International Journal of Statistics and Applied Mathematics
  • Printed Journal
  • Indexed Journal
  • Refereed Journal
  • Peer Reviewed Journal

2021, Vol. 6, Issue 3, Part A

Potential of artificial neural networks as compared to discriminant analysis in the classification of mustard accessions using grain yield


Author(s): Mujahid Khan and BK Hooda

Abstract: The possibility of using four different models (LDA, QDA, RDA and MLP neural network trained by the back-propagation algorithm) for the classification of mustard accessions was investigated and performances of the optimal models were compared. The secondary data of 870 mustard accessions for 13 morphological attributes was collected from the Department of Genetics and Plant Breeding, Chaudhary Charan Singh Haryana Agricultural University, Hisar. The attribute grain yield (g/plant) was used as class attribute in this study. When considering predictive accuracy over an independent testing dataset, the MLP neural network trained by the back-propagation algorithm, being able to correctly predict about 91% of mustard accessions. The corresponding predictive accuracies for LDA, QDA and RDA were 87.0%, 88.9% and 88.9%, respectively.

Pages: 20-23 | Views: 684 | Downloads: 18

Download Full Article: Click Here

International Journal of Statistics and Applied Mathematics
How to cite this article:
Mujahid Khan, BK Hooda. Potential of artificial neural networks as compared to discriminant analysis in the classification of mustard accessions using grain yield. Int J Stat Appl Math 2021;6(3):20-23.

Call for book chapter
International Journal of Statistics and Applied Mathematics