This paper discusses the estimation of autocorrelation function (ACF) of fractional Gaussian noise (fGn) with long-range dependence (LRD). A variance bound of ACF estimation of one block of fGn with LRD for a given value of the Hurst parameter (H) is given. The present bound provides a guideline to require the block size to guarantee that the variance of ACF estimation of one block of fGn with LRD for a given H value does not exceed the predetermined variance bound regardless of the start point of the block. In addition, the present result implies that the error of ACF estimation of a block of fGn with LRD depends only on the number of data points within the sample and not on the actual sample length in time. For a given block size, the error is found to be larger for fGn with stronger LRD than that with weaker LRD.
1. Introduction
ACF analysis, or equivalently spectral analysis according to the Wiener-Khintchine theorem, plays a role in many areas of sciences and technologies (see, e.g., [1, 2]), such as structural engineering [3–7]. In engineering, ACF or its Fourier transform (power spectrum density function (PSD)) can only be estimated according to a given record length in measurement. Note that the random load simulated in a laboratory test may be generated based on a predetermined ACF or PSD; see, for example, [8–13]. Thus, the quality of ACF or PSD estimation has great impact on structure analysis and design.
The literature of error analysis (mainly, bias, and variance) of ACF/PSD estimation of an ordinary random process is quite rich; see, for example, [1, 2, 14–19]. By ordinary random processes, we mean that the ACF and PSD of a process are ordinary functions except the Dirac delta function that is the ACF of white noise.
Note that processes with LRD or long-memory substantially differ from ordinary processes [20]. By LRD, we mean that the ACF of a process is nonsummable in the discrete case or nonintegrable in the continuous case [20]. Hence, its PSD should be considered in the sense of generalized function over the Schwartz space of test functions. FGn introduced in [21] is a widely used model of stationary fractal time series, which has found increasingly wide applications in many fields of sciences and technologies, ranging from hydrology to network traffic; see, for example, [22–45]. Note that the statistics of a zero mean Gaussian process are completely determined in terms of its ACF. Therefore, when using fGn-type load in structural engineering, the method to assure the quality of its ACF estimation is desired. In passing, we mention that, in the field of the Internet, ACF estimation of fGn-type teletraffic is utilized for detection of distributed denial-of-service flood attacks [32].
In the field, [46] discussed the statistical error of the structure function of Gaussian random fractals, and [47] studied the bias of the sample autocorrelations of fractional noise. This paper aims at providing a variance bound of the ACF estimation of one block of fGn.
An ACF is usually estimated on a block-by-block basis [1, 10, 13], where block size means the number of data points of a block of sample. Note that the ACF estimation of different blocks may be different, resulting in the estimation error caused by sectioning. The error resulted from sectioning can be reduced by the skill of averaging [1]. Different from conventional methods to reduce errors based on averaging, this research studies how to determine the size of one block according to a given degree of accuracy of ACF estimation of fGn with LRD.
Intuitively, if the size of one block is large enough, the ACF estimation will be independent of the start point for sectioning the block. Let N be the block size of fGn with LRD. The aim of this paper is to provide a formula to calculate the variance bound of ACF estimation of fGn with LRD for a given N and a given value of H.
The remaining article is organized as follows. Section 2 presents an error bound of ACF estimation of one block of fGn with LRD. Discussions are given in Section 3. Finally, Section 4 concludes the paper.
2. Variance Bound of ACF Estimation of One Block of fGn with LRD2.1. Preliminaries
Let B(t) be ordinary Brownian motion (Bm) for t≥0 and B(0) = 0 [48]. The stationary white noise can be taken as B′(t), which is the derivative of B(t) in the domain of generalized functions. Let D0t-v be the Riemann-Liouville integral operator [49, 50]. Then,
D0t-vB′(t)=1Γ(v)∫0t(t-u)v-1dB(u),
where Γ is the Gamma function. Replacing ν with H+1/2 in (2.1) yields
D0t-(H+1/2)B′(t)=1Γ(H+1/2)∫0t(t-u)H-1/2dB(u)≜BH0(t).
