Matlab 8.3.0.532 r2014a software

The work was conducted in three separate main steps: (i) the bacterial data points of Pseudomonas spp. in various food products (beef, pork, and poultry) and culture media were gathered from the ComBase database (www.combase.cc, accessed on 1 June 2021), (ii) data processing (data ingestion, standardisation, and featurisation) was performed in Matlab 8.3.0.532 (R2014a) software (MathWorks Inc., Natick, MA, USA), and (iii) various machine learning-based regression methods including support vector regression, Gaussian process regression, random forest regression, and decision tree regression were employed for estimation of the Pseudomonas spp. population using Matlab 8.3.0.532 (R2014a) software. The evaluation of machine learning-based regression methods involved assessing their estimation power using several metrics, including the coefficient of determination, root mean square error, bias factor, and accuracy factor. Figure 1 presents a flow chart illustrating the main steps followed in the current study. The subsequent subsections provide detailed descriptions of each stage in this work.

Shimadzu UV1800 double beam UV/Visible spectrophotometer (Japan) with 1 cm quartz cells. Matlab^® (8.3.0.532) R2014a software (The Mathworks, Natick, USA) with PLS toolbox 2.1 was used for the mean centering spectrophotometric method calculation.