Adaptive-projection intrinsically transformed multivariate empirical mode decomposition in cooperative brain–computer interface applications

Hemakom, Apit; Goverdovsky, Valentin; Looney, David; Mandic, Danilo P.

doi:10.1098/rsta.2015.0199

Cited by 36 publications

(26 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The conventional projection method of multivariate signals having power imbalances between channels fails to obtain the desired effect. Thus adaptive-projection intrinsically transformed multivariate empirical mode decomposition (APIT-MEMD) [ 28 ] was proposed to deal with nonlinear and non-stationary signals, improving mode-mixing problems and obtaining fewer IMFs for multivariate signals. Most importantly, the method can accommodate power imbalance phenomena.…”

Section: Introductionmentioning

confidence: 99%

Multi-Fault Diagnosis of Rolling Bearings via Adaptive Projection Intrinsically Transformed Multivariate Empirical Mode Decomposition and High Order Singular Value Decomposition

Yuan

Song

2018

Sensors

View full text Add to dashboard Cite

Rolling bearings are important components in rotary machinery systems. In the field of multi-fault diagnosis of rolling bearings, the vibration signal collected from single channels tends to miss some fault characteristic information. Using multiple sensors to collect signals at different locations on the machine to obtain multivariate signal can remedy this problem. The adverse effect of a power imbalance between the various channels is inevitable, and unfavorable for multivariate signal processing. As a useful, multivariate signal processing method, Adaptive-projection has intrinsically transformed multivariate empirical mode decomposition (APIT-MEMD), and exhibits better performance than MEMD by adopting adaptive projection strategy in order to alleviate power imbalances. The filter bank properties of APIT-MEMD are also adopted to enable more accurate and stable intrinsic mode functions (IMFs), and to ease mode mixing problems in multi-fault frequency extractions. By aligning IMF sets into a third order tensor, high order singular value decomposition (HOSVD) can be employed to estimate the fault number. The fault correlation factor (FCF) analysis is used to conduct correlation analysis, in order to determine effective IMFs; the characteristic frequencies of multi-faults can then be extracted. Numerical simulations and the application of multi-fault situation can demonstrate that the proposed method is promising in multi-fault diagnoses of multivariate rolling bearing signal.

show abstract

Section: Introductionmentioning

confidence: 99%

Multi-Fault Diagnosis of Rolling Bearings via Adaptive Projection Intrinsically Transformed Multivariate Empirical Mode Decomposition and High Order Singular Value Decomposition

Yuan

Song

2018

Sensors

View full text Add to dashboard Cite

show abstract

“…Financial time series contain different degrees of volatility, or in other words power imbalances among the signal channels; therefore in the intrinsic multiscale analysis we use the noise-assisted adaptive-projection intrinsically-transformed MEMD (NA-APIT-MEMD) which accounts for the different dynamics in multivariate data (see [44] for more detail). By virtue of NA-APIT-MEMD, these intrinsic scales physically represent short-term trading, short-, medium-, and long-term trends.…”

Section: E Intrinsic Phase Synchrony (Ips)mentioning

confidence: 99%

“…The four financial time series were combined into a single quadrivariate signal, for which the intrinsic, data-adaptive, scales were determined using the NA-APIT-MEMD with 10 adjacent noise channels, to cater for power imbalances among the four data channels (see [44] for more detail). The PSIs between pairs of the data channels at every IMF index were then calculated from 50 realisations of NA-APIT-MEMD, and the confidence intervals at each IMF index were calculated by benchmarking against the PSIs between pairs of noise channels (no synchrony).…”

Section: F Intrinsic Phase Synchrony (Ips)mentioning

confidence: 99%

Financial Stress Through Complexity Science

Hemakom

Chanwimalueang

Carrión

et al. 2016

IEEE J. Sel. Top. Signal Process.

Self Cite

View full text Add to dashboard Cite

Abstract-Financial markets typically undergo periods of prosperity followed by periods of stagnation, and this undulation makes it challenging to maintain market efficiency. The efficient market hypothesis (EMH) states that there exist differences in structural complexity of the security prices between regular conditions and abnormal situations. Yet, despite a clear link between market acceleration (cf. recession) and stress in systems, indices of financial stress still have significant scope for further development. The overarching aim of this work is therefore to determine those characteristics of financial indices which are related to their stress levels, and to establish a robust metric for the extent of 'stress' of the financial system. This is achieved based on systematic intrinsic multiscale analysis which enables us to test the so called complexity-

show abstract

“…Algorithm 2: Pseudo-code of the APIT-MEMD algorithm (Hemakom et al, 2016) a number as possible, in order to cancel out the effect of the artificial input. A 175 high enough number of noise channels not only ensures a uniform population in the frequency spectrum, but also little dependency among the input channels, resulting in better decomposition (Looney et al, 2015).…”

mentioning

confidence: 99%

Probabilistic guidance for catheter tip motion in cardiac ablation procedures

Constantinescu

Su-Lin

Ernst

et al. 2018

Medical Image Analysis

Self Cite

View full text Add to dashboard Cite

Radiofrequency catheter ablation is one of the commonly available therapeutic methods for patients suffering from cardiac arrhythmias. The prerequisite of successful ablation is sufficient energy delivery at the target site. However, cardiac and respiratory motion, coupled with endocardial irregularities, can cause catheter drift and dispersion of the radiofrequency energy, thus prolonging procedure time, damaging adjacent tissue, and leading to electrical reconnection of temporarily ablated regions. Therefore, positional accuracy and stability of the catheter tip during energy delivery is of great importance for the outcome of the procedure. This paper presents an analytical scheme for assessing catheter tip stability, whereby a sequence of catheter tip motion recorded at sparse locations on the endocardium is decomposed. The spatial sliding component along the endocardial wall is extracted from the recording and maximal slippage and its associated probability are computed at each mapping point. Finally, a global map is generated, allowing the assessment of potential areas that are compromised by tip slippage. The proposed framework was applied to 40 retrospective studies of congenital heart disease patients and further validated on phantom data and simulations. The results show a good correlation with other intraoperative factors, such as catheter tip contact force amplitude and orientation, and with clinically documented anatomical areas of high catheter tip instability.

show abstract

Adaptive-projection intrinsically transformed multivariate empirical mode decomposition in cooperative brain–computer interface applications

Cited by 36 publications

References 37 publications

Multi-Fault Diagnosis of Rolling Bearings via Adaptive Projection Intrinsically Transformed Multivariate Empirical Mode Decomposition and High Order Singular Value Decomposition

Multi-Fault Diagnosis of Rolling Bearings via Adaptive Projection Intrinsically Transformed Multivariate Empirical Mode Decomposition and High Order Singular Value Decomposition

Financial Stress Through Complexity Science

Probabilistic guidance for catheter tip motion in cardiac ablation procedures

Contact Info

Product

Resources

About