3.8. The comparison of the optimum R models and PLS models
The developed RBFNN models for monitoring glucose and pH have been optimized by selecting characteristic length variables, the number of hidden nodes, and the spread constants and efficacious pretreatment methods. The effica cious spectra pretreatment methods for glucose and pH were without the pretreatment method and SNV method, the num bers of the characteristic wavelengths were 62 and 71, the suitable numbers of hidden nodes were 19 and 28. and the optimum spread constants were 0.53000 and 0.13000, respec- tively. The optimum RBFNN models with the optimized parameters were used for determining the glucose concentra- tion and the pH values of all the samples and the results are shown in Fig. 6. The correlation coefficient of the calibration set(Re) and the prediction set(Rp) of the optimum RBFNN model for monitoring glucose and pH were over 0.9000. The comparison of capability parameters between the optimum PLS models and RBFNN models are shown in Table 3. As can be seen, the Re and RMSEP of RBFNN model for mon itoring the glucose were much better than those of the PLS model. The RMSEP of RBFNN model for monitoring pH was lower than that of the PLS model, meaning that RBFNN has a better predictive capability. It was suggested that the non-linear modeling method was better than linear