New York: Researchers led by an Indian-origin scientist have developed a software that can turn any smartphone into an eye-tracking device, a discovery that can help in psychological experiments and marketing research.
In addition to making existing applications of eye-tracking technology more accessible, the system could enable new computer interfaces or help detect signs of incipient neurological disease or mental illness.
Since few people have the external devices, there’s no big incentive to develop applications for them.
“Since there are no applications, there’s no incentive for people to buy the devices. We thought we should break this circle and try to make an eye tracker that works on a single mobile device, using just your front-facing camera,” explained Aditya Khosla, graduate student in electrical engineering and computer science at Massachusetts Institute of Technology (MIT).
Khosla and his colleagues from MIT and University of Georgia built their eye tracker using machine learning, a technique in which computers learn to perform tasks by looking for patterns in large sets of training examples.
Currently, Khosla says, their training set includes examples of gaze patterns from 1,500 mobile-device users.
Previously, the largest data sets used to train experimental eye-tracking systems had topped out at about 50 users.
To assemble data sets, “most other groups tend to call people into the lab,” Khosla says.
“It’s really hard to scale that up. Calling 50 people in itself is already a fairly tedious process. But we realised we could do this through crowdsourcing,” he added.
In the paper, the researchers report an initial round of experiments, using training data drawn from 800 mobile-device users.
On that basis, they were able to get the system’s margin of error down to 1.5 centimetres, a twofold improvement over previous experimental systems.
The researchers recruited application users through Amazon’s Mechanical Turk crowdsourcing site and paid them a small fee for each successfully executed tap. The data set contains, on average, 1,600 images for each user.
The team from MIT’s Computer Science and Artificial Intelligence Laboratory and the University of Georgia described their new system in a paper set to presented at the “Computer Vision and Pattern Recognition” conference in Las Vegas on June 28. (IANS)
Pregnant women have been systematically overlooked in the development and deployment of new vaccines, undermining their health and their communities’ safety, according to guidelines released this month by an international team of researchers, scientists and health care providers.
The report, developed by the Pregnancy Research Ethics for Vaccines, Epidemics and New Technologies (PREVENT) working group, identifies a cycle of exclusion that prevents pregnant women from accessing the benefits of vaccines.
“There’s a lot of reticence to include pregnant women in research,” said Carleigh Krubiner, the project director and a co-principal investigator for PREVENT.
And that’s led to a shortfall in data about how pregnant women respond to vaccines.
Krubiner, an associate faculty member at the Johns Hopkins Berman Institute of Bioethics, told VOA that researchers and health care providers tend to exclude pregnant women from trials, vaccinations and tracking because they lack evidence of the risks expectant mothers face.
“We continue to have this Catch-22 of not having enough evidence to feel like we can do the research. But if we don’t do the research, we don’t have the evidence,” Krubiner said.
There’s a lot of fear’
Concerns over “theoretical harm” drive decisions to exclude pregnant women from interventions, Krubiner said. But the data scientists do have, often from women not known to be pregnant when they received vaccinations, suggest those concerns are overblown.
In the case of rubella, for example, a contagious viral infection, researchers didn’t find a connection between congenital rubella syndrome and the vaccine when thousands of pregnant women were vaccinated before their pregnancy status was known.
“There’s a lot of fear,” Krubiner said. “And there are certainly biologically plausible risks associated with different types of live replicating viral vaccines.”
Live-virus vaccines contain a weakened version of the disease designed to stimulate an immune response in recipients.
“Very often, the benefits of vaccinating do still outweigh the theoretical, or even real harms that may be posed to the fetus,” Krubiner said.
One vaccine known to cause harm to pregnant women and their fetuses, Krubiner added, is for smallpox. But even in that case, she said, if a threat were imminent, pregnant women should get vaccinated, given the seriousness of the disease. The Centers for Disease Control and Prevention support that guidance.
The advice pregnant women receive about vaccination should reflect what’s known about the particular vaccine and the specific circumstances of the outbreak, Krubiner said.
Recommendations should follow current knowledge about the disease in question, the severity of the threat, and the likelihood of exposure, she added.
But the general guidance is unambiguous.
“At minimum, vaccines should be offered to women, and in many cases they should be strongly recommended,” Krubiner said.
Among those cases is the vaccine for seasonal and pandemic flu, which pregnant women should be urged to receive, in light of the severity of the risks tied to infection — not just for the expectant mother, but the future child as well.
Pregnant women should also be encouraged to receive vaccines for H1N1, also known as swine flu, and DPT, which protects against diphtheria, whooping cough and tetanus.
Involving pregnant women in the benefits of vaccines will require systemic shifts, the PREVENT group said in its report this month.
An important step is to become more proactive in bringing pregnant women into what Krubiner called the “development and research pipeline.” By involving pregnant women early, she said, health care providers aren’t left with the kinds of blind spots about how vaccines will affect expectant mothers and their fetuses that lead to their exclusion.
Even basic information, such as pregnancy status in case reports, sometimes goes untracked, despite being easy to collect and providing insight into the unique burden pregnant women face in disease outbreaks.
More complex data collection will paint a more complete picture. Specific studies could be designed to examine the safety and efficacy of vaccines for pregnant women, for example, or to track effects at different points in gestation.
“Starting anywhere at this point would be better than the dearth of data that we have right now to really try to address the needs of pregnant women and their babies,” Krubiner said.
Disease outbreaks devastate communities. But they also provide opportunities to better prepare for, and respond to, the next epidemic.
In this year’s Ebola outbreaks in Congo, responders have applied lessons from West Africa’s 2014-16 epidemic to community engagement. And drug trials toward the end of the West Africa outbreak produced evidence about the vaccine that’s now being deployed.
But pregnant women weren’t included in those trials, and researchers collected little in the way of data about the burden pregnant women and their offspring face.
“Pregnant women are continuously getting left out of the benefits of scientific advancement in medicine,” Krubiner said.
“If we continue to fail to collect the kinds of data that we need, to generate the kind of evidence that we need and to also have interventions that meet the broader population’s needs,” Krubiner said, “then we’re just going to continue to perpetuate the cycle.” (VOA)