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.
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?”
We’ve seen a number of heart rate monitoring projects on Hackaday, but [Peter’s] electrocardiography (ECG) Instructable really caught out attention.
If you’ve followed Hackaday for any period of time, you’re probably already somewhat familiar with the hardware needed to record the ECG. First, you need a high input impedance instrumentation amplifier to pick up the millivolt signal from electrical leads carefully placed on the willing subject’s body. To accomplish this, he used an AD8232 single-lead ECG module (we’ve actually seen this part used to make a soundcard-based ECG). This chip has a built-in instrumentation amplifier as well as an optional secondary amplifier for additional gain and low-pass filtering. The ECG signal is riddled with noise from mains that can be partially attenuated with a simple low-pass filter. Then, [Peter] uses an Arduino Nano to sample the output of the AD8232, implement a digital notch filter for added mains noise reduction, and display the output on a 2.8″ TFT display.
Other than the circuit itself, two things about his project really caught our attention. [Peter] walks the reader through all the different safety considerations for a commercial ECG device and applies these principles to his simple DIY setup to ensure his own safety. As [Peter] put it, professional medical electronics should follow IEC 60601. It’s a pretty bulky document, but the main tenets quoted from [Peter’s] write-up are:
- limiting how much current can pass through the patient
- how much current can I pass through the patient?
- what electrical isolation is required?
- what happens if a “component” fails?
- how much electromagnetic interference can I produce?
- what about a defibrillator?
[Peter] mentions that his circuit itself does not fully conform to the standard (though he makes some honest attempts), but lays out a crude plan for doing so. These include using high-valued input resistors for the connections to the electrodes and also adding a few protection diodes to the electrode inputs so that the device can withstand a defibrillator. And of course, two simple strategies you always want to follow are using battery power and placing the device in a properly shielded enclosure.
[Peter] also does a great job breaking down the electrophysiology of the heart and relates it to terms maybe a bit more familiar to non-medical professionals. Understanding the human heart might be a little less intimidating if we relate the heart to a simple voltage source like a battery or maybe even a function generator. You can imagine the ions in our cells as charger carriers that generate electrical potential energy and nerve fibers as electrical wires along which electrical pulses travel through the body.
Honestly, [Peter] has a wealth of information and tools presented in his project that are sure to help you in your next build. You might also find his ECG simulator code really handy and his low-memory display driver code helpful as well. Cool project, [Peter]!
Measuring ECG is something that is near and dear to my heart (sorry, couldn’t resist). Two of my own projects that were featured on Hackaday before I became a writer here include a biomedical sensor suite in Arduino shield form factor, and a simple ECG built around an AD623 instrumentation amplifier.
The internet has given us plenty of cool robotics projects, but we don’t think we’ve seen one zipline before. At least not until now.
This cool little ziplining robot is courtesy of the folks over at [Tart Robotics]. As they described it, the robot moves using a 4-bar linkage mechanism with the motor’s torque “transferred to the arm mechanisms through a pair of bevel gears and a worm drive.” Even cooler, the robot is activated by clapping. The faster you clap, the faster the robot moves. That’s sure to wow your friends at your next virtual hacker meetup.
They had to do a bit of custom 3D printing work to get a few of the Lego components to connect with their non-Lego off-the-shelf bits, so that took a bit of time. Specifically, they had some cheap, non-branded DC motors that they used that did not naturally mate with the Lego Technic components used to create the rest of the robot’s body. Nothing a few custom 3D printing jobs couldn’t solve.
It always amazes us what cool contraptions you can put together with a few Lego blocks. What’s your favorite Lego project?
Continue reading “Lego Ziplining Robot Climbs For Claps”
[familylovermommy] has been homeschooling her kids even before the pandemic, so she’s pretty well-versed on being a learning coach and a teacher. One of the activities she designed for her boys has them creating 3D models using Tinkercad. In the spirit of openness and cultivating freethinking, she did not give them very many constraints. But rather, gave them the liberty to creatively design whatever scene they imagined.
In the Instructable, she shares her sons’ designs along with instructions to recreate the models. The designs as you’ll see are pretty extensive, so she embedded the Tinkercad designs directly into it. You can even see a number of video showcases as well.
This is a really cool showcase of some pretty stellar workmanship. Also, maybe a bit of inspiration for some of our readers who are creating work from home activities of their own.
While you’re at it, check out some of these other work-from-home hacks.
Continue reading “Distance Learning Land”
Baby monitors are cool, but [Ish Ot Jr.] wanted his to only transmit sounds that required immediate attention and filter any non-emergency background noise. Posed with this problem, he made a baby monitor that would only send alerts when his baby was crying.
For his project, [Ish] used an Arduino Nano 33 BLE Sense due to its built-in microphone, sizeable RAM for storing large chunks of data, and it’s BLE capabilities for later connecting with an app. He began his project by collecting background noise using Edge Impulse Studio’s data acquisition functionality. [Ish] really emphasized that Edge Impulse was really doing all the work for him. He really just needed to collect some test data and that was mostly it on his part. The work needed to run and test the Neural Network was taken care of by Edge Impulse. Sounds handy, if you don’t mind offloading your data to the cloud.
[Ish] ended up with an 86.3% accurate classifier which he thought was good enough for a first pass at things. To make his prototype a bit more “finished”, he added some status LEDs, providing some immediate visual feedback of his classifier and to notify the caregiver. Eventually, he wants to add some BLE support and push notifications, alerting him whenever his baby needs attention.
We’ve seen a couple of baby monitor projects on Hackaday over the years. [Ish’s] project will most certainly be a nice addition to the list.
[ananords] and his girlfriend wanted to make a simple and easy to use music player for her grandmother. Music players like CD players and MP3s have gotten just a bit too difficult to handle, so they wanted to find a much simpler solution.
They conceived the idea of creating a little jukebox called Juuk, with a simple and easy to use interface. They created individual RFID cards with the artist’s photo on the front face, making it easy to select different options from the music library. Juuk has a built-in RFID reader that will recognize each RFID card and play the appropriate musical number from an SD card.
This simple interface is much more user-friendly than those awful touchscreen devices that we’re all forced to fiddle with today and also has a cool retro appeal that many of our readers are sure to appreciate. Juuk also has a pretty ergonomic interface with a big, easy-to-use knob for controlling the volume and two appropriately illuminated buttons, one green and one red, for simple stop and play options.
We love when our hacks are able to blend form with function and emphasize high usability. Check out some of our other assistive tech on the blog.
Continue reading “Juuke – An RFID Music Player For Elderly And Kids”