Table 13 Comparison of ANN and RSM Performance.

From: Machine learning and response surface analysis of mean drop size and dispersed phase holdup in an L-shaped pulsed sieve plate column

Output variable

Model

R2

MSE

d32h

ANN

0.9950

0.000314

RSM

0.9393

d32v

ANN

0.9970

0.000451

RSM

0.9820

\(\:\text{D}\text{P}\text{H}\:\text{h}\)

ANN

0.9900

0.000019

RSM

0.9304

\(\:\text{D}\text{P}\text{H}\:\text{v}\)

ANN

0.9822

0.000001

RSM

0.8839