Saved in:
Bibliographic Details
Main Authors: Iida, Momoka, Motohashi, Hayato, Takahashi, Hirotaka
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.03985
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917384185446400
author Iida, Momoka
Motohashi, Hayato
Takahashi, Hirotaka
author_facet Iida, Momoka
Motohashi, Hayato
Takahashi, Hirotaka
contents Damped sinusoidal oscillations are widely observed in many physical systems, and their analysis provides access to underlying physical properties. However, parameter estimation becomes difficult when the signal decays rapidly, multiple components are superposed, and observational noise is present. In this study, we develop an autoencoder-based method that uses the latent space to estimate the frequency, phase, decay time, and amplitude of each component in noisy multi-component damped sinusoidal signals. We investigate multi-component cases under Gaussian-distribution training and further examine the effect of the training-data distribution through comparisons between Gaussian and uniform training. The performance is evaluated through waveform reconstruction and parameter-estimation accuracy. We find that the proposed method can estimate the parameters with high accuracy even in challenging setups, such as those involving a subdominant component or nearly opposite-phase components, while remaining reasonably robust when the training distribution is less informative. This demonstrates its potential as a tool for analyzing short-duration, noisy signals.
format Preprint
id arxiv_https___arxiv_org_abs_2604_03985
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Autoencoder-Based Parameter Estimation for Superposed Multi-Component Damped Sinusoidal Signals
Iida, Momoka
Motohashi, Hayato
Takahashi, Hirotaka
Machine Learning
Signal Processing
Damped sinusoidal oscillations are widely observed in many physical systems, and their analysis provides access to underlying physical properties. However, parameter estimation becomes difficult when the signal decays rapidly, multiple components are superposed, and observational noise is present. In this study, we develop an autoencoder-based method that uses the latent space to estimate the frequency, phase, decay time, and amplitude of each component in noisy multi-component damped sinusoidal signals. We investigate multi-component cases under Gaussian-distribution training and further examine the effect of the training-data distribution through comparisons between Gaussian and uniform training. The performance is evaluated through waveform reconstruction and parameter-estimation accuracy. We find that the proposed method can estimate the parameters with high accuracy even in challenging setups, such as those involving a subdominant component or nearly opposite-phase components, while remaining reasonably robust when the training distribution is less informative. This demonstrates its potential as a tool for analyzing short-duration, noisy signals.
title Autoencoder-Based Parameter Estimation for Superposed Multi-Component Damped Sinusoidal Signals
topic Machine Learning
Signal Processing
url https://arxiv.org/abs/2604.03985