Matlab r2019a version 9

A BioView sensor (DELTA Lights and Optics, Venlighedsvej 4, 2970, Horsholm, Denmark) was used to collect 2D-fluorescence spectra. A fluorescence probe was attached to the sterilized bioreactor over a light guide, which connected with a 25 mm standard port. This standard port has a quartz glass window to interface with the bioreactor. Therefore, there was no contact between the fermenting medium and the actual probe. A BioView sensor measured several combinations of excitation (270–550) and emission (310–590). The observed fluorescence spectrum had 120 intensity values of wavelength combinations measured in intervals of 20 nm. Off-line measured results and the analogous fluorescence spectra data were utilized to develop calibration models of PLSR and ANN for the prediction of LPA6 and LCGG cell counts and concentrations of glucose and lactic acid. Software Unscrambler X version 10.3 (CAMO Software AS., Oslo, Norway) and MATLAB R2019a version 9.6 (The MathWorks Inc. 2019, Natick, MA, USA) were utilized to calibrate the models and to test and validate their predictive capabilities.

To build calibration and prediction models, Unscrambler X version 10.3 (CAMO Software AS., Oslo, Norway) and MATLAB R2019a version 9.6 (The MathWorks Inc. 2019, Natick, MA, USA) were utilized. Graphs were sketched with the same version of Matlab, which was used for model calibrations.