A Time-domain morphology and gradient based algorithm for ECG feature extraction


Mazomenos, Evangelos, Chen, Taihai, Acharyya, Amit, Bhattacharya, Arnab, Rosengarten, James and Maharatna, Koushik (2012) A Time-domain morphology and gradient based algorithm for ECG feature extraction At IEEE International Conference on Industrial Technology, Greece. 6 pp, pp. 117-122. (doi:10.1109/ICIT.2012.6209924).

Download

[img] PDF paperKC-003107_mazomenos.pdf - Other
Download (382kB)

Description/Abstract

A Time Domain Morphology and Gradient (TDMG) based algorithm is presented in this paper for the extraction of all the fiducial time instances from a single PQRST complex. By estimating these characteristic points, all clinically important temporal ECG parameters can be calculated. The proposed algorithm is based on a combination of extrema detection and slope information, with the use of adaptive thresholding to achieve the extraction of 11 time instances. A pre-processing step removes any noise and artefacts from the captured ECG signal. Initially, the position of the R-wave and the QRS-complex boundaries are localized in time. Following, by focusing on the part of the signal that precedes and succeeds the QRS-complex, the remaining fiducial points from the P and T waves are estimated. The initial localisation of the wave boundaries is complimented by amendment steps which are introduced to cater for atypical wave morphologies, indicative of particular heart conditions. The proposed algorithm is evaluated on the QT and PTB databases against medically annotated ECG samples. The results demonstrate the ability of the proposed scheme, to estimate the ECG fiducial points with acceptable accuracy from a single-lead ECG signal. In addition, this investigation reveals the ability of the TDMG algorithm to perform accurately irrespective of the lead chosen, the different disease categories and the sampling frequency of the captured ECG signal.

Item Type: Conference or Workshop Item (Paper)
Digital Object Identifier (DOI): doi:10.1109/ICIT.2012.6209924
Venue - Dates: IEEE International Conference on Industrial Technology, Greece, 2012-03-01
Subjects:
Organisations: Faculty of Health Sciences, Electronic & Software Systems
ePrint ID: 340407
Date :
Date Event
March 2012Published
Date Deposited: 21 Jun 2012 11:02
Last Modified: 17 Apr 2017 16:55
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/340407

Actions (login required)

View Item View Item