Linear Model Selection by Cross-validation

Parametric estimation of ultrasonic phase velocity and attenuation in dispersive media

“…different na, nb and nk. The best model size is determined by cross-validation [7] and residual analysis.…”

Rich Internet Application for Semi-automatic Annotation of Semantic Shots on Keyframes

“…This paper presents a frame work for semantic shot classication of sports video [9]. The proposed scheme has predefined a number of semantic shot classes for tennis, soccer and basketball with a relevant semantic meaning and which cover most of the sports broadcasting video.…”

“…This method does not ensure all instances are both used for training and detection, but in contrast to a full cross-validation procedure, random subsampling has been shown to be asymptotically consistent [9]. Predictions using this method give a realistic estimation of the classifier performance with external validation data, while K-fold cross-validation usually gives overly optimistic estimations [10].…”

Localized Model Selection for Regression

“…When at least one of the procedures is nonparametric with max(p n , q n ) converging more slowly than the parametric rate n −1/2 , Yang (2007) showed that for selecting the globally better procedure, it suffices to take n 2 at least of the same order as n 1 (which is not enough for comparing parametric models as shown in Shao (1993)). With local selection, however, we need to be more careful so as to satisfy…”