查看文章

The aims of this study were to investigate the effect of different reference data extraction (colony-counting) and selection variable methods (Regression Coefficient: RC; Forward and Stepwise Multiple Regression: FMR and SMR) on the performance of PLSR and MLR model to predict TVC value in rainbow-trout fish fillets. TVC values were measured based on manual and digital image (OpenCFU, IMJ, and Photoshop) counting methods. The most and lowest prediction powers were obtained for Photoshop-PLSR and OpenCFU-PLSR, respectively (R²_p = 0.873 and 0.815; RMSEP = 0.761 and 0.884 Log₁₀CFU/g). In simplified-model FMR-MLR has superior performance (R²_p = 0.89 and RMSEP = 0.65 Log₁₀CFU/g). In simplified PLSR model group, RC-PLSR showed better performance (R²_p = 0.866 and RSMEP = 0.782). This distribution map of TVC load was generated by transferring the FMR …