English

Detecting temporal scaling with modified diffusion entropy analysis

Adaptation and Self-Organizing Systems 2023-11-21 v1

Abstract

We present a modification to the diffusion entropy analysis method for detecting temporal scaling. Diffusion entropy analysis detects temporal scaling in a data set by converting a time-series into a diffusion trajectory and using the entropy of that trajectory to measure the temporal scaling in the data. We modify this by performing an event detection step to construct the diffusion trajectory. The new modified diffusion entropy analysis offers substantial improvements over the original method, especially for noisy data. We describe the method's purpose, how it works step-by-step, its application, and future development.

Keywords

Cite

@article{arxiv.2311.11453,
  title  = {Detecting temporal scaling with modified diffusion entropy analysis},
  author = {Garland Culbreth and Jacob Baxley and David Lambert},
  journal= {arXiv preprint arXiv:2311.11453},
  year   = {2023}
}

Comments

11 pages, 6 figures

R2 v1 2026-06-28T13:25:34.907Z