AI Powered Coffee Maker Knows A Bit Too Much About You

September 9, 2021 by Dave Rowntree 20 Comments

People keep warning that Skynet and the great robot uprising is not that far away, what with all this recent AI and machine-learning malarky getting all the attention lately. But we think going straight for a terminator robot army is not a very smart approach, not least due to a lack of subtlety. We think that it’s a much better bet to take over the world one home appliance at a time, and this AI Powered coffee maker might just well be part of that master plan.

Raspberry Pi Zero sitting atop the custom nixie tube driver PCB — PCB stackup with Pi Zero sat atop the driver / PSU PCBs

[Mark Smith] has taken a standard semi-auto espresso maker and jazzed it up a bit, with a sweet bar graph nixie tube the only obvious addition, at least from the front of the unit. Inside, a Raspberry Pi Zero sits atop his own nixie tube hat and associated power supply. The whole assembly is dropped into a 3D printed case and lives snuggled up to the water pump.

The Pi is running a web application written with the excellent Flask framework, and also an additional control application written in python. This allows the user to connect to the machine via Ethernet and see its status. The smarts are in the form of a simple self-grading machine learning algorithm, that takes a time series as an input (in this case when you take your shots of espresso) and after a few weeks of data, is able to make a reasonable prediction as to when you might want it in the future. It then automatically heats up in time for you to use the machine, when you usually do, then cools back down to save energy. No more pointless wandering around to see if the machine is hot enough yet – as you can just check the web page and see from the comfort of your desk.

But that’s not all [Mark] has done. He also improved the temperature control of the water boiler, and added an interlock that prevents the machine from producing a shot until the water temperature is just so. Water level is indicated by the glorious bar graph nixie tube, which also serves a few other user indication duties when appropriate. All in all a pretty sweet build, but we do add a word of caution: If your toaster starts making an unreasonable number of offers of toasted teacakes, give it a wide berth.

GitHub Copilot And The Unfulfilled Promises Of An Artificial Intelligence Future

August 2, 2021 by Maya Posch 36 Comments

In late June of 2021, GitHub launched a ‘technical preview’ of what they termed GitHub Copilot, described as an ‘AI pair programmer which helps you write better code’. Quite predictably, responses to this announcement varied from glee at the glorious arrival of our code-generating AI overlords, to dismay and predictions of doom and gloom as before long companies would be firing software developers en-masse.

As is usually the case with such controversial topics, neither of these extremes are even remotely close to the truth. In fact, the OpenAI Codex machine learning model which underlies GitHub’s Copilot is derived from OpenAI’s GPT-3 natural language model, and features many of the same stumbles and gaffes which GTP-3 has. So if Codex and with it Copilot isn’t everything it’s cracked up to be, what is the big deal, and why show it at all?

Continue reading “GitHub Copilot And The Unfulfilled Promises Of An Artificial Intelligence Future” →

Smart Camera Based On Google Coral

June 30, 2021 by Bryan Cockfield 8 Comments

As machine learning and artificial intelligence becomes more widespread, so do the number of platforms available for anyone looking to experiment with the technology. Much like the single board computer revolution of the last ten years, we’re currently seeing a similar revolution with the number of platforms available for machine learning. One of those is Google Coral, a set of hardware specifically designed to take advantage of this new technology. It’s missing support to work with certain hardware though, so [Ricardo] set out to get one working with a Raspberry Pi Zero with this smart camera build based around Google Coral.

The project uses a Google Coral Edge TPU with a USB accelerator as the basis for the machine learning. A complete image for the Pi Zero is available which sets most of the system up right away including headless operation and includes a host of machine learning software such as OpenCV and pytesseract. By pairing a camera to the Edge TPU and the Raspberry Pi, [Ricardo] demonstrates many of its machine learning capabilities with several example projects such as an automatic license plate detector and even a mode which can recognize whether or not a face mask is being worn, and even how correctly it is being worn.

For those who want to get into machine learning and artificial intelligence, this is a great introductory project since the cost to entry is so low using these pieces of hardware. All of the project code and examples are available on [Ricardo]’s GitHub page too. We could even imagine his license plate recognition software being used to augment this license plate reader which uses a much more powerful camera.

Speech Recognition On An Arduino Nano?

May 26, 2021 by Orlando Hoilett 24 Comments

Like most of us, [Peter] had a bit of extra time on his hands during quarantine and decided to take a look back at speech recognition technology in the 1970s. Quickly, he started thinking to himself, “Hmm…I wonder if I could do this with an Arduino Nano?” We’ve all probably had similar thoughts, but [Peter] really put his theory to the test.

The hardware itself is pretty straightforward. There is an Arduino Nano to run the speech recognition algorithm and a MAX9814 microphone amplifier to capture the voice commands. However, the beauty of [Peter’s] approach, lies in his software implementation. [Peter] has a bit of an interplay between a custom PC program he wrote and the Arduino Nano. The learning aspect of his algorithm is done on a PC, but the implementation is done in real-time on the Arduino Nano, a typical approach for really any machine learning algorithm deployed on a microcontroller. To capture sample audio commands, or utterances, [Peter] first had to optimize the Nano’s ADC so he could get sufficient sample rates for speech processing. Doing a bit of low-level programming, he achieved a sample rate of 9ksps, which is plenty fast for audio processing.

To analyze the utterances, he first divided each sample utterance into 50 ms segments. Think of dividing a single spoken word into its different syllables. Like analyzing the “se-” in “seven” separate from the “-ven.” 50 ms might be too long or too short to capture each syllable cleanly, but hopefully, that gives you a good mental picture of what [Peter’s] program is doing. He then calculated the energy of 5 different frequency bands, for every segment of every utterance. Normally that’s done using a Fourier transform, but the Nano doesn’t have enough processing power to compute the Fourier transform in real-time, so Peter tried a different approach. Instead, he implemented 5 sets of digital bandpass filters, allowing him to more easily compute the energy of the signal in each frequency band.

