Abstract
Influenza, an acute viral respiratory disease that is currently causing
severe financial and resource strains worldwide. With the recent
COVID-19 pandemic exceeding 153 million cases worldwide, there is a need
for a low-cost and contactless surveillance system to detect symptomatic
individuals, more so in counties with limited healthcare resources. As
with many diseases, there are bio-clinical signals relating to the
physical symptoms. The main objective of this study was to develop
FluNet, a novel, proof-of-concept, low-cost and contactless device for
the detection of high-risk individuals. The system passively conducts
face detection in the longwave infrared domain with a precision rating
of 0.9798 and mean intersection over union of 0.7386 while sequentially
taking the temperature trend of faces with a thermal accuracy of ± 1 K.
While in parallel determining if someone in audible proximity is
coughing by using a custom deep convolutional neural network with a
precision rating of 0.9519. In addition to presenting FluNet, two
datasets have been constructed, one for face detection in the longwave
infrared domain consisting of 250 images of 20 participants’ faces at
various rotations and coverings, including face masks. The other for the
real-time detection of cough patterns comprised of a sizeable dataset of
40,482 cough / not cough sounds, coupled with a new lightweight
artificial neural network architecture for the classification of cough
spectrograms. These findings could be helpful for future low-cost edge
computing applications for influenza-like monitoring.