![](bg5.png)
Figure 2: Artefact detection algorithm implementation in
an exam out of the used database. The red line represents
the ECG classified as artefacts and the blue the ECG
classified as signal. a) Signal classification. b) Zoom
around 1530 seconds.
4 CONCLUSIONS
In this work, it is presented an algorithm for artefact
detection over long-term ambulatory
electrocardiogram (ECG) signal. The algorithm is
based on standard deviation, maximum and
minimum slope evaluation in short windows, and the
imposition of differentiation rules based on
thresholds over the previous mentioned measures.
The algorithm proved to differentiate between signal
and artefact with a high performance considering the
percentage of signal correctly classified over eight
segments. However, the algorithm should be also
validated in a wider and representative sample, with
intervals marked as artefact by multiple specialists.
In conclusion, the present algorithm seems to be
promising results and in future a great help in
cardiac systems, once the misleading interpretation
of artefact as signal could conduce the cardiac
systems to erroneous outputs.
ACKNOWLEDGEMENTS
This work was partially supported by IEETA UA
(R&D centre financed by Fundação para a Ciência e
Tecnologia – FCT, Portugal through
POCI2010/POCTI/POSI programmes, with national
and CSF funds) and by Project “Vital Responder",
funded under the "Carnegie-Mellon|Portugal"
program from FCT (Portuguese R&D funding
agency) ref. CMU-PT/CPS/0046/2008. The authors
also acknowledge the support from Biodevices S.A.
REFERENCES
Almeida, R., Martínez, J. P., Rocha, A. P., Laguna, P.,
2010. P wave delineation using spatially projected
leads from wavelet transform loops. In Proceedings of
Computers in Cardiology, 37:1003-1006.
Chin, F. J., Fang, Q., Zhang, T., Cosic, I., 2010. A fast
critical arrhythmic ECG waveform identification
method using cross-correlation and multiple template
matching. In Proceedings of the 32nd Annual
International Conference of the IEEE EMBS, 1922-25.
Cunha, J. P. S., Cunha, B., Pereira, A. S., Xavier, W.,
Ferreira, N., Meireles, L., 2010. Vital Jacket: A
wearable wireless vital signs monitor for patients'
mobility in Cardiology and Sports. In Proceedings of
4th International ICST Conference on Pervasive
Computing Technologies for Healthcare, 1-2.
Gibson, C. M., Ciaglo, L. N., Southard, M.C., Takao, S.,
Harrigan, C., Lewis, J., Filopei, J., Lew, M., Murphy,
S. A., Buros, J., 2007. Diagnostic and prognostic value
of ambulatory ECG (Holter) monitoring in patients
with coronary heart disease: a review. In Journal of
Thrombosis and Thrombolysis, 23: 135-45.
Hamilton, P. S., Tompkins, W. J., 1986. Quantitative
investigation of QRS detection rules using the
MIT/BIH arrhythmia database. In IEEE Transactions
on Biomedical Engineering, BME-33:1157-65.
Malik, M., 2003. Assessment of T-wave morphology. In
Mayo Clinic Procedings, 78:18-20.
Martinez, J. P., Almeida, R., Olmos, S., Rocha, A. P.,
Laguna, P., 2004. A wavelet-based ECG delineator:
evaluation on standard databases. In IEEE
Transactions on Biomedical Engineering, 51:570-81.
Mittal, S., Movsowitz, C., Steinberg, J.S., 2011.
Ambulatory External Electrocardiographic
Monitoring: Focus on Atrial Fibrillation, Journal of
American College of Cardiology, 58:1741-1749.
Pan, J., Tompkins W. J., 1985. A real-time QRS detection
algorithm. In IEEE Transactions on Biomedical
Engineering, BME-32:230-6.
Sornmo, L., Laguna, P., 2006. Electrocardiogram (ECG)
signal processing. In Wiley Encyclopedia of
Biomedical Engineering, John Wiley & Sons, Inc
Stern, S., Tzivoni, D. and Stern Z., 1975. Diagnostic
accuracy of ambulatory ECG monitoring in ischemic
heart disease. In Circulation, 52:1045-9.
Tsipouras, M. G., Fotiadis, D. I., Sideris, D., 2002.
Arrhythmia classification using the RR-interval
duration signal. In Proceedings of Computers in
Cardiology, 29:485-88.
Vila, J. A., Gang, Y., Presedo, J. M. R., Fernández-
Delgado, M., Barro, S., Malik, M., 2000. A new
approach for TU complex characterization. In IEEE
Transactions on Biomedical Engineering, 47:764-72.
ECG ARTEFACT DETECTION ALGORITHM - An Algorithm to Improve Long-term ECG Analysis
333