Portable Cough Classification System Based on Sound Feature Extraction Using Tiny Machine Learning

Abstract

Cough is one of the most common markers that can provide information in diagnosing a disease. More specifically, cough is a common symptom of many respiratory infections. There are several types of cough, including: dry cough, wet cough (cough with phlegm), croup cough and whooping cough. This study aims to create a system that can classify the sounds of coughing up phlegm, dry cough, whooping cough and croup cough. The system development uses the concept of tiny machine learning. In the system built, Arduino Nano 33 BLE Sense is used as a control device and LED is used as an output device. In this study, the classification of dry cough, wet cough, croup cough and whooping cough was performed using the MFCC voice feature extraction. In the process of classifying coughing sounds using the Neural Network Classifier, the system has a percentage of dataset training accuracy from a total of 5 classes (croup, dry, noise, wet, whooping) of 97.1% by applying an epoch value of 500, window size 3000ms and a window increase of 500ms.