Part of #Application of Supervised Feature Selection Methods to Define the Most Important Feature on Sink/Source Relationships in Maize# :
Publishing year : 2010
Conference : The first international conference on plant, water, soil and air modeling
Number of pages : 9
Abstract: Kernel number per unit land area is also the major contributor to kernel yield. Final kernel weight is closely related to the maximum kernel water content (MKWC) achieved during grain filling. This study presents the results of applying supervised feature selection algorithms in the selection of the most important attributes contributing to MKWC as a major yield component. The experimental design was randomized complete blocks with three replicates and treatments in a split-split plot arrangement and from literature in the Experimental Farm of the College of Agriculture, Shiraz University, Badjgah. . Experiments on the subject of sink / source relations in the bread from twelve fields (as records) from the various parts of the world which were different in 22 characteristics. Features feature algorithm showed that14 features including: planting date (days), countries, Hibrid, P applied (kg / ha), final kernel weight (mg), soil type, season duration (days), days to silking, leaf dry weight (g / plant), mean kernel weight (mg), cob dry weight G / plant), kernel number per ear, N applied (kg / ha), and duration of the grain filling period (C day) were the most effective traits in determining the maximum kernel water content. Among the effective traits (features), the planting date (days) was the most important one. Our results showed that the classification of features by supervised feature selection algorithms can be used to clarify the important attributes that contribute to the content of the kernel water content and yield, providing a comprehensive view. This study identifies the future research areas in the feature selection in bread physiology, introduces newcomers to this field.