English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Anomalous diffusion is present at all scales, from atomic to large scales.Some exemplary systems are; ultra-cold atoms, telomeres in the nucleus ofcells, moisture transport in cement-based materials, the free movement ofarthropods, and the migration patterns of birds. The characterization of thediffusion gives critical information about the dynamics of these systems andprovides an interdisciplinary framework with which to study diffusivetransport. Thus, the problem of identifying underlying diffusive regimes andinferring the anomalous diffusion exponent {$\alpha$} with high confidence iscritical to physics, chemistry, biology, and ecology. Classification andanalysis of raw trajectories combining machine learning techniques withstatistics extracted from them have widely been studied in the AnomalousDiffusion Challenge ge (Munoz-Gil et al., 2021). Here we present a newdata-driven method for working with diffusive trajectories. This methodutilizes Gramian Angular Fields (GAF) to encode one-dimensional trajectories asimages (Gramian Matrices), while preserving their spatiotemporal structure forinput to computer-vision models. This allows us to leverage twowell-established pre-trained computer-vision models, ResNet and MobileNet, tocharacterize the underlying diffusive regime, and infer the anomalous diffusionexponent {$\alpha$}. Short raw trajectories, of lengths between 10 and 50, arecommonly encountered in single-particle tracking experiments and are the mostdifficult to characterize. We show that by using GAF images, we can outperformthe current state-of-the-art while increasing accessibility to machine learningmethods in an applied setting.

Gramian Angular Fields for leveraging pretrained computer vision models with anomalous diffusion trajectories