access icon free Collaborative framework for automatic classification of respiratory sounds

There are several diseases (e.g. asthma, pneumonia etc.) affecting the human respiratory apparatus altering its airway path substantially, thus characterising its acoustic properties. This work unfolds an automatic audio signal processing framework achieving classification between normal and abnormal respiratory sounds. Thanks to a recent challenge, a real-world dataset specifically designed to address the needs of the specific problem is available to the scientific community. Unlike previous works in the literature, the authors take advantage of information provided by several stethoscopes simultaneously, i.e. elaborating at the acoustic sensor network level. To this end, they employ two features sets extracted from different domains, i.e. spectral and wavelet. These are modelled by convolutional neural networks, hidden Markov models and Gaussian mixture models. Subsequently, a synergistic scheme is designed operating at the decision level of the best-performing classifier with respect to each stethoscope. Interestingly, such a scheme was able to boost the classification accuracy surpassing the current state of the art as it is able to identify respiratory sound patterns with a 66.7% accuracy.

Inspec keywords: feature extraction; pattern classification; convolutional neural nets; diseases; Gaussian processes; hidden Markov models; learning (artificial intelligence); pneumodynamics; audio signal processing; medical signal processing; signal classification

Other keywords: convolutional neural networks; wavelet domains; airway path; hidden Markov models; stethoscope; diseases; Gaussian mixture models; acoustic properties; classification accuracy; respiratory sound patterns; automatic classification; automatic audio signal; normal respiratory sounds; spectral domains; acoustic sensor network level; real-world dataset; human respiratory apparatus; decision level; collaborative framework; scientific community; abnormal respiratory sounds

Subjects: Markov processes; Combinatorial mathematics; Probability theory, stochastic processes, and statistics; Signal processing and detection; Biomedical engineering; Biomedical measurement and imaging; Markov processes; Neural computing techniques; Speech and audio signal processing; Knowledge engineering techniques; Biology and medical computing; Digital signal processing; Haemodynamics, pneumodynamics

