It's time to replace my ageing home automation server with a new PC. You
can tell that the old one is dying because it's started to slur its
words as it announces various events of interest like a car coming down
the driveway, or the fact that it announces an event 10 minutes after it
happened. I think the hard drive is provably failing again, seems to be
a design fault of that old small form factor Dell where it cooks the
hard drive.
Anyway, being somewhat conscious of the power consumed by my main
machine (a dual-proc Xeon 3.2GHz), I've been waiting anxiously for the
Pentium M or Core Duo chips to reach the desktop. Motherboards for both
have been around for sometime and there's the odd news story about a
manufacturer in Japan actually shipping complete systems but until now
there's been very little over here beyond the bare components and a DIY
assembly job.
I've been working on home automation for over 15 years and I'm close to achieving my goal which is a house that understands where everyone is at all times, can predict where you are going next and can control lighting, heating and other systems without you having to do or say anything. That's a true "smart home".
An overview of the many sensors I've experimented with for home automation including my favorite under-floor strain gauge, through all the usual PIR, beam and contact sensors to some more esoteric devices like an 8x8 thermal camera.
Why automated learning is hard for a smart home. The perils of over-fitting, under-fitting and how the general unpredictable nature of life makes it hard to build a system that learns your behavior.
In a home automation system we often want to convert a measurement into a probability. The ATAN curve is one of my favorite curves for this as it's easy to map overything onto a 0.0-1.0 range.
Several years ago we did a major remodel. I did all of the finish electrical myself and supervised all of the rough-in electrical. I also put in all of the electrical system and water in our barn. I have opinions ...
An if-this-then-that style rules machine is insufficient for lighting control. This state machine accomplishes 90% of the correct behavior for a light that is controlled automatically and manually in a home automation system.