It’s that time of year again, and with Halloween arguably being the hacker’s perfect holiday, we’re starting to see a tick up in projects with a spooky theme. Most seem to do with making some otherwise tame Halloween decorations scarily awesome, but this is different — using artificial intelligence to search for ghosts.
It seems like [Matt Reed]’s “DeepWhisper” project is meant to be taken as light-hearted fun for the spooky season, but there may be a touch of seriousness to his efforts to listen in on ghostly conversations. The principle behind this is electronic voice phenomena (EVP), whereby the metabolically and/or dimensionally challenged are purported to influence electronic systems, resulting in heavily processed audio clips that seem to have a whispered endearment from the departed or a threat from a malevolent spirit. DeepWhisper takes this a step further by using a Raspberry Pi to feed audio into the Google Cloud Speech API for analysis. If anything is whispered in one of the 110 or so languages Google knows, it’ll get displayed on a screen. [Matt] plans to set DeepWhisper up in the aptly-named Butchertown section of Nashville and live-stream the results next week.
It’ll be interesting to see what Google’s neural network makes out of the random noise it will probably only ever hear. And [Matt] is planning on releasing his code for all to see, so there may be some valuable cloud techniques to learn from DeepWhisper. But in the unlikely event that he does discover ghosts, it’s nice to know you can have the tools and the talent to bust ’em.
Continue reading “Listen To The Netherworld With Artificial Intelligence”
When you ask for recommendations on which 3D printer to buy, damn the cost, the Ultimaker is consistently at the top of the list. There’s a reason for the popularity of this printer — it’s easy to use, extremely high quality, and has an entire freakin’ Linux system running somewhere under the hood. That last bit is opening up a few doors to some interesting hacks, like using a 3D printer as an RGB LED.
While this is just a simple test of the Ultimaker API, it’s surprisingly high up on the Google results when you search, ‘Ultimaker API’. That’s a shame, because there’s a lot of power under the hood of this printer. If you have some sort of mod you’d like to throw into the ring, here’s the Hackaday Tip Line.
You can check out the demo video of this hack below.
Continue reading “Blinking LEDs On The Internet Of Printers”
One of the companion technologies in the developing field of augmented reality is gesture tracking. It’s one thing to put someone in a virtual or augmented world, but without a natural way to interact inside of it the user experience is likely to be limited. Of course, gestures can be used to control things in the real world as well, and to that end [Sarah]’s latest project uses this interesting human interface device to control a drone.
The project uses a Leap Motion sensor to detect and gather the gesture data, and feeds all of that information into LabVIEW. A Parrot AR Drone was chosen for this project because of a robust API that works well with this particular software suite. It seems as though a lot of the grunt work of recognizing gestures and sending commands to the drone are taken care of behind-the-scenes in software, so if you’re looking to do this on your own there’s likely to be quite a bit more work involved. That being said, it’s no small feat to get this to work in the first place and the video below is worth a view.
To some, gestures might seem like a novelty technology with no real applications, but they do have real-world uses for people with disabilities or others with unusual workflow that require a hands-free approach. So far we’ve seen hand gesture technologies that drive cars, help people get around in the physical world, and even play tetris.
Continue reading “Drone Takes Off With A Flick Of The Wrist”
A Raspberry Pi kicking around one’s workbench is a project waiting to happen — if they remain unused long enough to be considered a ‘spare.’ If you find you’ve been pining after an Alexa or your own personal J.A.R.V.I.S., [Novaspirit Tech] might be able to help you out — provided you have a USB mic and speaker handy — with an accessible tutorial for setting up Google Assistant on your Pi.
A quick run-through on enabling a fresh API client on Google’s cloud platform, [Novaspirit] jumps over to the Raspbian console to start updating Python and a few other dependencies. Note: this is being conducted in the latest version of Raspbian, so be sure to update before you get underway with all of your sudos.
Once [Novaspirit] gets that sorted, he sets up an environment to run Google Assistant on the Pi, authenticates the process, and gets it running after offering a couple troubleshooting tips. [Novaspirit] has plans to expand on this further in the near future with some home automation implementation, but this is a great jumping-off point if you’ve been looking for a way to break into some high-tech home deliciousness — or something more stripped-down — for yourself. Check out the video version of the tutorial after the break if you like watching videos of guys typing away at the command line.
Continue reading “Sudo Google Assistant”
[Erhan] has been playing around with the Telegram instant messaging service. Initially, he worked out how to turn on and off LEDs from his cell phone: he sent commands from the phone through the Telegram bot API, to a computer that’s connected over serial to an MSP430 board that actually controlled the LEDs.
But that’s a little bit complicated. Better to cut out the middleman (err…microcontroller) and implement the Telegram reception and LED blinking on a Raspberry Pi. For a project that’s already using a Pi, using the instant messaging service’s resources is a very simple way to interface to a cellphone.
The code for both the standalone RPi project and the MSP430-based microcontroller application are available at [Erhan]’s GitHub. You’re going to be installing Node.js for their telegram-bot-api and jumping through the usual OAuth hoops to get your bot registered with Telegram. But once you’ve done that all on the Raspberry Pi (or target computer of your choice) it’s all just a few lines of fairly high-level code.
We’ve only seen one other Telegram application on Hackaday.io and we’re wondering why. It looks pretty slick, and with the bot’s ability to send a custom “keyboard” to the phone along with the message, it could make cell-phone-based control interfaces a cinch. Anyone else using Telegram for bots?
There’s a lot to be said for open source software. The ability to change code to suit one’s needs, the fact that security vulnerabilities can be easier to find, and the overall transparency are just the tip of the iceberg when it comes to the strengths of using open source software. And, while Microsoft is no Apple when it comes to locking down their source code, their operating system is still, unfortunately, closed.
Don’t despair, though! There is a project out there that aims to change this. No, they’re not stealing anything or breaking into any computers to obtain Microsoft’s code. They’re writing their own version of Windows called ReactOS that aims to be binary-compatible with Windows. The software has been in development for over a decade, but they’re ready to release version 0.4 which will bring USB, sound, networking, wireless, SATA, and many more features to the operating system.
While ReactOS isn’t yet complete for everyday use, the developers have made great strides in understanding how Windows itself works. There is a lot of documentation coming from the project regarding many previously unknown or undocumented parts of Windows, and with more developers there could be a drop-in replacement for Windows within a few years. It’s definitely worth a shot if you fondly remember the frontier days of Linux where doing things like reading information on a CD required extensive experience using the terminal. If this is a little too much, though, there are other unique operating systems out there to investigate.
Thanks for the tip, [Matt]!
A home weather station is great geek street cred. Buying a commercially available station will get you all the bells and whistles, but the look tends to the utilitarian. And then there’s the trouble of placing the sensor array somewhere. To solve both problems, [GradyHillhouse] built this unique weather station with analog meters.
Based on a Particle Photon pulling weather data from the forecast.io API, values for temperature, pressure and the like are sent to analog IO pins. Each pin has a meter with a trimmer pot for calibration and a custom printed label. There’s also a digital output that goes high when a severe weather alert is posted; that drives an LED behind the bezel of one of the meters. Everything is mounted in a walnut plaque which makes for a nice presentation. The video after the break details the build.
As you can imagine, we’ve featured lots of weather stations before. Some display their data on a screen, some in more unique ways. But we really like the old school look and simplicity of this project.
Continue reading “Old School Analog Meters Tell You The Weather”