A Machine-Learning Based Nonintrusive Smart Home Appliance Status Recognition

Pseudocode 2

Training and disaggregation process of the MPS-CNN (mdl1)

(i)	Acquire the aggregate and ground truth signals for the selected parameter (p)
(ii)	Define: no. of parallel CNN networks (pn), hidden layers in each pn, filters in each pn, dense layers (ds), epochs, and early stopping condition
(iii)	Initialize all weights
	While parameter (p) is True: do(1)Epochs = 0 (train)(i)Iterate through each pn(ii)Concatenate all pn(iii)Iterate through each ds(iv)mdl1 converged ⟶ stop(2)Disaggregation(i)Pseudocode 1(3)mdl1 not converged(i)epochs = epochs + 1(ii)Return [(1) (i)]
	Otherwise: do(4) (next parameter): do (1) to (3).(5)Train and disaggregate all parameters:(i): return [(4)](ii): Exit