UMass FluSense Predicts Trends

UMass Device analyzes coughing and crowd size

Device invented at UMass Amherst analyzes coughing and crowd size.

As a computer scientist and mobile sensor expert at UMass Amherst, Tauhidur Rahman pondered the potential public health revelations of non-speech body sounds for a long time before he and PhD student Forsad al Hossain invented FluSense. In the Mosaic Lab that Rahman co-directs, he and a team of students—from undergraduates to PhD candidates—develop sensors to observe human health and behavior. Their goal is to solve real-world problems.

FluSense, a compact device about the size of a large dictionary, uses artificial intelligence (AI) to predict trends in infectious respiratory illnesses, such as influenza, by detecting cough sounds and counting people in public spaces. The custom enclosure was designed and 3D printed at the UMass Advanced Digital Design & Fabrication Core Facility


UMass FluSense device.
FluSense computing platform.
FluSense data analysis.
Tauhidur Rahman and Forsad Al Hossain.

“I thought if we could capture coughing or sneezing sounds from public spaces where a lot of people naturally congregate, we could utilize this information as a new source of data for predicting epidemiologic trends,” Rahman says.

The COVID-19 pandemic was sweeping across the world just as their timely FluSense research, conducted in UMass Amherst’s University Health Services waiting rooms, was published in the Proceedings of the Association for Computing Machinery on Interactive, Mobile, Wearable and Ubiquitous Technologies.

The researchers found that FluSense was able to accurately predict daily flu-like illness rates at the university clinic. Multiple and complementary sets of FluSense signals “strongly correlated” with lab-based testing for flu-like illnesses and influenza itself.

This new edge-computing platform, envisioned for use in hospitals, healthcare waiting rooms, and larger public spaces, may expand the arsenal of health surveillance tools used to forecast seasonal flu and other viral respiratory outbreaks, such as COVID-19.

FluSense was a multidisciplinary collaboration. Rahman and al Hossain worked with UMass Amherst epidemiologist Andrew Lover, a vector-borne disease expert in the School of Public Health and Health Sciences, and biostatistician Nicholas Reich, director of the UMass-based CDC Influenza Forecasting Center of Excellence, to understand the role a mobile sensing device like FluSense could play in filling the gaps in flu forecasting models.

The researchers will continue testing FluSense, gratified by the “overwhelmingly positive response” it has received from health care technology and AI writers, including coverage in India Times, the United Kingdom’s Daily Mail and The Register, UPI and Technology Networks, a global online scientific publication. “It is a great honor to receive world-wide press coverage,” Rahman says.


The Team

Tauhidur Rahman - Co-director of the Laboratory for Mobile Sensing and Ubiquitous Computing (MOSAIC Lab)
Forsad al Hossain - PhD Student, Mosaic Lab
Andrew Lover - vector-borne disease expert in the School of Public Health and Health Sciences
Nicholas Reich - biostatistician and director of the UMass-based CDC Influenza Forecasting Center of Excellence
Dave Follette - Director of Advanced Digital Design & Fabrication Core Facility

In the News

UMass News
India Times
Daily Mail
The Register
Technology Networks


April 23, 2020