Skip to main content

Table 4 Actual and predicted lipase activity by ANN and RSM models along with absolute deviation, R2 and AAD

From: A modeling study by response surface methodology and artificial neural network on culture parameters optimization for thermostable lipase production from a newly isolated thermophilic Geobacillus sp. strain ARM

Actual activity

ANN predicted activity

ANN absolute deviation

RSM predicted activity

RSM absolute deviation

0.2063

0.2063

0

0.2061

0.000969

0

0

0

0.00019

0

0.0207

0.0208

0.0048

0.0209

0.0097

0

0.0001

0

0.0002

0

0

0.0002

0

0.0002

0

0.0291

0.0291

0

0.0289

0.0069

0

0

0

0.0002

0

0.0886

0.0886

0

0.0888

0.0023

0.0724

0.0724

0

0.0722

0.0028

0

0

0

0.0002

0

0.0907

0.0908

0.0011

0.0909

0.0022

0.1945

0.1945

0

0.1947

0.001

0.04

0.04

0

0.04

0

0.0229

0.0227

0.0087

0.0229

0

0.0457

0.0457

0

0.0457

0

0.0551

0.0552

0.0018

0.0551

0

0

0

0

0

0

0.0841

0.084

0.0012

0.0841

0

0.0675

0.0677

0.003

0.0675

0

0

0

0

0

0

0.0851

0.0851

0

0.0851

0

0.0281

0.028

0.0044

0.0281

0

0

0

0

0

0

0

0

0

0

0

0.0467

0.0467

0

0.0465

0.0043

0

0.001

0

0.0002

0

0.0693

0.0692

0.0014

0.0691

0.0029

0.0792

0.0795

0.0038

0.0794

0.0025

0.0996

0.0992

0.004

0.0994

0.002

  1. ANN training set R2 = 1
  2. ANN training set AAD = 0.1%
  3. RSM R2 = 1
  4. RSM AAD = 0.129%
  5. ANN testing set R 2 = 1
  6. ANN testing set AAD = 0.23117%
  7. ANN training set: normal and italic (center points) numbers
  8. ANN testing set: bold numbers