Non-invasive Glucose Level Estimation: A Comparison of Regression Models Using the MFCC as Feature Extractor

  • Victor Francisco-García
  • Iris P. Guzmán-Guzmán
  • Rodolfo Salgado-Rivera
  • Gustavo A. Alonso-Silverio
  • Antonio Alarcón-ParedesEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11524)


The present study comprises a performance comparison on well-known regression algorithms for estimating the blood glucose concentration from non-invasively acquired signals. These signals were obtained measuring the light energy transmittance of a laser-beam source through the fingertip by means of an embedded light dependent resistor (LDR) microcontroller system. Signals were processed by computing the Mel frequency cepstral coefficients (MFCC) to perform the feature extraction. The glucose concentration in blood was measured by a commercial glucometer in order to evaluate the performance of five well-known regression models. The experimental results revealed comparable values of mean absolute error (MAE) and Clarke grid analysis. The best performance was obtained by the support vector regression with a mean absolute error of 9.45 mg/dl. However, this study serves as a starting point and alludes to the potential application of non-invasive systems in the glucose level estimation. Future experiments measuring the glucose concentration with laboratory standard tests should be conducted, and a model implementation in an embedded device for their use is also mandatory.


Non-invasive glucose measuring Mel frequency cepstral coefficients MFCC Optical sensing 


  1. 1.
    Ramasahayam, S., Koppuravuri, S.H., Arora, L., Chowdhury, S.R.: Noninvasive blood glucose sensing using near infra-red spectroscopy and artificial neural networks based on inverse delayed function model of neuron. J. Med. Syst. 39, 166 (2015)CrossRefGoogle Scholar
  2. 2.
    Atlas, D.: International diabetes federation. Press Release, Cape Town, South Africa, 4 (2006)Google Scholar
  3. 3.
    Guariguata, L., Whiting, D., Weil, C., Unwin, N.: The international diabetes federation diabetes atlas methodology for estimating global and national prevalence of diabetes in adults. Diabetes Res. Clin. Pract. 94, 322–332 (2011)CrossRefGoogle Scholar
  4. 4.
    Haxha, S., Jhoja, J.: Optical based noninvasive glucose monitoring sensor prototype. IEEE Photonics J. 8, 1–11 (2016)CrossRefGoogle Scholar
  5. 5.
    Clark, V.L., Kruse, J.A.: Clinical methods: the history, physical, and laboratory examinations. JAMA 264, 2808–2809 (1990)CrossRefGoogle Scholar
  6. 6.
    Mall, T.D.: Comparison of current continuous glucose monitors (CGMs) (2014). Accessed 16 July 14Google Scholar
  7. 7.
    So, C.-F., Choi, K.-S., Wong, T.K.S., Chung, J.W.Y.: Recent advances in noninvasive glucose monitoring. Med. Devices (Auckland, NZ) 5, 45 (2012)Google Scholar
  8. 8.
    Shao, J., et al.: In vivo blood glucose quantification using Raman spectroscopy. PLoS One 7, e48127 (2012)CrossRefGoogle Scholar
  9. 9.
    Yatim, N.N.M., et al.: Noninvasive glucose level determination using diffuse reflectance near infrared spectroscopy and chemometrics analysis based on in vitro sample and human skin. In: 2014 IEEE Conference on Systems, Process and Control (ICSPC), pp. 30–35. IEEE (2014)Google Scholar
  10. 10.
    Bakker, A., Smith, B., Ainslie, P., Smith, K.: Near-infrared spectroscopy, applied aspects of ultrasonography in humans. Appl. Asp. Ultrason, Humans (2012)Google Scholar
  11. 11.
    Jeon, K.J., Hwang, I.D., Hahn, S.J., Yoon, G.: Comparison between transmittance and reflectance measurements in glucose determination using near infrared spectroscopy. J. Biomed. Opt. 11, 14022 (2006)CrossRefGoogle Scholar
  12. 12.
    Chen, T.-L., Lo, Y.-L., Liao, C.-C., Phan, Q.-H.: Noninvasive measurement of glucose concentration on human fingertip by optical coherence tomography. J. Biomed. Opt. 23, 47001 (2018)Google Scholar
  13. 13.
    Davis, S., Mermelstein, P.: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust. 28, 357–366 (1980)CrossRefGoogle Scholar
  14. 14.
    Gaikwad, S., Gawali, B., Yannawar, P., Mehrotra, S.: Feature extraction using fusion MFCC for continuous marathi speech recognition. In: 2011 Annual IEEE India Conference (INDICON), pp. 1–5. IEEE (2011)Google Scholar
  15. 15.
    Tawfik, N., Eldin, M., Dessouky, M., AbdEl-samie, F.: Processing of corneal images with a cepstral approach. In: The 23rd International Conference on Computer Theory and Applications (ICCTA 2013), pp. 29–31 (2013)Google Scholar
  16. 16.
    Dessouky, M.M., Elrashidy, M.A., Taha, T.E., Abdelkader, H.M.: Effective features extracting approach using MFCC for automated diagnosis of Alzheimer’s disease. Age (Omaha) 63, 33–94 (2014)Google Scholar
  17. 17.
    Kocsis, L., Herman, P., Eke, A.: The modified Beer-Lambert law revisited. Phys. Med. Biol. 51, N91 (2006)CrossRefGoogle Scholar
  18. 18.
    Segman, Y.: Device and Method for Noninvasive Glucose Assessment. J. Diabetes Sci. Technol. 12, 1159–1168 (2018)CrossRefGoogle Scholar
  19. 19.
    Alarcón-Paredes, A., Rebolledo-Nandi, Z., Guzmán-Guzmán, I.P., Yáñez-Márquez, C., Alonso, G.A.: A non-invasive glucose level estimation in a multi-sensing health care monitoring system. Technol. Heal. Care. 26, 203–208 (2018)CrossRefGoogle Scholar
  20. 20.
    Monte-Moreno, E.: Non-invasive estimate of blood glucose and blood pressure from a photoplethysmograph by means of machine learning techniques. Artif. Intell. Med. 53, 127–138 (2011)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Facultad de IngenieríaUniversidad Autónoma de GuerreroChilpancingoMéxico
  2. 2.Facultad de Ciencias Químico-BiológicasUniversidad Autónoma de GuerreroChilpancingoMéxico

Personalised recommendations