Continuous Analytics for Monitoring Pulmonary Functions

Figure 1: Wearable sensor and analytics systems for COVID-19 onset detection and recovery tracking.


COVID-19, the disease caused by the novel coronavirus, affects lung functionality and leads to respiratory complications. It may leave long-term pulmonary health consequences. Prof. Ashok Agrawala and Prof. Nirupam Roy are developing wearable sensors and analytical systems for continuous lung function monitoring during recovery and rehabilitation. This system also targets onset prediction in healthy users and identification asymptomatic carriers through anomalies in breathing patterns.

Respiratory Patterns

Figure 2: a) Normal breathing (4 breaths); b) Cough incident; c) Restless sleep during fever.

Figure 3: a) Sneeze incident; b) Detection of non-breathing event.

We are able to extract a wealth of information from the respiratory patterns. In Figure 2, samples of natural breathing were retrieved for a flu patient. From this, we show an example of a cough, as well as restless behavior while the patient had incurred a fever (more specifically, the patient was in the right lateral recumbent position as indicated by the accelerometer signal). We can zoom into the breaths to identify latent changes before and after the patient became ill. Figure 3 shows a sample sneeze followed by brief laughter. Detection of such respiratory (and non-respiratory/anomalous) events will play a key role in understanding behavioral patterns.


Faculty Students
 Ashok Agrawala
 Dept of Computer Science
 Faizan Wajid
 Graduate Student
 Nirupam Roy
 Assistant Professor
 Dept of Computer Science
 Mara Cai