Identification of virtual plants using bayesian networks based on parametric L-system

Suhartono, Suhartono (2018) Identification of virtual plants using bayesian networks based on parametric L-system. International Journal of Advances in Intelligent Informatics, 4 (1). pp. 40-52. ISSN 2442-6571

[img]
Preview
Text (full text)
2526.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (1MB) | Preview
Full text available at: http://ijain.org/index.php/IJAIN/article/view/157

Abstract

Parametric L-System is a method for modelling virtual plants. Virtual plant modelling consists of components of axiom and production rules for alphabets in parametric L-System. Generally, to get the alphabet in parametric L-System, one would guess the production rules and perform a modification on the axiom. The objective of this study was to build virtual plant that was affected by the environment. The use of Bayesian networks was to extract the information structure of the growth of a plant as affected by the environment. The next step was to use the information to generate axiom and production rules for the alphabets in the parametric L-System. The results of program testing showed that among the five treatments, the combination of organic and inorganic fertilizer was the environmental factor for the experiment. The highest result of 6.41 during evaluation of the virtual plant came from the treatment with combination of high level of organic fertilizer and medium level of inorganic fertilizer. Mean error between real plant and virtual plan was 9.45 %.

Item Type: Journal Article
Keywords: plant growth modeling; Bayesian network; environment; distribution probability and L-system
Subjects: 08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080107 Natural Language Processing
Divisions: Faculty of Technology > Department of Informatics Engineering
Depositing User: Dr Suhartono M.Kom
Date Deposited: 15 May 2018 01:34

Downloads

Downloads per month over past year

Origin of downloads

Actions (login required)

View Item View Item