A New "Seeing" Prosthetic May Make Life Easier for Amputees

Courtesy of Newcastle University
Courtesy of Newcastle University

Every year, about 185,000 people undergo an amputation in the United States. Bionic prosthetic limbs for amputees who have lost their hands or part of their arms have come a long way, but it's hard to replicate grasping and holding objects the way a regular hand can. Current prostheses work by reading the myoelectric signals—electrical activity of the muscles recorded from the surface of the stump—but don't always work well for grasping motions, which require varied use of force in addition to opening and closing fingers.

Now, however, researchers at Newcastle University in the UK have developed a trial bionic hand that "sees" with the help of a camera, allowing its wearer to reach for and grasp objects fluidly, without having to put much thought into it. Their results were published in the Journal of Neural Engineering.

The research team, co-led by Ghazal Ghazaei, a Ph.D. student at Newcastle University, and Kianoush Nazarpour, a senior lecturer in biomedical engineering, used a machine learning algorithm known as “deep learning,” in which a computer system can learn and classify patterns when provided with a large amount of training—in this case, they provided the computer with visual patterns. The kind of deep learning system they used, known as a convolutional neural network, or CNN, learns better the more data is provided to it.

“After many iterations, the network learns what features to extract from each image to be able to classify a new object and provide the appropriate grasp for it,” Ghazaei tells Mental Floss.

TRAINING BY LIBRARIES OF OBJECTS

They first trained the CNN on 473 common objects from a database known as the Amsterdam Library of Objects (ALOI), each of which had been photographed 72 times from different angles and orientations, and in different lighting. They then labeled the images into four grasp types: palm wrist natural (as when picking up a cup); palm wrist pronated (such as picking up the TV remote); tripod (thumb and two fingers), and pinch (thumb and first finger). For example, "a screw would be classified as a pinch grasp type” of object, Ghazaei says.

To be able to observe the CNN training in real time, they then created a smaller, secondary library of 71 objects from the list, photographed each of these 72 times, and then showed the images to the CNN. (The researchers are also adapting this smaller library to create their own grasp library of everyday objects to refine the learning system.) Eventually the computer learns which grasp it needs to use to pick up each object.

To test the prosthetic with participants, they put two transradial (through the forearm or below the elbow) amputees through six trials while wearing the device. In each trial, the experimenter placed a series of 24 objects at a standard distance on the table in front of the participant. For each object, “the user aims for an object and points the hand toward it, so the camera sees the object. The camera is triggered and a snapshot is taken and given to our algorithm. The algorithm then suggests a grasp type,” Ghazaei explains.

The hand automatically assumes the shape of the chosen grasp type, and helps the user pick up the object. The camera is activated by the user’s aim, and it is measured by the user’s electromyogram (EMG) signals in real time. Ghazaei says the computer-driven prosthetic is “more user friendly” than conventional prosthetic hands, because it takes the effort of determining the grasp type out of the equation.

LEARNING THROUGH ERROR CORRECTION

The six trials were broken into different conditions aimed at training the prosthetic. In the first two trials, the subjects got a lot of visual feedback from the system, including being able to see the snapshot the CNN took. In the third and fourth trials, the prosthetic only received raw EMG signals or the control signals. In the fifth and sixth, the subjects had no computer-based visual feedback at all, but in the sixth, they could reject the grasp identified by the hand if it was the wrong one to use by re-aiming the webcam at the object to take a new picture. “This allowed the CNN structure to classify the new image and identify the correct grasp,” Ghazaei says.

For all trials, the subjects were able to use the prosthetic to grasp an object 73 percent of the time. However, in the sixth test, when they had the opportunity to correct an error, their performances rose to 79 and 86 percent.

Though the project is currently only in prototyping phase right now, the team has been given clearance from the UK's National Health Service to scale up the study with a larger number of participants, which they hope will expand the CNN’s ability to learn and correct itself.

“Due to the relatively low cost associated with the design, it has the potential to be implemented soon,” Ghazaei says.

Keep Hackers Out Forever With This Top-Rated VPN for Just $39

Poike/iStock via Getty Images Plus
Poike/iStock via Getty Images Plus

Think for a moment about how many private interactions you have on the internet. Saved passwords, credit card information, private conversations, medical records— almost your entire identity. Protect your privacy and identity across five devices for under $40 with a lifetime VPN from KeepSolid, which provides you peace of mind to continue using online conveniences without fear, bandwidth limits, or geographic restrictions.

Daily protection is extremely important when almost every transaction is made online. Groceries, movies, games, bills, and so much more are all paid for online with your personal and accessible information—but the concern doesn’t stop with others’ access to you. What happens when you’re restricted from accessing parts of the internet yourself? KeepSolid VPN Unlimited will also bypass censorship to allow you access to any site you’d like. This comes in handy when you’re traveling abroad in countries that restrict access to sites like Facebook.

More than 10 million customers globally have trusted KeepSolid VPN Unlimited with their internet access, identity, and privacy without compromised browsing speeds or the danger of leaving data exposed to theft and fraud. If the reviews of the general public don’t sway you, perhaps the military-grade AES 256-bit encryption will (that’s cybersecurity lingo for very secure).

