A Machine-Learning Based Nonintrusive Smart Home Appliance Status Recognition

Pseudocode 4

Training and disaggregation process of the CNN-RNN (LSTM (mdl3))

(i)	Acquire the aggregate and ground truth signals for the selected parameter (p)
(ii)	Define: no. of CNN networks including hidden (CNNn), filters, LSTM networks including hidden and memory cells (LSTMn), 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 CNNn(ii)Iterate through LSTMn(iii)Iterate through each ds(iv)mdl3 converged  stop(2)Disaggregation(i)Pseudocode 1(3)mdl3 not converged(i)epochs = epochs + 1(ii)Return [(1) (i)]
	Otherwise: do(4) (next parameter): do (3) to (3).(5)Train and disaggregate all parameters:(i): return [(4)](ii): Exit