Cough Detection from Acoustic signals for patient monitoring system

TL;DR

This paper introduces a lightweight neural network utilizing MFCC features for accurate cough detection, aiding early diagnosis in respiratory diseases and suitable for deployment on IoT devices.

Contribution

It presents an optimized feature selection method with MFCC and a compact neural network achieving high accuracy for cough detection.

Findings

97.77% sensitivity in cough detection

98.75% specificity achieved

Lightweight model suitable for IoT devices

Abstract

Cough is one of the most common symptoms in all respiratory diseases. In cases like Chronic Obstructive Pulmonary Disease, Asthma, acute and chronic Bronchitis and the recent pandemic Covid-19, the early identification of cough is important to provide healthcare professionals with useful clinical information such as frequency, severity, and nature of cough to enable better diagnosis. This paper presents and demonstrates best feature selection using MFCC which can help to determine cough events, eventually helping a neural network to learn and improve accuracy of cough detection. The paper proposes to achieve performance of 97.77% Sensitivity (SE), 98.75% Specificity (SP) and 98.17% F1-score with a very light binary classification network of size close to 16K parameters, enabling fitment into smart IoT devices.