Cyclic fractional Gaussian noise: time and frequency domain properties

Agnieszka Wylomanska; Hubert Woszczek

arxiv: 2604.22813 · v1 · submitted 2026-04-14 · 📊 stat.AP · math.PR

Cyclic fractional Gaussian noise: time and frequency domain properties

Hubert Woszczek , Agnieszka Wylomanska This is my paper

Pith reviewed 2026-05-10 13:56 UTC · model grok-4.3

classification 📊 stat.AP math.PR

keywords cyclic fractional Gaussian noiselong-range dependencecyclostationarityautocovariance functioncyclic spectrumtwo-dimensional fractional Brownian motionstochastic processessignal processing

0 comments

The pith

Cyclic fractional Gaussian noise merges periodic autocovariance with long-range dependence through modulated two-dimensional fractional Brownian motion increments.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper introduces cyclic fractional Gaussian noise (cfGn) as a stochastic model that combines second-order cyclostationarity with long-range dependence. Classical cyclostationary processes typically lack the persistent slow-decaying correlations seen in many empirical datasets. The authors build cfGn by summing two components formed from the univariate coordinates of two-dimensional fractional Brownian motion increments, each modulated by a periodic deterministic function. Through derivation of the autocovariance function and cyclic spectrum, plus asymptotic analysis and Monte Carlo simulations, they show the model retains periodic ACVF behavior while inheriting long-memory traits in both time and frequency domains. The framework supports applications such as signal-based condition monitoring where periodic fault signatures coexist with long-range dependent background noise.

Core claim

The central claim is that cfGn, formed by summing amplitude-modulated univariate coordinates of 2d fBm increments, preserves the periodic structure of its autocovariance function while inheriting the long-memory property of fractional Gaussian noise, as confirmed by theoretical asymptotics and simulations in both the time domain (ACVF) and frequency domain (cyclic spectrum).

What carries the argument

The construction of cfGn as the sum of two components, each consisting of a coordinate of two-dimensional fractional Brownian motion increments modulated by a periodic deterministic function.

If this is right

The ACVF of cfGn exhibits both periodic oscillations and the slow power-law decay characteristic of long memory.
The cyclic spectrum of cfGn reveals frequency-domain signatures of both cyclostationarity and long-range dependence.
Monte Carlo simulations confirm the theoretical asymptotic properties in time and frequency domains.
The model supplies a foundation for analyzing signals containing periodic fault components alongside long-range dependent noise.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The same modulation approach could be tested on other long-memory processes to create additional cyclostationary variants.
Parameter estimation procedures for cfGn would be a natural next step for fitting the model to observed data.
The framework suggests a general template for embedding long-range dependence into other cyclostationary models without loss of either feature.

Load-bearing premise

That modulating the coordinates of two-dimensional fractional Brownian motion increments with periodic deterministic functions successfully combines cyclostationarity and long-range dependence without destroying either property or creating inconsistencies in the ACVF and cyclic spectrum.

What would settle it

A demonstration that the autocovariance function of the constructed process either loses its periodic oscillations at all lags or fails to exhibit power-law decay at large lags would falsify the central claim.

read the original abstract

This article introduces cyclic fractional Gaussian noise (cfGn), a stochastic model that integrates second-order cyclostationarity with long-range dependence property. While classical cyclostationary processes are widely discussed in the literature, they often lack the capacity to account for the persistent, slow-decaying correlations found in complex empirical data. To bridge this gap, we extend the amplitude-modulated stationary framework by utilizing increments of two-dimensional fractional Brownian motion (2d fBm) as the underlying driving process. The proposed cfGn model is constructed by summing two components, which include periodic deterministic functions modulating the univariate coordinates of 2d fGn. We provide a rigorous derivation of the considered model's properties, specifically the autocovariance function (ACVF) and frequency-domain characteristics, including the cyclic spectrum. Through theoretical considerations of asymptotic properties and Monte Carlo simulations, we demonstrate that cfGn preserves periodic behavior of ACVF while inheriting long-memory traits which is manifested in time and frequency domains. This framework offers a robust foundation, for instance, in signal-based condition monitoring in systems where periodic fault components coexist with long-range dependent background noise.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

cfGn merges cyclostationarity and long memory by modulating 2D fBm increments with periodic functions, derives the ACVF and cyclic spectrum, and backs it with asymptotics plus simulations, but the cross-covariance terms need explicit checking.

