My topic was fall detection (as in elderly people falling) specifically without using cameras or wearables. The idea was to take the CSI (basically what you see in the image) and just stuff it into some machine learning model to get a prediction as to whether someone fell in a given time frame, so I was trying to classify the signature of the falling "activity". From my literature survey, this has been done successfully with CSI. But as with a lot of research, it typically lacked practicality. Much of my work was implementing the firmware, data recording, processing, and so on. I also had to record a ton of falls (ouch) and label them. I ended up throwing away the CSI approach though, because of the noise reasons I mentioned. That was simply a deal breaker. I went with FMCW radar instead (and it worked pretty good).

Interesting. I didn't actually read into BFI details, thank you

to be fair, maybe. To pass FCC/CE regulation regarding EMC, it has to adhere to strict limits at 2.4 GHz (but I could also imagine for microwave ovens specifically that the allowed emissions are higher than for other devices, because 2.4 GHz is just the band it operates in. But idk, I didnt read the standard for those). But it does not mean that it may not radiate anything in that band.

Anyways, my observation was that it did interfere and the microwave was definitely closed. But also it was not 10m distance to the microwave, more like 2m, so relatively close. WiFi receivers are quite sensitive to be able to work with low received powers. So just a little emission is sufficient to interfere. You are probably not disturbing the communication itself, because OFDM is quite robust, but it certainly destroyed my use case (which operated on the whole CSI).

And there is definitely some stuff leaking, e.g. through radiated emissions on the wiring (the power line). But it is certainly not cooking anything. That's also what the regulation makes sure of.