9 548 Pando UTB 01

Information about 9 548 Pando UTB 01

Published on November 19, 2007

Author: Laurence

Source: authorstream.com

Content

Characterizing Non-Gaussianities or How to tell a Dog from an Elephant:  Characterizing Non-Gaussianities or How to tell a Dog from an Elephant Jesús Pando DePaul University Contents :  Contents Gaussian Signals Distinguishing among Gaussian signals The non-Gaussian domain and the failure of spectral methods Wavelets Distinguishing dogs from elephants Conclusion Gaussian Signals:  Gaussian Signals Normal distributions are common, because the central limit theorem states that the sum of independent random variables with finite variance will result in normal distributions. Slide4:  The probability density is centered at the mean and 68% of the distribution lies within the square root of the second central moment, or the standard deviation. However, distributions caused by different physical processes with different time scales can have similar means and variances. Slide5:  Two Gaussian signals with mean = 0 and variance = 1.5 Spectral Methods:  Spectral Methods We need the variance as a function of scale in order to distinguish these distributions of the same mean and variance. The Power Spectrum reveals differences :  The Power Spectrum reveals differences Spectral Methods:  Spectral Methods Spectral techniques are effective in untangling Gaussian signals. The power spectrum, or variance as a function of scale, breaks down contributions of different physical processes to a signal. Non-Gaussian Signals:  Non-Gaussian Signals Non-Gaussian distributions Non-Linear dynamics and chaos Multi-component systems Non-Gaussian signals are much harder to characterize and detect. One easy way to distinguish between Gaussian and non-Gaussian signals is by the use of cumulants. Moments and Cumulants:  Moments and Cumulants The nth moment of distribution having probability density f and mean µ is:  xn f(x) dx  (x - µ)n f(x) dx is the nth central moment. Cumulants are defined via moments. For the the 1st and 2nd central moment (mean and variance), cumulants are equal to moments. However, higher order cumulants are given by the recursion formula: Slide12:  For instance, the first 3 cumulants defined in terms of the central moments are: 2 = 2 3 = 3 4 = 4 - 3 22 For a normal distribution 1 = 1 (mean) 2 = 2 (variance) n = 0 for n > 2 Cumulants are a way to detect non-Gaussian signals. However, we are faced with same problem as before; that is, it may be possible to have two very different signals with the nth cumulant equal. Wavelet Transform:  Wavelet Transform The wavelet transform is an integral transform whose basis functions are well localized in time and frequency (or space and scale). Wavelets have become increasingly important because of the ability to localize a signal efficiently in both time and frequency. Slide14:  Unlike the Fourier transform, there is no unique wavelet basis. Instead, the wavelets are defined by a function, , that is rescaled and translated: Slide15:  Wavelet Properties: Most useful wavelets have compact support. Wavelets can be classified as continuous or discrete. The discrete wavelet transform (DWT) produces two sets of coefficients; the scaling coefficients which give a local average, and the wavelet coefficients which give the fluctuation from the local average. The most useful DWT are also orthogonal. Especially, the wavelet coefficients are orthogonal in both space and scale (time and frequency). Slide17:  WFC’s, j,l , measure changes from local mean. A large WFC indicates a large local fluctuation. WFC’s look suspiciously like a central moment. As with the Fourier spectrum, we can define the Wavelet Variance Spectrum: Pj = <  l,j2 > where the average is done over position l at scale j. With wavelets, higher order cumulant spectra are readily defined. Slide18:  We define the third and fourth order cumulants as: Sj = Mj3/(Mj2)3/2 Kj = Mj4 /(Mj2)2 - 3 where Mn = < (j,l - j,l ) n > Thus, the wavelet gives a simple way to characterize some non-Gaussian distributions. Slide19:  Gaussian distribution with power spectrum, P(k) = k/(1 + a k4) where a is constant. Non-Gaussian Simulations:  Non-Gaussian Simulations Clumps or valleys with a signal/noise = 2.0 and random width between 1-5 bins are embedded in a Gaussian background. Distributions with16, 32, and 48 clumps (or valleys) are generated. 100 realizations of each is done and 95% confidence levels computed. Slide23:  Cumulant, 3 Cumulant, 4 Scale-Scale Correlations:  Scale-Scale Correlations The DWT cumulant spectra give a way to characterize different non-Gaussian signals. DWT measure can also give clues to the dynamics behind the non-Gaussian distributions. In scale dependent processes, one such measure is the scale-scale correlation. Slide26:  The Gaussian Block model results in a final distribution that is Gaussian since it is formed at each level by Gaussian random variables. The Branching block model results in a final distribution that is not Gaussian since each level(scale) has a memory of how it got there. Slide28:  The usual statistical measures fail to distinguish these distributions. We introduce the scale-scale DWT correlation: For a Gaussian distribution, Cjp,p = 1 for p  2. This statistical measure can therefore detect some types of dynamics (hierarchical). Conclusion:  Conclusion One point measures detect non-Gaussianities, but provide limited information about the signal. Traditional Fourier spectral methods are not ideal for higher order cumulants. Wavelets allow one to construct cumulant spectra. Wavelet versatility allows for the construction of customized measures and sometimes help us to say more than just a dog is not an elephant.

Related presentations


Other presentations created by Laurence

Growing Grapes in Wisconsin05
04. 01. 2008
0 views

Growing Grapes in Wisconsin05

lec29w
06. 03. 2008
0 views

lec29w

Positive Side of Life
03. 10. 2007
0 views

Positive Side of Life

022Neo Dada
03. 10. 2007
0 views

022Neo Dada

Soil Fertility 101 Wheat focus
09. 10. 2007
0 views

Soil Fertility 101 Wheat focus

gluthurk
04. 10. 2007
0 views

gluthurk

confined space training
07. 11. 2007
0 views

confined space training

Vogelsang
13. 11. 2007
0 views

Vogelsang

LR TMSA Danaos conference
15. 11. 2007
0 views

LR TMSA Danaos conference

HPSS IU slides
21. 11. 2007
0 views

HPSS IU slides

ri aquaculture permit process
28. 12. 2007
0 views

ri aquaculture permit process

Ch8
01. 01. 2008
0 views

Ch8

EEP101 15
03. 01. 2008
0 views

EEP101 15

AliyaKassamRE
04. 01. 2008
0 views

AliyaKassamRE

Shiva Kumar Sharma
06. 12. 2007
0 views

Shiva Kumar Sharma

Rabies 1
16. 11. 2007
0 views

Rabies 1

USDA Cultivar Poster
23. 11. 2007
0 views

USDA Cultivar Poster

Bio1100Ch3W
03. 01. 2008
0 views

Bio1100Ch3W

FinalMCX
19. 02. 2008
0 views

FinalMCX

20070412100800
12. 03. 2008
0 views

20070412100800

fasolSlides
14. 03. 2008
0 views

fasolSlides

q3ex
18. 03. 2008
0 views

q3ex

1129130239620
21. 03. 2008
0 views

1129130239620

chonSlides
27. 03. 2008
0 views

chonSlides

penrosepresentation
07. 04. 2008
0 views

penrosepresentation

refupdate
30. 03. 2008
0 views

refupdate

ogan
26. 11. 2007
0 views

ogan

GiraFlyer
23. 11. 2007
0 views

GiraFlyer

netinfo070919
28. 11. 2007
0 views

netinfo070919

Quiz Powerpoint3
06. 11. 2007
0 views

Quiz Powerpoint3

MuseumInformatics
02. 10. 2007
0 views

MuseumInformatics