Classification for Dynamical Systems: Model-based Approach and Support Vector Machines

TL;DR

This paper compares model-based and data-driven support vector machine approaches for classifying trajectories of dynamical systems, highlighting their connections and relative advantages.

Contribution

It provides a comparative analysis of control engineering and machine learning methods for dynamical system classification, revealing their links and benefits.

Findings

Connections between model-based and SVM approaches identified

Analysis of relative merits of both methods

Insights into combining control and machine learning techniques

Abstract

We consider the problem of classifying trajectories generated by dynamical systems. We investigate a model-based approach, the common approach in control engineering, and a data-driven approach based on Support Vector Machines, a popular method in the area of machine learning. The analysis points out connections between the two approaches and their relative merits.