|
Abstract:
|
We consider data from an experiment where measurements obtained longitudinally from various cell-based sensor chips are used to detect paracetamol added to an nutrient medium. For analyzing the data, we propose an ensemble method for nonparametric classification with functional data that inherently provides automatic and interpretable feature selection. It is designed for single as well as multiple functional (and non-functional) covariates. The ensemble members are posterior probability estimates which are obtained using k-nearest-neighbors based on different semi-metrics, with each of those semi-metrics focusing on a specific curve feature. Each ensemble member, and thus each curve feature, is weighted by a specific coefficient which is estimated using a proper scoring rule with implicit lasso-type penalty, such that some coefficients can be estimated to be exactly zero. Thus, the ensemble automatically provides feature (and variable) selection.
|
