Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jul 23;6(3):359-388.
doi: 10.3390/clockssleep6030025.

Generative Models for Periodicity Detection in Noisy Signals

Affiliations

Generative Models for Periodicity Detection in Noisy Signals

Ezekiel Barnett et al. Clocks Sleep. .

Abstract

We present the Gaussian Mixture Periodicity Detection Algorithm (GMPDA), a novel method for detecting periodicity in the binary time series of event onsets. The GMPDA addresses the periodicity detection problem by inferring parameters of a generative model. We introduce two models, the Clock Model and the Random Walk Model, which describe distinct periodic phenomena and provide a comprehensive generative framework. The GMPDA demonstrates robust performance in test cases involving single and multiple periodicities, as well as varying noise levels. Additionally, we evaluate the GMPDA on real-world data from recorded leg movements during sleep, where it successfully identifies expected periodicities despite high noise levels. The primary contributions of this paper include the development of two new models for generating periodic event behavior and the GMPDA, which exhibits high accuracy in detecting multiple periodicities even in noisy environments.

Keywords: algorithm; generative models; periodic leg movements during sleep; periodicity; periodicity detection.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure A1
Figure A1
Random Walk Model performance with respect to β, for σ=log(μ) and |μ|=1.
Figure A2
Figure A2
Clock Model performance with respect to β, for σ=log(μ) and |μ|=1.
Figure A3
Figure A3
Random Walk Model performance with respect to β, averaged over σ, |μ|=1.
Figure A3
Figure A3
Random Walk Model performance with respect to β, averaged over σ, |μ|=1.
Figure A4
Figure A4
Clock Model performance with respect to β, averaged over σ, |μ|=1.
Figure A5
Figure A5
Random Walk Model performance with respect to σ, averaged over noise, |μ|=1.
Figure A6
Figure A6
Clock Model performance with respect to σ, averaged over noise, |μ|=1.
Figure A6
Figure A6
Clock Model performance with respect to σ, averaged over noise, |μ|=1.
Figure A7
Figure A7
Comparison of GMPA loss with and without curve fitting for individual nights (left panel) and single sleep bouts (right panel).
Figure 1
Figure 1
Example of a well-posed test case with two underlying periodicities and no noise. Histogram of the intervals D(μ)z^ and generative curves G(μ,σ) for the Random Walk Model with n=30 and β=0.
Figure 2
Figure 2
Example of an ill-posed test case with a signal-to-noise ratio of 1:2. Histogram of the intervals D(μ)z^ and generative curves G(μ,σ) for the Random Walk Model with n=100 and β=2.
Figure 3
Figure 3
Performance of the GMPDA without curve fitting for the Random Walk Model (a) and for the Clock Model (b), with β=0 and |μ|=1 and varying number of events (n).
Figure 4
Figure 4
Performance of the GMPDA with curve fitting for the Random Walk Model (a) and for the Clock Model (b), with β=0 and |μ|=1 and varying number of events (n).
Figure 5
Figure 5
Performance of the GMPDA with curve fitting for the Random Walk Model (a), and for the Clock Model (b), with |μ|=1 and σ=log(μ) across varying levels of uniform noise beta and number of events.
Figure 6
Figure 6
Comparison of the GMPDA to alternative algorithms: for the Random Walk Model (a), and for the Clock Model (b). Accuracy is plotted for different levels of variance σ for cases with one period (|μ|=1), no noise (β=0) and number of events, n=100.
Figure 7
Figure 7
Comparison of the GMPDA to alternative methods: for the Random Walk Model (a), and for the Clock Model (b). Accuracy is plotted against increasing levels of noise β for cases with one period (|μ|=1), known variance, i.e., σ=log(μ)) and number of events, n=100.
Figure 8
Figure 8
Comparison of the GMPDA to alternative methods for the Random Walk Model (a), and for the Clock Model (b). Accuracy is plotted against the number of events averaged over σ={1,log(μ),μ16,μ8} and β2.
Figure 9
Figure 9
Detection of multiple periodicities (|μ|=2) quantified as the number of correctly extracted periodicities by the GMPDA and alternative methods for the Random Walk Model.
Figure 10
Figure 10
Detection of multiple periodicities (|μ|=3) quantified as the number of correctly extracted periodicities by the GMPDA and alternative methods for the Random Walk Model.
Figure 11
Figure 11
Detection of multiple periodicities (|μ|=2) quantified as the number of correctly extracted periodicities by the GMPDA and alternative methods for the Clock Model.
Figure 12
Figure 12
Detection of multiple periodicities (|μ|=3) quantified as the number of correctly extracted periodicities by the GMPDA and alternative methods for the Clock Model.
Figure 13
Figure 13
Effect of the GMPDA parameter max_periods, the maximum number of searched for periodicities, on computational performance averaged over 1200 executions for the GMPDA, with (dark blue symbols) and without curve fitting (light blue symbols).
Figure 14
Figure 14
The GMPDA loss for 100 whole night time series plotted against the number of events (left panel) and length of time series (ts, in seconds, right panel).
Figure 15
Figure 15
The GMPDA loss for 579 sleep bouts of at least 5 min plotted against the number of events (left panel) and the length of the sleep bout (in seconds, right panel).
Figure 16
Figure 16
Histogram of significant periodicities identified in 100 whole night time series by the GMPDA.
Figure 17
Figure 17
Histogram of significant periodicities identified in 579 sleep bouts, 5 min or longer, by the GMPDA.

References

    1. Welch P. The use of fast Fourier transform for the estimation of power spectra: A method based on time averaging over short, modified periodograms. IEEE Trans. Audio Electroacoust. 1967;15:70–73. doi: 10.1109/TAU.1967.1161901. - DOI
    1. Priestley M.B. Spectral Analysis and Time Series: Univariate Series. Academic Press; London, UK: 1981.
    1. Madsen H. Time Series Analysis. CRC Press; Boca Raton, FL, USA: 2007.
    1. Mitsa T. Temporal Data Mining. CRC Press; Boca Raton, FL, USA: 2010.
    1. Box G.E.P., Jenkins G.M., Reinsel G.C., Ljung G.M. Time Series Analysis: Forecasting and Control. John Wiley & Sons; New York, NY, USA: 2015.

LinkOut - more resources