Designing enhanced classifiers using prior process knowledge: Regularized maximum-likelihood

We propose a novel optimization-based paradigm for designing enhanced classifiers. The proposed paradigm allows us to incorporate available prior process knowledge into classifier design, thereby improving the performance of the resulting classifiers. In this work, we focus on dynamical systems that can be represented as finite-state multi-dimensional stochastic processes that possess labeled steady-state distributions. Given prior operational knowledge of the process, our goal is to build a classifier that can accurately label future observations obtained from the steady-state, by utilizing both the available prior knowledge and the training data. Simulation results show that the proposed paradigm yields improved classifiers that outperform traditional classifiers that use only training data.