Cough Detection from Acoustic signals for patient monitoring system
This addresses the problem of early cough identification for healthcare professionals in respiratory diseases like COPD and COVID-19, but it is incremental as it builds on existing feature selection and neural network methods.
The paper tackled cough detection from acoustic signals for patient monitoring by selecting MFCC features to improve a neural network's accuracy, achieving 97.77% sensitivity, 98.75% specificity, and 98.17% F1-score with a lightweight model of about 16K parameters.
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.