read the letter

This paper introduces cyclic fractional Gaussian noise by summing two modulated components, each a periodic deterministic function times one coordinate of increments from two-dimensional fractional Brownian motion. The authors derive the autocovariance function and the cyclic spectrum, then show through asymptotic analysis and Monte Carlo runs that the ACVF stays periodic while the lag decay follows the expected power-law form with a bounded periodic multiplier. That combination is the central new piece: earlier cyclostationary models rarely carried long memory, and this construction uses the joint structure of the 2D fBm to link the two properties without separate fitting steps. The explicit ACVF expression and the frequency-domain results are the parts that stand out as usable for downstream work. The simulations confirm that the periodic behavior and slow decay both appear in finite samples, which is helpful for applications like condition monitoring where periodic fault signatures sit on top of persistent noise. One point worth verifying is the cross-covariance between the two fBm coordinates. Because those coordinates are correlated in the standard 2D fBm definition, the term involving the product of the two modulating functions times their cross-covariance enters the total ACVF. For the claimed cyclostationarity and the exact long-memory exponent to hold without extra restrictions on the modulators, that term must not introduce non-periodic residuals or alter the decay rate. The abstract presents the derivation as rigorous, so the paper likely shows the full expression factors appropriately, but the algebra on this step is load-bearing and should be inspected directly. The work is aimed at researchers already comfortable with fractional processes and cyclostationary spectra, particularly those modeling signals in engineering or geophysics that mix periodic structure with memory. A reader who needs a concrete stochastic model for such data will find the derivations and simulation protocol directly applicable. The paper deserves peer review because the model is new, the claims are stated in terms of verifiable properties, and both analytic and numerical evidence are supplied. A referee can focus on the cross-term handling and the simulation design without needing to reconstruct the whole framework.

Referee Report

2 major / 2 minor

Summary. The paper introduces cyclic fractional Gaussian noise (cfGn) constructed as the sum of two terms, each consisting of a periodic deterministic function modulating one coordinate of the increments of a two-dimensional fractional Brownian motion. It derives the autocovariance function (ACVF) and cyclic spectrum in closed form, then uses asymptotic analysis of the ACVF decay and Monte Carlo simulations to claim that the process simultaneously exhibits second-order cyclostationarity (periodic ACVF) and long-range dependence (power-law decay with exponent 2H-2).

Significance. If the derivation is correct, the model supplies a parametric family that merges cyclostationarity with exact long-memory behavior without destroying either property, which is useful for applications such as condition monitoring of systems containing both periodic fault signatures and persistent background noise. The explicit ACVF formula and cyclic-spectrum expression constitute a concrete, falsifiable contribution.

major comments (2)

[§3.2] §3.2 (ACVF derivation): the cross-covariance term p1(t)p2(s)Cov(G1_t,G2_s) arising from the correlated coordinates of the 2D fBm must be shown explicitly to preserve both R(t+T,s+T)=R(t,s) and the exact power-law exponent 2H-2; the current sketch does not isolate this term or state the required orthogonality condition on the modulating functions.
[§4.1] §4.1 (Monte Carlo setup): the reported sample ACVF plots and cyclic-spectrum estimates use a single pair of modulating functions and a fixed H; the paper should add a table or figure showing the fitted decay exponent across H=0.6,0.7,0.8 to confirm that the long-memory rate is not altered by the modulation.

minor comments (2)

[Abstract] Notation: the abbreviation '2d fBm' appears in the abstract but is not defined until §2.1; introduce it at first use.
[Figure 2] Figure 2: the frequency axis labeling for the cyclic spectrum is ambiguous with respect to the cyclic frequencies; add explicit tick labels or a legend.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed and constructive report. The comments highlight opportunities to strengthen the explicitness of the ACVF derivation and the numerical confirmation of the long-memory property. We address each major comment below and will incorporate the suggested clarifications and additions in the revised manuscript.

read point-by-point responses

Referee: [§3.2] §3.2 (ACVF derivation): the cross-covariance term p1(t)p2(s)Cov(G1_t,G2_s) arising from the correlated coordinates of the 2D fBm must be shown explicitly to preserve both R(t+T,s+T)=R(t,s) and the exact power-law exponent 2H-2; the current sketch does not isolate this term or state the required orthogonality condition on the modulating functions.

Authors: We will revise §3.2 to isolate the cross-covariance term explicitly. Let the cfGn be defined as X_t = p1(t) G1_t + p2(t) G2_t, where G = (G1, G2) is a 2D fractional Gaussian noise with stationary increments and cross-covariance Cov(G1_t, G2_s) ~ c |t-s|^{2H-2} for large |t-s|. The ACVF then contains the term p1(t)p2(s) Cov(G1_t, G2_s). Periodicity follows immediately: because p1 and p2 are T-periodic, p_i(t+T) = p_i(t), and stationarity of G gives Cov(G1_{t+T}, G2_{s+T}) = Cov(G1_t, G2_s), so R(t+T, s+T) = R(t, s). For the asymptotic decay, the bounded periodic multipliers p1(t)p2(s) do not change the exponent; the cross term therefore inherits the exact power-law rate 2H-2. No orthogonality condition on p1 and p2 is required; boundedness of the modulating functions is sufficient. The revised section will contain the expanded calculation. revision: yes
Referee: [§4.1] §4.1 (Monte Carlo setup): the reported sample ACVF plots and cyclic-spectrum estimates use a single pair of modulating functions and a fixed H; the paper should add a table or figure showing the fitted decay exponent across H=0.6,0.7,0.8 to confirm that the long-memory rate is not altered by the modulation.

