Harnessing Smartwatch Microphone Sensors for Cough Detection and Classification
This addresses health monitoring for individuals with respiratory issues, but it is incremental as it applies existing methods to a new sensor type.
The study tackled cough detection and classification using smartwatch microphones, achieving 98.49% accuracy in non-walking conditions and 98.2% while walking, and identified four distinct cough types.
This study investigates the potential of using smartwatches with built-in microphone sensors for monitoring coughs and detecting various cough types. We conducted a study involving 32 participants and collected 9 hours of audio data in a controlled manner. Afterward, we processed this data using a structured approach, resulting in 223 positive cough samples. We further improved the dataset through augmentation techniques and employed a specialized 1D CNN model. This model achieved an impressive accuracy rate of 98.49% while non-walking and 98.2% while walking, showing smartwatches can detect cough. Moreover, our research successfully identified four distinct types of coughs using clustering techniques.