In the above expression, BH0(t) is termed the Riemann-Liouville fractional Brownian motion (fBm) and 0<H<1. This fBm is self-similar but does not have stationary increments. In passing, it is noted that the fBm described in the sense of the Riemann-Liouville fractional integral can be explained as the response of a fractional system, the impulse response of which is tH-1/2/Γ(H+1/2) under the excitation of white noise from a view of the theory of linear fractional systems discussed in [51, 52].
Following Mandelbrot and van Ness [21], the fBm that is self-similar and has stationary increments is defined for t>0 by
BH(t)-BH(0)=1Γ(H+1/2){∫-∞0[(t-u)H-0.5-(-u)H-0.5]dB(u)+∫0t(t-u)H-0.5dB(u)},
where BH(0)=b0 is the starting value at time 0. If b0=0, B1/2(t)=B(t). Hence, fBm generalizes Bm. The fBm expressed by (2.3) is the fractional integral of B(t) in the sense of Weyl (see [49, 50] for the details of the fractional Weyl integral operator).
FGn is the increment process of fBm. It is stationary and self-affine with parameter H. Let X(t) be fGn in the continuous case. Then, the ACF of X(t) is given by
r(τ)=σ2ε2H-22[(|τ|ε+1)2H+||τ|ε-1|2H-2|τε|2H],τ∈ℝ,
where 0<H<1, σ2=(Hπ)-1Γ(1-2H)cos(Hπ) is the intensity of fGn, and ε>0 is used by regularizing fBm so that the regularized fBm is differentiable [21, pages 427-428]. The PSD of X(t) is given by (Li and Lim [53])
S(ω)=σ2sin(Hπ)Γ(2H+1)|ω|1-2H.
Letting ε= 1 and replacing τ∈ℝ by k∈ℤ in (2.4) yields the ACF of the discrete fGn (dfGn):
r(k)=σ22[(|k|+1)2H+||k|-1|2H-2|k|2H],k∈ℤ.
Recall that a stationary Gaussian process with ACF r(τ) is of LRD if [20]
∫0∞r(τ)dτ=∞;
otherwise it is of short-range dependence (SRD). Another definition of LRD is given as follows. For asymptotically large time scales, if
r(τ)~τ-β,β∈(0,1)asτ→∞,
then the process is of LRD.
Note that the expression 0.5[(k + 1)2H − 2k 2H + (k − 1)2H ] described in (2.6) is the finite second-order difference of 0.5(k)2H . Approximating it with the second-order differential of 0.5 (k)2H yields
0.5[(k+1)2H-2k2H+(k-1)2H]≈H(2H-1)(k)2H-2.
Expressing β in (2.8) by the Hurst parameter H gives β=2-2H, or
H=1-β2.
The LRD condition expressed by H therefore is 0.5 < H < 1. The larger the H value, the stronger the long-range persistence.
FGn contains three subclasses of time series. In the case of 0.5 < H < 1, r(τ) is positive and finite for all τ. It is monotonously decreasing but nonintegrable. In fact, from the ACF of dfGn described by (2.9), one immediately has ∑0∞k2H-2=∞. Thus, for 0.5 < H < 1, the corresponding fGn is of LRD. For H∈(0,0.5), the integral of r(τ) is zero. Hence, fGn is of SRD in this case. Moreover, r(τ) changes its sign and becomes negative for some τ proportional to ε in the parameter domain [21, page 434]. FGn reduces to white noise when H=0.5.
Note that if r(τ) is sufficiently smooth on (0,∞) and if
r(0)-r(τ)~c|τ|αfor|τ|→0,
where c is a constant, then one has the fractal dimension of X(t) as
D=2-α2;
see, for example, [54–57]. The local irregularity of the sample paths is measured by α, which can be regarded as the fractal index of the process. Thus, the behaviour of r(τ) near the origin determines the local irregularity or the local self-similarity of the sample paths. The larger the D value, the higher the local irregularity.
Now, in the case of ε=1, we apply the binomial series to r(τ). Then, one has
r(0)-r(τ)~c|τ|2Hfor|τ|→0.
