Towards Enhanced Classification of Abnormal Lung sound in Multi-breath: A Light Weight Multi-label and Multi-head Attention Classification Method

TL;DR

This paper presents a lightweight multi-label and multi-head attention model that improves automatic classification of abnormal lung sounds, addressing dataset imbalance and achieving high accuracy on the ICBHI2017 dataset.

Contribution

The study introduces a novel lightweight multi-label and multi-head attention approach for lung sound classification, enhancing accuracy and robustness in clinical diagnostics.

Findings

Achieved 59.2% ICBHI score on four-category lung sound classification.

Addressed class imbalance and dataset diversity issues effectively.

Demonstrated high accuracy with a lightweight model suitable for clinical use.

Abstract

This study aims to develop an auxiliary diagnostic system for classifying abnormal lung respiratory sounds, enhancing the accuracy of automatic abnormal breath sound classification through an innovative multi-label learning approach and multi-head attention mechanism. Addressing the issue of class imbalance and lack of diversity in existing respiratory sound datasets, our study employs a lightweight and highly accurate model, using a two-dimensional label set to represent multiple respiratory sound characteristics. Our method achieved a 59.2% ICBHI score in the four-category task on the ICBHI2017 dataset, demonstrating its advantages in terms of lightweight and high accuracy. This study not only improves the accuracy of automatic diagnosis of lung respiratory sound abnormalities but also opens new possibilities for clinical applications.