aiqbench analysis
This research introduces PI-AMFM, a neural framework utilizing Mamba backbones and permutation-invariant matching to solve variable-cardinality mode decomposition in nonstationary biomedical signals. By training on synthetic data, the model successfully isolates cardiac and respiratory dynamics from photoplethysmographic recordings with superior reconstruction accuracy compared to existing methods. The work advances machine learning applications in signal processing by addressing the challenge of dynamic component counts without predefined stopping criteria.
PI-AMFM: Permutation-Invariant Learning for Variable-Cardinality AM-FM Mode Decomposition in Biomedical Signal Analysis
arXiv:2610.00819v1 Announce Type: cross Abstract: Physiological recordings often contain nonstationary oscillatory components whose number and dynamics vary across signals. Amplitude- and frequency-modulated (AM-FM) representations are well suited to characterizing such dynamics and have shown broad utility in biomedical signal analysis. Recent approaches have incorporated neural networks to learn mode decomposition patterns from data, but component cardinality is often predefined or determined through separate stopping or selection mechanisms. We propose a permutation-invariant neural framework for variable-cardinality AM-FM mode decomposition (PI-AMFM). PI-AMFM combines a multiscale temporal encoder, Mamba backbone, and component-presence estimation, with permutation-invariant Hungarian matching during training. On synthetic AM-FM signals, PI-AMFM achieved lower decomposition, instantaneous-frequency, reconstruction, and mode-count errors than the compared methods while preserving the overall trajectory pattern in a crossing-chirp example. On photoplethysmographic recordings, recovered modes captured cardiac and respiratory dynamics despite training only on synthetic signals. These results support the feasibility of PI-AMFM for variable-cardinality decomposition of nonstationary biomedical signals.
Abstract:Physiological recordings often contain nonstationary oscillatory components whose number and dynamics vary across signals. Amplitude- and frequency-modulated (AM-FM) representations are well suited to characterizing such dynamics and have shown broad utility in biomedical signal analysis. Recent approaches have incorporated neural networks to learn mode decomposition patterns from data, but component cardinality is often predefined or determined through separate stopping or selection mechanisms. We propose a permutation-invariant neural framework for variable-cardinality AM-FM mode decomposition (PI-AMFM). PI-AMFM combines a multiscale temporal encoder, Mamba backbone, and component-presence estimation, with permutation-invariant Hungarian matching during training. On synthetic AM-FM signals, PI-AMFM achieved lower decomposition, instantaneous-frequency, reconstruction, and mode-count errors than the compared methods while preserving the overall trajectory pattern in a crossing-chirp example. On photoplethysmographic recordings, recovered modes captured cardiac and respiratory dynamics despite training only on synthetic signals. These results support the feasibility of PI-AMFM for variable-cardinality decomposition of nonstationary biomedical signals.
Signal Processing (eess.SP); Machine Learning (cs.LG)
arXiv:2610.00819 [eess.SP]
(or arXiv:2610.00819v1 [eess.SP] for this version)
https://doi.org/10.48550/arXiv.2610.00819 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 245 words
Related coverage
Turnover-Orthogonal Credit Assignment for Open-Team Multi-Agent Reinforcement Learning
arXiv · Oct 5, 2026
The exact LCU sampling overhead of collective diagonal unitaries: resonances and a continued-fraction dichotomy
arXiv · Oct 5, 2026
OnlyDense: Reduced-Order Modeling for Lagrangian simulation
arXiv · Jun 9, 2026
Symmetry Adapted Hierarchical Equations of Motion for Exact Simulations of Large Polariton Systems
arXiv · Aug 24, 2026