Never miss a story

Get subscribed to our newsletter


×
Smartphone camera likely to measure pulse. Pixabay

Researchers have developed a method that uses the camera on a person’s smartphone or computer to take their pulse and respiration signal from a real-time video of their face. The development comes at a time when telehealth has become a critical way for doctors to provide health care while minimizing in-person contact during Covid-19.

The University of Washington-led team’s system uses machine learning to capture subtle changes in how light reflects off a person’s face, which is correlated with changing blood flow. Then it converts these changes into both pulse and respiration rate. The researchers presented the system in December at the Neural Information Processing Systems Conference.


Follow NewsGram on Instagram to keep yourself updated.

Now the team is proposing a better system to measure these physiological signals. This system is less likely to be tripped up by different smartphone cameras, lighting conditions, or facial features, such as skin color, according to the researchers who will present these findings on April 8 at the Association for Computing Machinery (ACM) Conference on Health, Interference, and Learning.

“Every person is different,” said lead study author Xin Liu, a UW doctoral student. “So this system needs to be able to quickly adapt to each person’s unique physiological signature, and separate this from other variations, such as what they look like and what environment they are in.”


Light reflects off a person’s face. Pixabay

The first version of this system was trained with a dataset that contained both videos of people’s faces and “ground truth” information: each person’s pulse and respiration rate measured by standard instruments in the field. The system then used spatial and temporal information from the videos to calculate both vital signs. While the system worked well on some datasets, it still struggled with others that contained different people, backgrounds, and lighting. This is a common problem known as “overfitting,” the team said.

ALSO READ: Smartphone Users Are Already Clamouring For 5G, High-Speed Connectivity

The researchers improved the system by having it produce a personalized machine learning model for each individual. Specifically, it helps look for important areas in a video frame that likely contain physiological features correlated with changing blood flow in a face under different contexts, such as different skin tones, lighting conditions, and environments.

From there, it can focus on that area and measure the pulse and respiration rate. While this new system outperforms its predecessor when given more challenging datasets, especially for people with darker skin tones, there is still more work to do, the team said. (IANS/SP)


Popular

VOA

Facebook, Whatsapp and Instagram logos are displayed in this illustration taken October 4, 2021.

Facebook says it plans to hire 10,000 workers in the European Union over the next five years to work on a new computing platform.

The company said in a blog post Sunday that those high-skilled workers will help build "the metaverse," a futuristic notion for connecting people online that encompasses augmented and virtual reality.

Keep Reading Show less
Wikimedia Commons

The most popular version of the rhyme/lullaby

As children, singing the rhyme Rock A Bye Baby was a fun thing to do. It was a statement of thrill and adventure to imagine a child climbing to the top of a tree and rocking to sleep. Especially in the Indian context, rocking a baby to sleep by attaching the cradle to the tree is quite a common thing. But the origin of this rhyme, or lullaby, seems rooted in other histories.

The most popular notion associated with this lullaby is of women leaving their babies tied to tree branches, rocking to sleep with the wind. It is believed that at the time this lullaby was written, it was inspired by a coloniser who saw the Native American women tie their children in birch bark cradles to the trees. The babies went to sleep rocked by the gusts of wind while the parents went about their tasks.

Keep Reading Show less
VOA

This image released by Disney Theatrical Productions shows, from second left, Michael James Scott as Genie, Michael Maliakel as Aladdin, and Shoba Narayan as Jasmine after a performance of the Broadway musical "Aladdin" in New York on Sept. 28, 2021

As kids growing up in different states, Shoba Narayan and Michael Maliakel shared a love of one favorite film — "Aladdin." Both are of Indian descent, and in the animated movie, they saw people who looked like them.

That shared love has gone full-circle this month as Narayan and Maliakel lead the Broadway company of the musical "Aladdin" out of the pandemic, playing Princess Jasmine and the hero from the title, respectively.

Keep reading... Show less