Tuesday June 25, 2019
Home Lead Story Facial Recogn...

Facial Recognition Tech Helps Develop Patient Safety Tool

The study was presented at the annual meeting of the European Society of Anaesthesiology in Austria

0
//
Shanghai,
Rana el Kaliouby, CEO of the Boston-based artificial intelligence firm Affectiva, demonstrates the company's facial recognition technology, in Boston, April 23, 2018. VOA

By using facial recognition technology, an automated system has been developed that can predict unsafe behaviour of patients in the intensive care unit (ICU), such as accidentally removing their breathing tube.

“Using images of a patient’s face and eyes we were able to train computer systems to recognise high-risk arm movement,” said study lead author Akane Sato from Yokohama City University in Japan.

According to researchers, the automated risk detection tool can be used for continuous monitoring of patient’s safety and can remove some of the limitations associated with limited staff capacity that makes it difficult to observe continuously critically-ill patients.

“We were surprised about the high degree of accuracy that we achieved, which shows this technology has the potential to be a useful tool for improving patient safety, and is the first step for a smart ICU, which is planned in our hospital,” Sato said.

For the study, the researchers included 24 post-operative patients (average age 67 years), admitted to ICU in Yokohama City University Hospital.

Facial recognition technology is used to screen people before they visit the Statue of Liberty in New York, US.
Facial recognition technology is used to screen people before they visit the Statue of Liberty in New York, US. Flickr

The proof-of-concept model was created using pictures taken by a camera mounted on the ceiling above patients’ beds. Around 300 hours of data were analysed to find daytime images of patients facing the camera in a good body position that showed their face and eyes clearly.

In total, 99 images were subject to machine learning — an algorithm that can analyse specific images based on input data, in a process that resembles the way a human brain learns new information.

Also Read- Zomato Expands to 100 New Cities, Crosses 300 in India

The model was able to alert against high-risk behaviour, especially around the subject’s face with high accuracy, said the researchers.

The study was presented at the annual meeting of the European Society of Anaesthesiology in Austria. (IANS)

Next Story

Microsoft Pulls a Massive Facial Recognition Database

Several the people included in the dataset were not asked for their consent to be included, but their images were scraped from the Internet under the Creative Commons license

0
microsoft
FILE - Microsoft Corp. signage is seen outside the Microsoft Visitor Center in Redmond, Washington, July 3, 2014. VOA

Tech giant Microsoft has reportedly pulled a massive facial recognition database containing more than 10 million images of roughly 100,000 people from the Internet, however traces of the data trove remain online, the media reported.

Microsoft released MS-Celeb-1M, a dataset of roughly 10 million photos from 100,000 individuals collected from the Internet in 2016.

The database was designed to contain photos of celebrities, but as Berlin-based researcher Adam Harvey pointed out with his project Megapixels, the definition of “celebrity” was quite broad, the Vice reported on Friday.

Shanghai,
Rana el Kaliouby, CEO of the Boston-based artificial intelligence firm Affectiva, demonstrates the company’s facial recognition technology, in Boston, April 23, 2018. VOA

The database reportedly contained photos of “journalists, artists, musicians, activists, policy makers, writers, and academics”.

Microsoft said that the database was taken down just because the research challenge is over. Even so, it’s doubtful that the MS-Celeb-1M database’s life is over as well, Microsoft was quoted as saying by the Financial Times.

Also Read- Paytm Payments Bank Ahead of Major Banks in Digital Transaction Target

Several the people included in the dataset were not asked for their consent to be included, but their images were scraped from the Internet under the Creative Commons license, the Vice report added. (IANS)