Hi Andy,
Andy Farnell wrote:
JFYI the application is rainfall. Many papers I read describe
rainfall as Gaussian.
maybe mine is a simplistic approach, but shouldn't this be
one of the cases in which measuring the spectrum of true
rainfall sounds and trying to emulate it with one of
spectrum
Hey Alberto,
Thanks for the ideas. What this bit is for.. its not the
noisy background you get to rain, 1/x noise (everyone loves
that sound, sometimes called comfort noise), but I'm
looking at the effect of very light rain when it's on your window
and you can hear every individual drop. Apart
Hey Andy,
On 16/03/2008, at 23.12, Andy Farnell wrote:
I just neatened that up into an abstration + help
Thanks for wrapping it up.
All vanilla
I don't think [ln~] is vanilla. But [expr~ ln($v1)] could maybe do,
as it's shipped with vanilla.
Best, Steffen
Okay thanks for nfo.
@ Miller, please, could we get [abs~] and [ln~] into vanilla.
I think we all agree they are bread and butter objects.
cheers,
Andy
On Mon, 17 Mar 2008 16:59:08 +0100
Steffen Juul [EMAIL PROTECTED] wrote:
Hey Andy,
On 16/03/2008, at 23.12, Andy Farnell wrote:
I
On Mon, 2008-03-17 at 16:21 +, Andy Farnell wrote:
@ Miller, please, could we get [abs~] and [ln~] into vanilla.
I think we all agree they are bread and butter objects.
i do agree.
btw: thank you all for this very interesting thread. it was very
insightful. i really liked following it,
Andy Farnell wrote:
Okay thanks for nfo.
@ Miller, please, could we get [abs~] and [ln~] into vanilla.
I think we all agree they are bread and butter objects.
and ~, =~, ~, =~
thnks,
marius.
___
PD-list@iem.at mailing list
UNSUBSCRIBE and
Andy Farnell wrote:
Could a stats mathematician please help me check this. (attached)
Well I'm not one but...
I'm following the Box Muller formula for getting a cheap Gaussian
distribution (instead of adding up 12 sources a la central limit method).
On Sun, Mar 16, 2008 at 10:30 AM, Andy Farnell
[EMAIL PROTECTED] wrote:
Also, I have no idea how to check the distribution. It sounds the same as
uniform noise and looks the same in the spectrograph? What gives?
Do I need to average over a very long time or something to see any
On Sun, Mar 16, 2008 at 11:16 AM, Martin Peach
[EMAIL PROTECTED] wrote:
(gaussianoise has occasional values that exceed [-1 ... 1], which I
suppose is normal...white noise is always on [-1...1])
That's true. With the Box-Muller method, there is the log(~U1) term,
but you can always just add
Hi,
Could a stats mathematician please help me check this. (attached)
I'm following the Box Muller formula for getting a cheap Gaussian
distribution (instead of adding up 12 sources a la central limit method).
http://www.dspguru.com/howto/tech/wgn.htm
Does this look right?
I agree that
Charles Henry wrote:
On Sun, Mar 16, 2008 at 11:16 AM, Martin Peach
[EMAIL PROTECTED] wrote:
(gaussianoise has occasional values that exceed [-1 ... 1], which I
suppose is normal...white noise is always on [-1...1])
That's true. With the Box-Muller method, there is the log(~U1) term,
but
Oh no that's wrong isn't it :(
The log is necessary to keep the distribution normal, and the range is
going to get wider the closer to zero the radius is allowed to get.
The attached patch has a scale adjustment...
Still I wonder what kind of distribution gaussianoise2 gives, it's not
just
from the first equation that andy posted, I produced a gem
representation. the box muller noise seems wrong, because it does not
use the whole range but is shifted to the negative side.
note, this is not a distribution of frequencies, but of noise values..
marius.
Martin Peach wrote:
Oh no
GEM is broken here, but thanks for the info Marius.
I'm reading through the docs for R at the moment.
It makes lovely plots, but haven't figured how to get
my data in to it yet...
JFYI the application is rainfall. Many papers I read describe
rainfall as Gaussian.
I know from physical analysis
(sorry for the duplicate, Martin!)
The Box-Muller method (I've always thought it was just Ross who did
this one) is a classic trick. It probably goes back even to
Gauss--who knows and who cares
pdf of Gaussian:
f(x)= k * e^-(x^2/ (2*sigma^2))
k is a normalization constant--which we will
On Sun, Mar 16, 2008 at 2:49 PM, Charles Henry [EMAIL PROTECTED] wrote:
our cdf (cumulative dist function)
G(Z)=P( Zr^2 )= integral ( r^2 = 0 to Z, 1/sigma^2 * e^-(r^2/sigma^2) d(r^2)
G(Z)=1 - e^-(Z/sigma^2)
Take U1=Z on [0,1] , take U2 on [0,1]
Actually, it makes more sense for U1 to be
Here's a histogram generator (binner) that shows the distribution of
[gaussianoise]. Using it I can quickly see that [gaussianoise2] is too
peaked around zero and that [gaussianoise3] chops the tails off when the
scale is low.
If you have uniformly distributed raindrops falling, any given area
So, we can find g(r) independently by integrating with respect to theta.
we get g(r)= 1/sigma^2 * e^-(r^2/sigma^2)
Ah, here's a missing factor of 2 in the exponent. That should be
g(r)= 1/sigma^2 * e^-(r^2/ ( 2*sigma^2) )
And the correct formulae are
x=r*cos(theta) = sigma * sqrt(-2 * ln
Wow, that's a gorgeous demonstraton Martin!
Everything becomes clear as time - infinity :)
And somehow our little Earthling brains are able to
spot this signature distribution as we listen to rainfall.
Now I'm getting how uniform fall leads to
a Gaussian bell around the mean for an area over
I just neatened that up into an abstration + help
All vanilla
Replaced [abs~]
More efficient [q8-sqrt~] seens fine
No need for pi multiplier as is implicit in [cos~] radians (?)
Martins histogram in separate GOP abs
If I made a mistake please correct and repost.
a.
On Sun, 16 Mar 2008
# Hi, sorry for jumping into the conversation. I am doing my
statistical physics homework and can not read whole mails just skim
read them and saw terms like uniform distribution and gaussian
distribution. I thought it could be worth to mention the central
limit theorem which says that the
One thing I've been thinking of lately for pd is to synthesize a
impulse train with the poisson process. Many natural phenomena, like
the timing of rain drops, can be simulated with the poisson process.
It's just one of those ubitquitous relations that pops up everywhere.
A poisson process
On Sun, 16 Mar 2008 18:11:50 -0500
Charles Henry [EMAIL PROTECTED] wrote:
My interest in making an impulse train is to make the impulses, which
will have subtle deviations about a central frequency, and process
them through a filter (formant).
Would be useful. It's certainly common, saw this
23 matches
Mail list logo
