Linear-Phase-Type probability modelling of functional PCA with applications to resistive memories

Functional principal component analysis (FPCA) based on Karhunen–Loève (K–L) expansion allows to describe the stochastic evolution of main characteristics associated multiple systems and devices. Identifying probability distribution scores is fundamental characterize whole process. The aim this work consider a family statistical distributions that could be accurately adjusted previous transformation. Then, new class distributions, linear-phase-type, introduced model components. This studied in detail order prove, through K–L expansion, certain linear transformations process at each time point are phase-type distributed. way, one-dimensional same linear-phase-type class. Finally, an application reset with resistive memories developed explained.