ECG beat detection using filter banks

Afonso, V.X.; Tompkins, W.J.; Nguyen, Truong Q.; Luo, Shen

doi:10.1109/10.740882

Cited by 636 publications

(278 citation statements)

References 8 publications

Supporting

Mentioning

274

Contrasting

Unclassified

Order By: Relevance

“…As a performance measure the values gained from the binomial classification (see Table 1) are used to compute the sensitivity (true positive rate, TPR) and the precision (positive prediction value, PPV), whereby TP denotes the number of true positives, FN the number of false negatives and FP the number of false positives (see Equation 1 and 2) [9,7]. Table 2 shows the results of the algorithm grouped by activity.…”

Section: Resultsmentioning

confidence: 99%

Evaluation of QRS detection algorithm implemented for mobile applications based on ECG data acquired from sensorized garments

Tantinger¹,

Feilner²,

Schmitz³

et al. 2012

Biomedical Engineering / Biomedizinische Technik

View full text Add to dashboard Cite

People can greatly benefit from mobile technologies that continuously monitor their vital signs, in medicine as well as in home environments and sports. In order to meet the requirements of mobile systems the algorithms have to be robust, reliable, take the limited resources into account and overcome the drawback of motion artefacts. This paper presents the evaluation of an algorithm for QRS detection based on ECG signals from a sensorized garment. The system saves the ECG data, measured via two textile electrodes sewed into the shirt, on a microSD card using the EDF+-format. The raw data is processed on a desktop PC using a modified state-of-the-art algorithm. QRS complexes and R-peaks of electrocardiographic signals are detected using the technique of zero crossings. Hereby, main focus has to be placed on the proper specification of the band pass filter, which is the basis for high accuracy. For the evaluation a well-defined test protocol has been specified. Six activities respectively postures were defined: Sitting, standing, walking, running, cycling and rowing. Each activity was performed by 10 test persons for a fixed time interval. Various parameters, where the temporal location of the R-peak is of importance, can be derived from the recorded ECG raw data, such as heart rate, heart rate variability or ECG classification. This method is robust and provides high accuracy even in case of noisy signals. Motion artefacts could be compensated on a high level. The performed study illustrates that even validated state-of-the-art R-peak detection algorithms have to be adapted and optimized for the mobile and daily usage. Due to its computational efficiency it is suitable for mobile applications in real-time.

show abstract

Section: Resultsmentioning

confidence: 99%

Evaluation of QRS detection algorithm implemented for mobile applications based on ECG data acquired from sensorized garments

Tantinger¹,

Feilner²,

Schmitz³

et al. 2012

Biomedical Engineering / Biomedizinische Technik

View full text Add to dashboard Cite

show abstract

“…We employ simple post-processing techniques in this work in comparison to other approaches [8]. Figure 3 shows an example of the post-processing methodology with unhealthy ECG.…”

Section: E Post-processingmentioning

confidence: 99%

“…[8]). In these publications, the researchers must perform multiple stages of post-processing each of which introduces new metrics and adaptive thresholds in order to produce reliable predictions.…”

Section: Post-processingmentioning

confidence: 99%

A Machine Learning Approach to Objective Cardiac Event Detection

Twomey¹,

Flach

2014

2014 Eighth International Conference on Complex, Intelligent and Software Intensive Systems

View full text Add to dashboard Cite

General rightsThis document is made available in accordance with publisher policies. Please cite only the published version using the reference above. Full terms of use are available: http://www.bristol.ac.uk/pure/about/ebr-terms A Machine Learning Approach to Objective Cardiac Event Detection N. Twomey, P. A. FlachAbstract-This paper presents an automated framework for the detection of the QRS complex from Electrocardiogram (ECG) signals. We introduce an artefact-tolerant pre-processing algorithm which emphasises a number of characteristics of the ECG that are representative of the QRS complex. With this processed ECG signal we train Logistic Regression and Support Vector Machine classification models. With our approach we obtain over 99.7% detection sensitivity and precision on the MIT-BIH database without using supplementary de-noising or pre-emphasis filters.

show abstract

“…Most commonly, the R complex is used for peak-to-peak alignment (Afonso et al, 1999;Al-Khalidi et al, 2001). The R complex is nearly invariant to heart rate and is readily observable, which makes ideal for registration.…”

Section: Heartbeat Alignmentmentioning

confidence: 99%

“…Within a domain, features are extracted as either raw (Israel et al, 2005), texture (Porta et al, 2001), power spectrum (Barros and Ohnishi, 2001;Stridh et al, 2004), and PCA/ ICA (Garcia et al, 1998;Barros et al, 2000). Afonso et al (1999) integrated the noise reduction and feature extraction by using filterbanks. This estimates the heartbeat trace with a polynomial spine and uses the polynomial coefficients as features themselves.…”

Section: Feature Extractionmentioning

confidence: 99%

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

ECG beat detection using filter banks

Cited by 636 publications

References 8 publications

Evaluation of QRS detection algorithm implemented for mobile applications based on ECG data acquired from sensorized garments

Evaluation of QRS detection algorithm implemented for mobile applications based on ECG data acquired from sensorized garments

A Machine Learning Approach to Objective Cardiac Event Detection

Heartbeat biometrics: a sensing system perspective

Contact Info

Product

Resources

About