Authors: We agree that additional numerical evidence across H values will strengthen the claim that modulation preserves the long-memory rate. In the revised §4.1 we will include a new table (or supplementary figure) reporting the least-squares fitted decay exponents obtained from Monte Carlo sample ACVFs for H = 0.6, 0.7, 0.8. The simulations will retain the same modulating functions used in the original plots and will also report results for a second, qualitatively different pair of periodic functions to illustrate robustness. This will confirm that the observed decay remains consistent with the theoretical exponent 2H-2. revision: yes

Circularity Check

0 steps flagged

Direct construction of cfGn from 2D fBm increments with explicit derivation of ACVF and spectrum

full rationale

The paper defines cfGn explicitly as the sum of two components, each a periodic deterministic function times one coordinate of the increments of 2D fractional Brownian motion. It then derives the autocovariance function and cyclic spectrum directly from this construction using the known covariance structure of 2D fBm. No step equates a claimed property to its own definition, renames a fitted parameter as a prediction, or relies on a self-citation chain for the central result. The preservation of cyclostationarity follows immediately from the periodic modulators, while long-memory asymptotics inherit from the fractional Brownian motion kernel; both are independent of the target claims. Monte Carlo simulations serve only as verification, not as the source of the properties.

Axiom & Free-Parameter Ledger

1 free parameters · 2 axioms · 1 invented entities

Based solely on the abstract, the central claim rests on standard properties of fractional Brownian motion and the definition of cyclostationarity; the model itself is the primary new entity introduced.

free parameters (1)

periodic deterministic modulation functions
These functions are chosen as part of the model definition to impose cyclostationarity; their specific forms are not detailed in the abstract.

axioms (2)

standard math Increments of two-dimensional fractional Brownian motion possess long-range dependence
The construction relies on this established property of 2D fBm to impart long-memory traits to the modulated process.
domain assumption Amplitude modulation of stationary processes yields second-order cyclostationarity
The paper extends the known amplitude-modulated framework to the fractional case.

invented entities (1)

cyclic fractional Gaussian noise (cfGn) no independent evidence
purpose: A stochastic process that simultaneously exhibits periodic autocovariance and long-range dependence
Newly defined via summation of modulated 2D fGn components; no independent external evidence provided beyond the paper's own derivations and simulations.

pith-pipeline@v0.9.0 · 5492 in / 1571 out tokens · 41545 ms · 2026-05-10T13:56:18.111046+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

48 extracted references · 48 canonical work pages

[1]

Antoni, Cyclostationarity by examples, Mechanical Systems and Signal Processing 23 (4) (2009) 987 – 1036

J. Antoni, Cyclostationarity by examples, Mechanical Systems and Signal Processing 23 (4) (2009) 987 – 1036

work page 2009
[2]

Antoni, F

J. Antoni, F. Bonnardot, A. Raad, M. El Badaoui, Cyclostationary modelling of rotating machine vibration signals, Mechanical Systems and Signal Processing 18 (6) (2004) 1285–1314

work page 2004
[3]

Brelsford, R

M. Brelsford, R. Jones, Time series with periodic structure, Biometrika 54 (1967) 403–407

work page 1967
[4]

Bukofzer, Optimum and suboptimum detector performance for signals in cyclostationary noise, Journal of Oceanic Engineering 12 (1987) 97–115

D. Bukofzer, Optimum and suboptimum detector performance for signals in cyclostationary noise, Journal of Oceanic Engineering 12 (1987) 97–115

work page 1987
[5]

Bloomfield, H

P. Bloomfield, H. Hurd, R. Lund, Periodic correlation in stratospheric ozone time series, Journal of Time Series Analysis 15 (1994) 127–150

work page 1994
[6]

Dargaville, S

R. Dargaville, S. Doney, I. Fung, Inter-annual variability in the interhemispheric atmospheric CO2 gradient, Tellus B 15 (2003) 711–722

work page 2003
[7]

Broszkiewicz-Suwaj, A

E. Broszkiewicz-Suwaj, A. Makagon, R. Weron, A. Wyłoma´nska, On detecting and modeling periodic correla- tion in financial data, Physica A: Statistical Mechanics and its Applications 336 (1-2) (2004) 196–205

work page 2004
[8]

Guzdenko, The small fluctuation in essentially nonlinear autooscillation system, Dokl

L. Guzdenko, The small fluctuation in essentially nonlinear autooscillation system, Dokl. Akad. Nauk USSR 125 (1959) 62–65

work page 1959
[9]

