Vol. 6 (06) pp. 976-982 DOI: 10.21474/IJAR01/7300

APPLICATION OF INSTANCE-BASED LEARNERS FOR ARRHYTHMIA DETECTION IN ECG SIGNALS.

  • Department Of Electronic Systems, Vilnius Gediminas Technical University.
10 Downloads 61 Views
Crossref

Download Full Paper (PDF)

Abstract

Cardiac arrhythmia detection in heart activity related signals, like ECG, has been a center of attention for many researchers in medical field, and is as relevant, if not more, to this day. Aim of this paper is to investigate the accuracy of commonly used classifiers in classifying ECG signal segments of one heart beat into three classes ? normal, unrecognizable and arrhythmia ? and provide insight, which type of, or even specific classifier has a tendency to perform the best under given scenario. Results of the experiments showed that best performing classifiers are instance-based learning algorithms, top two performers being K* algorithm, based on entropic distance measure, with 99% correlation and 3,5% relative absolute error, while testing all input data as test data, 90% and 20% respectively, when testing with 75% of input data as training set, and the rest as testing set, along with IBk ? nearest neighbor based algorithm, which was only applicable with percentage split training method (75% / 25%), resulting in 84% correlation and 19% relative absolute error.

Article Analytics

References

  1. Pan, J. and Tompkins, W.J., 1985. A real-time QRS detection algorithm. IEEE transactions on biomedical engineering, (3), pp.230-236.
  2. Ortigosa, N., Cano, ?., Galbis, A. and Fern?ndez, C., 2015, September. Classification of atrial fibrillation episodes by means of phase variations of time-frequency transforms. In Computing in Cardiology Conference (CinC), 2015 (pp. 41-44). IEEE.
  3. Felix, J., Alcaraz, R. and Rieta, J.J., 2015, September. Adaptive wavelets applied to automatic local activationwave detection in fractionated atrial electrograms of atrial fibrillation. In Computing in Cardiology Conference (CinC), 2015 (pp. 45-48). IEEE.
  4. Chandra, B.S., Sastry, C.S. and Jana, S., 2016, September. Subject-specific detection of ventricular tachycardia using convolutional neural networks. In Computing in Cardiology Conference (CinC), 2016 (pp. 53-56). IEEE.
  5. Eerik?inen, L.M., Vanschoren, J., Rooijakkers, M.J., Vullings, R. and Aarts, R.M., 2015, September. Decreasing the false alarm rate of arrhythmias in intensive care using a machine learning approach. In Computing in Cardiology Conference (CinC), 2015 (pp. 293-296). IEEE.
  6. Daluwatte, C., Johannesen, L., Vicente, J., Scully, C.G., Galeotti, L. and Strauss, D.G., 2015, September. Heartbeat fusion algorithm to reduce false alarms for arrhythmias. In Computing in Cardiology Conference (CinC), 2015 (pp. 745-748). IEEE.
  7. Aha, D.W., Kibler, D. and Albert, M.K., 1991. Instance-based learning algorithms. Machine learning, 6(1), pp.37-66.
  8. Cleary, J.G. and Trigg, L.E., 1995. K*: An instance-based learner using an entropic distance measure. In Machine Learning Proceedings 1995 (pp. 108-114).
  9. Frank, E., Hall, M. and Pfahringer, B., 2002, August. Locally weighted naive bayes. In Proceedings of the Nineteenth conference on Uncertainty in Artificial Intelligence (pp. 249-256). Morgan Kaufmann Publishers Inc.

How to Cite This Article

Andrius gudiskis. (2018); APPLICATION OF INSTANCE-BASED LEARNERS FOR ARRHYTHMIA DETECTION IN ECG SIGNALS., Int. J. of Adv. Res., 6 (06), 976-982, ISSN 2320-5407. DOI: https://doi.org/10.21474/IJAR01/7300

Corresponding Author

Andrius Gudiškis
Department of Electronic Systems, Vilnius Gediminas Technical University
Creative Commons Attribution 4.0 This work is licensed under a Creative Commons Attribution 4.0 International License.