Never miss a story

Get subscribed to our newsletter


×
FluSense is a deivce that can detect coughing and crowd size in real time, analyse the data to directly monitor flu-like illnesses and influenza trends and predict the next pandemic in the making. Pixabay

A team of US researchers has invented a portable surveillance device powered by machine learning called ‘FluSense’ that can detect coughing and crowd size in real time, analyse the data to directly monitor flu-like illnesses and influenza trends and predict the next pandemic in the making.

The ‘FluSense’ creators from University of Massachusetts Amherst said that the 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 the COVID-19 pandemic or SARS.


“This may allow us to predict flu trends in a much more accurate manner,” said study co-author Tauhidur Rahman, assistant professor of computer and information sciences.

Models like these can be lifesavers by directly informing the public health response during a flu epidemic.


The next step is to test ‘FluSense’ in other public areas and geographic locations. Pixabay

These data sources can help determine the timing for flu vaccine campaigns, potential travel restrictions, the allocation of medical supplies and more.

The ‘FluSense’ platform processes a low-cost microphone array and thermal imaging data with a Raspberry Pi and neural computing engine.

It stores no personally identifiable information, such as speech data or distinguishing images.

In Rahman’s Mosaic Lab, the researchers first developed a lab-based cough model.

They 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,” said Rahman.

From December 2018 to July 2019, the FluSense platform collected and analyzed more than 350,000 thermal images and 21 million non-speech audio samples from the public waiting areas.

The researchers found that FluSense was able to accurately predict daily illness rates at the university clinic.


Models like ‘FluSense’ can be lifesavers by directly informing the public health response during a flu epidemic. Pixabay

According to the study, “the early symptom-related information captured by FluSense could provide valuable additional and complementary information to current influenza prediction efforts”.

Study lead author Forsad Al Hossain said FluSense is 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 says, pointing to the compact components inside the FluSense device. “All of the processing happens right here. These systems are becoming cheaper and more powerful.”

The next step is to test ‘FluSense’ in other public areas and geographic locations.

Also Read- Find some Family ‘Me-Time’ Amid Social Distancing Due to COVID-19

“We have the initial validation that the coughing indeed has a correlation with influenza-related illness. Now we want to validate it beyond this specific hospital setting and show that we can generalize across locations,” said epidemiologist Andrew Lover.

Rahman added: “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”. (IANS)


Popular

Photo by Alexander Shatov on Unsplash

Twitter has confirmed that its algorithms amplify right-leaning political content.

By Nikhila Natarajan

In a continuing study on the effects of machine learning (ML) on public conversation, Twitter has confirmed that its algorithms amplify right-leaning political content. "In six out of seven countries - all but Germany - tweets posted by accounts from the political right receive more algorithmic amplification than the political left when studied as a group," Twitter blogged.

"Right-leaning news outlets, as defined by the independent organisations, see greater algorithmic amplification on Twitter compared to left-leaning news outlets." Since 2016, Twitter users are able to choose between viewing algorithmically ordered tweets first in their home timeline or viewing the most recent tweets in reverse chronological order.

"An algorithmic home timeline displays a stream of tweets from accounts we have chosen to follow on Twitter, as well as recommendations of other content Twitter thinks we might be interested in based on accounts we interact with frequently, tweets we engage with, and more. "As a result, what we see on our timeline is a function of how we interact with Twitter's algorithmic system, as well as how the system is designed."

The new research is based on tweets of elected officials of House of Commons members in Canada, the French National Assembly, the German Bundestag, House of Representatives in Japan, Congress of Deputies of Spain, House of Commons in the UK, and official and personal accounts of House of Representatives and Senate members in the US, as well as news outlets, from April 1 to August 15, 2020.

gold Apple iPhone 6s displaying Twitter logo Tweets about political content from elected officials, regardless of party or whether the party is in power, do see algorithmic amplification when compared to political content on the reverse chronological timeline. | Photo by Sara Kurfeß on Unsplash

Keep Reading Show less
Flickr

Snapdeal co-founder and COO Rohit Bansal on Friday lauded a man who facilitated 64 registrations for the vaccine on the CoWin portal.

Even as India celebrates reaching a milestone of 100 crore Covid vaccine doses, Snapdeal co-founder and COO Rohit Bansal on Friday lauded a man who facilitated 64 registrations for the vaccine on the CoWin portal. In a video shared on his Facebook and Twitter page, Bansal hailed Sonu Kumar as a "citizen celebrity".

Bansal said that Kumar not only helped "just co-workers and family but complete strangers too. With patience, empathy and uncanny jugaad". He added that Kumar joined him "many moons ago" and completed his open school from a parking lot.

"Education has helped this wonderful man enable others to get India back on track. Bravo! The CoWin portal on Thursday mentioned that a total of 100 crore vaccine doses has been administered so far to the eligible population under the vaccination drive in India, nine months after the nationwide inoculation programme was started to protect the people against Covid-19.

"It's a cause of significant celebration and happiness," Bansal said in the video. He said that while people just help a few around them, Kumar "bridged the digital gap" for 64 people, who were finding it difficult to register themselves online on the vaccine portal. Kumar said he doesn't feel that he has contributed much towards the 100 crore vaccine dose count. "I have been able to help only 64 people, if I was able to help more I would have been happier." (IANS/ MBI)


Keep Reading Show less
VOA

A health worker counts antiretroviral drug tablets for a patient at The AIDS Support Organization (TASO) in the capital Kampala, Uganda, July 12, 2012.

KAMPALA, UGANDA — Uganda has kickstarted a trial for the injectable HIV drugs cabotegravir and rilpivirine. Researchers and those living with HIV say the trial will likely end pill fatigue, fight stigma, improve adherence and ensure patients get the right dosage.

The two drugs have been in use as tablets. The World Health Organization last year licensed their use as injectables.

Keep reading... Show less