E. G. Gladyshev, Periodically correlated random sequences, Sov. Math. 2 (1961) 385–388. 11 Figure 2:Comparison of theoretical ACVF given in Eq. (29) and its Monte Carlo simulated counterpart for different values of ρ, with causal and well-balanced 2d fGn as the underlying process, forH 1 =0.4,H 2 =0.7,λ 0 =0.1π,n=20 and 10000 Monte Carlo simulations

work page 1961
[10]

Hurd, An investigation of periodically correlated stochastic processes, PhD Dissertation, Duke University, Department of Electrical Engineering, 1969

H. Hurd, An investigation of periodically correlated stochastic processes, PhD Dissertation, Duke University, Department of Electrical Engineering, 1969

work page 1969
[11]

Gardner, Representation and estimation of cyclostationary processes, PhD Dissertation, University of Mas- sachusetts, Department of Electrical Engineering, 1972

W. Gardner, Representation and estimation of cyclostationary processes, PhD Dissertation, University of Mas- sachusetts, Department of Electrical Engineering, 1972

work page 1972
[12]

Napolitano, Cyclostationary Processes and Time Series

A. Napolitano, Cyclostationary Processes and Time Series. Theory, Applications, and Generalizations, Elsevier Academic Press, 2019

work page 2019
[13]

H. L. Hurd, A. Miamee, Periodically correlated random sequences: Spectral theory and practice, V ol. 355, John Wiley & Sons, 2007

work page 2007
[14]

Antoni, Cyclic spectral analysis of rolling-element bearing signals: facts and fictions, Journal of Sound and vibration 304 (3) (2007) 497–529

J. Antoni, Cyclic spectral analysis of rolling-element bearing signals: facts and fictions, Journal of Sound and vibration 304 (3) (2007) 497–529

work page 2007
[15]

D. Wang, X. Zhao, L.-L. Kou, Y . Qin, Y . Zhao, K.-L. Tsui, A simple and fast guideline for generating en- hanced/squared envelope spectra from spectral coherence for bearing fault diagnosis, Mechanical Systems and Signal Processing 122 (2019) 754 – 768

work page 2019
[16]

A. V . Vecchia, Periodic autoregressive-moving average (PARMA) modeling with applications to water resources, J. Am. Water Resour. Assoc. 21 (5) (1985) 721–730

work page 1985
[17]

W. A. Gardner, A. Napolitano, L. Paura, Cyclostationarity: Half a century of research, Signal processing 86 (4) (2006) 639–697. 12 Figure 3:Comparison of theoretical real part of CAF at frequency 2λ 0 given in Proposition 2 and its Monte Carlo simulated counterpart for different values ofρ, with causal and well-balanced 2d fGn as the underlying process, f...

work page 2006
[18]

A. N. Kolmogorov, Wienersche Spiralen und einige andere interessante Kurven im Hilbertschen Raum, C.R. (Doklady) Acad. Sci. URSS (NS) 26 (1940) 115

work page 1940
[19]

B. B. Mandelbrot, J. W. Van Ness, Fractional Brownian Motions, Fractional Noises and Applications, SIAM Review 10 (4) (1968) 422–437

work page 1968
[20]

Beran, Statistics for long-memory processes, Chapman & Chal, 1994

J. Beran, Statistics for long-memory processes, Chapman & Chal, 1994

work page 1994
[21]

F. J. Molz, H. H. Liu, J. Szulga, Fractional Brownian motion and fractional Gaussian noise in subsurface hy- drology: A review, presentation of fundamental properties, and extensions, Water Resources Research 33 (10) (1997) 2273–2286

work page 1997
[22]

D. A. Benson, M. M. Meerschaert, J. Revielle, Fractional calculus in hydrologic modeling: A numerical per- spective, Advances in Water Resources 51 (2013) 479–497

work page 2013
[23]

A. Pashko, Simulation of telecommunication traffic using statistical models of fractional Brownian motion, in: 2017 4th International Scientific-Practical Conference Problems of Infocommunications. Science and Technol- ogy (PIC S&T), 2017, pp. 414–418

work page 2017
[24]

Frecon, G

J. Frecon, G. Didier, N. Pustelnik, P. Abry, Non-Linear Wavelet Regression and Branch & Bound Optimiza- tion for the Full Identification of Bivariate Operator Fractional Brownian Motion, IEEE Transactions on Signal Processing 64 (15) (2016) 4040–4049. 13 Figure 4:Comparison of theoretical imaginary part of CAF at frequency 2λ0 given in Proposition 2 and i...

work page 2016
[25]

Chang, S

Y . Chang, S. Chang, A fast estimation algorithm on the Hurst parameter of discrete-time fractional Brownian motion, IEEE Transactions on Signal Processing 50 (3) (2002) 554–559

work page 2002
[26]

S. Liu, S. Chang, Dimension estimation of discrete-time fractional Brownian motion with applications to image texture classification, IEEE Transactions on Image Processing 6 (8) (1997) 1176–1184

work page 1997
[27]

