# Feature Selection and Hyperparameter Optimization for Machine Learned Classification of 3D Single-Particle Tracking

## TL;DR

This paper uses machine learning to classify 3D particle movement in complex environments, improving understanding of diffusion in crowded and charged media.

## Contribution

A novel approach combining feature selection and decision tree algorithms to classify mixed motion types in 3D single-particle tracking.

## Key findings

- Six relevant features were identified for accurate trajectory characterization.
- Machine learning improves classification of heterogeneous transport in complex environments.

## Abstract

Understanding diffusion in charged
and crowded media is crucial
for solving a wide range of biological and materials challenges. Classifying
diffusion by traditional methods such as mean square displacement
in three-dimensional single-particle tracking (3D SPT) is difficult,
especially when there are mixed motion types. To address this, we
employed machine learning (ML), specifically decision tree algorithms
with feature selection, to identify the six most relevant features
for accurate characterization of trajectories. This work demonstrates
the value of ML in advancing our understanding of heterogeneous transport
that occurs in charged and crowded environments, with a broad range
of applications.