Support vector machine regression for the prediction of maize hybrid performance.

Abstract excerpt

Accurate prediction of the phenotypical performance of untested single-cross hybrids allows for a faster genetic progress of the breeding pool at a reduced cost. We propose a prediction method based on epsilon-insensitive support vector machine regression (epsilon-SVR). A brief overview of the theoretical background of this fairly new technique and the use of specific kernel functions based on commonly applied...

Topics

Join the communities discussing this publication.

• Crosses, Genetic
• Forecasting
• Genetic Markers
• Hybridization, Genetic
• Linear Models