Lung Sound Classification Using Co-Tuning and Stochastic Normalization

Truc Nguyen, Franz Pernkopf

Research output: Contribution to journalArticlepeer-review


Computational methods for lung sound analysis are beneficial for computer-aided diagnosis support, storage and monitoring in critical care. In this paper, we use pre-trained ResNet models as backbone architectures for classification of adventitious lung sounds and respiratory diseases. The learned representation of the pre-trained model is transferred by using vanilla fine-tuning, co-tuning, stochastic normalization and the combination of the co-tuning and stochastic normalization techniques. Furthermore, data augmentation in both time domain and time-frequency domain is used to account for the class imbalance of the ICBHI and our multi-channel lung sound dataset. Additionally, we introduce spectrum correction to account for the variations of the recording device properties on the ICBHI dataset. Empirically, our proposed systems mostly outperform all state-of-the-art lung sound classification systems for the adventitious lung sounds and respiratory diseases of both datasets.
Original languageEnglish
Pages (from-to)2872-2882
Number of pages11
JournalIEEE Transactions on Biomedical Engineering
Issue number9
Publication statusPublished - 1 Sept 2022


  • Adventitious lung sound classification
  • co-tuning for transfer learning
  • crackles
  • ICBHI dataset
  • respiratory disease classification
  • stochastic normalization
  • wheezes

ASJC Scopus subject areas

  • Biomedical Engineering

Fields of Expertise

  • Information, Communication & Computing
  • Intelligent Systems

    Pernkopf, F.

    1/01/02 → …

    Project: Research area

Cite this