• WhatAmLemmy@lemmy.world
      link
      fedilink
      English
      arrow-up
      5
      ·
      edit-2
      16 hours ago

      I believe it would require a specific ML model to be trained, due to the slight variances in the hardware and each environment. This means you would also need the hardware to run the model 24/7.

      It could definitely be done, and I suspect the fascist surveillance state already has projects to weaponize it; they’re probably also building the capability into the 6G or 7G spec, so they can monitor everything, everyone, everywhere, 24/7 from cell towers alone.

      • Farid@startrek.website
        link
        fedilink
        English
        arrow-up
        1
        ·
        16 hours ago

        Oh man, that sounds way inefficient. Guess I’ll stick to the human presence sensors, then…

        • WhatAmLemmy@lemmy.world
          link
          fedilink
          English
          arrow-up
          2
          ·
          13 hours ago

          ML models trained for a specific task are not necessarily inefficient. It’d probably be more efficient to add a single pi or container for “sensing” than adding a dozen physical sensors all over the place.

          But it also looks like a new wifi standard will include some non-ML sensing capability on router anyway, but probably won’t be available till the 2030’s. I’d expect the ML approach to have solid options within a couple of years.