Gelbaum, M

Z. Gelbaum, M. Titus, Simulation of Fractional Brownian Surfaces via Spectral Synthesis on Manifolds, IEEE Transactions on Image Processing 23 (10) (2014) 4383–4388

work page 2014
[28]

Rostek, R

S. Rostek, R. Schöbel, A note on the use of fractional Brownian motion for financial modeling, Economic Modelling 30 (2013) 30–35

work page 2013
[29]

Maraj, D

K. Maraj, D. Szarek, G. Sikora, A. Wyłoma´nska, Time-averaged mean squared displacement ratio test for Gaus- sian processes with unknown diffusion coefficient, Chaos: An Interdisciplinary Journal of Nonlinear Science 31 (7) (2021) 073120

work page 2021
[30]

W. Xiao, W. Zhang, X. Zhang, Y . Wang, Pricing currency options in a fractional Brownian motion with jumps, Economic Modelling 27 (5) (2010) 935–942

work page 2010
[31]

Ernst, M

D. Ernst, M. Hellmann, J. Köhler, M. Weiss, Fractional Brownian motion in crowded fluids, Soft Matter 8 (2012) 4886

work page 2012
[32]

Höfling, T

F. Höfling, T. Franosch, Anomalous transport in the crowded world of biological cells, Rep. Prog. Phys. 76 (2013) 046602. 14 Figure 5:Comparison of theoretical cyclic spectrum at frequency 0 given in Eq. (44) and ts Monte Carlo simulated counterpart for different values ofρ, with causal and well-balanced 2d fGn as the underlying process, forH 1 =0.4,H 2 =...

work page 2013
[33]

Metzler, J

R. Metzler, J. Jeon, A. G. Cherstvy, E. Barkai, Anomalous diffusion models and their properties: non-stationarity, non-ergodicity, and ageing at the centenary of single particle tracking, Phys. Chem. Chem. Phys. 16 (44) (2014) 24128–24164

work page 2014
[34]

Szarek, K

D. Szarek, K. Maraj-Zygmat, G. Sikora, D. Krapf, A. Wylomanska, Statistical test for anomalous diffusion based on empirical anomaly measure for Gaussian processes, Computational Statistics & Data Analysis 168 (2022) 107401

work page 2022
[35]

Krapf, N

D. Krapf, N. Lukat, E. Marinari, R. Metzler, G. Oshanin, C. Selhuber-Unkel, A. Squarcini, L. Stadler, M. Weiss, X. Xu, Spectral Content of a Single Non-Brownian Trajectory, Phys. Rev. X 9 (2019) 011019

work page 2019
[36]

Amblard, J.-F

P.-O. Amblard, J.-F. Coeurjolly, F. Lavancier, A. Philippe, Basic properties of the multivariate fractional Brow- nian motion, in: Séminaires et congrès, V ol. 28, 2013, pp. 65–87

work page 2013
[37]

Coeurjolly, P.-O

J.-F. Coeurjolly, P.-O. Amblard, S. Achard, On multivariate fractional Brownian motion and multivariate frac- tional Gaussian noise, in: 2010 18th European Signal Processing Conference, IEEE, 2010, pp. 1567–1571

work page 2010
[38]

Lavancier, A

F. Lavancier, A. Philippe, D. Surgailis, Covariance function of vector self-similar processes, Statistics & Proba- bility Letters 79 (23) (2009) 2415–2421

work page 2009
[39]

Maejima, J

M. Maejima, J. Mason, Operator-self-similar stable processes, Stochastic Processes and their Applications 54 (1) (1994) 139–163. 15 Figure 6:Comparison of theoretical real part of cyclic spectrum at frequency 2λ0 given in Eq. (45) and its Monte Carlo simulated counterpart for different values ofρ, with causal and well-balanced 2d fGn as the underlying pro...

work page 1994
[40]

Balcerek, A

M. Balcerek, A. Pacheco-Pozo, A. Wyłoma´nska, K. Burnecki, D. Krapf, Two-dimensional fractional Brownian motion: Analysis in time and frequency domains (2025)

work page 2025
[41]

J. R. M. Hosking, Fractional differencing, Biometrika 68 (1981) 165–176

work page 1981
[42]

G. S. Dissanayake, M. S. Peiris, T. Proietti, Fractionally differenced Gegenbauer processes with long memory: A review, Statistical Science 33 (2018)

work page 2018
[43]

V . V . Anh, V . P. Knopova, N. N. Leonenko, Continuous-time stochastic processes with cyclical long-range dependence, Australian & New Zealand Journal of Statistics 46 (2) (2004) 275–296

work page 2004
[44]

Papoulis, Random modulation: A review, IEEE Transactions on Acoustics, Speech, and Signal Processing 31 (1) (1983) 96–105