Therefore, one immediately gets
D=2-H.
Hence, H measures both LRD and self-similarity of fGn. In other words, the local properties of fGn are reflected in the global ones as remarked by Mandelbrot [58, page 27].
Figures 1(a) and 1(b) give the plots of the ACFs of fGn with LRD and SRD in the case of ε=1, respectively.
Plots of ACF of fractional Gaussian noise. (a) ACF of fGn with LRD. Solid line is for H = 0.95, dot line is for H = 0.75, and dadot line is for H = 0.55. (b) ACF of fGn with SRD. Solid line is for H = 0.45, dot line is for H = 0.25, and dadot line is for H = 0.05.
2.2. Variance Bound
In practical terms, the number of measured data points within a sample of fGn is finite. Let a positive integer N be the number of data points of a measured sample of dfGn sequence x(i). Then, the ACF of x(i) is estimated by
R(k)=1N∑i=1Nx(i)x(i+k).
Usually, for l,m∈ℤ+,
1N∑i=mN(m+1)Nx(i)x(i+k)≠1N∑i=lN(l+1)Nx(i)x(i+k).
Therefore, R(k) is a random variable.
Let M2(R) be the mean square error in terms of R. Denote R(k) by R(k; H, N). The aim of the statistical error analysis in this research is to derive a relationship between M2(R) and N as well as H so as to establish a reference guideline for requiring N under the conditions that the bound of M2(R) and the value of H are given.
Theorem 2.1.
Let x(i) be dfGn series with LRD. Let r(k) be the true ACF of x(i). Let N be the number of data points of a sample sequence. Let R(k) be an estimate of r(k). Let Var(R) be the variance of R. Then,
Var(R)≤4|Γ(1-2H)|2cos2(Hπ)(2H-1)2π2N∑i=1N(i)4H-4.
Proof.
Mathematically, r(k) is computed over infinite interval [1, 2, 59]:
r(k)=E[x(i)x(i+k)]=limN→∞1N∑i=0Nx(i)x(i+k).
In practice, r(k) can only be estimated with a finite sequence. Therefore,
r(k)≈R(k)=1N∑i=N0N0+Nx(i)x(i+k),
where N0 is the start point.
Let b2(R) be the bias of R. Then, M2(R)=E[(r-R)2]= Var(R) +b2(R). Since
E[R(τ)]=1N∑i=N0N0+NE[x(i)x(i+k)]=1N∑i=N0N0+Nr(k)=r(k),R(k) is the unbiased estimate ofr(k) and M2(R)=Var(R) accordingly. We need to express Var(R) by the following proposition to prove the theorem.
Proposition 2.2.
Let x(i) be dfGn with LRD. Let r(k) be the true ACF of x(i). Let N be the number of data points of a sample sequence. Let R(k) be an estimate of r(k). Let Var(R ) be the variance of R. Suppose that r(k) is monotonously decreasing and r(k) ≥ 0. Then,
Var(R)≤4N∑i=0Nr2(k).
Proof.
As Var(R) = E{[R-E(R)]2} = E(R2) – E2(R), according to (P-3), one has
Var(R)=E(R2)-r2.
Expanding E(R2) yields
E(R2)=E{[1N∑N0N0+Nx(i)x(i+k)]2}=E[1N2∑N0N0+Nx(i1)x(i1+k)∑N0N0+Nx(i2)x(i2+k)]=E[1N2∑N0N0+N∑N0N0+Nx(i1)x(i2)x(i1+k)x(i2+k)]=1N2∑N0N0+N∑N0N0+NE[x(i1)x(i2)x(i1+k)x(i2+k)].
Thus,
Var(R)=1N2∑N0N0+N∑N0N0+NE[x(i1)x(i2)x(i1+k)x(i2+k)]-r2(k).
Let
X1=x(n1),X2=x(n2),X3=x(n1+k),X4=x(n2+k).
Then,
E[x(n1)x(n2)x(n1+k)x(n2+k)]=E(X1X2X3X4).
