An improved QRS complex detection method having low computational load

Yakut, Önder; Bolat, Emine Doğru

doi:10.1016/j.bspc.2018.02.004

Cited by 42 publications

(17 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The efficiency of the given R-peaks finding technique is compared with other exiting methodologies and summarized in Table 2. It shows the significant improvement compared with the techniques which use the non-linear filtering in their preprocessing stage [15][16][17][18]. and comparable results with the Fractional Fourier transform [14], S-transform [19], and wavelet transforms [20].…”

Section: Resultsmentioning

confidence: 71%

See 1 more Smart Citation

An Improved R-Peaks Marking Method Using Fourier Decomposition and Teager Energy Operator

Harikrishna¹,

Shaik²

2020

View full text Add to dashboard Cite

The exact discovery of R-peak becomes very much crucial while extracting prominent features from Electrocardiogram (ECG) signal. However, identification of R-peaks precisely becomes more challenging due to contamination of noise and fragmented QRS complexes. This paper presents an improved method of marking R-peaks. Initially, an efficient Fourier Decomposition Methodology (FDM) is used for removing noise. The accuracy of finding R-peaks can be improved by enhancing the QRS complexes using Teager Energy Operator. Hilbert Transform and Zero Cross Detector (ZCD) are used for marking the R-peaks. The MIT-BIH arrhythmia database is used for validating the proposed scheme and attained 99.97% accuracy, 99.98% of sensitivity and 99.98% of positive predictivity. The findings proved that proposed method is superior as compared to the proven techniques in the literature.

show abstract

Section: Resultsmentioning

confidence: 71%

“…These are optimum compared with standard FIR filters. Nonlinear energy operator and simple thresholding technique has also been used for efficient marking of R-Peaks [15][16][17]. Fractional Stock well transform is a combination of fractional fourier transform and Stockwell transform has been used by Bajaj and Kumar [18].…”

Section: Literature Reviewmentioning

confidence: 99%

An Improved R-Peaks Marking Method Using Fourier Decomposition and Teager Energy Operator

Harikrishna¹,

Shaik²

2020

View full text Add to dashboard Cite

show abstract

“…Linear filter, nonlinear processing, and decision are the three main stages used for most QRS detection algorithm [11]. These methods are based on filters design [4,7,12,13], Short Time Fourier Transform [3], Hilbert Transform [14], Wavelet [15,16], neural network (NN) [17,18], energy detection [19,20], entropy [18], Bayesian framework [8], and decision rules [21].…”

Section: Introductionmentioning

confidence: 99%

“…A moderate accuracy for this technique, less computation, and the same [7] computational detection model. Excluding the derivative filter and based on new decision techniques Yakut and Bolat are proposed a new method [21]. The first stage is contained two filters, square, and normalization.…”

Section: Introductionmentioning

confidence: 99%

A QRS-Detection Algorithm for Real-Time Applications

Khalaf¹,

Mohammed²

2021

IJIES

View full text Add to dashboard Cite

The QRS detection algorithm is substantial for healthcare monitoring and diagnostic applications. A low error detection without adding more computation is a big challenge for researchers. The proposed QRS detection algorithm is a simple, real-time, and high-performance hybrid technique based on decision tree and artificial neural networks (ANN). In this study, the five stages algorithm is designed, implemented, and evaluated for wearable healthcare applications. The first stage is filtering the original ECG signal to reduce the noise and baseline wandering. After that, a maximum or minimum moving-window for positive or negative peaks respectively is searching R-peaks for any expected value and finding the Q and S corresponding to this R-peak. Only these values from all ECG samples are passed to the next stage for feature extraction to reduce the algorithm computation. Stage four is excluded any unlikely points using the mean of the slope and level based on a simple decision tree. Finally, artificial neural networks are designed to classify the rest point for QRS detection using ANNs for each peak polarity to improve the network’s performance by separating the data as a positive or negative peak. The algorithm is evaluated based on MATLAB using the MIT-BIH Arrhythmia Database, and the results show a low error rate detection of 0.25%, high sensitivity of 99.86%, and high predictivity of 99.89%. We develop a new approach for real-time QRS detection with low resources and high efficiency compared with other approaches.

