Research Article
A Machine-Learning Based Nonintrusive Smart Home Appliance Status Recognition
(1) | Begin: obtain preprocessed, formatted, and transformed training input aggregate data of series length secs according to Figure 7 | (2) | Obtain training target data of series length secs with redundancies removed | (3) | Train the network | (4) | Obtain preprocessed, formatted, and transformed validation/test input aggregate data of series length secs according to Figure 9 | (5) | Specify disaggregation window, | (6) | Slide trained network input through validation/test aggregate data by amount equal to disaggregation window | (7) | Repeat 6, until end of validation/test aggregate data series length | (8) | Use mean method sum up all results of disaggregation window movement to obtain disaggregated signal of series length TTt secs | (9) | Input 7 into trained classification network for appliance recognition | (10) | Repeat 1 to 9, until performance ⟶ 100% |
|