Since x is Gaussian, random variables X1,X2,X3, and X4 have a joint-normal distribution and E(X1X2X3X4)=m12m34+m13m24+m14m23, where
m12=E[x(n1)x(n2)]=r(n2-n1),m13=E[x(n1)x(n1+k)]=r(k),m14=E[x(n1)x(n2+k)]=r(n2-n1+k),m23=E[x(n2)x(n1+k)]=r(n1-n2+k),m24=E[x(n2)x(n2+k)]=r(k),m34=E[x(n1)x(n2+k)]=r(n2-n1).
Therefore,
1N2∑N0N0+N∑N0N0+NE[x(i1)x(i2)x(i1+k)x(i2+k)]=1N2∑N0N0+N∑N0N0+NE(X1X2X3X4)=1N2∑N0N0+N∑N0N0+N(m12m34+m13m24+m14m23)=1N2∑N0N0+N∑N0N0+Nr2(i2-i1)+r2(k)+r(i2-i1+k)r(i1-i2+k)=1N2∑N0N0+N∑N0N0+Nr2(i2-i1)+r(i2-i1+k)r(i1-i2+k)+r2(k).
According to (P-6), the variance is expressed as
Var(R)=1N2∑N0N0+N∑N0N0+Nr2(i2-i1)+r(i2-i1+k)r(i1-i2+k).
Replacing (i2-i1) with i in the above expression yields
Var(R)=1N2∑i1=N0N0+N∑i=N0N0-N1+Nr2(i)+r(i+k)r(-i+k)=1N2∑i1=N0N0+N∑i=N0N0-N1+Nf(i),
where f(i) = r2(i)+r(i+k)r(-i+k). Without losing generality, let N0=0. Then, the above becomes
Var(R)=1N2∑i=0N(N-i)f(i)+1N2∑i=-N0(N+i)f(i).
Since ACF is an even function, the above expression is written by
Var(R)≤4N∑i=0Nr2(i)≤4N∑i=1Nr2(i)≤σ4N∑i=1N[(i+1)2H-2i2H+(i-1)2H]2.
According to (2.9), replacing [(i+1)2H-2i2H+(i-1)2H] on the right hand of the above expression by (i)2H, we have
Var(R)≤4|Γ(1-2H)|2cos2(Hπ)(2H-1)2π2N∑i=1N(i)4H-4.
Theorem results.
The above formula represents an upper bound of Var(R). Denote by s(N,H) the bound of standard deviation. Then,
s(N,H)=2Γ(1-2H)cos(Hπ)|2H-1|π1N∑i=1N(i)4H-4.
We illustrate s(N, H) in terms of N by Figure 2 for H = 0.60, 0.70, 0.80, and 0.90.
Error bound s(N, H). (a) H = 0.60, 0.70. (b) H = 0.80, 0.90.
From Figure 2, we see that s(N,H1)>s(N,H2) for H1>H2, meaning that the error of ACF estimation of fGn is larger with stronger LRD than that with weaker LRD.
3. Discussions3.1. To Avoid Misleading Result of ACF Estimation
Recall that processes with LRD substantiality differ from those with SRD [20]. Therefore, possible SRD signs of an ACF estimate of an fGn series that is of LRD may be taken as a misleading result of ACF estimation.
Suppose that we have a block of fGn with H = 0.75. Hence, this series is of LRD. Figure 3(a) shows an fGn series with H = 0.75, which is synthesized with the method given in [60].
Case study. Solid line: theoretic ACF of fGn. Dot line: ACF estimate. (a) FGn with H = 0.75. (b) AFC estimate for N = 256. (c) The first 64 points of Figure 3(b). (d) The first 128 points of Figure 3(b).
Assume the block size N = 256. Then, we have Var(R)≤0.015 according to Theorem 2.1. The dotted line in Figure 3(b) indicates its ACF estimation with N = 256 and the solid line in Figure 3(b) shows the theoretical ACF of fGn with H = 0.75. We note that the error regarding the ACF estimate reflected by the dotted line in Figure 3(b) is severe because many points of the dotted line are negative. Thus, it may probably confuse the property of the positive correlation (i.e., LRD) of the data being processed. Consequently, by the dotted line in Figure 3(b), one might likely be misled to take the data being processed (Figure 3(a)) as SRD. Figures 3(c) and 3(d) show the first 64 and 128 points of Figure 3(b), respectively. They again show the possible confusions caused by severe estimation error.
Now we increase the block size such that N = 2048. Then, one has Var(R)≤2.5×10-3 according to (2.17). In this case, the ACF estimation is indicated by the dotted line in Figure 4(a). Comparing Figure 4(a) to Figure 3(b), we see that the error of ACF estimation is considerably reduced when N increases to 2048 because most data points of the ACF estimate are positive. Figures 4(b), 4(c), and 4(d) give the plots of the first 64, 128, and 256 points of Figure 4(a), respectively. They evidently interpret the improvement of the quality of ACF estimation of one block of fGn with LRD by increasing the block size.
Solid line: theoretic ACF of FGN. Dot line: ACF estimate. (a) ACF estimate of fGn with H = 0.75 for N = 2048. (b) The first 64 points of Figure 4(b). (c) The first 128 points of Figure 4(b). (d) The first 256 points of Figure 4(b).
From the above, one sees that the accuracy of ACF estimate of fGn with LRD can be increased if the block size increases. Therefore, in addition to the direct way to increase the record length, increasing the sampling rate in measurement of fGn to be processed may yet be a way to increase the accuracy of the ACF estimation in the case that the block size is given.
3.2. One Block Estimation
The previous discussions regarding ACF estimation of fGn with LRD do not relate to averaging. In fact, once the block size N is such that it meets the required accuracy according to Theorem 2.1, the ACF estimation is independent of the start point of the block. That is, for any N0∈ℤ+,(1/N)∑i=N0N0+Nx(i)x(i+k) yields an ACF estimate, the error of which is bounded based on Theorem 2.1. Further, we note that the discussed ACF estimation does not relate to sectioning. As a matter of fact, for each m∈ℤ+,(1/N)∑i=mN(m+1)Nx(i)x(i+k) yields an ACF estimate, the error of which is bounded by (2.17).
3.3. Remarks
In the field of fractional order signal processing (see, e.g., [61]), [62] recently introduced a method to obtain a reliable estimation of H based on fractional Fourier transform for processing very long experimental time series locally. It is worth noting that the present error bound in this paper may yet be an explanation why the reliable estimation of H discussed in [62] requires long series.
Finally, we note that the ACF estimate expressed by (2.15) is biased one. However, that does not matter because the present variance bound relates to the fluctuation of the ACF estimate regardless of whether it is biased or not.
4. Conclusions
We have established an error bound of ACF estimation of one block of fGn with LRD. It has been shown that the error does not depend on the absolute length of the sample but only relies on the number of data points, that is, the block size N, of the sample. The error of an ACF estimate of fGn with stronger LRD is larger than that with weaker LRD for a given N. The discussed ACF estimation is not related to averaging. The accuracy of an ACF estimate of a block of fGn with LRD can be guaranteed once the block size is selected according to (2.17) without the relation to sectioning.
Acknowledgment
This work was supported in part by the National Natural Science Foundation of China under the project Grant nos. 60573125, 60873264, and 60873102.
MitraS. K.KaiserJ. F.1993New York, NY, USAJohn Wiley & SonsBendatJ. S.PiersolA. G.20003rdNew York, NY, USAJohn Wiley & SonsElishakoffI.LyonR. H.198614New York, NY, USAElsevierxx+565Studies in Applied MechanicsMR1035307PreumontA.199333London, UKKluwerStudies in Applied MechanicsJensenJ. J.DoglianiM.Wave-induced ship hull vibrations in stochastic seaways199693-43533872-s2.0-002570302610.1016/0951-8339(95)00031-3GuX.-K.HuJ.-J.ShenJ.-W.The frequency characteristics of ship vertical wave bending moments20004113138BenasciuttiD.TovoR.Spectral methods for lifetime prediction under wide-band stationary random processes20052788678772-s2.0-000099547610.1016/j.ijfatigue.2004.10.007ZBL1068.74055Technical Software Consultants LimitedFLAPS: Fatigue Laboratory Applications Package, Version 01:03Instron 2165035, UKLiM.An optimal controller of an irregular wave maker200529155632-s2.0-774424042310.1016/j.apm.2004.07.008ZBL1147.76554LiM.An iteration method to adjusting random loading for a laboratory fatigue test20052777837892-s2.0-834424459110.1016/j.ijfatigue.2005.01.011LiM.Experimental stability analysis of a test system for doing fatigue tests under random loading20063443643672-s2.0-0032047505LiM.WuY.-S.XuB.-H.JiaW.ZhaoW.An on-line correction technique of random loading with a real-time signal processor for a laboratory fatigue test20002854094142-s2.0-004218529910.1520/JTE12129JLiM.XuB.-H.WuY.-S.An H2-optimal control of random loading for a laboratory fatigue test19982666196252-s2.0-002018952710.1520/JTE12121JMarriottF. H. C.PopeJ. A.Bias in the estimation of autocorrelations195441390402MR0065125ZBL0056.13302JakemanE.PikeE. R.SwainS.Statistical accuracy in the digital autocorrelation of photon counting fluctuations19714451753410.1088/0305-4470/4/4/0152-s2.0-0006370302PickandsJ.IIISpectral estimation with random truncation19704114458MR025822010.1214/aoms/1177697187ZBL0213.20603GrenanderU.Bandwidth and variance in estimation of the spectrum1958201152157MR0096343ZBL0091.15003ThomsonD. J.Spectrum estimation and harmonic analysis1982709105510962-s2.0-002018954110.1109/PROC.1982.12433LiM.A method for requiring block size for spectrum measurement of ocean surface waves2006556220722152-s2.0-2114444076810.1109/TIM.2006.884134BeranJ.199461New York, NY, USAChapman & Hallx+315Monographs on Statistics and Applied ProbabilityMR1304490MandelbrotB. B.van NessJ. W.Fractional Brownian motions, fractional noises and applications1968104422437MR024223910.1137/1010093ZBL0179.47801HurstH. E.Long-term storage capacity of reservoirs1951116770808MandelbrotB. B.WallisJ. R.Noah, Joseph and operational hydrology19684590991810.1029/WR004i005p00909BarbosaS. M.FernandesM. J.SilvaM. E.Long-range dependence in North Atlantic sea level2006371272573110.1016/j.physa.2006.03.0462-s2.0-33748699789LawranceA. J.KottegodaN. T.Stochastic modelling of riverflow time series197714011472-s2.0-001744897110.2307/2344516RadziejewskiM.KundzewiczZ. W.Fractal analysis of flow of the river Warta19972001–428029410.1016/S0022-1694(97)00024-32-s2.0-0031574174MandelbrotB. B.2002New York, NY, USASpringerx+654Selected Works of Benoit B. MandelbrotMR1878884StallingsW.1998chapter 8Upper Saddle River, NJ, USAPrentice-HallLiM.An approach to reliably identifying signs of DDOS flood attacks based on LRD traffic pattern recognition20042375495582-s2.0-074226930610.1016/j.cose.2004.04.005MandelbrotB. B.2002New York, NY, USASpringerx+654Selected Works of Benoit B. MandelbrotMR1878884Levy-VehelJ.LuttonE.TricotC.1997Berlin, GermanySpringerLiM.ZhaoW.Detection of variations of local irregularity of traffic under DDOS flood attack20082008114758782-s2.0-0029323403LiM.Modeling autocorrelation functions of long-range dependent teletraffic series based on optimal approximation in Hilbert space-A further study20073136256312-s2.0-834424459110.1016/j.apm.2005.11.029LiM.Change trend of