References

    1. 1)
      • 15. Reynolds, D.A., Rose, R.C.: ‘Robust text-independent speaker identification using Gaussian mixture speaker models’, IEEE Trans. Speech Audio Process., 1995, 3, (1), pp. 7283. Available from: http://dx.doi.org/10.1109/89.365379.
    2. 2)
      • 4. Yap, M.H., Pons, G., Marti, J., et al: ‘Automated breast ultrasound lesions detection using convolutional neural networks’, IEEE. J. Biomed. Health. Inform., 2018, 22, (4), pp. 12181226. Available from: https://doi.org/10.1109/jbhi.2017.2731873.
    3. 3)
      • 30. Bahoura, M.: ‘Pattern recognition methods applied to respiratory sounds classification into normal and wheeze classes’, Comput. Biol. Med., 2009, 39, (9), pp. 824843. Available from: http://www.sciencedirect.com/science/article/pii/S0010482509001267.
    4. 4)
      • 2. Rizal, A., Hidayat, R., Nugroho, H.A.: ‘Signal domain in respiratory sound analysis: methods, application and future development’, J Comput Sci, 2015, 11, (10), pp. 10051016. Available from: https://doi.org/10.3844/jcssp.2015.1005.1016.
    5. 5)
      • 5. Rocha, B.M., Filos, D., Mendes, L., et al: ‘A respiratory sound database for the development of automated classification’, in Maglaveras, N., Chouvarda, I., de Carvalho, P. (Eds.): ‘Precision medicine powered by phealth and connected health’ (Springer, Singapore, 2017), pp. 3337. Available from: https://doi.org/10.1007/978-981-10-7419-6_6.
    6. 6)
      • 10. Ntalampiras, S.: ‘Automatic acoustic classification of insect species based on directed acyclic graphs’, J Acoust Soc Am, 2019, 145, (6), pp. EL541EL546. Available from: https://doi.org/10.1121/1.5111975.
    7. 7)
      • 20. Marcos, E., Londei, F., Genovesio, A.: ‘Hidden markov models predict the future choice better than a PSTH-based method’, Neural Comput., 2019, 31, (9), pp. 18741890. Available from: https://doi.org/10.1162/neco_a_01216.
    8. 8)
      • 31. Kochetov, K., Putin, E., Azizov, S., et al: ‘Wheeze detection using convolutional neural networks’, in Oliveira, E., Gama, J., Vale, Z., Lopes Cardoso, H., (eds): ‘Progress in artificial intelligence’ (Springer International Publishing, Cham, 2017), pp. 162173.
    9. 9)
      • 1. Pramono, R.X.A., Bowyer, S., Rodriguez Villegas, E.: ‘Automatic adventitious respiratory sound analysis: A systematic review’, PLOS ONE, 2017, 12, (5), p. e0177926. Available from: https://doi.org/10.1371/journal.pone.0177926.
    10. 10)
      • 9. Ntalampiras, S.: ‘Moving vehicle classification using wireless acoustic sensor networks’, IEEE Trans. Emerg. Top. Comput. Intell., 2018, 2, (2), pp. 129138.
    11. 11)
      • 26. Mun, S., Shon, S., Kim, W., et al:‘Deep neural network based learning and transferring mid-level audio features for acoustic scene classification’. 2017 IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, LA, USA, 2017, pp. 796800.
    12. 12)
      • 23. Rabiner, L.R.: ‘A tutorial on hidden markov models and selected applications in speech recognition’. Proc. IEEE, 1989, 77, (2), pp. 257286.
    13. 13)
      • 8. Serbes, G., Ulukaya, S., Kahya, Y.P.: ‘An automated lung sound preprocessing and classification system based onspectral analysis methods’, in Maglaveras, N., Chouvarda, I., de Carvalho, P., (eds): ‘Precision medicine powered by pHealth and connected health’ (Springer Singapore, Singapore, 2018), pp. 4549.
    14. 14)
      • 17. Aucouturier, D.B.P.F.J.J: ‘The bag-of-frame approach to audio pattern recognition: a sufficient model for urban soundscapes but not for polyphonic music’, J. Acoust. Soc. Am., 2007, 122, (2), pp. 881891.
    15. 15)
      • 13. Kaufman, L., Rousseeuw, P.J.: ‘Clustering by means of medoids’, in Dodge, Y. (ed.): ‘Statistical data analysis based on the L1-norm and related methods’ (Elsevier, North-Holland, 1987), pp. 405416.
    16. 16)
      • 29. Rabiner, L.R.: ‘A tutorial on hidden markov models and selected applications in speech recognition’, Proc. IEEE, 1989, 77, (2), pp. 257286.
    17. 17)
      • 14. McLachlan, G.J., Basford, K.E.: ‘Mixture models: inference and applications to clustering’ (Marcel Dekker, New York, 1988).
    18. 18)
      • 12. Ntalampiras, S., Potamitis, I., Fakotakis, N.: ‘Exploiting temporal feature integration for generalized sound recognition’, EURASIP J. Adv. Signal Process., 2009, 2009, Article number: 807162.
    19. 19)
      • 27. Piczak, K.J.: ‘Environmental sound classification with convolutional neural networks’. 2015 IEEE 25th Int. Workshop on Machine Learning for Signal Processing (MLSP), Boston, MA, USA, 2015, pp. 16.
    20. 20)
      • 16. Ntalampiras, S., Potamitis, I., Fakotakis, N.: ‘Probabilistic novelty detection for acoustic surveillance under real-world conditions’, IEEE Trans. Multimed., 2011, 13, (4), pp. 713719.
    21. 21)
      • 3. Ravì, D., Wong, C., Deligianni, F., et al: ‘Deep learning for health informatics’, IEEE. J. Biomed. Health. Inform., 2017, 21, (1), pp. 421.
    22. 22)
      • 32. Li, J., Ritter, A., Jurafsky, D.: ‘Learning multi-faceted representations of individuals from heterogeneous evidence using neural networks’. CoRR, 2015, abs/1510.05198. Available from: http://arxiv.org/abs/1510.05198.
    23. 23)
      • 11. Purwins, H., Li, B., Virtanen, T., et al: ‘Deep learning for audio signal processing’, IEEE. J. Sel. Top. Signal. Process., 2019, 13, (2), pp. 206219.
    24. 24)
      • 22. Ntalampiras, S.: ‘Generalized sound recognition in reverberant environments’, J. Audio Eng. Soc., 2019, 67, (10), pp. 772781. Available from: https://doi.org/10.17743/jaes.2019.0030.
    25. 25)
      • 21. Ntalampiras, S.: ‘Fault identification in distributed sensor networks based on universal probabilistic modeling’, IEEE Trans. Neural Netw. Learning Syst., 2015, 26, (9), pp. 19391949.
    26. 26)
      • 18. Theodoridis, S., Koutroumbas, K.: ‘Pattern recognition’ (Academic Press, Inc., Orlando, FL, USA, 2006, 3rd edn.).
    27. 27)
      • 28. Glorot, X., Bordes, A., Bengio, Y.: ‘Deep sparse rectifier neural networks’, in Gordon, G., Dunson, D., Dudík, M. (eds): Proc. of the Fourteenth Int. Conf. on Artificial Intelligence and Statistics. vol. 15 of Proc. of Machine Learning Research, PMLR, Fort Lauderdale, FL, USA, 2011, pp. 315323. Available from: http://proceedings.mlr.press/v15/glorot11a.html.
    28. 28)
      • 24. Rabiner, L.R., Juang, B.H.: ‘An introduction to hidden markov models’, IEEE ASSP Mag., 1986, 3, (1), pp. 415.
    29. 29)
      • 25. Durbin, E.S.R.K.A. R., Mitchison, G.J.: ‘Biological sequence analysis: probabilistic models of proteins and nucleic acids’ (Cambridge University Press, London, 1998).
    30. 30)
      • 7. Jakovljević, N., Lončar Turukalo, T.: ‘Hidden markov model based respiratory sound classification’, in Maglaveras, N., Chouvarda, I., de Carvalho, P. (eds): ‘Precision medicine powered by phealth and connected health’ (Springer Singapore, Singapore, 2018), pp. 3943.
    31. 31)
      • 19. Ntalampiras, S., Potamitis, I.: ‘A statistical inference framework for understanding music-related brain activity’, IEEE. J. Sel. Top. Signal. Process., 2019, 13, (2), pp. 275284.
    32. 32)
      • 6. Ntalampiras, S., Potamitis, I.: ‘Classification of sounds indicative of respiratory diseases’, in Macintyre, J., Iliadis, L., Maglogiannis, I., Jayne, C., (eds): ‘Engineering applications of neural networks’ (Springer International Publishing, Cham, 2019), pp. 93103.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-spr.2019.0487
Loading

Related content

content/journals/10.1049/iet-spr.2019.0487
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading