ECG Identification Based on PCA and Adaboost Algorithm

  • Qi Liu
  • Yujuan SiEmail author
  • Liangliang Li
  • Di Wang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11582)


Electrocardiogram (ECG) is a weak electrical signal that reflects the process of heart activity, and has multiple excellent features such as uniqueness, stability, versatility, non-repeatability, easy collection and so on. As a new type of biometric authentication technology, the feature extraction and classification of ECG have become a hot research topic. However, there still exists some problems such as poor timeliness and low recognition accuracy. In order to solve these problems, in this paper, we propose an identification method based on Principal Component Analysis (PCA) and Adaboost algorithm. In this method, firstly, we remove the noise from the ECG signal and segment the ECG signal into multiple single heart beats based on detected R points. Then, PCA is used to process heart beat data to reduce feature dimension. Finally, the Adaboost algorithm is used to ensemble weak classifiers to construct a stronger classifier with higher accuracy. In order to validate the effectiveness of the proposed method, we tested our algorithm on 89 healthy subjects of the ECG-ID database. Experimental results show that the proposed method can achieve accuracy rate of 98.88% within 7 s, which demonstrates that the proposed method can provide an effective and practical way for ECG identification.


ECG Identification PCA Feature extraction Adaboost 



This work was supported by the Science and Technology Development Plan Project of Jilin Province under Grant Nos. 20170414017GH and 20190302035GX; the Natural Science Foundation of Guangdong Province under Grant No. 2016A030313658; the Innovation and Strengthening School Project (provincial key platform and major scientific research project) supported by Guangdong Government under Grant No. 2015KTSCX175; the Premier-Discipline Enhancement Scheme Supported by Zhuhai Government under Grant No. 2015YXXK02-2; the Premier Key-Discipline Enhancement Scheme Supported by Guangdong Government Funds under Grant No. 2016GDYSZDXK036.


  1. 1.
    Biel, L., Pettersson, O., Philipson, L., et al.: ECG analysis: a new approach in human identification. IEEE Trans. Instrum. Meas. 50(3), 808–812 (2002)CrossRefGoogle Scholar
  2. 2.
    Babak, M.A., Sharafat, A.R., Setarehdan, S.K.: An adaptive backpropagation neural network for arrhythmia classification using R-R interval signal. Neural Netw. World 22(6), 535–548 (2012)CrossRefGoogle Scholar
  3. 3.
    Chen, X., Chen, G., Shen, H.: ECG sensor signal identification method based on SVM. Transducer Microsyst. Technol. 33(10), 40–42 (2014)Google Scholar
  4. 4.
    Palaniappan, R., Krishnan, S.M.: Identifying individuals using ECG beats. In: International Conference on Signal Processing & Communications. IEEE (2005)Google Scholar
  5. 5.
    Zhao, Z., Yang, L., Chen, D.: Research of ECG identification based on FFT-matching pursuit algorithm. Chin. J. Sens. Actuators 26(3), 307–314 (2013)Google Scholar
  6. 6.
    Chen, D., Zhao, Z.: Identification method of ECG signal based on SVD and dissimilarity analysis. Comput. Simul. 33(2), 427–432 (2016)Google Scholar
  7. 7.
    Jammoussi, A.Y., Ghribi, S.F., Masmoudi, D.S.: Adaboost face detector based on joint integral histogram and genetic algorithms for feature extraction process. SpringerPlus 3(1), 355 (2014)CrossRefGoogle Scholar
  8. 8.
    Song, M.K., Sarker, M.M.K.: Modeling and implementing two-stage AdaBoost for real-time vehicle license plate detection. J. Appl. Math. 2014, 1–8 (2014)Google Scholar
  9. 9.
    Ahmed, W., Khalid, S.: ECG signal processing for recognition of cardiovascular diseases: a survey. In: Sixth International Conference on Innovative Computing Technology. IEEE (2017)Google Scholar
  10. 10.
    Bin, H., Bai, Y., Zhang, Y.: Wavelet soft threshold ECG denoising based on different empirical mode decomposition. Math. Pract. Theory 46(6), 136–144 (2016)MathSciNetGoogle Scholar
  11. 11.
    Yang, Z.: Real-time detection of ECG waveform based on differential algorithm. J. Mudanjiang Normal Univ. (Nat. Sci. Ed.) (4), 23–25 (2015)Google Scholar
  12. 12.
    Martinez, A.M., Kak, A.C.: PCA versus LDA. IEEE Trans. Pattern Anal. Mach. Intell. 23(2), 228–233 (2002)CrossRefGoogle Scholar
  13. 13.
    Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55(1), 119–139 (1997)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Zhu, J., Zou, H., Rosset, S., et al.: Multi-class AdaBoost. Stat. Interface 2(3), 349–360 (2009)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Lugovaya, T.S.: Biometric human identification based on electrocardiogram. [Master’s thesis] Faculty of Computing Technologies and Informatics, Electrotechnical University “LETI”, Saint-Petersburg, Russian Federation (2005)Google Scholar
  16. 16.
    Yu, J., Si, Y., Liu, X., Wen, D., Luo, T., Lang, L.: ECG identification based on PCA-RPROP. In: Duffy, V.G. (ed.) DHM 2017. LNCS, vol. 10287, pp. 419–432. Springer, Cham (2017). Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.College of Communication EngineeringJilin UniversityChangchunChina
  2. 2.Zhuhai College of Jilin UniversityZhuhaiChina

Personalised recommendations