A Deep Ensemble Neural Network with Attention Mechanisms for Lung Abnormality Classification Using Audio Inputs

Wall, Conor, Zhang, Li, Yu, Yonghong, Kumar, Akshi and Gao, Rong (2022) A Deep Ensemble Neural Network with Attention Mechanisms for Lung Abnormality Classification Using Audio Inputs. Sensors, 22 (15). p. 5566. ISSN 1424-8220

sensors-22-05566.pdf - Published Version
Available under License Creative Commons Attribution 4.0.

Download (693kB) | Preview
Official URL: https://doi.org/10.3390/s22155566


Medical audio classification for lung abnormality diagnosis is a challenging problem owing to comparatively unstructured audio signals present in the respiratory sound clips. To tackle such challenges, we propose an ensemble model by incorporating diverse deep neural networks with attention mechanisms for undertaking lung abnormality and COVID-19 diagnosis using respiratory, speech, and coughing audio inputs. Specifically, four base deep networks are proposed, which include attention-based Convolutional Recurrent Neural Network (A-CRNN), attention-based bidirectional Long Short-Term Memory (A-BiLSTM), attention-based bidirectional Gated Recurrent Unit (A-BiGRU), as well as Convolutional Neural Network (CNN). A Particle Swarm Optimization (PSO) algorithm is used to optimize the training parameters of each network. An ensemble mechanism is used to integrate the outputs of these base networks by averaging the probability predictions of each class. Evaluated using respiratory ICBHI, Coswara breathing, speech, and cough datasets, as well as a combination of ICBHI and Coswara breathing databases, our ensemble model and base networks achieve ICBHI scores ranging from 0.920 to 0.9766. Most importantly, the empirical results indicate that a positive COVID-19 diagnosis can be distinguished to a high degree from other more common respiratory diseases using audio recordings, based on the combined ICBHI and Coswara breathing datasets.

Item Type: Article
Additional Information: Funding information: This research is funded by UKRI Research England (Purposeful Health Growth Accelerator, Grant No. 101053).
Uncontrolled Keywords: Long Short-Term Memory; Gated Recurrent Unit; bidirectional Recurrent Neural Network; Convolutional Neural Network; attention mechanism; ensemble model; audio lung abnormality classification
Subjects: G400 Computer Science
G500 Information Systems
G600 Software Engineering
Depositing User: Elena Carlaw
Date Deposited: 29 Jul 2022 13:38
Last Modified: 29 Jul 2022 13:48
URI: http://nrl.northumbria.ac.uk/id/eprint/49656

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics