The results illustrated that the proposed RSM-GHS is as uncomplicated as the RSM but performed better, where fewer errors and better correlation was observed (R = 0.95, MAE = 18.09 (ton/day), RMSE = 25.16 (ton/day)) compared to the ANN (R = 0.91, MAE = 20.17 (ton/day), RMSE = 33.09 (ton/day)) and RSM (R = 0.91, MAE = 20.06 (ton/day), RMSE = 31.92 (ton/day)) for all types of input variables.
A better correlation was observed as to potentially contractile muscle tissue elements and the interstitial cells of Cajal.
In general a better correlation was observed between the serum NCA level and the number of maturing myeloid cells than with the number of polymorphs.
In other words, it appears that a better correlation was observed between SAGE and oligonucleotide arrays, than between both DNA microarray methods.
Curiously, a better correlation was observed between all of the other phenylpropanoid genes and CGA, than between HQT and CGA, as calculated using Pearson product moment correlation coefficients.
In other words, it appears that a better correlation was observed between MMTV-ErbB2 with the other two models, than between p53-null and C3(1)-SV40 tag transgenic mouse mammary gland models.
In general, a better expression correlation was observed for high copy number tags in the MPSS and RL-SAGE libraries with their corresponding genes on the oligoarray.
Additionally, a stronger correlation was observed between HSUVs and better-seeing eye VA compared to worse-seeing eye VA.
Although no significant correlation was observed between XPD genotype and objective response, a trend toward better response was observed in patients with XPD polymorphism at codon 312.