A. Papoulis, Random modulation: A review, IEEE Transactions on Acoustics, Speech, and Signal Processing 31 (1) (1983) 96–105

work page 1983
[45]

Kechagias, V

S. Kechagias, V . Pipiras, P. Zoubouloglou, Cyclical long memory: Decoupling, modulation, and modeling, Stochastic Processes and their Applications 175 (2024) 104403

work page 2024
[46]

Maddanu, T

F. Maddanu, T. Proietti, Modelling persistent cycles in solar activity, Solar Physics 297 (1) (2022) 13

work page 2022
[47]

Proietti, F

T. Proietti, F. Maddanu, Modelling cycles in climate series: The fractional sinusoidal waveform process, Journal of Econometrics 239 (1) (2024) 105299

work page 2024
[48]

P. J. Brockwell, R. A. Davis, Time Series: Theory and Methods, 2nd Edition, Springer, New York, 1991. 16 Figure 7:Comparison of theoretical imaginary part of cyclic spectrum at frequency 2λ 0 given in Eq. (45) and its Monte Carlo simulated counterpart for different values ofρ, with causal and well-balanced 2d fBm as the underlying process, forH 1 =0.4, H2...

work page 1991

[1] [1]

Antoni, Cyclostationarity by examples, Mechanical Systems and Signal Processing 23 (4) (2009) 987 – 1036

J. Antoni, Cyclostationarity by examples, Mechanical Systems and Signal Processing 23 (4) (2009) 987 – 1036

work page 2009

[2] [2]

Antoni, F

J. Antoni, F. Bonnardot, A. Raad, M. El Badaoui, Cyclostationary modelling of rotating machine vibration signals, Mechanical Systems and Signal Processing 18 (6) (2004) 1285–1314

work page 2004

[3] [3]

Brelsford, R

M. Brelsford, R. Jones, Time series with periodic structure, Biometrika 54 (1967) 403–407

work page 1967

[4] [4]

Bukofzer, Optimum and suboptimum detector performance for signals in cyclostationary noise, Journal of Oceanic Engineering 12 (1987) 97–115

D. Bukofzer, Optimum and suboptimum detector performance for signals in cyclostationary noise, Journal of Oceanic Engineering 12 (1987) 97–115

work page 1987

[5] [5]

Bloomfield, H

P. Bloomfield, H. Hurd, R. Lund, Periodic correlation in stratospheric ozone time series, Journal of Time Series Analysis 15 (1994) 127–150

work page 1994

[6] [6]

Dargaville, S

R. Dargaville, S. Doney, I. Fung, Inter-annual variability in the interhemispheric atmospheric CO2 gradient, Tellus B 15 (2003) 711–722

work page 2003

[7] [7]

Broszkiewicz-Suwaj, A

E. Broszkiewicz-Suwaj, A. Makagon, R. Weron, A. Wyłoma´nska, On detecting and modeling periodic correla- tion in financial data, Physica A: Statistical Mechanics and its Applications 336 (1-2) (2004) 196–205

work page 2004

[8] [8]

Guzdenko, The small fluctuation in essentially nonlinear autooscillation system, Dokl

L. Guzdenko, The small fluctuation in essentially nonlinear autooscillation system, Dokl. Akad. Nauk USSR 125 (1959) 62–65

work page 1959

[9] [9]

E. G. Gladyshev, Periodically correlated random sequences, Sov. Math. 2 (1961) 385–388. 11 Figure 2:Comparison of theoretical ACVF given in Eq. (29) and its Monte Carlo simulated counterpart for different values of ρ, with causal and well-balanced 2d fGn as the underlying process, forH 1 =0.4,H 2 =0.7,λ 0 =0.1π,n=20 and 10000 Monte Carlo simulations

work page 1961

[10] [10]

Hurd, An investigation of periodically correlated stochastic processes, PhD Dissertation, Duke University, Department of Electrical Engineering, 1969

H. Hurd, An investigation of periodically correlated stochastic processes, PhD Dissertation, Duke University, Department of Electrical Engineering, 1969

work page 1969

[11] [11]

Gardner, Representation and estimation of cyclostationary processes, PhD Dissertation, University of Mas- sachusetts, Department of Electrical Engineering, 1972

W. Gardner, Representation and estimation of cyclostationary processes, PhD Dissertation, University of Mas- sachusetts, Department of Electrical Engineering, 1972

work page 1972

[12] [12]

Napolitano, Cyclostationary Processes and Time Series

A. Napolitano, Cyclostationary Processes and Time Series. Theory, Applications, and Generalizations, Elsevier Academic Press, 2019

work page 2019

[13] [13]

H. L. Hurd, A. Miamee, Periodically correlated random sequences: Spectral theory and practice, V ol. 355, John Wiley & Sons, 2007

work page 2007

[14] [14]

