Advertisement

Private Audio-Based Cough Sensing for In-Home Pulmonary Assessment Using Mobile Devices

  • Ebrahim NematiEmail author
  • Md. Mahbubur Rahman
  • Viswam Nathan
  • Jilong Kuang
Conference paper
  • 45 Downloads
Part of the EAI/Springer Innovations in Communication and Computing book series (EAISICC)

Abstract

With the prevalence of smartphones and smartwatches during the last decade, ambulatory audio-based monitoring of lung function has become more common. A symptom that provides significant information for determining the pulmonary patients’ state is cough. This work proposes a novel algorithm to detect the cough features such as frequency, type, and intensity, in a privacy preserving manner using readily-available mobile devices for daily monitoring. The cough classification algorithm consists of three main modules. Audio events will be detected in the first layer after pre-processing of raw audio data. Then, a random forest algorithm is applied to classify the event as cough, speech, or none for each of the time frames. Lastly, a majority voting scheme is applied on the output of the second layer for each time window (which consists of multiple time frames) to determine the final label for that window. The implemented sound event detector has detection error of less than 3% in an indoor situation and cough/speech/none classification reaches 96% accuracy using random forest algorithm. The system benefits from a privacy preservation algorithm (proposed in our previous work) to make the speech unintelligible while keeping the important cough features recognizable. The privacy preservation algorithm reduces the accuracy of classification by 11% (8% for cough and speech labels) which is not significant comparing to the benefit it delivers.

Keywords

COPD Asthma Hierarchical algorithm Speech obfuscation Random forest SVM Majority voting STD MFCC LPC 

References

  1. 1.
  2. 2.
    Environmental Protection Agency. Asthma Facts. https://www.epa.gov/sites/production/files/2018-05/documents/asthma_fact_sheet_0.pdf. Accessed 29 May 2018
  3. 3.
    Nemati, E., Liaqat, D., Rahman, M.M., Kuang, J.: A novel algorithm for activity state recognition using smartwatch data. In Healthcare Innovations and Point of Care Technologies (HI-POCT), 2017 IEEE (pp. 18–21). IEEE, 2017Google Scholar
  4. 4.
    Nemati, E., Suh, Y.S., Motamed, B. and Sarrafzadeh, M.: Gait velocity estimation for a smartwatch platform using kalman filter peak recovery. In Wearable and Implantable Body Sensor Networks (BSN), 2016 IEEE 13th International Conference on (pp. 230–235). IEEE, 2016Google Scholar
  5. 5.
    Tehrany, R. M.: Speech breathing patterns in health and chronic respiratory disease. 2015Google Scholar
  6. 6.
    Miravitlles, M.: Cough and sputum production as risk factors for poor outcomes in patients with copd. Respir. Med. 105(8), 1118–1128 (2011)CrossRefGoogle Scholar
  7. 7.
    Burgel, P.-R., Nesme-Meyer, P., Chanez, P., Caillaud, D., Carre, P., Perez, T., Roche, N.: Cough and sputum production are associated with frequent exacerbations and hospitalizations in copd subjects. Chest. 135(4), 975–982 (2009)CrossRefGoogle Scholar
  8. 8.
    Dicpinigaitis, P.V.: Chronic cough due to asthma: ACCP evidence-based clinical practice guidelines. Chest. 129(1), 75S–79S (2006)CrossRefGoogle Scholar
  9. 9.
    Shi, Y., Liu, H., Wang, Y., Cai, M., Xu, W.: Theory and application of audio-based assessment of cough. Hindawi J Sensors, 2018, 9845321, 10 pages, (2018)Google Scholar
  10. 10.
    Matos, S., Birring, S.S., Pavord, I.D., Evans, D.H.: An automated system for 24-h monitoring of cough frequency: the Leicester cough monitor. IEEE Trans. on Biomed. Eng. 54, 1472–1479 (2007)CrossRefGoogle Scholar
  11. 11.
    McGuinness, K., Kelsall, A., Lowe, J., Woodcock, A., Smith, J. A.: Automated cough detection: a novel approach. J Resp Crit Care Med (2007)Google Scholar
  12. 12.
    Amoh, J., Odame, K.: Deep neural networks for identifying cough sounds. IEEE TCAS (2016)Google Scholar
  13. 13.
    Birring, S., Fleming, T., Matos, S., et al.: The Leicester cough monitor: Preliminary validation of an automated cough detection system in chronic cough. Eur. Respir. (2008)Google Scholar
  14. 14.
    Barry, S., Dane, A., Morice, A., Walmsley, A.: The automatic recognition and counting of cough. Cough J. 2, 8, (2006)Google Scholar
  15. 15.
    Swarnkar, V., Abeyratne, U.R., Amrulloh, Y., Hukins, C., Triasih, R., Setyati, A.: Neural network based algorithm for automatic identification of cough sounds. IEEE EMBC. 2013, 1764–1767 (2013)Google Scholar
  16. 16.
    Sun, X., et al.: SymDetector: detecting sound-related respiratory symptoms using smartphones. In: Proceedings of ACM International Joint Conference on PerComp and UbiComp (2015)Google Scholar
  17. 17.
    Lane, N.D., Georgiev, P., Qendro, L.: DeepEar: robust smartphone audio sensing in unconstrained acoustic environments using deep learning. In Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing (pp. 283–294). ACM (2015)Google Scholar
  18. 18.
    Korpas, J., Sadlonova, J., Vrabec, M.: Analysis of the cough sound: an overview. Pulm. Pharmacol. 261–268 (1996)Google Scholar
  19. 19.
    Zephyr HomePage. http://www.zephyranywhere.com/. Accessed 17 May 2018
  20. 20.
    Sheikh, Naveed A., and Debra, A.: Titone. “Sensorimotor and linguistic information attenuate emotional word processing benefits: An eye-movement study.” Emotion (2013)Google Scholar
  21. 21.
    Eyben, F., Weninger, F., Gross, B.: Schuller Recent developments in openSMILE the munich open-source multimedia feature extractor ACM Press pp. 835–838 (2013)Google Scholar
  22. 22.
    Liaqat, D., Nemati, E., Rahman, M., Kuang, J.: A method for preserving privacy during audio recordings by filtering speech. In Life Sciences Conference (LSC), 2017 IEEE (pp. 79–82). IEEE, 2017Google Scholar
  23. 23.
    Rahman, M., Nemati, E., Nathan, V. and Kuang, J., Instant, R.R.: Instantaneous Respiratory Rate Estimation on Context-aware Mobile Devices. In EAI BodyNets, (2018)Google Scholar
  24. 24.
    Nemati, E., Sideris, K., Kalantarian, H., Sarrafzadeh, M.: A dynamic data source selection system for smartwatch platform. In Engineering in Medicine and Biology Society (EMBC), 2016 IEEE 38th Annual International Conference of the (pp. 5993–5996). IEEE, 2016Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Ebrahim Nemati
    • 1
    Email author
  • Md. Mahbubur Rahman
    • 1
  • Viswam Nathan
    • 1
  • Jilong Kuang
    • 1
  1. 1.Digital Health LabSamsung Research AmericaMountain ViewUSA

Personalised recommendations