ECG Classification System based on time Domain Features with Least Square Support Vector Machine (LS-SVM


  • Computer Science Department, College of Education for pure Sciences, University of Thi-Qar , Iraq
  • Computer Science Department, College of Education for pure Sciences, University of Thi-Qar , Iraq


ECG, Authentication, Time domains features, LS-SVM


The development of authentication and identification procedures has become a critical requirement to
ensure the integrity of device data. Although passwords provide enough control and authentication, they
have been shown to have significant speed and security flaws, making biometrics the preferred
authentication technique. Consequently, most authentication systems have given much consideration to
an electrocardiogram (ECG) signal. However, ECG signals are distinct, making them difficult to imitate
yet relatively frequent. We offer a novel ECG validation model that combines multi-domain
characteristics with an LSSVM in this work. ECG signals examine two characteristics to determine each
individual's ideal mix of characteristics. First, the best 3-band filter bank is used to extract time-domain
properties from ECG data. The retrieved characteristics are examined for the most relevant ones, and the
unimportant ones are removed. The Least Square Support Vector Machine(LS-SVM) classifier collects
specified characteristics data. Our ECG authentication technology outperformed the competition,
according to the findings. The suggested model was applied to categorize EKG signals, and it achieved an
average accuracy of 92 %and 91 %when time features were used. The suggested model is evaluated
based on its ability to interact with open data.


W. Wu, S. Pirbhulal, A. K. Sangaiah, S. C. Mukhopadhyay, and G. Li, “Optimization of signal

quality over comfortability of textile electrodes for ECG monitoring in fog computing based

medical applications,” Futur. Gener. Comput. Syst., vol. 86, pp. 515–526, 2018.

M. Hammad and K. Wang, “Parallel score fusion of ECG and fingerprint for human authentication

based on convolution neural network,” Comput. Secur., vol. 81, pp. 107–122, 2019.

T. Bai et al., “A lightweight method of data encryption in BANs using electrocardiogram signal,”

Futur. Gener. Comput. Syst., vol. 92, pp. 800–811, 2019.

P. Peris-Lopez, L. González-Manzano, C. Camara, and J. M. de Fuentes, “Effect of attacker

characterization in ECG-based continuous authentication mechanisms for Internet of Things,”

Futur. Gener. Comput. Syst., vol. 81, pp. 67–77, 2018.

N. Rabinezhadsadatmahaleh and T. Khatibi, “A novel noise-robust stacked ensemble of deep and

conventional machine learning classifiers (NRSE-DCML) for human biometric identification from

electrocardiogram signals,” Informatics Med. Unlocked, vol. 21, p. 100469, 2020.

S. Hamza and Y. Ben Ayed, “Svm for human identification using the ecg signal,” Procedia

Comput. Sci., vol. 176, pp. 430–439, 2020.

S. Hong, Y. Zhou, J. Shang, C. Xiao, and J. Sun, “Opportunities and challenges of deep learning

methods for electrocardiogram data: A systematic review,” Comput. Biol. Med., vol. 122, p.

, 2020.

W. Klonowski, “Fractal analysis of electroencephalographic time series (EEG Signals),” in The

fractal geometry of the brain, Springer, 2016, pp. 413–429.

H. Namazi and S. Jafari, “Age-based variations of fractal structure of EEG signal in patients with

epilepsy,” Fractals, vol. 26, no. 04, p. 1850051, 2018.

B. Hjorth, “EEG analysis based on time domain properties,” Electroencephalogr. Clin.

Neurophysiol., vol. 29, no. 3, pp. 306–310, 1970.

M. Hammad, S. Zhang, and K. Wang, “A novel two-dimensional ECG feature extraction and

classification algorithm based on convolution neural network for human authentication,” Futur.

Gener. Comput. Syst., vol. 101, pp. 180–196, 2019.

J. S. Arteaga Falconi and A. El Saddik, “Security with ECG Biometrics,” in Advanced Methods for

Human Biometrics, Springer, 2021, pp. 65–79.

J. S. Arteaga Falconi, “Towards an Accurate ECG Biometric Authentication System with Low

Acquisition Time.” Université d’Ottawa/University of Ottawa, 2020.

J. S. Arteaga-Falconi, H. Al Osman, and A. El Saddik, “ECG and fingerprint bimodal

authentication,” Sustain. Cities Soc., vol. 40, no. August 2017, pp. 274–283, 2018, doi:


D. Jha et al., “Resunet++: An advanced architecture for medical image segmentation,” in 2019

IEEE International Symposium on Multimedia (ISM), 2019, pp. 225–2255.

S. G. Mallat, “A theory for multiresolution signal decomposition: the wavelet representation,”

IEEE Trans. Pattern Anal. Mach. Intell., vol. 11, no. 7, pp. 674–693, 1989.

D. Stoller, S. Ewert, and S. Dixon, “Wave-u-net: A multi-scale neural network for end-to-end

audio source separation,” arXiv Prepr. arXiv1806.03185, 2018.

T. Nakamura and H. Saruwatari, “Time-Domain Audio Source Separation Based on Wave-U-Net

Combined with Discrete Wavelet Transform,” ICASSP, IEEE Int. Conf. Acoust. Speech Signal

Process. - Proc., vol. 2020-May, pp. 386–390, 2020, doi: 10.1109/ICASSP40776.2020.9053934.

S. V Stehman, “Selecting and interpreting measures of thematic classification accuracy,” Remote

Sens. Environ., vol. 62, no. 1, pp. 77–89, 1997.

D. M. W. Powers, “Evaluation: from precision, recall and F-measure to ROC, informedness,

markedness and correlation,” arXiv Prepr. arXiv2010.16061, 2020.

C. Sammut and G. I. Webb, Encyclopedia of machine learning. Springer Science & Business

Media, 2011.

H. Brooks et al., “WWRP/WGNE Joint Working Group on Forecast Verification Research,”

Collab. Aust. Weather Clim. Res. World Meteorol. Organ., 2015.