While Keepsolid VPN Unlimited can't keep your fingers from accidentally sending that Snapchat to the wrong person (that’s on you), it can protect you from the privacy violations that are out of your control and often go undetected. Add the best VPN to your cybersecurity toolkit at the sale price of $39, and enjoy a massive selection of servers worldwide, a rich variety of VPN protocols, and much more to keep hackers out of your sensitive data for a lifetime.

 

KeepSolid VPN Unlimited: Lifetime Subscription - $39

See Deal



At Mental Floss, we only write about the products we love and want to share with our readers, so all products are chosen independently by our editors. Mental Floss has affiliate relationships with certain retailers and may receive a percentage of any sale made from the links on this page. Prices and availability are accurate as of the time of publication.

Winter is Coming: Why Some People Seem to Feel Colder Than Others

Work blanket? Check. Hot tea? Check. Writing gloves? Check.
Work blanket? Check. Hot tea? Check. Writing gloves? Check.
shironosov/iStock via Getty Images

For a few weeks a year, as winter turns into spring, or summer gives way to fall, people in heavy coats coexist with those in sandals and shorts. Similarly, in an office where the thermostat is set at 74°F, some workers will be comfortable in short sleeves, while others will be wearing sweaters and scarves.

Underlying this disagreement are the different ways people perceive cold—and scientists are still trying to understand them.  

Men, Women, and Metabolism

In work settings, men and women often have different opinions about the ideal temperature. A 2019 study found that women performed better in math and verbal tasks at temperatures between 70°F and 80°F, while men did better below 70°F. The researchers proposed that gender-mixed workplaces might boost productivity by setting the thermostat higher than the current norm (which the Occupational Safety and Health Administration suggests should be between 68°F and 76°F).  

The discrepancy has a known physical basis: Women tend to have lower resting metabolic rates than men, due to having smaller bodies and higher fat-to-muscle ratio. According to a 2015 study, indoor climate regulations are based on an “empirical thermal comfort model” developed in the 1960s with the male workers in mind, which may overestimate female metabolic rates by up to 35 percent. To compound the problem, men in business settings might wear suits year-round, while women tend to have more flexibility to wear skirts or sundresses when it's warm outside.

Culture and the Cold

Cultural factors are also involved. European visitors are habitually alarmed by the chilly temperatures in American movie theaters and department stores, while American tourists are flabbergasted at the lack of air conditioning in many European hotels, shops, and offices. The preferred temperature for American workspaces, 70°F, is too cold for Europeans that grew up without the icy blast of air conditioners, Michael Sivak, a transportation researcher formerly at the University of Michigan, told The Washington Post in 2015.

The effects of cultural change on the human ability to withstand extreme temperatures can be dramatic. In the 19th century, 22 percent of women on the Korean island of Jeju were breath-hold divers (haenyeo). Wearing thin cotton bathing suits, haenyeo dove nearly 100 feet to gather shellfish from the sea floor, holding their breath for more than three minutes in each dive. In winter, they stayed in 55°F-57°F water for up to an hour at the time, and then warmed up by the fire for three of four hours before jumping back in.

In the 1970s, haenyeo starting wearing protective wet suits. Studies conducted between the 1960s and the 1980s showed that their tolerance for cold diminished [PDF].

Blame Your Brain

Beyond the effects of cultural practice and body composition, scientists have started to identify the cognitive factors that influence our temperature perception. It turns out that what feels unpleasantly cold versus comfortably chill is partly in our own minds.

One example is the phenomenon described as “cold contagion.” A 2014 study asked participants to view videos of people immersing their hands in visibly warm or cold water. Observers not only rated the hands in cold water as cooler than those in hot water, but their own hands became cooler when watching the cold-water videos. There was no comparable effect for the warm water videos, however. The findings suggest that we may feel colder when surrounded by shivering people at the office than if we're there by ourselves, even when setting the thermostat at the same temperature in both cases.

Other studies highlight the psychological aspects of temperature perception. Experimental participants at the Institute of Biomedical Investigations in Barcelona, Spain, watched their arms become blue, red, or green by means of virtual reality, while the neuroscientist Maria Victoria Sanchez-Vives and her team applied heat to their actual wrists. As the temperature increased, participants felt pain earlier when their virtual skin turned red than when it turned blue or green.

Subjectivity in temperature perception has led to some creative treatments for burn patients. In the 1990s, Hunter Hoffman, David Patterson, and Sam Sharar of the University of Washington developed a virtual-reality game called SnowWorld, which allows patients in hospital burn units to experience virtual immersion in a frozen environment. Amazingly, playing SnowWorld counteracted pain during wound care more effectively than morphine did.

“The perception of temperature is influenced by expectations,” Sanchez-Vives tells Mental Floss. “Putting one’s hand inside a virtual oven is perceived as ‘hot,’ while sticking one’s hand into a virtual bucket filled with iced water is perceived as ‘cold,’ despite being at room temperature in each scenario.”

In other words, if you expect to feel cold walking into the office or out on the street, chances are that you will.