averaged Hurst parameter of traffic under DDOS flood attacks20062532132202-s2.0-000179070310.1016/j.cose.2005.11.007CattaniC.Shannon wavelets theory20082008241648082-s2.0-5454911129710.1155/2008/164808ZBL1162.42314BakhoumE. G.TomaC.Relativistic short range phenomena and space-time aspects of pulse measurements20082008204101562-s2.0-024237109710.1155/2008/410156ZBL1163.83319CattaniC.Harmonic wavelet analysis of a localized fractal2009113544AbryP.BorgnatP.RicciatoF.ScherrerA.VeitchD.Revisiting an old friend: on the observability of the relation between long range dependence and heavy tailTelecommunication Systems, 20092-s2.0-7035000816610.1007/s11235-009-9025-6LiM.ChenW.-S.HanL.Correlation matching method of the weak stationarity test of LRD trafficTelecommunication Systems, 20092-s2.0-7034989321510.1007/s11235-009-9206-5JanowskiL.OwezarskiP.Assessing the accuracy of using aggregated traffic traces in network engineeringTelecommunication Systems, 20092-s2.0-7035012143010.1007/s11235-009-9210-9LiC.ZhaoW.Stochastic performance analysis of non-feedforward networksTelecommunication Systems, 20092-s2.0-7034999943810.1007/s11235-009-9211-8LiM.Fractal time series—a tutorial201020102615726410.1155/2010/157264LiM.ZhaoW.Representation of a stochastic traffic boundIEEE Transactions on Parallel & Distributed Systems, 2009, http://doi.ieeecomputersociety.org/10.1109/TPDS.2009.162TianK.-L.LiM.A reliable anomaly detector against low-rate DDOS attack20091116CattaniC.Harmonic wavelet approximation of random, fractal and high frequency signalsTelecommunication Systems. In pressJakemanE.JordanD. L.Statistical accuracy of measurements on Gaussian random fractals19902343974052-s2.0-002541490410.1088/0022-3727/23/4/002NewboldP.AgiakloglouC.Bias in the sample autocorrelations of fractional noise1990303698702HidaT.198011New York, NY, USASpringerxvi+325Applications of MathematicsMR562914KilbasA. A.SrivastavaH. M.TrujilloJ. J.2006204Amsterdam, The NetherlandsElsevier Sciencexvi+523North-Holland Mathematics StudiesMR2218073MillerK. S.RossB.1993New York, NY, USAJohn Wiley & Sonsxvi+366A Wiley-Interscience PublicationMR1219954OrtigueiraM. D.Introduction to fractional linear systems, part I: continuous-time systems20001471627010.1049/ip-vis:20000272OrtigueiraM. D.BatistaA. G.A fractional linear system view of the fractional brownian motion2004381–42953032-s2.0-1554437866410.1007/s11071-004-3762-8ZBL1115.60044LiM.LimS. C.A rigorous derivation of power spectrum of fractional Gaussian noise200664C33C362-s2.0-3384608937110.1142/S0219477506003604AdlerR. J.1981New York, NY, USAJohn Wiley & Sonsxi+280Wiley Series in Probability and Mathematical StatisticMR611857HallP.RoyR.On the relationship between fractal dimension and fractal index for stationary stochastic processes199441241253MR125818310.1214/aoap/1177005210ZBL0798.60035ChanG.HallP.PoskittD. S.Periodogram-based estimators of fractal properties199523516841711MR137030310.1214/aos/1176324319ZBL0843.62090KentJ. T.WoodA. T. A.Estimating the fractal dimension of a locally self-similar gaussian process by using increments19975936796992-s2.0-14244255625ZBL0889.62072MandelbrotB. B.1982New York, NY, USAW. H. Freemanv+460MR665254KornG. A.KornT. M.1961New York, NY, USAMcGraw-HillLiM.ChiC.-H.A correlation-based computational model for synthesizing long-range dependent data20043406-750351410.1016/j.jfranklin.2003.09.0022-s2.0-0942299299MR2034553ChenY.SunR.ZhouA.An overview of fractional order signal processing (FOSP) techniques5Proceedings of the ASME International Design Engineering Technical Conferences & Computers and Information in Engineering Conference (IDETC/CIE '07)September 2007Las Vegas, Nev, USA12051222DETC2007-342282-s2.0-0001494578ChenY.-Q.SunR.ZhouA.An improved Hurst parameter estimator based on fractional Fourier transformTelecommunication Systems, 200910.1007/s11235-009-9207-4