An online variable selection method using recursive least squares

This paper proposes a method for online variable selection and model learning (AdaFSML-RLS) to be applied in industrial applications in the context of adaptive soft sensors. In the proposed method the model learning is made online and recursivelly, i.e it is not necessary to store the past values of data while learning the model. Furthermore, the proposed method has the capability of tracking the real time correlation coefficient between each variable and the target, allowing the knowledge about the importance of variables over the time. Moreover, in this method is not necessary to have any knowledge about the process or variables. The method was sucessfully applied in two datasets, an artificial dataset and in a real-world dataset.