The performance of visible and near infrared (Vis-NIR) spectroscopy as a rapid and non-destructive technique to determine the boiling time of yardlong beans was investigated. Vis-NIR spectra of beans boiled for 0, 30 to 300 s were measured. Robust least-squares support vector machines (R-LS-SVM) with RBF kernel obtained the best result. Partial least square based variable elimination (VE(PLS)) and robust least square-support vector machines based variable elimination (VE(R-LS-SVM)) were used for variable selections. Four most important variables at 409, 614, 880, and 984 nm were selected. After the variable selection, 90% of the variables were eliminated and the model's residual predictive deviation (RPD) only decreased 10% compared to that of the model without the variable elimination. The results showed that the Vis-NIR spectra can be used to determine the boiling time of yardlong beans during the boiling process. (C) 2011 Elsevier Ltd. All rights reserved.