Antoni, Cyclic spectral analysis of rolling-element bearing signals: facts and fictions, Journal of Sound and vibration 304 (3) (2007) 497–529

J. Antoni, Cyclic spectral analysis of rolling-element bearing signals: facts and fictions, Journal of Sound and vibration 304 (3) (2007) 497–529

work page 2007

[15] [15]

D. Wang, X. Zhao, L.-L. Kou, Y . Qin, Y . Zhao, K.-L. Tsui, A simple and fast guideline for generating en- hanced/squared envelope spectra from spectral coherence for bearing fault diagnosis, Mechanical Systems and Signal Processing 122 (2019) 754 – 768

work page 2019

[16] [16]

A. V . Vecchia, Periodic autoregressive-moving average (PARMA) modeling with applications to water resources, J. Am. Water Resour. Assoc. 21 (5) (1985) 721–730

work page 1985

[17] [17]

W. A. Gardner, A. Napolitano, L. Paura, Cyclostationarity: Half a century of research, Signal processing 86 (4) (2006) 639–697. 12 Figure 3:Comparison of theoretical real part of CAF at frequency 2λ 0 given in Proposition 2 and its Monte Carlo simulated counterpart for different values ofρ, with causal and well-balanced 2d fGn as the underlying process, f...

work page 2006

[18] [18]

A. N. Kolmogorov, Wienersche Spiralen und einige andere interessante Kurven im Hilbertschen Raum, C.R. (Doklady) Acad. Sci. URSS (NS) 26 (1940) 115

work page 1940

[19] [19]

B. B. Mandelbrot, J. W. Van Ness, Fractional Brownian Motions, Fractional Noises and Applications, SIAM Review 10 (4) (1968) 422–437

work page 1968

[20] [20]

Beran, Statistics for long-memory processes, Chapman & Chal, 1994

J. Beran, Statistics for long-memory processes, Chapman & Chal, 1994

work page 1994

[21] [21]

F. J. Molz, H. H. Liu, J. Szulga, Fractional Brownian motion and fractional Gaussian noise in subsurface hy- drology: A review, presentation of fundamental properties, and extensions, Water Resources Research 33 (10) (1997) 2273–2286

work page 1997

[22] [22]

D. A. Benson, M. M. Meerschaert, J. Revielle, Fractional calculus in hydrologic modeling: A numerical per- spective, Advances in Water Resources 51 (2013) 479–497

work page 2013

[23] [23]

A. Pashko, Simulation of telecommunication traffic using statistical models of fractional Brownian motion, in: 2017 4th International Scientific-Practical Conference Problems of Infocommunications. Science and Technol- ogy (PIC S&T), 2017, pp. 414–418

work page 2017

[24] [24]

Frecon, G

J. Frecon, G. Didier, N. Pustelnik, P. Abry, Non-Linear Wavelet Regression and Branch & Bound Optimiza- tion for the Full Identification of Bivariate Operator Fractional Brownian Motion, IEEE Transactions on Signal Processing 64 (15) (2016) 4040–4049. 13 Figure 4:Comparison of theoretical imaginary part of CAF at frequency 2λ0 given in Proposition 2 and i...

work page 2016

[25] [25]

Chang, S

Y . Chang, S. Chang, A fast estimation algorithm on the Hurst parameter of discrete-time fractional Brownian motion, IEEE Transactions on Signal Processing 50 (3) (2002) 554–559

work page 2002

[26] [26]

S. Liu, S. Chang, Dimension estimation of discrete-time fractional Brownian motion with applications to image texture classification, IEEE Transactions on Image Processing 6 (8) (1997) 1176–1184

work page 1997

[27] [27]

Gelbaum, M

Z. Gelbaum, M. Titus, Simulation of Fractional Brownian Surfaces via Spectral Synthesis on Manifolds, IEEE Transactions on Image Processing 23 (10) (2014) 4383–4388

work page 2014

[28] [28]

Rostek, R

S. Rostek, R. Schöbel, A note on the use of fractional Brownian motion for financial modeling, Economic Modelling 30 (2013) 30–35

work page 2013

[29] [29]

Maraj, D

K. Maraj, D. Szarek, G. Sikora, A. Wyłoma´nska, Time-averaged mean squared displacement ratio test for Gaus- sian processes with unknown diffusion coefficient, Chaos: An Interdisciplinary Journal of Nonlinear Science 31 (7) (2021) 073120

work page 2021

[30] [30]

W. Xiao, W. Zhang, X. Zhang, Y . Wang, Pricing currency options in a fractional Brownian motion with jumps, Economic Modelling 27 (5) (2010) 935–942

work page 2010

[31] [31]

Ernst, M

D. Ernst, M. Hellmann, J. Köhler, M. Weiss, Fractional Brownian motion in crowded fluids, Soft Matter 8 (2012) 4886

work page 2012

[32] [32]

