DeepCough: A Deep Convolutional Neural Network in A Wearable Cough Detection System

TL;DR

This paper introduces DeepCough, a wearable cough detection system using a deep convolutional neural network, achieving high sensitivity and specificity in identifying coughs from acoustic data.

Contribution

It presents a novel wearable cough detection system employing deep learning, with performance comparable or superior to existing methods.

Findings

Achieved 95.1% sensitivity in cough detection

Achieved 99.5% specificity in cough detection

Validated on 14 healthy volunteers

Abstract

In this paper, we present a system that employs a wearable acoustic sensor and a deep convolutional neural network for detecting coughs. We evaluate the performance of our system on 14 healthy volunteers and compare it to that of other cough detection systems that have been reported in the literature. Experimental results show that our system achieves a classification sensitivity of 95.1% and a specificity of 99.5%.