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.

Looking to Downsize? You Can Buy a 5-Room DIY Cabin on Amazon for Less Than $33,000

Five rooms of one's own.
Five rooms of one's own.
Allwood/Amazon

If you’ve already mastered DIY houses for birds and dogs, maybe it’s time you built one for yourself.

As Simplemost reports, there are a number of house kits that you can order on Amazon, and the Allwood Avalon Cabin Kit is one of the quaintest—and, at $32,990, most affordable—options. The 540-square-foot structure has enough space for a kitchen, a bathroom, a bedroom, and a sitting room—and there’s an additional 218-square-foot loft with the potential to be the coziest reading nook of all time.

You can opt for three larger rooms if you're willing to skip the kitchen and bathroom.Allwood/Amazon

The construction process might not be a great idea for someone who’s never picked up a hammer, but you don’t need an architectural degree to tackle it. Step-by-step instructions and all materials are included, so it’s a little like a high-level IKEA project. According to the Amazon listing, it takes two adults about a week to complete. Since the Nordic wood walls are reinforced with steel rods, the house can withstand winds up to 120 mph, and you can pay an extra $1000 to upgrade from double-glass windows and doors to triple-glass for added fortification.

Sadly, the cool ceiling lamp is not included.Allwood/Amazon

Though everything you need for the shell of the house comes in the kit, you will need to purchase whatever goes inside it: toilet, shower, sink, stove, insulation, and all other furnishings. You can also customize the blueprint to fit your own plans for the space; maybe, for example, you’re going to use the house as a small event venue, and you’d rather have two or three large, airy rooms and no kitchen or bedroom.

Intrigued? Find out more here.

[h/t Simplemost]

This article contains affiliate links to products selected by our editors. Mental Floss may receive a commission for purchases made through these links.

The Psychological Tricks Disney Parks Use to Make Long Wait Times More Bearable

© Jorge Royan, Wikimedia Commons // CC BY-SA 3.0
© Jorge Royan, Wikimedia Commons // CC BY-SA 3.0

No one goes to Disneyland or Disney World to spend the day waiting in line, but when a queue is well-designed, waiting can be part of the experience. Disney knows this better than anyone, and the parks' Imagineers have developed several tricks over the years to make long wait times as painless as possible.

According to Popular Science, hacking the layout of the line itself is a simple way to influence the rider's perspective. When a queue consists of 200 people zig-zagging around ropes in a large, open room, it's easy for waiting guests to feel overwhelmed. This design allows riders to see exactly how many people are in line in front of them—which isn't necessarily a good thing when the line is long.

Imagineers prevent this by keeping riders in the dark when they enter the queue. In Space Mountain, for example, walls are built around the twisting path, so riders have no idea how much farther they have to go until they're deeper into the building. This stops people from giving up when they first get in line.

Another example of deception ride designers use is the "Machiavellian twist." If you've ever been pleasantly surprised by a line that moved faster than you expected, that was intentional. The signs listing wait times at the beginning of ride queues purposefully inflate the numbers. That way, when a wait that was supposed to be 120 minutes goes by in 90, you feel like you have more time than you did before.

The final trick is something Disney parks are famous for: By incorporating the same level of production design found on the ride into the queue, Imagineers make waiting in line an engaging experience that has entertainment value of its own. The Tower of Terror queue in Disney World, which is modeled after a decrepit 1930s hotel lobby down to the cobwebs and the abandoned coffee cups, feels like it could be a movie set. Some ride lines even use special effects. While waiting to ride Star Wars: Ride of the Resistance in Galaxy's Edge, guests get to watch holograms and animatronics that set up the story of the ride. This strategy exploits the so-called dual-task paradigm, which makes the line feel as if it's going by faster by giving riders mental stimulation as they wait.

Tricky ride design is just one of Disney's secrets. Here are more behind-the-scenes facts about the beloved theme parks.

[h/t Popular Science]