Combining Bootstrap Aggregation with Support Vector Regression for Small Blood Pressure Measurement

  • Soojeong Lee
  • Awais Ahmad
  • Gwanggil Jeon
Image & Signal Processing
Part of the following topical collections:
  1. Convergence of Deep Machine Learning and Nature Inspired Computing Paradigms for Medical Informatics


Blood pressure measurement based on oscillometry is one of the most popular techniques to check a health condition of individual subjects. This paper proposes a support vector using fusion estimator with a bootstrap technique for oscillometric blood pressure (BP) estimation. However, some inherent problems exist with this approach. First, it is not simple to identify the best support vector regression (SVR) estimator, and worthy information might be omitted when selecting one SVR estimator and discarding others. Additionally, our input feature data, acquired from only five BP measurements per subject, represent a very small sample size. This constitutes a critical limitation when utilizing the SVR technique and can cause overfitting or underfitting, depending on the structure of the algorithm. To overcome these challenges, a fusion with an asymptotic approach (based on combining the bootstrap with the SVR technique) is utilized to generate the pseudo features needed to predict the BP values. This ensemble estimator using the SVR technique can learn to effectively mimic the non-linear relations between the input data acquired from the oscillometry and the nurse’s BPs.


Blood pressure Oscillometric method Support vector regression Bootstrap 



This work was supported by the NRF Grant funded by the Korean Government 2016R1D1A1B03932925 and 2015R1D1A1A01058171.


  1. 1.
    Lee, S., Chang, J.-H., Nam, S.W., Lim, C., Rajan, S., Dajani, H., and Groza, V., Oscillometric blood pressure estimation based on maximum amplitude algorithm employing Gaussin mixture regression. IEEE Trans. Instumen. Meas. 62(12):3387–3389, 2013.CrossRefGoogle Scholar
  2. 2.
    Lee, S., Bolic, M., Groza, V., Dajani, H., and Rajan, S., Confidence interval estimation for oscillometric blood pressure measurements using bootstrap approach. IEEE Trans. Instumen. Meas. 60(10):3405–3415, 2011.CrossRefGoogle Scholar
  3. 3.
    Forouzanfar, M., Dajani, H., Groza, V., Bolic, M., and Rajan, S., Feature-based neural network approach for oscillometric blood pressure estimation. IEEE Trans. Instumen. Meas. 60(8):2786–2796, 2011.CrossRefGoogle Scholar
  4. 4.
    Lee, S. et al., Improved Gaussian mixture regression based on pseudo feature generation using bootstrap in blood pressure measurement. IEEE Trans. Ind. Informat. 12(6):2269–2280 , 2016.CrossRefGoogle Scholar
  5. 5.
    Association for the advancement of medical instrumentation (AAMI), American national standard manual, electronic or automated sphygmonanometers. AASI/AAMI SP 10:2002, 2003.Google Scholar
  6. 6.
    Rakotomamonjy, A., Analysis of SVM regression bound for variable ranking. Neurocomputing 70:1489–1491, 2007.CrossRefGoogle Scholar
  7. 7.
    Theodoridis, S., Machine learning. London: Academic Press, 2015.Google Scholar
  8. 8.
    Buhlmann, P., and Yu, B., Analyzing bagging. ANN. STAT. 30(4):927–961, 2002.CrossRefGoogle Scholar
  9. 9.
    Lee, S., and Chang, J.-H., Deep belief networks ensemble for blood pressure estimation. IEEE ACCESS 5:9962–9972, 2017.CrossRefGoogle Scholar
  10. 10.
    Lee, S., and Chang, J.-H., Deep learning ensemble with asymptotic techniques based on bootstrap for oscillometric blood pressure estimation. Comput. Methods Prog. Biomed. 151:1–13, 2017.CrossRefGoogle Scholar
  11. 11.
    Sangaiah, A.K., Samuel, O.W., Li, X., Abdel-Basset, M., and Wang, H.: Towards an efficient risk assessment in software projects–Fuzzy reinforcement paradigm. Computers & Electrical Engineering. in press, 2017Google Scholar
  12. 12.
    Aborokbah, M.M., Al-Mutairi, S., Sangaiah, A.K., and Samuel, O.W.: Adaptive context aware decision computing paradigm for intensive health care delivery in smart cities—A case analysis, sustainable cities and society,in press, 2017Google Scholar
  13. 13.
    Wu, F., Li, X., Sangaiah, A.K., Xu, L., Kumari, S., Wu, L., and Shen, J.: A lightweight and robust two-factor authentication scheme for personalized healthcare systems using wireless medical sensor networks, Futur. Gener. Comput. Syst. in press, 2017Google Scholar
  14. 14.
    Ahmad, S., Bolic, M., Dajani, H., Groza, V., Batkin, I., and Rajan, S., Measurement of heart rate variability using an oscillometric blood pressure monitor. IEEE Trans. Instumen. Meas. 59(10):2575–2590, 2010.CrossRefGoogle Scholar
  15. 15.
    Efron, B., and Tibshirani, R., Bootstrap methods for standard errors, confidence interval, and other measures of statistical accuracy. Stat. Sci. 1(1):54–77, 1986.CrossRefGoogle Scholar
  16. 16.
    Lee, S., Rajan, S., Park, C.H., Chang, J.-H., Dajani, H., and Groza, V., Estimated confidence interval from single blood pressure measurement based on algorithm fusion. Comput. Biol. Med. 62:154–163, 2015.CrossRefPubMedGoogle Scholar
  17. 17.
    O’Brien, E. et al., European society of hypertension recommendations for conventional, ambulatory and home blood pressure measurement. J. of Hypertension 21(5):821–848, 2003.CrossRefGoogle Scholar
  18. 18.
    Sangaiah, A.K., Thangavelu, A.K., Gao, X.Z., Anbazhagan, N., and Durai, M.S., An ANFIS approach for evaluation of team-level service climate in GSD projects using Taguchi-genetic learning algorithm. Appl. Soft Comput. 30:628–635, 2015.CrossRefGoogle Scholar
  19. 19.
    Medhane, D. V., and Sangaiah, A. K., ESCAPE: Effective Scalable Clustering Approach For Parallel Execution of continuous position-based queries in position monitoring applications. IEEE Transactions on Sustainable Computing 2(2):49–61 , 2017.CrossRefGoogle Scholar
  20. 20.
    Qiu, T., Zhang, Y., Qiao, D., Zhang, X., Wymore, M.L., and Sangaiah, A.K.: A robust time synchronization scheme for industrial internet of things, IEEE Trans. Ind. Inf., to appearGoogle Scholar
  21. 21.
    Qiu, T., Qiao, R., Han, M., Sangaiah, A. K., and Lee, I., A Lifetime-Enhanced data collecting scheme for the internet of things. IEEE Communications Magazine 55(11):132–137 , 2017.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Electronics and Computer EngineeringHanyang UniversitySeongdong-guRepublic of Korea
  2. 2.Department of Information and Communication EngineeringYeungnam UniversityGyeongbukRepublic of Korea
  3. 3.Department of Embedded Systems Engineering, College of Information TechnologyIncheon National UniversityYeonsu-guKorea

Personalised recommendations