Comparison of discrete wavelet and Fourier transforms for ECG beat classification

Dokur, Zümray; Ölmez, Tamer; Yazgan, E.

doi:10.1049/el:19991095

Cited by 61 publications

(25 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Unlike the Fourier transform, signal analysis using wavelets is localized in both time and frequency (or scale) and often reveals features that might not be revealed by Fourier analysis, such as distinct morphological components and nonperiodic components [21], [23]. As our results show, the separation of fTmp signal components using a wavelet analysis is relatively straight forward while separation using a Fourier analysis can be difficult due to overlapping spectral content.…”

Section: Discussionmentioning

confidence: 96%

Signal Decomposition of Transmembrane Voltage-Sensitive Dye Fluorescence Using a Multiresolution Wavelet Analysis

Asfour

Swift

Sarvazyan

et al. 2011

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Fluorescence imaging of transmembrane voltage-sensitive dyes is used to study electrical activation in cardiac tissue. However, the fluorescence signals, typically, have low SNRs and may be contaminated with motion artifact. In this report, we introduce a new processing approach for fluoresced transmembrane potentials (fTmps) that is based upon a discrete wavelet transform. We show how fTmp signals can be decomposed and reconstructed to form three subsignals that contain signal noise (noise signal), the early depolarization phase of the action potential (rTmp signal), and motion artifact (rMA signal). A coiflet4 wavelet is used for fTmp decomposition and reconstruction of these subsignals. Results using fTmp signals that are contaminated with motion artifact indicate that the approach is a useful processing step to remove baseline drift, reduce noise, and reveal wavefronts. It streamlines the preprocessing of fTmps for the subsequent measurement of activation times and conduction velocities. It is a promising approach for studying wavefronts without aggressive mechanical tissue constraint or electromechanical uncoupling agents and is, useful for single-camera systems that do not provide for ratiometric imaging.

show abstract

Section: Discussionmentioning

confidence: 96%

Signal Decomposition of Transmembrane Voltage-Sensitive Dye Fluorescence Using a Multiresolution Wavelet Analysis

Asfour

Swift

Sarvazyan

et al. 2011

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

show abstract

“…The over specification, of attributes to output classes, does not provide any level confidence on the extrapolation of these results into the operational environment. Dokur et al (1999) found that wavelet measures were significantly better able to classify heartbeats than Fourier features. Israel et al (2008) fused ECG, Pulse Oximetry, and blood pressure data for human identification (Figure 12).…”

Section: Feature Extractionmentioning

confidence: 97%

Heartbeat biometrics: a sensing system perspective

Israel¹,

Irvine²

2012

IJCB

View full text Add to dashboard Cite

This paper reviews the emerging research into exploitation of heartbeat data as a biometric for human identification. A variety of methods have been proposed for acquiring heartbeat signatures and a range of processing methods has been examined. We approach the biometric identification and verification problem by characterising the three major factors affecting performance: individual variants, environmental variants, and sensor variants. The ability to collect and process the signal, exploit the data for individual identification or verification, and disseminate the information depends on all three of these factors. Within each component, we have identified the relevant research. Where possible, we have tied these research papers to practical examples using high resolution ECG data. The research indicates that the heartbeat contains rich information about the individual, their level of anxiety, and the cardiac state.Keywords: biometrics; heartbeat; ECG; sensing system; cardiovascular function; human identification. areas of interest include novel biometrics, signal and image processing, quantification and modelling of data quality, and cognitive modeling. He was a Principal Investigator for DARPA's Human Identification at a Distance Program (HumanID). He serves on planning committees for IEEE and SPIE, and has served on several advisory panels for the Department of Defence and the Department of Energy. He has authored over a hundred journal and conference papers and holds a PhD in Mathematical Statistics from Yale University.

show abstract

“…Although STFT or windowed FT improves the FT, it suffers from fixed window width. Fixed window size cannot analyze lowfrequency and high-frequency of transient signals at the same time which is important for disturbance detection [34]. Later, WT gained popularity among researchers because of its capability to analyze power system's nonstationary root in various disturbances [35,36].…”

Section: Literature Reviewmentioning

confidence: 99%

Online power quality disturbance detection by support vector machine in smart meter

Parvez

Aghili

Sarwat

et al. 2018

J. Mod. Power Syst. Clean Energy

View full text Add to dashboard Cite

Power quality assessment is an important performance measurement in smart grids. Utility companies are interested in power quality monitoring even in the low level distribution side such as smart meters. Addressing this issue, in this study, we propose segregation of the power disturbance from regular values using one-class support vector machine (OCSVM). To precisely detect the power disturbances of a voltage wave, some practical wavelet filters are applied. Considering the unlimited types of waveform abnormalities, OCSVM is picked as a semisupervised machine learning algorithm which needs to be trained solely on a relatively large sample of normal data. This model is able to automatically detect the existence of any types of disturbances in real time, even unknown types which are not available in the training time. In the case of existence, the disturbances are further classified into different types such as sag, swell, transients and unbalanced. Being light weighted and fast, the proposed technique can be integrated into smart grid devices such as smart meter in order to perform a real-time disturbance monitoring. The continuous monitoring of power quality in smart meters will give helpful insight for quality power transmission and management.

show abstract

Comparison of discrete wavelet and Fourier transforms for ECG beat classification

Cited by 61 publications

References 2 publications

Signal Decomposition of Transmembrane Voltage-Sensitive Dye Fluorescence Using a Multiresolution Wavelet Analysis

Signal Decomposition of Transmembrane Voltage-Sensitive Dye Fluorescence Using a Multiresolution Wavelet Analysis

Heartbeat biometrics: a sensing system perspective

Online power quality disturbance detection by support vector machine in smart meter

Contact Info

Product

Resources

About