It’s easy to be worried when you cough these days — is it COVID-19, or are you just clearing your throat? You might get a clearer answer soon. MIT researchers have developed AI that can recognize forced coughing from people who have COVID-19, even if they’re otherwise asymptomatic. The trick was to develop a slew of neural networks that can distinguish subtle changes indicative of the novel coronavirus’ effects.
One neural network detects sounds associated with vocal strength. Another listens for emotional states that reflect a neurological decline, such as increased frustration or a “flat affect.” A third network, meanwhile, gauges changes in respiratory performance. Throw in an algorithm that checks for muscular degradation (that is, weaker coughs) and it provides a more complete picture of someone’s health.
The AI is highly accurate in early tests. After the team trained its model on tens of thousands of cough and dialog samples, the technology recognized 98.5 percent of coughs from people with confirmed COVID-19 cases. It identified 100 percent of people who were ostensibly asymptomatic, too.
There are clear limits. The technology isn’t meant to diagnose symptomatic people, as they might have other conditions that produce similar behavior. And while it’s quite capable, you wouldn’t want to use this for a definitive verdict on whether or not you’re infected.
This isn’t a theoretical exercise, though. The scientists are developing a “user-friendly” app that could be used as a prescreening tool for the virus. You might only have to cough into your phone each day to determine if it’s safe for you to head outside. The researchers even suggest this could put an end to pandemics if the tool was always listening in the background, although that’s a big “if” when it would likely raise privacy issues.
Ask VR fans about their gripes and they’ll likely mention the “screen door” effect, or the gaps between pixels that you notice when looking at a display so close to your eyes. That annoyance might disappear entirely if Samsung and Stanford University have their way. They’ve developed (via IEEE Spectrum) OLED technology that supports resolutions up to 10,000 pixels per inch — well above what you see in virtually any existing display, let alone what you’d find in a modern VR headset like the Oculus Quest 2.
The newOLED tech uses films to emit white light between reflective layers, one silver and another made of reflective metal with nano-sized corrugations. This “optical metasurface” changes the reflective properties and allows specific colors to resonate through pixels. The design allows for much higher pixel densities than you see in the RGB OLEDs on phones, but doesn’t hurt brightness to the degree you see with white OLEDs in some TVs.
This would be ideal for VR and AR, creating a virtually ‘flawless’ image where you can’t see the screen door effect or even individual pixels. This might take years to arrive when it would require much more computing power, but OLED tech would no longer be an obstacle.
It’s also more practical than you might think. Samsung is already working on a “full-size” display using the 10,000PPI tech, and the design of the corrugations makes large-scale manufacturing viable. It may just be a question of when and where you see this OLED rather than “if.”
Electronic skins can already react to touch, but they’re not much good at reacting to the jabs and burns that cause pain. That’s a problem for prosthetics and robots that are supposed to have human-like responses. They may be more sensitive in the future, though. RMIT University researchers have developed an artificial skin (via SciTechDaily) that reacts to pain much like humans do. It would provide “near-instant” feedback if pressure and temperatures hit levels that would make someone yelp.
The wearable prototype is made of stretchable, extremely thin electronics (oxides and biocompatible silicone) with pressure sensing, temperature-reactive coatings and brainlike memory cells. It’s subtle enough to communicate the difference between gently poking yourself with a pin versus a painful jab, researcher Md Ataur Rahman said. The design mimics the neurons, neural pathways and receptors that guide human senses.
The project is a long way from reaching practical products. The potential uses are clear, however. A prosthetic arm could better replicate the sensations of the real thing and keep people clear of danger. Robots could be less intimidating as they’d exhibit more human-like fragility. It could also be useful for non-invasive skin grafts where conventional methods aren’t effective. It won’t be surprising if any uses are selective, though. While pain is a helpful natural defense mechanism, there aren’t many people (or bots, for that matter) looking for it.
TikTok may drop its ties to China in very short order. Reuters sources claim TikTok’s Chinese owner, ByteDance, has agreed to sell its stake in the social network’s US operations to avert a possible ban. The agreement would have Microsoft protect American user data, according to the report, but Microsoft wouldn’t necessarily own TikTok itself — it would leave the possibility of another company taking stewardship.
The company told Engadget that it didn’t comment on rumors, but that it was “confident in the long-term success of TikTok.” It pointed to a video response to talk of a ban where US General Manager Vanessa Pappas said TikTok was “not planning on going anywhere.” Microsoft declined to comment. The White house has already declined to comment on whether or not this move would prevent a ban.
There’s no guarantee this would be enough. President Trump said on Air Force One that he would ban TikTok outright and rejected talk of allowing a sell-off. He suggested he would use an executive order or emergency economic powers to block the company. However, he also said this before word of a possible US deal emerged. If TikTok sheds its Chinese links, a ban might not have much effect.
A ban could have serious consequences if it remained intact for a significant period, and not just to TikTok’s bottom line. The company has about 100 million American users, and a sudden shutdown could both make people scramble to alternatives and possibly create resentment. It could affect creator money and TikTok jobs, too. In that regard, the social media giant might not have much choice if it wants to prevent chaos.
Update 8/1 5:08PM: The Wall Street Journal and The Information claim Microsoft has “paused” talks with TikTok following Trump’s suggestion he would ban the app. The tech companies were reportedly hoping to finish a deal by Monday, sources for the news outlets said. This doesn’t mean they’re scrapping the deal, but they apparently want “clarity” on what happens next.
Many proposed anti-asteroid solutions involve knocking them off-course, which carries its own problems — what if you create a fragment that hits Earth regardless? Researchers might have a safer solution. They’ve proposed a system (spotted by Parabolic Arc) that would tether a threatening asteroid to a smaller rock, throwing off the larger body’s center of mass and steering it away from our homeworld. As the method only involves a giant cable, it wouldn’t risk cracking an object into pieces.
The scientists couldn’t test this in real life, of course, so they used a simulated version of Bennu to see how well their idea would work. It’s viable for protecting the planet in a range of conditions, the team said.
There are catches. You need a small asteroid in the first place, of course. Moreover, this requires considerably more time to implement than smacking an asteroid with a spacecraft or projectile. It would work well with a coordinated detection and response system, but might take too much time if observers are caught off-guard. It’s another tool in the arsenal, though, and it may be necessary when it’s likely just a matter of when an asteroid enters a collision course, not if.
