Skip to Main content Skip to Navigation
Conference papers

Accurate Inference of Rice Biomass Based on Support Vector Machine

Abstract : Biomass is an important phenotypic trait in plant growth analysis. In this study, we established and compared 8 models for measuring aboveground biomass of 402 rice varieties. Partial least squares (PLS) regression and all subsets regression (ASR) were carried out to determine the effective predictors. Then, 6 models were developed based on support vector regression (SVR). The kernel function used in this study was radial basis function (RBF). Three different optimization methods, Genetic Algorithm (GA) K-fold Cross Validation (K-CV), and Particle Swarm Optimization (PSO), were applied to optimize the penalty error C and RBF $$ \upgamma $$γ. We also compared SVR models with models based on PLS regression and ASR. The result showed the model in combination of ASR, GA optimization and SVR outperformed other models with coefficient of determination (R2) of 0.85 for the 268 varieties in the training set and 0.79 for the 134 varieties in the testing set, respectively. This paper extends the application of SVR and intelligent algorithm in measurement of cereal biomass and has the potential of promoting the accuracy of biomass measurement for different varieties.
Document type :
Conference papers
Complete list of metadata

Cited literature [20 references]  Display  Hide  Download
Contributor : Hal Ifip Connect in order to contact the contributor
Submitted on : Thursday, July 6, 2017 - 3:50:45 PM
Last modification on : Tuesday, April 5, 2022 - 9:02:02 PM
Long-term archiving on: : Wednesday, January 24, 2018 - 3:13:20 AM


Files produced by the author(s)


Distributed under a Creative Commons Attribution 4.0 International License



Lingfeng Duan, Wanneng yang, Guoxing Chen, Lizhong Xiong, Chenglong Huang. Accurate Inference of Rice Biomass Based on Support Vector Machine. 9th International Conference on Computer and Computing Technologies in Agriculture (CCTA), Sep 2015, Beijing, China. pp.356-365, ⟨10.1007/978-3-319-48357-3_35⟩. ⟨hal-01557851⟩



Record views


Files downloads