show abstract

“…Several QRS complex detection techniques have been reported in the recent literature. These include quadratic filter, level crossing sampling‐based analog to digital conversion logic, integrate and fire sampling, least mean square algorithm‐based adaptive linear predictor, empirical mode decomposition (EMD), multiscale mathematical morphology (MM), sigmoidal radial basis function artificial neural network (ANN), max‐min difference (MMD) algorithm, filter banks (FBs), quadratic spline wavelet transform (WT), daubechies (db10) WT, Harr WT, wavelet filter bank, digital filtering with dynamic threshold, combination of WT, derivative, and Hilbert transform (HT), adaptive MM, phase space reconstruction and box‐scoring calculation, ECG structural analysis (SA), relative energy (RE), parallel delta modulator (PDM), modified S‐transform (ST), and deterministic finite automata (DFA) …”

Section: Introductionmentioning

confidence: 99%

Optimal SSA‐based wideband digital differentiator design for cardiac QRS complex detection application

Nayak

Saha

Kar

et al. 2018

Int J Numerical Modelling

View full text Add to dashboard Cite

In this paper, a computationally efficient, highly accurate, wideband, stable, and minimum phase infinite impulse response type first-order digital differentiator (DD) is designed by employing a swarm intelligence-based search method called Salp Swarm Algorithm (SSA) for the QRS complex detection application. The optimal coefficients of the DD are computed by minimizing a suitable fitness function to meet the ideal differentiator magnitude response characteristics.The simulation results and the root mean square magnitude error metric justify the superiority of the proposed SSA-based DD design as compared with all other differentiators employed in the QRS complex detection application, and the reported first-order DDs based on the numerical methods and the other evolutionary algorithms. The electrocardiogram signal is preprocessed by the proposed DD to generate the feature signal corresponding to each QRS complex.The generated feature signal is used as a marker to identify the exact occurrence of the QRS complex by using an adaptive threshold-based detection logic. The proposed DD-based QRS detection approach achieves a sensitivity (Se), positive prediction (PP), detection error rate (DER), and accuracy (Acc) of 99.94%, 99.93%, 0.1279%, and 99.87%, respectively, when validated against MIT/BIH arrhythmia database. Also, against the QT database, the proposed QRS detector produces a Se of 99.93%, PP of 99.97%, DER of 0.09%, and Acc of 99.90%. The performance of the proposed QRS detection technique is compared with the methods already reported in the recent literature, and the superiority of the proposed approach is established with respect to different standard performance metrics. The noise tolerance capability of the proposed QRS detector is demonstrated against MIT/BIH noise stress test database. KEYWORDS digital differentiator (DD), electrocardiogram (ECG), QRS complex detection, Salp swarm algorithm (SSA) /journal/jnm 1 of 25sinus rhythm. Any deviation from the standard sinus rhythm, called arrhythmia, can be detected by close observation of the shape and the interval duration of the waves. Hence, from a diagnosis point of view, the calculation of the wave interval is essential and can be determined by accurately identifying the time of occurrence of the R-wave/R-peak (peak of the QRS wave). From the appearance of the R-wave, the R-R interval duration can be estimated. Also, by knowing the occurrence of the R-waves, several post-processing applications like heartbeat classification, foetal heart rate monitoring, ECG coder, and heart rate variability analysis can be implemented. The time of occurrences of the R-waves is considered as markers to identify the time of the presence of the P/T-waves, QRS interval, PR interval, QT interval, ST segment, and PQ segment. 1 This information plays a pivotal role to diagnose various cardiac diseases. With the accurate estimation of the QT interval and the heart rate, a potentially dangerous disease called hypoglycaemia (low blood glucose level) can be monitored noninvasively...

show abstract

An improved QRS complex detection method having low computational load

Cited by 42 publications

References 31 publications

An Improved R-Peaks Marking Method Using Fourier Decomposition and Teager Energy Operator

An Improved R-Peaks Marking Method Using Fourier Decomposition and Teager Energy Operator

A QRS-Detection Algorithm for Real-Time Applications

Optimal SSA‐based wideband digital differentiator design for cardiac QRS complex detection application

Contact Info

Product

Resources

About