Colorful underwater world

Twenty-five years ago, lionfish started invading coastal waters in the Americas, and the species is now causing damage to the local ecosystems from Venezuela, through the Caribbean, and up the East Coast of the United States. Since most of these fish are genetically similar, the theory goes that a few private fish collectors dumped their fish in the water, and now we have a problem: these fish can lay 30,000 eggs every five days, local prey aren’t scared of them because they still don’t recognize them as predators, and lionfish have no natural predators in these foreign waters.

But humans could become their main predators because these fish are tasty—and they sell for up to $20 a pound at upscale restaurants, when scuba divers can get to them. However, there aren’t enough scuba divers fishing for them, and these fish hideout in spots much deeper than humans can go. Enter stage right: an untethered, autonomous, underwater robot powered by machine learning aims to hunt these fish. Students from Worcester Polytechnic Institute are training the robot to use computer vision to recognize what a lionfish is and then to run it through with a spear.

heart-shaped pills coming out of a bottle

It’s incredibly important to understand how drugs interact with each other to keep patients out of dangerous and deadly situations. South Korea’s KAIST University recently shared that it’s developed a deep learning system to precisely predict interactions between certain drugs. With an accuracy rate of 92.4, this tech can predict 192,284 drug-to-drug interactions. But it doesn’t stop there. In its most recent iteration, it can predict drug-to-food interactions as well.

Photo by rawpixel.com on Unsplash

Cockroaches on a rock

If there’s anything more terrifying than artificial intelligence being used by an authoritarian state to control it’s citizens, it’s probably this: AI being used to optimize breeding and living conditions for cockroaches. Yes, it’s true. In China, a pharmaceutical company breeds cockroaches—in fact, currently 6,000,000,000 cockroaches. There are so many that the company says if they were released all at once, it would cause a catastrophe.

So why are they doing this? (Skip if you have a sensitive stomach.) Because 40 million people in China drink a potion that calls for crushed cockroaches.

Photo by Jesper Aggergaard on Unsplash

A helicopter on the ground

A US Army project is developing an artificial intelligence tool that can recognize faces through walls and in the dark. How does it do it? By using thermal imagery scanning: the AI takes a map of your body heat and matches the facial thermal scan against a database of faces. It sounds tricky because pictures in a database are not in thermal scan form. But preliminary research has successfully matched these scans against regular pictures. Since the US military has thermal scanning built into many of its tools, this tech would easily enhance a preexisting ecosystem. So, ultimately, if you’re not on some sort of watchlist or in a database of most wanted, you don’t need to fear that this AI tool will recognize your face. For now.

Photo by DON JACKSON-WYATT on Unsplash

A horse's head

If your horse gets sick with colic and the sickness isn’t caught soon enough, you may lose one of your favorite friends, like Alexa Anthony did with her horse, Magic. Eventually this was the motivation for her to create Stableguard. It uses computer vision to monitor your horse and identify unusual behavior.

Photo by samuel lopez on Unsplash

Elephant spraying itself

When elephants have tuberculosis (TB), they often don’t show the symptoms for it. In fact, the disease can remain dormant in an elephant for years before it’s detected. It also spreads from elephant to elephant, and since these animals are very social and zoos frequently trade them, the spread of TB is hard to control. It’s very expensive to test and treat elephants for TB, so it can be hard for zookeepers to track its spread.

Now a new machine learning model is tracking the disease better than any prior method. While a six percent increase in accuracy through this model may seem like only a small step forward, it can still save cash-strapped zoos a lot of money in testing and treatment. This machine learning tool draws from 20 years of elephant TB data, improving the odds of predicting which elephants are more likely to have the disease.

Photo by Andrew Rice on Unsplash

Cave with light coming through

Sometimes it’s hard for archeologists to tell if a location is an ancient burial site or simply where someone died long ago. One group of researchers trained a machine learning algorithm to decipher between these two possibilities, as well as other situations. While the results of this group’s study are heavily disputed by other archeologists (and for good reason since there are many factors that need to be taken into consideration), the researchers say their conclusions can’t be discounted.

Photo by Joshua Sortino on Unsplash

City roof tops

Have you ever wondered if your roof is a good candidate for solar panels? Of course sales people want you to believe it is, but if you want an unbiased opinion (or an opinion biased only on the datasets it uses), you can turn to Project Sunroof. This tool uses machine learning algorithms to identify if your roof is a good option for solar panels, based on Google Earth satellite images and meteorological data—and it’ll also estimate how much money you might save.

Photo by Alejandro Franco on Unsplash

A burning news paper

Tired of having to parse the news to separate bias from fact? Soon, AI may be able to do it for you. A website called Knowhere is using AI to rewrite news stories from three distinct perspectives: liberal, impartial, and conservative, so users can read one story from all three angles to gain (hopefully) a broader perspective on the actual story. The site uses AI to aggregate stories covering the same event, humans verify their trustworthiness, and the AI rewrites from the three angles previously mentioned. The founder hopes this will help people breakout of their online echo chambers. Time will tell if this approach to journalism works.

Photo by Elijah O’Donell on Unsplash