Back Propagation Neural Network Model for Predicting the Performance of Immobilized Cell Biofilters Handling Gas-Phase Hydrogen Sulphide and Ammonia

Table 4

Weights and bias terms obtained after network training.

(a) Input to hidden layer weights

	𝑊11	𝑊12
Unit flow, per min	−6.61	−8.00
Concentration, ppmv	2.49	−26.6
Bias term	−8.19	1.95

𝑊₁₁,𝑊₁₂: Weights between neurons in input layer and hidden layer.

(b) Hidden to output layer weights

	RE, %
𝑊21	1.56
𝑊22	2.28
Bias term	−1.03

𝑊₂₁,𝑊₂₂: Weights between neurons in hidden layer and output layer.