Discriminating between Nasal and Mouth Breathing

TL;DR

This study develops a system to distinguish nasal from mouth breathing using acoustic sensors and neural networks, achieving up to 90% accuracy, to support health monitoring and breathing pattern improvements.

Contribution

It introduces a novel acoustic-based method for classifying breathing types with high accuracy, suitable for integration into health monitoring systems.

Findings

High classification accuracy (up to 90%) using acoustic signals.

Effective discrimination achieved with sensor on neck hollow.

Visual spectrum analysis and neural networks both successful.

Abstract

The recommendation to change breathing patterns from the mouth to the nose can have a significantly positive impact upon the general well being of the individual. We classify nasal and mouth breathing by using an acoustic sensor and intelligent signal processing techniques. The overall purpose is to investigate the possibility of identifying the differences in patterns between nasal and mouth breathing in order to integrate this information into a decision support system which will form the basis of a patient monitoring and motivational feedback system to recommend the change from mouth to nasal breathing. Our findings show that the breath pattern can be discriminated in certain places of the body both by visual spectrum analysis and with a Back Propagation neural network classifier. The sound file recoded from the sensor placed on the hollow in the neck shows the most promising accuracy which is as high as 90%.