Advertisement

Performance Comparison of SVM and ANN for Reversible ECG Data Hiding

  • Siddharth Bhalerao
  • Irshad Ahmad AnsariEmail author
  • Anil Kumar
Conference paper
  • 6 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1154)

Abstract

In the telemedicine industry, data security is a prime aspect because medical data is frequently transferred and stored over networks. In such scenario watermarking emerges as an important technique that ensures data security and integrity. In this work, use of SVM and ANN is investigated for a high capacity ECG data hiding technique. Watermarking is done using prediction error expansion (PEE). SVM and ANN are used to predict the ECG values. Two separate regression SVM models with linear kernel and Gaussian kernel are trained. ANN model used is a feed-forward deep neural network with three hidden layers. The proposed method provides a completely reversible watermarking. The patient’s confidential data is used as a watermark. For testing and training of algorithms, signals from MIT-BIH arrhythmia database are used. Performance of both SVM and ANN-based prediction models are evaluated using normalized cross-correlation, signal-to-noise ratio, and percentage residual difference. Linear SVM and deep ANN are comparable in performance and are better than Gaussian SVM.

Keywords

Reversible medical data hiding Deep neural network Regression SVM 

References

  1. 1.
    Shimizu, K.: Telemedicine by mobile communication. IEEE Eng. Med. Biol. Mag. 18(4), 32–44 (1999)CrossRefGoogle Scholar
  2. 2.
    Caldelli, R., Filippini, F., Becarelli, R.: Reversible watermarking techniques: an overview and a classification. EURASIP J. Inf. Secur. (2010)Google Scholar
  3. 3.
    Engin, M., Çıdam, O., Engin, E.Z.: Wavelet transformation based watermarking technique for human electrocardiogram (ECG). J. Med. Syst. 29(6), 589–594 (2005)CrossRefGoogle Scholar
  4. 4.
    Ibaida, A., Khalil, I.: Wavelet-based ECG steganography for protecting patient confidential information in point-of-care systems. IEEE Trans. Biomed. Eng. 60(12), 3322–3330 (2013)CrossRefGoogle Scholar
  5. 5.
    Ibaida, A., Khalil, I., Van Schyndel, R.: A low complexity high capacity ECG signal watermark for wearable sensor-net health monitoring system. In: Computing in Cardiology, pp. 393–396. IEEE (2011)Google Scholar
  6. 6.
    Chen, S.T., Guo, Y.J., Huang, H.N., Kung, W.M., Tseng, K.K., Tu, S.Y.: Hiding patients confidential data in the ECG signal viaa transform-domain quantization scheme. J. Med. Syst. 38(6), 54 (2014)CrossRefGoogle Scholar
  7. 7.
    Dey, N., Dey, M., Mahata, S.K., Das, A., Chaudhuri, S.S.: Tamper detection of electrocardiographic signal using watermarked bio-hash code in wireless cardiology. Int. J. Signal Imaging Syst. Eng. 8(1–2), 46–58 (2015)CrossRefGoogle Scholar
  8. 8.
    Tian, J.: Reversible data embedding using a difference expansion. IEEE Trans. Circuits Syst. Video Technol. 13(8), 890–896 (2003)CrossRefGoogle Scholar
  9. 9.
    Thodi, D.M., Rodríguez, J.J.: Expansion embedding techniques for reversible watermarking. IEEE Trans. Image Process. 16(3), 721–730 (2007)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Zheng, K.M., Qian, X.: Reversible data hiding for electrocardiogram signal based on wavelet transforms. In: International Conference on Computational Intelligence and Security, CIS’08, vol. 1, pp. 295–299. IEEE (2008)Google Scholar
  11. 11.
    Wu, W., Liu, B., Zhang, W., Chen, C.: Reversible data hiding in ECG signals based on histogram shifting and thresholding. In: 2nd International Symposium on Future Information and Communication Technologies for Ubiquitous HealthCare (Ubi-HealthTech), pp. 1–5. IEEE (2015)Google Scholar
  12. 12.
    Wang, H., Zhang, W., Yu, N.: Protecting patient confidential information based on ECG reversible data hiding. Multimedia Tools Appl. 75(21), 13733–13747 (2016)CrossRefGoogle Scholar
  13. 13.
    Shiu, H.J., Lin, B.S., Huang, C.H., Chiang, P.Y., Lei, C.L.: Preserving privacy of online digital physiological signals using blind and reversible steganography. Comput. Methods Programs Biomed. 151, 159–170 (2017)CrossRefGoogle Scholar
  14. 14.
    Yang, C.Y., Cheng, L.T., Wang, W.F.: Effective reversible data hiding in electrocardiogram based on fast discrete cosine transform. In: Proceedings of the Future Technologies Conference, pp. 640–648. Springer, Berlin (2018)Google Scholar
  15. 15.
    Bhalerao, S., Ansari, I.A., Kumar, A., Jain, D.K.: A reversible and multipurpose ECG data hiding technique for telemedicine applications. Pattern Recogn. Lett. 125 (2019)Google Scholar
  16. 16.
    Vapnik, V.: Statistical Learning Theory. Wiley, New York (1998)zbMATHGoogle Scholar
  17. 17.
    Smola, A.J., Schoelkopf, B.: A Tutorial on Support Vector Regression, vol. 14 (2004)Google Scholar
  18. 18.
    Moody, G.B., Mark, R.G.: The impact of the MIT-BIH arrhythmia data-base. IEEE Eng. Med. Biol. Mag. 20(3), 45–50 (2001)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Siddharth Bhalerao
    • 1
  • Irshad Ahmad Ansari
    • 1
    Email author
  • Anil Kumar
    • 1
  1. 1.Electronics and Communication EngineeringPDPM Indian Institute of Information Technology Design and ManufacturingJabalpurIndia

Personalised recommendations