Office buildings occupancy analysis and prediction associated with the impact of the COVID-19 pandemic

. 2021 Nov 20;77:103557. doi: 10.1016/j.scs.2021.103557

Require:The training data: {x_i}^T ∈ Rⁿ and {t_i}^T ∈ R^m (x_i = [x_i1, x_i2,…, x_in]^T∈ Rⁿ and t_i = [t_i1, t_i2,…, t_in]^T∈ R^m)
Hidden node output function g(x) and the number of hidden nodes, L;
Ensure: The output weight vector, β
Random generation hidden node parameters (w_j, b_j), here j = 1, …,N;
Calculate the hidden-layer output matrix H;
Calculate the output weights β: β =H†T ;
End.