convolution and Hilbert transform. The relationship between the EEG data recorded from pairs of different electrodes is then quantified by calculating phase synchrony using Shannon entropy, as a phase synchrony index (PSI). Statistical analysis was used to evaluate the significant pairs of electrodes for the features extracted in the different frequency bands. The findings suggest confirm that both wavelet and Hilbert transform based phase synchrony analysis provide similar results. In particular, Hilbert transform might be a more suitable method for phase synchrony analysis to characterize coma or QBD brain states for lower frequency bands. Using non-parametric statistical tools is reliable and does not require strong assumption on the dataset distribution. The algorithm is not designed to be a diagnosis tool; it rather serves as a secondary test to confirm diagnosis. It also has a potential contribution for the systematic distinction of brain states in other areas of EEG-based research.

show abstract

Section: A Step 1: Phase Analysis For Each Channel Of Eeg Datamentioning

confidence: 99%

Unconsciousness state identification using phase information extracted by Wavelet and Hilbert transform

Berthelot

Witon

2017

2017 22nd International Conference on Digital Signal Processing (DSP)

View full text Add to dashboard Cite

show abstract

“…The complex empirical mode decomposition (cEMD) is an extension of the basic EMD suitable for dealing with complex signals [27]. The motivation to extend EMD is that a large number of signal processing applications have complex signals.…”

Section: Bivariate Emd (Bemd)mentioning

confidence: 99%

Empirical Mode Decomposition for Advanced Speech Signal Processing

Molla

Das

Hamid

et al. 2013

Journal of Signal Processing

View full text Add to dashboard Cite

Empirical mode decomposition (EMD) is a newly developed tool to analyze nonlinear and non-stationary signals.It is used to decompose any signal into a finite number of time varying subband signals termed as intrinsic mode functions (IMFs). Such data adaptive decomposition is recently used in speech enhancement. This study presents the concept of EMD and its application to advanced speech signal processing paradigms including speech enhancement by soft-thresholding, voiced/unvoiced (V/Uv) speech discrimination and pitch estimation. The speech processing is frequently performed in the transformed domain and the transformation is usually achieved by traditional signal analysis techniques i.e. Fourier and wavelet transformations. These analysis methods employ priori basis function and it is not suitable for data adaptive analysis for non-stationary signal like speech. Recently, EMD is taken much attention for speech signal processing in data adaptive way. Several EMD based potential soft-thresholding algorithms for speech enhancement are discussed here. The V/Uv discrimination is an important concern in speech processing. It is usually performed by using acoustic features. The training data is used to determine the threshold for classification. The EMD based data adaptive thresholding approach is developed for V/Uv discrimination without any training phase. Noticeable improvement is achieved with the application of EMD in pitch estimation of noisy speech signals. The related experimental results are also presented to realize the effectiveness of EMD in advanced speech processing algorithms.

show abstract

“…The first method of employing EMD in the complex domain, complex empirical mode decomposition, was introduced in 2007 [19]. The method is rigorously derived, based on the inherent relationship between the positive and negative frequency components of a complex signal and the properties of the Hilbert transform.…”

Section: Importance Of Complex Emdmentioning

confidence: 99%

“…As an example of its mathematical robustness, it preserves the dyadic filter property of standard EMD. In other words, the algorithm acts as dyadic filter bank when processing complex noise [19]. Rotation-invariant EMD, introduced in [1], proposes a way of extending EMD theory so that it operates fully in C. This is achieved through the use of complex splines.…”

Section: Importance Of Complex Emdmentioning

confidence: 99%