2.6.3. Biomass concentration determination
The residue obtained from the centrifuged sample was used for the Dry Cell Weight (DCW) analysis denoted as XAV-939 concentration. The residue was dried in an electric oven (Manufacturing Resource Corporation), in a preweighed centrifuge tube, at 80 °C for 24 h. It was later cooled in a desiccator. The biomass concentration was calculated on the basis of the volume of the fresh sample as the difference between the weight of the empty tube and the final weight of the tube plus the dried biomass after drying and cooling .
2.7. Modeling and optimization studies
2.7.1. RSM analysis
2.7.2. ANN analysis
2.7.3. Verification of estimated data
22.214.171.124. Evaluation of model predictability in artificial neural network (ANN)
In order to perform a supervised training, a way in which the ANN output error between the actual and the predicted output could be evaluated is dendrites required. Eqs. (2) and (3) show Mean Squared Error (MSE) and RMSE as a popular measure for model predictability :equation(2)MSE=1n∑i=1n(yi−ydi)2equation(3)RMSE=MSE1/2RMSE=MSE1/2where, n is the number of points, yi is the predicted value obtained from the neural network model, ydi is the actual value.