Binary particle swarm optimization for variables selection optimization Taguchi's T method
Prediction analysis has drawn signi?cant interest in numerous ?elds Taguchi’s T-Method is a prediction tool that was practically developed to predict even with a limited sample data. It was developed explicitly for multivariate system prediction by relying on historical data as the baseline model an...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Penerbit UTM Press
2020
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/93320/1/NoliaHarudin2020_BinaryParticleSwarmOptimization.pdf http://eprints.utm.my/id/eprint/93320/ http://dx.doi.org/10.11113/matematika.v36.n1.1181 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Prediction analysis has drawn signi?cant interest in numerous ?elds Taguchi’s T-Method is a prediction tool that was practically developed to predict even with a limited sample data. It was developed explicitly for multivariate system prediction by relying on historical data as the baseline model and adapting the signal to noise ratio (SNR) as well as zero proportional concepts in strengthening its robustness. Orthogonal array (OA) in T-Method is a variable selection optimization technique in improving the prediction accuracy as well as helping to eliminate variables that may deteriorate the overall performance. However, the limitation of OA in dealing with higher multivariate data restrains the optimization accuracy. The binary particle swarm optimization used in this study helps to cater to the limitation of OA as well as optimizing the variable selection process for better prediction accuracy. A comparison between the T-Method+OA and T- Method+BPSO in four di?erent case studies shows that the T-Method+BPSO performs better with a higher coe?cient of determination (R2) value and means relative error (MRE) value compared to the T-Method+OA. The T-Method with the BPSO element as variables screening optimization is able to increase or even maintain the prediction accuracy for cases that are normally distributed, have a high R2value, and with low sample data. |
|---|