Previous Topic Back Forward Next Topic
Print Page Frank Dieterle
 
Ph. D. ThesisPh. D. Thesis 7. Results – Genetic Algorithm Framework7. Results – Genetic Algorithm Framework 7.4. Genetic Algorithm Framework – Conclusions7.4. Genetic Algorithm Framework – Conclusions
Home
News
About Me
Ph. D. Thesis
  Abstract
  Table of Contents
  1. Introduction
  2. Theory – Fundamentals of the Multivariate Data Analysis
  3. Theory – Quantification of the Refrigerants R22 and R134a: Part I
  4. Experiments, Setups and Data Sets
  5. Results – Kinetic Measurements
  6. Results – Multivariate Calibrations
  7. Results – Genetic Algorithm Framework
    7.1. Single Run Genetic Algorithm
    7.2. Genetic Algorithm Framework - Theory
    7.3. Genetic Algorithm Framework - Results
    7.4. Genetic Algorithm Framework – Conclusions
  8. Results – Growing Neural Network Framework
  9. Results – All Data Sets
  10. Results – Various Aspects of the Frameworks and Measurements
  11. Summary and Outlook
  12. References
  13. Acknowledgements
Publications
Research Tutorials
Downloads and Links
Contact
Search
Site Map
Print this Page Print this Page

7.4.   Genetic Algorithm Framework – Conclusions

In this chapter, a genetic algorithm was used for the optimization of neural networks by variable selection. It was shown that single runs of the GA are faced with irreproducible variable selections and with unstable predictions of the external validation data, which were even worse than the predictions by non-optimized neural networks. A genetic algorithm framework was suggested, which uses repeated runs of the GA. The predictions of the neural networks optimized by this framework were superior to the commonly used non-optimized neural networks and to all other calibration methods used before. It was also shown that the variable selection is reproducible and not subject to noise. Addi­tionally, it was demonstrated that the predictions are hardly influenced by interfering analytes rendering the combination of time-resolved measurements, the genetic algorithm framework for the variable selection and for the calibration open to the parallel quantification of more analytes using only one single sensor. The unique framework introduced in this works is not restricted to the calibration and variable selection of sensor signals, but can be used for the variable selection and multivariate calibration of virtually any data set as long as a sensible number of data is available.

 

Method

Calibration

Data Set

Validation

Data Set

R22

R134a

R22

R134a

Non-optimized Neural Networks

1.47

2.62

2.18

3.26

GA-NN (1st run)

2.13

2.75

2.32

2.93

GA-NN (2nd run)

2.19

2.87

2.63

3.35

GA-NN Framework

1.89

2.69

2.04

2.89

table 3:      Comparison of the rel. RMSE of the calibration and validation data in % for the genetic algorithm approaches and the non-optimized neural networks used in section 6.8.

Page 105 © Frank Dieterle, 03.03.2019 Navigation