Limits...
Real time QRS detection based on M-ary likelihood ratio test on the DFT coefficients.

Górriz JM, Ramírez J, Olivares A, Padilla P, Puntonet CG, Cantón M, Laguna P - PLoS ONE (2014)

Bottom Line: This paper shows an adaptive statistical test for QRS detection of electrocardiography (ECG) signals.The motivations for proposing another detection algorithm based on maximum a posteriori (MAP) estimation are found in the high complexity of the signal model proposed in previous approaches which i) makes them computationally unfeasible or not intended for real time applications such as intensive care monitoring and (ii) in which the parameter selection conditions the overall performance.In this sense, we propose an alternative model based on the independent Gaussian properties of the Discrete Fourier Transform (DFT) coefficients, which allows to define a simplified MAP probability function.

View Article: PubMed Central - PubMed

Affiliation: Department of Signal Theory, Telematics and Communications, CITIC, University of Granada, Granada, Spain.

ABSTRACT
This paper shows an adaptive statistical test for QRS detection of electrocardiography (ECG) signals. The method is based on a M-ary generalized likelihood ratio test (LRT) defined over a multiple observation window in the Fourier domain. The motivations for proposing another detection algorithm based on maximum a posteriori (MAP) estimation are found in the high complexity of the signal model proposed in previous approaches which i) makes them computationally unfeasible or not intended for real time applications such as intensive care monitoring and (ii) in which the parameter selection conditions the overall performance. In this sense, we propose an alternative model based on the independent Gaussian properties of the Discrete Fourier Transform (DFT) coefficients, which allows to define a simplified MAP probability function. In addition, the proposed approach defines an adaptive MAP statistical test in which a global hypothesis is defined on particular hypotheses of the multiple observation window. In this sense, the observation interval is modeled as a discontinuous transmission discrete-time stochastic process avoiding the inclusion of parameters that constraint the morphology of the QRS complexes.

Show MeSH

Related in: MedlinePlus

Patient 101 of the MIT-BIH arrhythmia database [20] sampled with . In both cases a 25% overlap between observation windows is selected. The M-ary LRT test is performed with M = 5, order L = 2. Left: r = 0. Right: r = 1 Note how the false alarm in in the last T segment is removed.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4214710&req=5

pone-0110629-g005: Patient 101 of the MIT-BIH arrhythmia database [20] sampled with . In both cases a 25% overlap between observation windows is selected. The M-ary LRT test is performed with M = 5, order L = 2. Left: r = 0. Right: r = 1 Note how the false alarm in in the last T segment is removed.

Mentions: On the other hand, the selection criteria are analyzed in figure 5. The decision function of the detector is plotted for r = 0 and r = 1 radii, where the benefits of the restrictive conditions imposed in (9) for r = 1 are highlighted. Under these conditions the detector removes possible false alarms that occur in peaked T segments. Using r = 1 and an overlap of 30 samples is a suitable choice taking into account the duration of the QRS segment (∼40 samples). Therefore, this configuration will be used in the experimental part.


Real time QRS detection based on M-ary likelihood ratio test on the DFT coefficients.

Górriz JM, Ramírez J, Olivares A, Padilla P, Puntonet CG, Cantón M, Laguna P - PLoS ONE (2014)

Patient 101 of the MIT-BIH arrhythmia database [20] sampled with . In both cases a 25% overlap between observation windows is selected. The M-ary LRT test is performed with M = 5, order L = 2. Left: r = 0. Right: r = 1 Note how the false alarm in in the last T segment is removed.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4214710&req=5

pone-0110629-g005: Patient 101 of the MIT-BIH arrhythmia database [20] sampled with . In both cases a 25% overlap between observation windows is selected. The M-ary LRT test is performed with M = 5, order L = 2. Left: r = 0. Right: r = 1 Note how the false alarm in in the last T segment is removed.
Mentions: On the other hand, the selection criteria are analyzed in figure 5. The decision function of the detector is plotted for r = 0 and r = 1 radii, where the benefits of the restrictive conditions imposed in (9) for r = 1 are highlighted. Under these conditions the detector removes possible false alarms that occur in peaked T segments. Using r = 1 and an overlap of 30 samples is a suitable choice taking into account the duration of the QRS segment (∼40 samples). Therefore, this configuration will be used in the experimental part.

Bottom Line: This paper shows an adaptive statistical test for QRS detection of electrocardiography (ECG) signals.The motivations for proposing another detection algorithm based on maximum a posteriori (MAP) estimation are found in the high complexity of the signal model proposed in previous approaches which i) makes them computationally unfeasible or not intended for real time applications such as intensive care monitoring and (ii) in which the parameter selection conditions the overall performance.In this sense, we propose an alternative model based on the independent Gaussian properties of the Discrete Fourier Transform (DFT) coefficients, which allows to define a simplified MAP probability function.

View Article: PubMed Central - PubMed

Affiliation: Department of Signal Theory, Telematics and Communications, CITIC, University of Granada, Granada, Spain.

ABSTRACT
This paper shows an adaptive statistical test for QRS detection of electrocardiography (ECG) signals. The method is based on a M-ary generalized likelihood ratio test (LRT) defined over a multiple observation window in the Fourier domain. The motivations for proposing another detection algorithm based on maximum a posteriori (MAP) estimation are found in the high complexity of the signal model proposed in previous approaches which i) makes them computationally unfeasible or not intended for real time applications such as intensive care monitoring and (ii) in which the parameter selection conditions the overall performance. In this sense, we propose an alternative model based on the independent Gaussian properties of the Discrete Fourier Transform (DFT) coefficients, which allows to define a simplified MAP probability function. In addition, the proposed approach defines an adaptive MAP statistical test in which a global hypothesis is defined on particular hypotheses of the multiple observation window. In this sense, the observation interval is modeled as a discontinuous transmission discrete-time stochastic process avoiding the inclusion of parameters that constraint the morphology of the QRS complexes.

Show MeSH
Related in: MedlinePlus