PerDMCS: Weighted Fusion of PPG Signal Features for Robust and Efficient Diabetes Mellitus Classification

V. Ramu Reddy, Anirban Dutta Choudhury, Srinivasan Jayaraman, Naveen Kumar Thokala, Parijat Deshpande, Venkatesh Kaliaperumal

Abstract

Non-invasive detection of Diabetes Mellitus (DM) has attracted a lot of interest in the recent years in pervasive health care. In this paper, we explore features related to heart rate variability (HRV) and signal pattern of the waveform from photoplethysmogram (PPG) signal for classifying DM (Type 2). HRV features includes timedomain (F1), frequency domain (F2), non-linear features (F3) where as waveform features (F4) are one set of features such as height, width, slope and durations of pulse. The study was carried out on 50 healthy subjects and 50 DM patients. Support Vector Machines (SVM) are used to capture the discriminative information between the above mentioned healthy and DM categories, from the proposed features. The SVM models are developed separately using different sets of features F1, F2, F3,and F4, respectively. The classification performance of the developed SVM models using time-domain, frequency domain, non-linear and waveform features is observed to be 73%, 78%, 80% and 77%. The performance of the system using combination of all features is 82%. In this work, the performance of the DM classification system by combining the above mentioned feature sets with different percentage of discriminate features from each set is also examined. Furthermore weight based fusion is performed using confidence values obtained from each model to find the optimal set of features from each set with optimal weights for each set. The best performance accuracy of 89% is obtained by scores fusion where combinations of mixture of 90% features from the feature sets F1 and F2 and mixture of 100% features from the feature sets F3 and F4, with fusion optimal weights of 0.3 and 0.7, respectively.

References

  1. Allen, J. (2007). Photoplethysmography and its application in clinical physiological measurement. Physiological Measurement, 28(3):R1.
  2. Association, A. D. et al. (2015). 2. classification and diagnosis of diabetes. Diabetes care, 38(Supplement 1):S8-S16.
  3. Banerjee, R., Vempada, R., Mandana, K., Choudhury, A. D., and Pal, A. (2016). Identifying coronary artery disease from photoplethysmogram. In Int. Joint Conf. on Pervasive and Ubiquitous Computing: Adjunct, pages 1084-1088. ACM.
  4. Billman, G. E. (2007). The lf/hf ratio does not accurately measure cardiac sympatho-vagal balance. Heart Rate Variability: Clinical Applications and Interaction between HRV and Heart Rate, page 54.
  5. Collaboration, N. R. F. et al. (2016). Worldwide trends in diabetes since 1980: a pooled analysis of 751 population-based studies with 4· 4 million participants. The Lancet, 387(10027):1513-1530.
  6. Elgendi, M. (2012). On the analysis of fingertip photoplethysmogram signals. Current cardiology reviews, 8(1):14-25.
  7. Hall, M. A. (2000). Correlation-based feature selection of discrete and numeric class machine learning.
  8. Koolagudi, S. G., Reddy, V. R., and Rao, K. S. (2010). Emotion recognition from speech signal using epoch parameters. In Proc. of SPCOM, pages 1-5, India.
  9. Ning, X., Selesnick, I. W., and Duval, L. (2014). Chromatogram baseline estimation and denoising using sparsity (beads). Chemometrics and Intelligent Laboratory Systems, 139:156-167.
  10. Reddy, V. R., Chakravarty, K., and Aniruddha, S. (2014). Person identification in natural static postures using kinect. In ECCV, pages 793-808. Springer.
  11. Reddy, V. R. and Chattopadhyay, T. (2014). Human activity recognition from kinect captured data using stick model. In HCI. Adv. Interaction Modalities and Techniques, pages 305-315. Springer.
  12. Reddy, V. R., Sinha, A., and Seshadri, G. (2013). Fusion of spectral and time domain features for crowd noise classification system. In Intelligent Systems Design and Applications, pages 1-6. IEEE.
  13. Schroeder, E. B., Chambless, L. E., Liao, D., Prineas, R. J., Evans, G. W., Rosamond, W. D., and Heiss, G. (2005). Diabetes, glucose, insulin, and heart rate variability the atherosclerosis risk in communities (aric) study. Diabetes care, 28(3):668-674.
  14. Seyd, A., Joseph, P. K., and Jacob, J. (2012). Automated diagnosis of diabetes using heart rate variability signals. Journal of medical systems, 36(3):1935-1941.
  15. Tabish, S. A. (2007). Is diabetes becoming the biggest epidemic of the twenty-first century? International Journal of health sciences, 1(2):V.
  16. Welch, P. D. (1967). The use of fast fourier transform for the estimation of power spectra: A method based on time averaging over short, modified periodograms. IEEE Transactions on audio and electroacoustics, 15(2):70-73.
Download


Paper Citation


in Harvard Style

Reddy V., Dutta Choudhury A., Jayaraman S., Kumar Thokala N., Deshpande P. and Kaliaperumal V. (2017). PerDMCS: Weighted Fusion of PPG Signal Features for Robust and Efficient Diabetes Mellitus Classification . In Proceedings of the 10th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 5: SmartMedDev, (BIOSTEC 2017) ISBN 978-989-758-213-4, pages 553-560. DOI: 10.5220/0006297205530560


in Bibtex Style

@conference{smartmeddev17,
author={V. Ramu Reddy and Anirban Dutta Choudhury and Srinivasan Jayaraman and Naveen Kumar Thokala and Parijat Deshpande and Venkatesh Kaliaperumal},
title={PerDMCS: Weighted Fusion of PPG Signal Features for Robust and Efficient Diabetes Mellitus Classification},
booktitle={Proceedings of the 10th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 5: SmartMedDev, (BIOSTEC 2017)},
year={2017},
pages={553-560},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006297205530560},
isbn={978-989-758-213-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 5: SmartMedDev, (BIOSTEC 2017)
TI - PerDMCS: Weighted Fusion of PPG Signal Features for Robust and Efficient Diabetes Mellitus Classification
SN - 978-989-758-213-4
AU - Reddy V.
AU - Dutta Choudhury A.
AU - Jayaraman S.
AU - Kumar Thokala N.
AU - Deshpande P.
AU - Kaliaperumal V.
PY - 2017
SP - 553
EP - 560
DO - 10.5220/0006297205530560