Data-Driven Multivariate Signal Denoising Using Mahalanobis Distance

Naveed Ur Rehman; Khuram Naveed; Bushra Khan

doi:10.1109/LSP.2019.2932715

Data-Driven Multivariate Signal Denoising Using Mahalanobis Distance

Naveed Ur Rehman^*, Khuram Naveed, Bushra Khan

^*Corresponding author for this work

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaper › Journal article › Research › peer-review

Abstract

A novel multivariate signal denoising method is presented that computes Mahalanobis distance measure at multiple data scales obtained from multivariate empirical mode decomposition (MEMD) algorithm. That enables joint multichannel data denoising directly in multidimensional space where input signal resides, by employing interval thresholding on multiple data scales in . We provide theoretical justification of using Mahalanobis distance at multiple scales obtained from MEMD and prove that the proposed method is able to incorporate inherent correlation between multiple data channels in the denoising process. The performance of the proposed method is verified on a range of synthetic and real world signals.

Original language	English
Journal	IEEE Signal Processing Letters
Volume	26
Issue	9
Pages (from-to)	1408-1412
ISSN	1070-9908
DOIs	https://doi.org/10.1109/LSP.2019.2932715
Publication status	Published - Sept 2019
Externally published	Yes

Access to Document

10.1109/LSP.2019.2932715

Cite this

@article{6985e8b55bf64dceb349c6952939b0c2,

title = "Data-Driven Multivariate Signal Denoising Using Mahalanobis Distance",

abstract = "A novel multivariate signal denoising method is presented that computes Mahalanobis distance measure at multiple data scales obtained from multivariate empirical mode decomposition (MEMD) algorithm. That enables joint multichannel data denoising directly in multidimensional space where input signal resides, by employing interval thresholding on multiple data scales in . We provide theoretical justification of using Mahalanobis distance at multiple scales obtained from MEMD and prove that the proposed method is able to incorporate inherent correlation between multiple data channels in the denoising process. The performance of the proposed method is verified on a range of synthetic and real world signals.",

author = "Rehman, {Naveed Ur} and Khuram Naveed and Bushra Khan",

year = "2019",

month = sep,

doi = "10.1109/LSP.2019.2932715",

language = "English",

volume = "26",

pages = "1408--1412",

journal = "IEEE Signal Processing Letters",

issn = "1070-9908",

publisher = "Institute of Electrical and Electronics Engineers",

number = "9",

}

TY - JOUR

T1 - Data-Driven Multivariate Signal Denoising Using Mahalanobis Distance

AU - Rehman, Naveed Ur

AU - Naveed, Khuram

AU - Khan, Bushra

PY - 2019/9

Y1 - 2019/9

N2 - A novel multivariate signal denoising method is presented that computes Mahalanobis distance measure at multiple data scales obtained from multivariate empirical mode decomposition (MEMD) algorithm. That enables joint multichannel data denoising directly in multidimensional space where input signal resides, by employing interval thresholding on multiple data scales in . We provide theoretical justification of using Mahalanobis distance at multiple scales obtained from MEMD and prove that the proposed method is able to incorporate inherent correlation between multiple data channels in the denoising process. The performance of the proposed method is verified on a range of synthetic and real world signals.

AB - A novel multivariate signal denoising method is presented that computes Mahalanobis distance measure at multiple data scales obtained from multivariate empirical mode decomposition (MEMD) algorithm. That enables joint multichannel data denoising directly in multidimensional space where input signal resides, by employing interval thresholding on multiple data scales in . We provide theoretical justification of using Mahalanobis distance at multiple scales obtained from MEMD and prove that the proposed method is able to incorporate inherent correlation between multiple data channels in the denoising process. The performance of the proposed method is verified on a range of synthetic and real world signals.

U2 - 10.1109/LSP.2019.2932715

DO - 10.1109/LSP.2019.2932715

M3 - Journal article

SN - 1070-9908

VL - 26

SP - 1408

EP - 1412

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

IS - 9

ER -

Data-Driven Multivariate Signal Denoising Using Mahalanobis Distance

Abstract

Access to Document

Fingerprint

Cite this