I decided to update my NILM research website today. I added my NILM publications. Hopefully in the next month I can add some algorithm accuracy results to the website, too.
One other thing to note is that come April 1 (2014) I will be making available a second year’s worth of data for AMPds. I am also thinking of having a different file format. Instead of having files based on load (e.g. CDE.csv, etc) with measurements as columns . I would have files based on measurement (e.g. A.csv, P.csv, etc) with loads as columns. This would make it easier to load and use. Also, Nipun Batra pointed out an error with the water meter data where the pulse counters were reset when I installed new water meters. The old meters pulsed every cubic-foot and the new meters pulse every 0.5 litres. The pulse counter unit caused what looks like a rest because of the unit conversion from the old pulse measurements to the new 0.5 litres measurements. I had completely forgot about this. I will be fixing this problem when year 2 is released.