Body sensor network (BSN) is simple and effective biophysical data capture in real time to monitor human activities, such as health status and physiological signals for a wide range of application area. Electrocardiogram (ECG) uses medical body sensors to record the electrical activity of the heart to help diagnose of heart disease, and also monitor how well different heart medications are working. ECG is usually by affected by various types of noises. The most common noises originated from the power line interference, electrodes loss contact, baselines wander and motion artifact. This paper introduces a new technique for improving the quality of ECG using multi scale quantitive recurrence analysis (QRA) for feature extraction and decision tree classifier. The approach achieved classification accuracy of 92.4%, when tested on a dataset from the Computing in cardiology/PhysioNet Challenge 2011.
BSN, ECG, QRA, Decision tree
- Jones V., Gay V. and Leijdekkers P. â€œBody Sensor Networks for Mobile Health Monitoringâ€ Fourth International Conference on Digital Society: Icds Proceedings, 204-209, 2010
- Otto C., Milenkovic A., Sanders C., and Jovanov E. â€œSystem architecture of a wireless body area sensor network for ubiquitous health monitoringâ€ Journal of Mobile Multimedia, vol. 1, no. 4, pp. 307â€“326, Jan. 2006
- Silva I., Moody G. B. and Celi L. â€œImproving the quality of ECGs collected using mobile phonesâ€: the PhysioNet/computing in cardiology challenge Comput. Cardiol. 38 273â€“6, 2011
- Tat T. H C, Xiang C. and Thiam L E. â€œPhysionet challenge 2011: improving the quality of electrocardiography data collected using real time QRS-complex and T-wave detectionâ€ Comput. Cardiol. 38 441â€“4 , 2012
- Chen and Yang. â€œSelf-organized neural network for the quality control of 12-lead ECG signalsâ€ Comput. Cardiol 2012
- Zaunseder S., Huhle R. and Malberg H. â€œAssessing the usability of ECG by ensemble decision treesâ€, Comput. Cardiol. 2012
- Clifford G D, Lopez D, Li Q and Rezek I â€œSignal quality indices and data fusion for determining acceptability of electrocardiograms collected in noisy ambulatory environmentsâ€ Comput. Cardiol. 38 285â€“8, 2012
- Redmond S J, Xie Y, Chang D, Basilakis J and Lovell N H., â€Electrocardiogram signal quality measures forunsupervised telehealth environments,â€ Comput. Cardiol. 2012
- Jekova I, Krasteva V, Dotsinsky I, Christov I and Abacherli R â€œRecognition of diagnostically useful ECG recordings: Alert for corrupted or interchanged leadsâ€ Comput. Cardiol. 38 429â€“32, 2012
- Johannesen L., â€œAssessment of ECG quality on an Android platform,â€ Comput. Cardiol. 38 433â€“6, 2012
- Hayn D, Jammerbund B. and Schreier G., â€œECG quality assessment for patient empowerment in mHealth Applications,â€ Comput. Cardiol. 38 353â€“6, 2012
- Kalkstein N, Kinar Y, Naâ€™aman M, Neumark N and Akiva P., â€œUsing machine learning to detect problems in ECG data collection,â€ Comput. Cardiol. 38 437â€“40, 2012
- Langley P., Marco L Y D., King S., Duncan D., Maria C D., Duan W., Bojarnejad M, Zheng D, Allen J and Murray A., â€œAn algorithm for assessment of quality of ECGs acquired via mobile telephones,â€ Comput. Cardiol 38 281â€“4, 2012
- Dower G E, Yakush A, Nazzal S B, Jutzy R V and Ruiz C E â€œDeriving the 12-lead electrocardiogram from four (EASI) electrodesâ€ J. Electrocardiol. 21 (Suppl 1) S182â€“7,1988
- Burrus, R.A. Gopinath, H. Guo, â€œIntroduction to Wavelets and Wavelet. Transformsâ€, a Primer, Prentice Hall Inc. 1997
- Rioul O. and Vetterli M., â€œWavelets and signal processing,â€ IEEE Signal Processing Magazine, vol. 8, no. 4, Oct. pp. 14-38, 1991
- Webber C.L., Jr. â€œIntroduction to recurrence quantification analysisâ€ 2004
- Webber C L. and Zbilut J P, â€œDynamical assessment of physiological systems and states using recurrence plot strategies,â€ J. Appl. Physiol. 76 965â€“73, 1994
- Marwan N., Carmen Romano M., Thiel M and Kurths J ., â€œRecurrence plots for the analysis of complex systems,â€ Phys. Rep. 438 237â€“329, 2007
- Yang H â€œMultiscale recurrence quantification analysis of spatial cardiac vectorcardiogram (VCG) signalsâ€ IEEE Trans. Biomed. Eng. 58 339â€“47,2011
- Quinlan R., â€œInduction of Decision Trees,â€ Machine Learning, Vol. 81â€”106, 1986
- Breiman, L., et al., â€œClassification and Regression Trees,â€ Chapman & Hall, Boca Raton, 1993
- Efron, B., â€œEstimating the error rate of a prediction rule: Improvement on cross-validation.â€ Journal of the American Statistical Association, Vol. 78, 316-331.1983
- Byon, E., Shrivastava, A. K., and Ding, Y., â€œA classification procedure for highly imbalanced class sizes,â€ IIE Transactions, Vol. 42, No. 4, pp. 288-303, 2010
Cite this Article:
International Journal of Sciences is Open Access Journal.
This article is licensed under a Creative Commons Attribution 4.0 International (CC BY 4.0) License.
Author(s) retain the copyrights of this article, though, publication rights are with Alkhaer Publications.