Combining Bootstrap Aggregation with Support Vector Regression for Small Blood Pressure Measurement
- 61 Downloads
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.
KeywordsBlood pressure Oscillometric method Support vector regression Bootstrap
This work was supported by the NRF Grant funded by the Korean Government 2016R1D1A1B03932925 and 2015R1D1A1A01058171.
- 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
- 7.Theodoridis, S., Machine learning. London: Academic Press, 2015.Google Scholar
- 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.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.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
- 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