Collaborative framework for automatic classification of respiratory sounds

• Published in: IET signal processing 2020-06, Vol.14 (4), p.223-228
• Main Author: Ntalampiras, Stavros
• Format: Article
• Language: English
• Subjects: abnormal respiratory sounds; acoustic properties; acoustic sensor network level; airway path; audio signal processing; automatic audio signal; automatic classification; classification accuracy; collaborative framework; convolutional neural nets; convolutional neural networks; decision level; diseases; feature extraction; Gaussian mixture models; Gaussian processes; hidden Markov models; human respiratory apparatus; learning (artificial intelligence); medical signal processing; normal respiratory sounds; pattern classification; pneumodynamics; real‐world dataset; Research Article; respiratory sound patterns; scientific community; signal classification; spectral domains; stethoscope; wavelet domains
• ISSN: 1751-9675; 1751-9683; 1751-9683
• DOI: 10.1049/iet-spr.2019.0487

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.