Abstract
ECG classification algorithm based on machine learning is often required to obtain a classification model by analyzing and studying a large number of sample data. Whether the distribution of sample data is uniform or whether the coverage of the sample is comprehensive determines the accuracy of the classification model finally obtained. The method proposed in this paper to classify ECG waveforms using shape context features combined with labeling information, zoom matrix mechanism, sliding comparison mechanism, standard deviation distance and Hamming distance, requires only a few typical samples. Experiments have shown that this method can obtain fairly accurate classification results for typical common heart diseases. Compared with the traditional diagnosis method based on the discriminant tree, this method has less dependence on prior knowledge, it does not need to measure the width and amplitude of each wave, and it has good robustness, and will not cause jumps in the classification results due to wave group boundary measurement errors. Compared with the machine learning method, this method does not need a large number of training sets and does not need to train the model. It is also relatively easy to extend the new disease classification type.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Xiong, P., et al.: A stacsked contractive denoising auto-encoder for ECG signal denoising. Physiol. Meas. 37(12), 2214 (2016)
Muhammad, Z., Kim, J., Yoon C.: An automated ECG beat classification system using convolutional neural networks. In: International Conference on It Convergence and Security IEEE, pp. 1–5 (2016)
Kiranyaz, S., et al.: Convolutional neural networks for patient-specific ecg classification. In: Engineering in Medicine and Biology Society IEEE, p. 2608 (2015)
Ge, D.: Application of an improved fisher criteria in feature extraction of similar ECG patterns. In: Huang, D.-S., Ma, J., Jo, K.-H., Gromiha, M.M. (eds.) ICIC 2012. LNCS (LNAI), vol. 7390, pp. 358–365. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-31576-3_46
Das, M.K., Ari, S.: ECG beats classification using mixture of features. Int. Sch. Res. Not. 2014(3) (2014)
Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. Lect. Notes Comput. Sci. 2(4), 509–522 (2002)
Han, M., Zheng, D.C.: Shape recognition based on fuzzy shape context. Acta Autom. Sin. 38(1), 68–75 (2012)
Schwartz, W.R., Menotti, D.: ECG-based heartbeat classification for arrhythmia detection. Comput. Methods Prog. Biomed. 127C, 144 (2016)
Goh, K.W., et al.: Issues in implementing a knowledge-based ECG analyzer for personal mobile health monitoring. In: International Conference of the IEEE Engineering in Medicine and Biology Society. p. 6265 (2006)
Kiranyaz, S., Ince, T., Gabbouj, M.: Real-time patient-specific ECG classification by 1D convolutional neural networks. IEEE Trans. Biomed. Eng. 63(3), 664 (2016)
Romero, D., et al.: Ensemble classifier based on linear discriminant analysis for distinguishing Brugada syndrome patients according to symptomatology. In: Computing in Cardiology Conference IEEE (2017)
Shaji, S., Vinodini Ramesh, M., Menon, V.N.: Real-time processing and analysis for activity classification to enhance wearable wireless ECG. Syst. Comput. 45, 55 (2015). https://doi.org/10.1007/978-81-322-2523-2_3
Rajpurkar, P., et al.: Cardiologist-level arrhythmia detection with convolutional neural networks. arXiv:1707.01836v1 (2017)
Chen, S.-L., Tuan, M.-C., Chi, T.-K., Lin, T.-L.: VLSI architecture of lossless ECG compression design based on fuzzy decision and optimisation method for wearable devices. Electron. Lett. 51(18), 1409–1411 (2015)
Chu, C.-T., Chiang, H.-K., Hung, J.-J.: Dynamic heart rate monitors algorithm for reflection green light wearable device. IEEE (2015). 978-1-4799-8562-3/15
Muduli, P.R., Gunukula, R.R., Mukherjee, A.: A deep learning approach to fetal-ECG signal reconstruction. In: Communication IEEE, pp. 1–6 (2016)
Srivastava, V.K.: DWT-based feature extraction from ECG signal. Am. J. Eng. Res. 2, 3 (2013)
Tang, X., Shu, L.: Classification of electrocardiogram signals with RS and quantum neural networks. Int. J. Multimed. Ubiquit. Eng. 9(2), 363–372 (2014)
Acknowledgements
This work is supported by The Aoshan Innovation Project in Science and Technology of Qingdao National Laboratory for Marine Science and Technology (No. 2016ASKJ07).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, X., Wei, Z. (2018). ECG Classification Algorithm Using Shape Context. In: Hong, R., Cheng, WH., Yamasaki, T., Wang, M., Ngo, CW. (eds) Advances in Multimedia Information Processing – PCM 2018. PCM 2018. Lecture Notes in Computer Science(), vol 11166. Springer, Cham. https://doi.org/10.1007/978-3-030-00764-5_50
Download citation
DOI: https://doi.org/10.1007/978-3-030-00764-5_50
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-00763-8
Online ISBN: 978-3-030-00764-5
eBook Packages: Computer ScienceComputer Science (R0)