Höfling, T

F. Höfling, T. Franosch, Anomalous transport in the crowded world of biological cells, Rep. Prog. Phys. 76 (2013) 046602. 14 Figure 5:Comparison of theoretical cyclic spectrum at frequency 0 given in Eq. (44) and ts Monte Carlo simulated counterpart for different values ofρ, with causal and well-balanced 2d fGn as the underlying process, forH 1 =0.4,H 2 =...

work page 2013

[33] [33]

Metzler, J

R. Metzler, J. Jeon, A. G. Cherstvy, E. Barkai, Anomalous diffusion models and their properties: non-stationarity, non-ergodicity, and ageing at the centenary of single particle tracking, Phys. Chem. Chem. Phys. 16 (44) (2014) 24128–24164

work page 2014

[34] [34]

Szarek, K

D. Szarek, K. Maraj-Zygmat, G. Sikora, D. Krapf, A. Wylomanska, Statistical test for anomalous diffusion based on empirical anomaly measure for Gaussian processes, Computational Statistics & Data Analysis 168 (2022) 107401

work page 2022

[35] [35]

Krapf, N

D. Krapf, N. Lukat, E. Marinari, R. Metzler, G. Oshanin, C. Selhuber-Unkel, A. Squarcini, L. Stadler, M. Weiss, X. Xu, Spectral Content of a Single Non-Brownian Trajectory, Phys. Rev. X 9 (2019) 011019

work page 2019

[36] [36]

Amblard, J.-F

P.-O. Amblard, J.-F. Coeurjolly, F. Lavancier, A. Philippe, Basic properties of the multivariate fractional Brow- nian motion, in: Séminaires et congrès, V ol. 28, 2013, pp. 65–87

work page 2013

[37] [37]

Coeurjolly, P.-O

J.-F. Coeurjolly, P.-O. Amblard, S. Achard, On multivariate fractional Brownian motion and multivariate frac- tional Gaussian noise, in: 2010 18th European Signal Processing Conference, IEEE, 2010, pp. 1567–1571

work page 2010

[38] [38]

Lavancier, A

F. Lavancier, A. Philippe, D. Surgailis, Covariance function of vector self-similar processes, Statistics & Proba- bility Letters 79 (23) (2009) 2415–2421

work page 2009

[39] [39]

Maejima, J

M. Maejima, J. Mason, Operator-self-similar stable processes, Stochastic Processes and their Applications 54 (1) (1994) 139–163. 15 Figure 6:Comparison of theoretical real part of cyclic spectrum at frequency 2λ0 given in Eq. (45) and its Monte Carlo simulated counterpart for different values ofρ, with causal and well-balanced 2d fGn as the underlying pro...

work page 1994

[40] [40]

Balcerek, A

M. Balcerek, A. Pacheco-Pozo, A. Wyłoma´nska, K. Burnecki, D. Krapf, Two-dimensional fractional Brownian motion: Analysis in time and frequency domains (2025)

work page 2025

[41] [41]

J. R. M. Hosking, Fractional differencing, Biometrika 68 (1981) 165–176

work page 1981

[42] [42]

G. S. Dissanayake, M. S. Peiris, T. Proietti, Fractionally differenced Gegenbauer processes with long memory: A review, Statistical Science 33 (2018)

work page 2018

[43] [43]

V . V . Anh, V . P. Knopova, N. N. Leonenko, Continuous-time stochastic processes with cyclical long-range dependence, Australian & New Zealand Journal of Statistics 46 (2) (2004) 275–296

work page 2004

[44] [44]

Papoulis, Random modulation: A review, IEEE Transactions on Acoustics, Speech, and Signal Processing 31 (1) (1983) 96–105

A. Papoulis, Random modulation: A review, IEEE Transactions on Acoustics, Speech, and Signal Processing 31 (1) (1983) 96–105

work page 1983

[45] [45]

Kechagias, V

S. Kechagias, V . Pipiras, P. Zoubouloglou, Cyclical long memory: Decoupling, modulation, and modeling, Stochastic Processes and their Applications 175 (2024) 104403

work page 2024

[46] [46]

Maddanu, T

F. Maddanu, T. Proietti, Modelling persistent cycles in solar activity, Solar Physics 297 (1) (2022) 13

work page 2022

[47] [47]

Proietti, F

T. Proietti, F. Maddanu, Modelling cycles in climate series: The fractional sinusoidal waveform process, Journal of Econometrics 239 (1) (2024) 105299

work page 2024

[48] [48]

P. J. Brockwell, R. A. Davis, Time Series: Theory and Methods, 2nd Edition, Springer, New York, 1991. 16 Figure 7:Comparison of theoretical imaginary part of cyclic spectrum at frequency 2λ 0 given in Eq. (45) and its Monte Carlo simulated counterpart for different values ofρ, with causal and well-balanced 2d fBm as the underlying process, forH 1 =0.4, H2...

work page 1991