Lending A Helping Hand To Hens With AI

As anyone who has taken care of chickens or other poultry before will tell you, it can be backbreaking work. So why not build a robot to do all the hard work for us? That’s precisely what [Aktar Kutluhan] demonstrated with an AI-powered IoT system that automatically feeds chicks and monitors unhatched eggs.

Make no mistake, hens are adorable, feathered creatures, but they can be quite finicky. An egg’s weight, size, and frequency can determine the overall health of a hen, and they can stop laying eggs altogether if something as simple as their feeding schedule is too sporadic. This is precisely what inspired [Aktar] to create a system that can feed hens at a consistent time every day while keeping track of the eggs laid to ensure the coop is happy and healthy.

What’s so impressive about this build isn’t just the clever automation that scratches off a daily chore, it’s built completely with IoT devices, including the AI. The setup uses Edge Impulse as an object detection model on an OPenMV Cam H7 microcontroller to recognize eggs in the coop. From there, an WizFi360-EVB-Pico board was attached so data could be sent over WiFi, with a DHT22 thrown in to monitor and record the overall temperature of the coop.

This is already an amazing setup, but when it comes to IoT devices, the sky’s the limit. You could control heat lamps in larger coops, automatically refill a water bowl if the hens’ water is low, or even build a hands-off incubator.  We’re only just beginning to see the clever ways with which AI can help monitor our pet’s health. Just look at how another hacker used AI to monitor cat poop to make sure their furry friend wasn’t eating plastic. Thanks to [Aktar Kutluhan] for showing us more ways we can use AI to help our pets!

Continue reading “Lending A Helping Hand To Hens With AI”

This Pico-W IoT Starter Project Gets You Into Home Assistant Quick As A Flash

Many of us hacker types with some hardware knowledge and a smattering of embedded experience would like to get into home automation, but there can be quite a learning curve. If you’re looking for a hackable starting point; something to deploy, learn about and then later expand upon, then look no further than the PicoW Home Assistant Starter project from [Danilo Campos].

The project is based upon the arduino-pico core, which supports a whole pile of RP2040-based boards, so you don’t need to restrict yourself to the “official” Pico-W, so long as you have working networking, Wi-Fi or otherwise. Integration is provided by the arduino-home-assistant library, which acts as the bridge between your sensors and other widgets, MQTT, and thence the network beyond. Events and sensor data on the end-point are packaged up with MQTT and published out to the broker via the network provided, all for minimal initial effort. Once you’ve got the basic connectivity to your Home Assistant instance working, there are many code examples in the arduino-home-assistant GitHub page to give you a helping start to connect whatever tickles your fancy.

It turns out we’ve covered HA quite a bit on these fair pages, like for example, these sweet automated window blinds. Another hack uses load cells under the bed legs to detect if someone is in bed or not, and if this isn’t your thing, maybe your idea of a home assistant is a bit more like this one?

Swarm Vs. Iridium: Which Satellite IoT Service Is Right For You?

In a world where it seems like everyone’s face is glued to a device screen, the idea that wireless service might be anything other than universal seems just plain silly. But it’s not, as witnessed by vast gaps in cell carrier coverage maps, not to mention the 70% of the planet covered by oceans. The lack of universal coverage can be a real pain for IoT applications, which is a gap that satellite-based IoT services aim to fill.

But which service is right for your application? To help answer that question, [Mike Krumpus] has performed the valuable work of comparing the services offered by Swarm and Iridium in a real-world IoT shootout. On the face of it, the match-up seems a little lopsided — Iridium has been around forever and has a constellation of big satellites and an extensive ground-based infrastructure. But as our own [Al Williams] discovered when he tested out Swarm, there’s something to be said for having a lot of 1/4U Cubesats up there.

[Mike] picked up the gauntlet and did head-to-head tests of the two services under real-world conditions. Using the same Swarm development kit that [Al] used for his test, alongside an Iridium dev board of his own design, [Mike] did basic tests on uplink and downlink times for a short message on each service. We couldn’t find specs on the test message length, but Swarm’s FAQ indicates that packets are limited to 192 bytes, so we assume they’re both in that ballpark. Iridium was the clear winner on uplink and downlink times, which makes sense because Swarm’s constellation is much smaller at this point and leaves large gaps in coverage. But when you consider costs, Swarm wins the day; what would cost over $1,500 with Iridium would set you back a mere $60 with Swarm.

The bottom line, as always, depends on your application and budget, but [Mike]’s work makes it easier to do that analysis.

Food Irradiation Detector Doesn’t Use Banana For Scale

How do the potatoes in that sack keep from sprouting on their long trip from the field to the produce section? Why don’t the apples spoil? To an extent, the answer lies in varying amounts of irradiation. Though it sounds awful, irradiation reduces microbial contamination, which improves shelf life. Most people can choose to take it or leave it, but in some countries, they aren’t overly concerned about the irradiation dosages found in, say, animal feed. So where does that leave non-vegetarians?

If that line of thinking makes you want to Hulk out, you’re not alone. [kutluhan_aktar] decided to build an IoT food irradiation detector in an effort to help small businesses make educated choices about the feed they give to their animals. The device predicts irradiation dosage level using a combination of the food’s weight, color, and emitted ionizing radiation after being exposed to sunlight for an appreciable amount of time. Using this information, [kutluhan_aktar] trained a neural network running on a Beetle ESP32-C3 to detect the dosage and display relevant info on a transparent OLED screen. Primarily, the device predicts whether the dosage falls into the Regulated, Unsafe, or just plain Hazardous category.

