Respiratory Sound Classification Using Long-Short Term Memory

TL;DR

This paper explores the use of deep learning, specifically LSTM networks, for classifying respiratory sounds to improve disease detection, addressing challenges in sound recognition with a focus on medical applications.

Contribution

It investigates the application of LSTM networks for respiratory sound classification, comparing it with traditional methods like ICA and BSS, and discusses implementation challenges.

Findings

LSTM networks show promise in respiratory sound classification.

Traditional methods like ICA and BSS have limitations in this context.

Deep learning approaches can enhance disease detection accuracy.

Abstract

Developing a reliable sound detection and recognition system offers many benefits and has many useful applications in different industries. This paper examines the difficulties that exist when attempting to perform sound classification as it relates to respiratory disease classification. Some methods which have been employed such as independent component analysis and blind source separation are examined. Finally, an examination on the use of deep learning and long short-term memory networks is performed in order to identify how such a task can be implemented.