IdeaFest
 

Document Type

Poster

Loading...

Media is loading
 

Publication Date

4-2021

Keywords

respiratory, lung, health abnormalities, healthcare

Abstract

Audio-based technologies and healthcare go hand-in-hand [1]. Research has shown that it is possible to automatically monitor lung health abnormalities through respiratory sounds. In our study, filter bank energy-based features and Random Forests can classify lung problem types from respiratory sounds. More specifically, we propose a respiratory sounds representation technique capable of modeling the dominant frequency range present in such sounds. On a publicly available dataset (ICBHI) our results are encouraging to classify respiratory sounds: crackles and wheezes.

First Advisor

KC Santosh

Research Area

Computer Science

Share

COinS