[kutluhan_aktar] lets this baby loose on some uncooked pasta in the short demo video after the break. The macaroni is spread across a load cell to detect the weight, while [kutluhan_aktar] uses a handheld sensor to determine the color.

This isn’t the first time we’ve seen AI on the Hackaday menu. Remember when we tried those AI-created recipes?

Odd Inputs And Peculiar Peripherals: RoenDi Smart Knob Thinks Outside The Box

When it comes to design decisions, we’re often advised to “think outside the box.” It’s generally good advice, if a bit abstract — it could really mean anything. But it appears that someone took it quite literally with this nifty little smart knob display and input device.

[Dimitar]’s inspiration for RoenDi — for “rotary encoder and display” — came from an unusual source: a car dashboard, and specifically, the multipurpose knobs that often crop up in a car’s climate control cluster. Designed for ease of use while driving while causing as little distraction as possible, such knobs often combine a rotary encoder with one or more indicators or buttons. RoenDi builds on that theme by putting a 1.7″ round LCD display in the middle of a ring attached to an Alps rotary encoder, allowing the knob to be customized for whatever you want it to represent. The backplane sports a powerful STM32 microcontroller with a lot of the GPIO pins broken out, so customization and interfacing are limited only by your imagination. The design is open source, so you can either build your own or support the project via Crowd Supply.

Unlike the haptic smart knob we’ve been seeing a bit about lately, which also features a round LCD at its center, RoenDi’s feedback is via the physical detents on the encoder. We think both devices are great, and they fill different niches in the novel input ecosystem.

Continue reading “Odd Inputs And Peculiar Peripherals: RoenDi Smart Knob Thinks Outside The Box”

This Week In Security: IoT In The Hot Tub, App Double Fail, And FreeBSD BadBeacon

[Eaton Zveare] purchased a Jacuzzi hot tub, and splurged for the SmartTub add-on, which connects the whirlpool to the internet so you can control temperature, lights, etc from afar. He didn’t realize he was about to discover a nightmare of security problems. Because as we all know, in IoT, the S stands for security. In this case, the registration email came from smarttub.io, so it was natural to pull up that URL in a web browser to see what was there. The page presented a login prompt, so [Eaton] punched in the credentials he had just generated. “Unauthorized” Well that’s not surprising, but what was very odd was the flash of a dashboard that appeared just before the authorization complaint. Could that have been real data that was unintentionally sent? A screen recorder answered that question, revealing that there was indeed a table loaded up with valid-looking data.

Digging around in the page’s JavaScript comes up with the login flow. The page uses the Auth0 service to handle logins, and that service sends back an access token. The page sends that access token right back to the Auth0 service to get user privileges. If the logged in user isn’t an admin, the redirect happens. However, we already know that some real data gets loaded. It appears that the limitations to data is all implemented on the client side, and the backend only requires a valid access token for data requests. What would happen if the response from Auth0 were modified? There are a few approaches to accomplish this, but he opted to use Fiddler. Rewrite the response so the front-end believes you’re an admin, and you’re in.

This approach seems to gain admin access to all of the SmartTub admin controls, though [Eaton] didn’t try actually making changes to see if he had write access, too. This was enough to demonstrate the flaw, and making changes would be flirting with that dangerous line that separates research from computer crime. The real problem started when he tried to disclose the vulnerability. SmartTub didn’t have a security contact, but an email to their support email address did elicit a reply asking for details. And after details were supplied, complete radio silence. Exasperated, he finally turned to Auth0, asking them to intervene. Their solution was to pull the plug on one of the two URL endpoints. Finally, after six months of trying to inform Jacuzzi and SmartTub of their severe security issues, both admin portals were secured.

Continue reading “This Week In Security: IoT In The Hot Tub, App Double Fail, And FreeBSD BadBeacon”

Machine Learning Does Its Civic Duty By Spotting Roadside Litter

If there’s one thing that never seems to suffer from supply chain problems, it’s litter. It’s everywhere, easy to spot and — you’d think — pick up. Sadly, most of us seem to treat litter as somebody else’s problem, but with something like this machine vision litter mapper, you can at least be part of the solution.

For the civic-minded [Nathaniel Felleke], the litter problem in his native San Diego was getting to be too much. He reasoned that a map of where the trash is located could help municipal crews with cleanup, so he set about building a system to search for trash automatically. Using Edge Impulse and a collection of roadside images captured from a variety of sources, he built a model for recognizing trash. To find the garbage, a webcam with a car window mount captures images while driving, and a Raspberry Pi 4 runs the model and looks for garbage. When roadside litter is found, the Pi uses a Blues Wireless Notecard to send the GPS location of the rubbish to a cloud database via its cellular modem.

Cruising around the streets of San Diego, [Nathaniel]’s system builds up a database of garbage hotspots. From there, it’s pretty straightforward to pull the data and overlay it on Google Maps to create a heatmap of where the garbage lies. The video below shows his system in action.

Yes, driving around a personal vehicle specifically to spot litter is just adding more waste to the mix, but you’d imagine putting something like this on municipal vehicles that are already driving around cities anyway. Either way, we picked up some neat tips, especially those wireless IoT cards. We’ve seen them used before, but [Nathaniel]’s project gives us a path forward on some ideas we’ve had kicking around for a while.

Continue reading “Machine Learning Does Its Civic Duty By Spotting Roadside Litter”