Caring for the elderly and vulnerable people while preserving their privacy and independence is a challenging proposition. Reaching a panic button or calling for help may not be possible in an emergency, but constant supervision or camera surveillance is often neither practical nor considerate. Researchers from MIT CSAIL have been working on this problem for a few years and have come up with a possible solution called RF Diary. Using RF signals, a floor plan, and machine learning it can recognize activities and emergencies, through obstacles and in the dark. If this sounds familiar, it’s because it builds on previous research by CSAIL.
The RF system used is effectively frequency-modulated continuous-wave (FMCW) radar, which sweeps across the 5.4-7.2 GHz RF spectrum. The limited resolution of the RF system does not allow for the recognition of most objects, so a floor plan gives information on the size and location of specific features like rooms, beds, tables, sinks, etc. This information helps the machine learning model recognize activities within the context of the surroundings. Effectively training an activity captioning model requires thousands of training examples, which is currently not available for RF radar. However, there are massive video data sets available, so researchers employed a “multi-modal feature alignment training strategy” which allowed them to use video data sets to refine their RF activity captioning model.
There are still some privacy concerns with this solution, but the researchers did propose some improvements. One interesting idea is for the monitored person to give an “activation” signal by performing a specified set of activities in sequence.
Continue reading “Recognizing Activities Using Radar”
Blinking an LED is generally considered the hardware equivalent of the classic “Hello World” project. It’s a quick and simple test to show that you’ve got the basics worked out, and a launching point for bigger and better things. So why should it be any different in this glorious new Internet of Things era?
The “WiFi HDD LED” created by [Limbo] is essentially just that, a status LED that can be triggered remotely thanks to the WiFi capability of the ever-popular ESP8266. Don’t think there’s much use for a wireless LED that blinks when your computer’s hard drive is thrashing around? Maybe not, but it’s definitely worth checking out if you’re looking for a good way to get your feet wet in the world of ESP hacking.
On the hardware side, this is exactly what you’d expect: an LED hanging off the digital pin of an ESP8266 module. If you go with the bare ESP-01 like [Limbo], things are somewhat more complex due to the need for a voltage regulator, but if you’re using one of the more common ESP development boards then there’s nothing else you need to add. Really, as a proof of concept you could even use the built-in LED on those boards.
As you might imagine, this project is more about the software than the hardware. The code on both sides of the equation has been released as open source for your hacking pleasure, and is more capable than you’d probably expect. The LED is actually an extension of a system activity monitor that [Limbo] had previously developed and includes a binding function to make sure you’re talking to the right blinking ESP. It’s probably overkill for many purposes, but it’s a good example of how to do more robust UDP connections than we’re used to seeing.
This project is one of many that prove there’s more than one way to accomplish a particular goal, and that there’s something to be learned from even the most eccentric of hacks.
Continue reading “Blink An LED On The Internet Of Things”
A while ago [Frank Zhao] built a computer in an aquarium. It’s exactly what you would expect – a bunch of parts stuffed into a container filled with mineral oil. Yes, there’s an i7 and a GTX970 in there, but there’s also a bunch of neopixels and a neat little bubbling treasure chest. That wasn’t enough for [Frank], and he wanted to add a HDD activity monitor. What’s the most absurd activity monitor for an SSD? An old platter-based drive, of course.
The build is relatively simple and something [Frank] put together from spare parts in a day. After cracking open an old PATA hard drive, the voice coil for the hard drive arm was connected to the motherboard’s HDD activity signal through a few MOSFETs. The platter motor is controlled by an MTD6501 motor driver, set to spin up when the circuit is on.
It’s a kludge as far as controlling the components of a hard drive go, but that’s not really the point. It’s just a neat project to show when the SSD in the aquarium computer is being accessed. That said, the activity monitor is currently disconnected because the old HDD is so freakin’ loud. It looks really cool, though.
The Upverter team loves their FitBit activity tracking devices, but wanted access to raw data. They decided to build their own Open Activity Tracker that would pump data onto an SD card or to a Bluetooth device for processing.
The device uses MPU-9150 motion tracking IC to gather information on movement. This chip combines an accelerometer, gyro, and compass. It also does on-board processing, providing useful data to your host processor over I2C. The only bad news is that it’s a LGA package, which aren’t fun to solder by hand.
The design also has a SD card, Bluetooth module, pressure sensor, and e-ink display. These are all connected to a low power ARM microcontroller.
The team has been webcasting their design sessions, and tonight [Eric Evenchick] (that’s me) will be joining them as they try to cram all of these components onto a PCB. You can watch the live webcast starting at 8:30pm Eastern.
You can watch the previous design sessions after the break.
Continue reading “Open Activity Tracker Webcast”