Skip to main content

Table 3 Comparison of response surface methodology (RSM) and artificial neural network (ANN) models

From: Optimization of salicylic acid and chitosan treatment for bitter secoiridoid and xanthone glycosides production in shoot cultures of Swertia paniculata using response surface methodology and artificial neural network

Parameters

Amarogentin (I)

Swertiamarin (II)

Mangiferin (III)

RSM

ANN

RSM

ANN

RSM

ANN

Root mean square error (RMSE)

0.004624

0.003351

0.046971

0.02104

0.03464

0.014931

Absolute average deviation (AAD)

0.089432

0.089124

1.296331

1.300059

0.572083

0.568817

Regression coefficient (r2)

99.8%

99.9%

99.9%

100%

99.7%

100%