If you find "wave hunting" this interesting but don't have a SDR / receiver of your own, there are plenty of (free to use) WebSDRs to get started: http://websdr.org/
For those of you already set up to receive or send WSPR, FT8, or CW (Morse code), make sure you’re receiving and sending reports tomorrow during and around the eclipse (1200-2200 UTC)
> The Simulated Emergency Test (SET) is a Canada-wide exercise in emergency communications, which is administered by Radio Amateurs of Canada’s Community Services Officer and Section Managers.This year ‘s event is known as “Operation Dark Skies” and will be held in two parts which are described (here).
The HN hug strikes again! What I saw before it went down was pretty amazing though, and definitely something I will be returning to later when the heat dies down.
Looks like all the data is in a fairly decently scrapable format. Could one, in theory at least, add auto-identificaton to an SDR app?
Is there an (possibly ML) algorithm that says "take this single example picture and tell me if there is a match(Which could be scaled differently) in this other picture"?
Are there any ML approaches to identifying signals? Since using a receiver that produces sound given a FM/SSB demodulation of whatever true modulation is used, or visually inspecting a waterfall certainly has limitations.
My students Dianne, Pauli, Mikko and Juho tried [1] this. They wrote a blog [2] and a git repository [3]. It's not a ready to use product, but an exploration and learning journey to using machine learning for identifying signals.
Multiple steps are required to get to readable or audible output: identifying a signal, identifying modulation and demodulating.
Yes of course, but anybody doing anything non-trivial is selling it to the government and not writing about it online. Using the spectrum or waterfall as the input to an RFML system is very common and in my experience works pretty well. A lot of systems also train on I/Q data. Usually these systems are designed to be trained on signals that are relevant to a specific mission. So a product might look like both a platform for annotating and training a model as well as deploying it, usually as a plug-in into a separate expensive SIGINT platform. The biggest products I'm aware of aren't even advertised and last I heard cost in the six figures.
Rohde & Schwarz ran a contest on this idea a while ago. I can't find a link with a quick google, but I'm pretty sure I'm not making it up -- if anyone here knows more I'd love to know what came of that.
ML feels like an overkill for a single signal. If you want to process large, wideband scans, you could iterate over peaks and check things like: does phase shift create any interesting set of points, does PLL find consistent amplitude keying, does the frequency move around the centre. That covers 99% of what you're going to find in the wild. The first part (transform the signal) is definitely not great for ML, but the second part (does the result look like set of points / digital on/off key / voice) could be classified that way.
Automatic classifiers tend to look for power above the background noise and then AM demodulate the signal around it. That demodulated signal, or video as it's called, is centered around 0 Hz and can be matched against a database of spectrum masks for various modulations, baud rates and other parameters.
No neural nets required. Just good old regression.