The energy of each frequency band for every segment is then sent to a PC where a custom-written program creates “templates” based on the sample utterances he generates. The crux of his algorithm is comparing how closely the energy of each frequency band for each utterance (and for each segment) is to the template. The PC program produces a .h file that can be compiled directly on the Nano. He uses the example of being able to recognize the numbers 0-9, but you could change those commands to “start” or “stop,” for example, if you would like to.

[Peter] admits that you can’t implement the type of speech recognition on an Arduino Nano that we’ve come to expect from those covert listening devices, but he mentions small, hands-free devices like a head-mounted multimeter could benefit from a single word or single phrase voice command. And maybe it could put your mind at ease knowing everything you say isn’t immediately getting beamed into the cloud and given to our AI overlords. Or maybe we’re all starting to get used to this. Whatever your position is on the current state of AI, hopefully, you’ve gained some inspiration for your next project.

Self-Driving Or Mind Control? Which Do You Prefer?

May 24, 2021 by Orlando Hoilett 9 Comments

We know you love a good biohack as much as we do, so we thought you would like [Tony’s] brainwave-controlled RC truck. Instead of building his own electroencephalogram (EEG), he thought he would use NeuroSky’s MindWave. EEGs are pretty complex, multi-frequency waves that require some fairly sophisticated circuitry and even more sophisticated signal processing to interpret. So, [Tony] thought it would be nice to off-load a bit of that heavy-lifting, and luckily for him, the MindWave headset is fairly hacker-friendly.

EEGs are a very active area of research, so some of the finer details of the signal are still being debated. However, It appears that attention can be quantified by measuring alpha waves which are EEG content between 8-10 Hz. And it seems as though eye blinks can be picked from the EEG as well. Conveniently, the MindWave exports these energy levels to an accompanying smartphone application which [Tony] then links to his Arduino over Bluetooth using the ever-so-popular HC-05 module.

To control the car, he utilized the existing remote control instead of making his own. Like most people, [Tony] thought about hooking up the Arduino pins to the buttons on the remote control, thereby bypassing the physical buttons, but he noticed the buttons were a bit smaller than he was comfortable soldering to and he didn’t want to risk damaging the circuit board. [Tony’s] RC truck has a pistol grip transmitter, which inspired a slightly different approach. He mounted the servo onto the controller’s wheel mechanism, allowing him to control the direction of the truck by rotating the wheel using the servo. He then fashioned another servo onto the transmitter such that the servo could depress the throttle when it rotates. We thought that was a pretty nifty workaround.

Cool project, [Tony]! We’ve seen some cool EEG Hackaday Prize entries before. Maybe this could be the next big one.

Continue reading “Self-Driving Or Mind Control? Which Do You Prefer?” →

AI Makes Linux Do What You Mean, Not What You Say

April 20, 2021 by Al Williams 30 Comments

We are always envious of the Star Trek Enterprise computers. You can just sort of ask them a hazy question and they will — usually — figure out what you want. Even the automatic doors seemed to know the difference between someone walking into a turbolift versus someone being thrown into the door during a fight. [River] decided to try his new API keys for the private beta of an AI service to generate Linux commands based on a description. How does it work? Watch the video below and find out.

Some examples work fairly well. In response to “email the Rickroll video to Jeff Bezos,” the system produced a curl command and an e-mail to what we assume is the right place. “Find all files in the current directory bigger than 1 GB” works, too.

Continue reading “AI Makes Linux Do What You Mean, Not What You Say” →

AI Upscaling And The Future Of Content Delivery

April 5, 2021 by Tom Nardi 29 Comments

The rumor mill has recently been buzzing about Nintendo’s plans to introduce a new version of their extremely popular Switch console in time for the holidays. A faster CPU, more RAM, and an improved OLED display are all pretty much a given, as you’d expect for a mid-generation refresh. Those upgraded specifications will almost certainly come with an inflated price tag as well, but given the incredible demand for the current Switch, a $50 or even $100 bump is unlikely to dissuade many prospective buyers.

But according to a report from Bloomberg, the new Switch might have a bit more going on under the hood than you’d expect from the technologically conservative Nintendo. Their sources claim the new system will utilize an NVIDIA chipset capable of Deep Learning Super Sampling (DLSS), a feature which is currently only available on high-end GeForce RTX 20 and GeForce RTX 30 series GPUs. The technology, which has already been employed by several notable PC games over the last few years, uses machine learning to upscale rendered images in real-time. So rather than tasking the GPU with producing a native 4K image, the engine can render the game at a lower resolution and have DLSS make up the difference.

The implications of this technology, especially on computationally limited devices, is immense. For the Switch, which doubles as a battery powered handheld when removed from its dock, the use of DLSS could allow it to produce visuals similar to the far larger and more expensive Xbox and PlayStation systems it’s in competition with. If Nintendo and NVIDIA can prove DLSS to be viable on something as small as the Switch, we’ll likely see the technology come to future smartphones and tablets to make up for their relatively limited GPUs.

But why stop there? If artificial intelligence systems like DLSS can scale up a video game, it stands to reason the same techniques could be applied to other forms of content. Rather than saturating your Internet connection with a 16K video stream, will TVs of the future simply make the best of what they have using a machine learning algorithm trained on popular shows and movies?

Continue reading “AI Upscaling And The Future Of Content Delivery” →