Single trajectory characterization via machine learning
Gorka Muñoz-Gil, Miguel Ángel García-March, Carlo Manzo et al. · New Journal of Physics · 2019
Abstract In order to study transport in complex environments, it is extremely important to determine the physical mechanism underlying diffusion and precisely characterize its nature and parameters. Often, this task is strongly impacted by data consisting of trajectories with short length (either due to brief recordings or previous trajectory segmentation) and limited localization precision. In this paper, we propose a machine learning method based on a random forest architecture, which is able to associate single trajectories to the underlying diffusion mechanism with high accuracy. In addition, the algorithm is able to determine the anomalous exponent with a small error, thus inherently providing a classification of the motion as normal or anomalous (sub- or super-diffusion). The method provides highly accurate outputs even when working with very short trajectories and in the presence of experimental noise. We further demonstrate the application of transfer learning to experimental and simulated data not included in the training/test dataset. This allows for a full, high-accuracy characterization of experimental trajectories without the need of any prior information.
Cited by 150 works. doi:10.1088/1367-2630/ab6065 Open-access PDF
Authors
References
- Random Forests
- Classification and Regression Trees.
- Fractional Brownian Motions, Fractional Noises and Applications
- Classification And Regression Trees
- Do we need hundreds of classifiers to solve real world classification problems
- Graph-based approach for airborne light detection and ranging segmentation
- Weak ergodicity breaking and aging in disordered systems
- Anomalous diffusion models and their properties: non-stationarity, non-ergodicity, and ageing at the centenary of single particle tracking
- Physical Nature of Bacterial Cytoplasm
- Anomalous transport in the crowded world of biological cells