1. Physics driven behavioural clustering of free-falling paper shapes
- Author
-
Fumiya Iida, Toby Howison, Josie Hughes, Fabio Giardina, Howison, Toby [0000-0001-8548-5550], Iida, Fumiya [0000-0001-9246-7190], and Apollo - University of Cambridge Repository
- Subjects
Inertia ,Physiology ,Physical system ,Social Sciences ,computer.software_genre ,Systems Science ,01 natural sciences ,010305 fluids & plasmas ,Physical Phenomena ,Physical phenomena ,Medicine and Health Sciences ,Psychology ,Cluster Analysis ,Moment of Inertia ,Multidisciplinary ,Applied Mathematics ,Simulation and Modeling ,theoretical model ,article ,Classical Mechanics ,Dynamical Systems ,Variety (cybernetics) ,Free falling ,machine learning ,Physical Sciences ,Medicine ,physics ,Algorithms ,Research Article ,Paper ,Computer and Information Sciences ,Reynolds Number ,Science ,Fluid Mechanics ,Research and Analysis Methods ,Machine learning ,Continuum Mechanics ,Motion ,Machine Learning Algorithms ,Artificial Intelligence ,0103 physical sciences ,010306 general physics ,Set (psychology) ,Cluster analysis ,Behavior ,Biological Locomotion ,business.industry ,Biology and Life Sciences ,Fluid Dynamics ,Models, Theoretical ,Nonlinear Dynamics ,Artificial intelligence ,business ,computer ,Mathematics - Abstract
Many complex physical systems exhibit a rich variety of discrete behavioural modes. Often, the system complexity limits the applicability of standard modelling tools. Hence, understanding the underlying physics of different behaviours and distinguishing between them is challenging. Although traditional machine learning techniques could predict and classify behaviour well, typically they do not provide any meaningful insight into the underlying physics of the system. In this paper we present a novel method for extracting physically meaningful clusters of discrete behaviour from limited experimental observations. This method obtains a set of physically plausible functions that both facilitate behavioural clustering and aid in system understanding. We demonstrate the approach on the V-shaped falling paper system, a new falling paper type system that exhibits four distinct behavioural modes depending on a few morphological parameters. Using just 49 experimental observations, the method discovered a set of candidate functions that distinguish behaviours with an error of 2.04%, while also aiding insight into the physical phenomena driving each behaviour. © 2019 Howison et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
- Published
- 2019