Take the pledge to vote

For a better tommorow#AajSawaroApnaKal
  • I agree to receive emails from News18

  • I promise to vote in this year's elections no matter what the odds are.
  • Please check above checkbox.

    SUBMIT

Thank you for
taking the pledge

Vote responsibly as each vote counts
and makes a diffrence

Disclaimer:

Issued in public interest by HDFC Life. HDFC Life Insurance Company Limited (Formerly HDFC Standard Life Insurance Company Limited) (“HDFC Life”). CIN: L65110MH2000PLC128245, IRDAI Reg. No. 101 . The name/letters "HDFC" in the name/logo of the company belongs to Housing Development Finance Corporation Limited ("HDFC Limited") and is used by HDFC Life under an agreement entered into with HDFC Limited. ARN EU/04/19/13618
»
1-min read

Calling Emergency Services: Smart Assistants in Amazon Echo And Google Home Can Detect Heart Attacks

Researchers say the technology was able to detect agonal breathing 97 percent of the time from up to 20 feet away.

Vishal Mathur | @vishalmathur85

Updated:June 24, 2019, 9:35 AM IST
facebookTwitterskypewhatsapp
Calling Emergency Services: Smart Assistants in Amazon Echo And Google Home Can Detect Heart Attacks
Researchers say the technology was able to detect agonal breathing 97 percent of the time from up to 20 feet away.
Loading...

Smart speakers and smart assistants are not just about commanding it to play music or tell you the weather or book an Uber for you. Researchers at the University of Washington have developed and artificial intelligence (AI) tool that allows smart speakers to detect signs of a heart attack or cardiac arrest, and alert emergency services as well as friends and relatives. In the research published in NJP Digital Medicine, researchers Justin Chan, Thomas Rea, Shyamnath Gollakota and Jacob E. Sunshine say that the technology was able to detect agonal breathing 97 percent of the time from up to 20 feet away.

The researchers say that they sourced the pre-heart attack or pre-cardiac arrest agonal breathing recording samples from the 9-1-1 emergency calls between the years of 2009 and 2017, from the Public Health-Seattle & King County, Division of Emergency Medical Services. This dataset included 162 calls, roughly about 19 hours of clear recordings of agonal breathing. Those who may be suffering with sudden cardiac arrest or initial stages of a heart attack struggle with irregular gasps of breath, also known as agonal breathing. If they are alone at the time, they may be unable to seek help.

“For each occurrence, we extract 2.5 seconds worth of audio from the start of each agonal breath. We extracted a total of 236 clips of agonal breathing instances. Given the relatively small size of our agonal breathing dataset, we augment the number of agonal breathing instances with label preserving transformations, a common technique applied to sparse datasets. We augment the data by playing the recordings over the air over distances of 1, 3, and 6 meters, in the presence of interference from indoor and outdoor sounds with different volumes and when a noise cancellation filter is applied,” say the researchers. The indoor and outdoor sounds could include the noise made by air-conditioners, pets and even traffic movement outside.

The recordings were captured on different devices, including an Amazon Alexa smart speaker, an Apple iPhone 5s and a Samsung Galaxy S4 to get 7316 positive samples.

This tool, currently in the testing phase, can be activated on smart speakers—similar to how an Amazon Alexa speaker can enable a skill, and will detect the breathing patterns of users. Incidentally, this process will run on the processors built inside smart speakers and will operate locally. The researchers want to further tune the algorithms to eliminate the false alarms.

Read full article
Loading...
Next Story
Next Story

Also Watch

facebookTwitterskypewhatsapp

Live TV

Loading...
Countdown To Elections Results
To Assembly Elections 2018 Results