A Quantitative Plant Type Recognition algorithm based on Gene Expression Programming

Abstract

Efficient and accurate plant type identification is an important foundation for biological research. The existing traditional machine learning classification algorithms have the defects of low classification accuracy in solving plant type recognition and cannot quantitatively give the corresponding class recognition model. In this paper, we propose a Quantitative Plant Type Recognition algorithm based on Gene Expression Programming (QPTR-GEP). Firstly, the plant type data set to be processed is preprocessed; then, the GEP population corresponding to plant type identification is constructed, and the corresponding quantitative identification function expressions are obtained after genetic operations such as mutation, recombination and transposition; finally, the classification expression with the highest fitness is used as the classifier corresponding to a single plant type, and the classifier model integrating the data set containing all plant type is put into the data set for plant type identification. Experimental results on the open source Iris demonstrate that our proposed algorithm outperforms SVM and Decision Tree algorithms for plant type identification.