Potential Pneumoconiosis Patients Monitoring and Warning System with Acoustic Signal
Monitoring for early symptoms is a critical step in preventing pneumoconiosis. The early signs of pneumoconiosis can be characterized by dyspnea, tachypnea, and cough. While traditional sensor-based methods are promising, they necessitate the wearing of devices and confine human physical movements....
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/6/1874 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Monitoring for early symptoms is a critical step in preventing pneumoconiosis. The early signs of pneumoconiosis can be characterized by dyspnea, tachypnea, and cough. While traditional sensor-based methods are promising, they necessitate the wearing of devices and confine human physical movements. On the other hand, camera-based methods have issues related to illumination, obstruction, and privacy. Recently, wireless sensing has attracted a significant amount of research attention. Among wireless signals, acoustic signals possess unique advantages for fine-grained sensing due to their low propagation speed in the air and low hardware requirement. In this paper, we propose a system called <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi>P</mi><mn>3</mn></msup><mi>W</mi><mi>a</mi><mi>r</mi><mi>n</mi><mi>i</mi><mi>n</mi><mi>g</mi></mrow></semantics></math></inline-formula> to realize low-cost warnings for potential pneumoconiosis patients in a contactless manner. For the first time, the designed system utilizes the inaudible acoustic signal to monitor early symptoms of pneumoconiosis (i.e., abnormal respiration and cough), leveraging a pair of commercial speaker and microphone. We introduce and address unique technical challenges, such as formulating a delay elimination method to synchronize transceiver signals and providing a search-based strategy to amplify signal variation for accurate and long-distance vital sign sensing. Ultimately, we apply an innovative signal decomposition technique to reconstruct the respiration waveform and extract features for cough detection. Comprehensive experiments were conducted to evaluate <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi>P</mi><mn>3</mn></msup><mi>W</mi><mi>a</mi><mi>r</mi><mi>n</mi><mi>i</mi><mi>n</mi><mi>g</mi></mrow></semantics></math></inline-formula>. Experiment results show that it can achieve a robust performance with a median error of 0.39 bpm for abnormal respiration pattern monitoring and an accuracy of 95% for cough detection in total, and support the furthest sensing range of up to 4 m. |
|---|---|
| ISSN: | 1424-8220 |