AI-Powered Portable, Real-Time Monitoring Device May Help Fight Covid-19
A team of researchers at the University of Massachusetts, Amherst, have developed a portable surveillance device powered by machine learning that they say can detect coughing and crowd size in real time, and then analyze the data to directly monitor flu-like illnesses and influenza trends. They believe the device can be used to help combat the corona-virus pandemic.
The team described the device, called FluSense, in a paper published in the Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies as a "contactless syndromic surveillance platform" that "aims to expand the current paradigm of influenza-like illness (ILI) surveillance by capturing crowd-level bio-clinical signals directly related to physical symptoms of ILI from hospital waiting areas in an unobtrusive and privacy-sensitive manner."
In other words, it detects and counts the number of people coughing nearby.
About the size of a standard college student dictionary, the device processes input from a low-cost microphone array and thermal imaging camera with a Raspberry Pi and neural computing engine. It stores no personally identifiable information, the researchers said, such as speech data or distinguishing images, but "passively and continuously characterizes speech and coughing sounds, along with changes in crowd density, on the edge in a real-time manner."
FluSense was developed in the University's Mosaic Lab, which focuses on "mobile sensing and ubiquitous computing. Led by Deepak Ganesan and Tauhidur Rahman, the lab conducts research on a variety of sensor systems, networking, and data analytics for health and behavior modeling. "Our focus is on building scalable, energy-efficient sensor systems through the use of heterogeneous sensor modalities and platforms for solving real-world problems," the website reads.
Rahman, who is an assistant professor of computer and information sciences, advised the project lead, Ph.D. student Forsad Al Hossain. "I've been interested in non-speech body sounds for a long time," Rahman said in a statement. "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."
The researchers initially developed a lab-based "cough model," and then trained the deep neural network classifier to draw bounding boxes on thermal images representing people, and then to count them. "Our main goal was to build predictive models at the population level, not the individual level," Rahman said.
Al Hossain characterizes FluSense as an example of the power of combining artificial intelligence with edge computing. "We are trying to bring machine-learning systems to the edge," Al Hossain said in a statement, "All of the processing happens right here. These systems are becoming cheaper and more powerful."
John K. Waters is the editor in chief of a number of Converge360.com sites, with a focus on high-end development, AI and future tech. He's been writing about cutting-edge technologies and culture of Silicon Valley for more than two decades, and he's written more than a dozen books. He also co-scripted the documentary film Silicon Valley: A 100 Year Renaissance, which aired on PBS. He can be reached at firstname.lastname@example.org.