Decoding Anomalous Diffusion Using Higher-Order Spectral Analysis and Multiple Signal Classification

• DOI: 10.3390/photonics12020145
• Publication Date: 2025-02-10T14:29:26Z
• Authors: Miguel E. Iglesia...; Òscar Garibo-i-Orts; J. Alberto Conejero
• Keywords: SIGNAL (programming language)

Anomalous diffusion is characterized by nonlinear growth in the mean square displacement of a trajectory. Recent advances using statistical methods and recurrent neural networks have made it possible to detect such phenomena, even noisy conditions. In this work, we explore feature extraction through parametric non-parametric spectral analysis decode anomalously diffusing trajectories, achieving reduced computational costs compared with other approaches that require additional data or prior training. Specifically, propose use higher-order statistics, as bispectrum, hybrid algorithm combines kurtosis multiple-signal classification technique. Our results demonstrate type trajectory can be identified based on amplitude values. The proposed deliver accurate results, short trajectories presence noise.