Confidence bounds for non-linear fit

Is it possible to get the confidence bounds for the fitted coeficients when using non-linear fits?

Hello Dahl
Do you mean like Upper Bound and Lower Bound output terminals of NI_Gmath.lvlib::Nonlineat Curve fir intervals.vi?
Message Edited by Eirikur on 01-09-2008 01:25 PM
Regards,
Eirikur Runarsson
Platinum Applications Engineer
NI Denmark

Similar Messages

  • Need examples for non-linear optimization

    In the mathematics - optimization section there is a VI which is..... unconstrained optimization
    I am using the downhill simplex option and the input that describes the objective function is "another VI" which I will create.
    Are there any examples on how to use this VI since I am not sure how to use the "objective function" input which is a reference to another VI and how to set up the "function data" input either (i.e do you use it specify constants ???? how do you do this ????)

    Hi sammy,
    You can find more information about this command by right-clicking on the VI and choosing Help. You can then choose the Downhill Simplex option for a detailed description of how to use this VI. The following information is provided in the Help about the "objective VI" you must build:
    objective function is a reference to the VI that implements the
    function to optimize. Create this VI by starting from the VI template located at
    labview\vi.lib\gmath\NumericalOptimization\ucno_objective
    function template.vit.
    Also, more help information can be viewed here:
    Downhill Simplex nD (Not in Base Package)
    I didn't find an example program in our Developer Zone, but you might be able to find one by searching the Discussion Forums.
    Hope this helps!
    Amanda Howard
    Americas Services and Support Recruiting Manager
    National Instruments

  • Solving Coefficien​ts for Non-Linear Equation

    I have the following equation that I need to solve a, b and c. y = a+bexp(-x/c). Is there a VI that is written to help me?

    i don't understand what do you suppose to mean?
    you have not a,b and c values and you wanna solve 3 unknown variables with just one equation?
    do you think is that possible?
    even you had x and y values!
    but if you have 4 values and you just want to find another variables value it's so easy
    you can easily use a formula node.
    i have write a simple program for you to solve this equation and i attached it to this answer.
    it's with LabVIEW 5.
    Attachments:
    formula_node_example.vi ‏25 KB

  • PPro CS5 Crash Course for Non-Linear Editors

    Backstory: I was asked this morning to teach a crash course in Premiere CS5 for the students in the film program at my school in the Introduction to Editing class who have been using FCP. They have to edit several projects using RED footage, and rather than spend a huge amount of time transcoding it to a format which FCP can work with, the prof has just decided to have his students use PPro CS5 (which is also on their editing computers). Since the prof doesn't use PPro, he's asked me to teach the class for him.
    I created a very brief crash course powerpoint to assist me in giving them the fundamentals of the program, and supply them with a resource to refer back to as they work on their projects after class is over tomorrow morning. I created this for students who already have done some editing in an NLE, and so don't need to be taught WHAT everything is and HOW to cut footage and put together a timeline. This is just to introduce editors to PPro CS5 who are not already familiar with the PPro workflow.
    Anyway, I wondered if some of you gurus would want to take a look at it and give me your feedback on what I've covered well, what I might have missed, and any other thoughts y'all had.
    You can view a PDF of the document at www.bryan.edu/pprocs5 The viewer will bring it up embedded in the page at about 40-50%, so you'd be best off to click the download link and open it in Acrobat where you can go full size with it.

    Thanks for the input!
    I actually taught hem REDCINE-X last week so that they could use it to export their files to an intermediate codec that FCP would understand, and preserve the new colorspace. Unfortunately these computers are so slow that the export process was gonna take nearly a week for all the files they need to work with, so the prof opted to swtich over to PPro midstream since it can handle the raw 4k and supports the new colorspace.
    I didn't mention the saving thing... forgot about it; but the conforming issue did come up and we were able to talk about that in class!
    The class went okay, I guess... I don't know what it is about students these days, but most of them (like all but one) weren't really paying very good attention and they were just sorta goofing off, talking amongst themselves, etc... made it really frustrating to teach this platform!
    Oh well.

  • Fit non lineare basato su una funzione f(x)

    -Sto cercando di fare un fit non lineare su una curva. La funzione che utilizzo per il fit è il prodotto di una lorentziana per un polinomio del terzo ordine x un totale di 7 parametri (3 x la lorentziana e 4 x il polinomio).
    Il problema è che il fit non mi soddifsfa affatto. Sarebbe forse utile dare ai parametri un range limitato di valori (almeno x l'ampiezza della lorentziana) entro il quale variare ma non saprei proprio come fare(..e se si possa fare..)
    -Esiste un altro modo x risolvere il problema?
    -E se il numero di parametri salisse a 13 (3 lorentziane e un polinomio del terzo ordine) il calcolo del fit sarebbe ancora più difficoltoso?
    -Vorrei inoltre sapere, una volta assegnati i parametri iniziali, come il blocco proceda nelle iterazioni e cioè se continui ad incrementare il valore dei parametri fino a trovare l'ottimo o se si muova in un range che abbia come centro il valore iniziale dei parametri.
    Grazie

    Ciao Fortu,
    in questo documento puoi trovare informazioni riguardanti l'algoritmo utilizzato per determinare i coefficienti (a1, a2, ..., aM): What is the Difference Between the Two Levenberg-Marquardt VIs in LabVIEW? http://digital.ni.com/public.nsf/websearch/BACF6FDF1B40993686256CC300657BA4?OpenDocument
    Non è possibile, settare un intervallo di appartenza dei coefficienti ma si deve settare solo un valore iniziale. La precisione e la velocità del processo di fitting è fortemente determinato dalla scelta di questi valori iniziali.
    ciao buon lavoro.

  • Non linearity between pixels and widht for linescan

    Hi
    I'm developing a width gauge based on a linescan camera.
    The gauge is measuring the surface of a steel strip moving at 200m/sec.
    I found a non linearity between the relation of pixels and real widht:
    1904mm X 6635,6pixels
    1308mm X 4616,7pixels
    814mm X 2880,6pixels
    I've tried the working distances between 2600 to 2800mm.
    The field of view is 2200mm.
    The focal lengh is 35mm.
    The size of CCD is 28.67mm (3.5um X 8192pixels - Basler raL8192-12gm).
    Somebody already faced this problem?
    Thanks,
    Alexandre.
    Solved!
    Go to Solution.

    Hi Greg
    Thanks for your idea. I implemented a polynomial from Excel according the attached. It's running well until now.
    Another problem that I'm facing is the oscilation on the image (https://www.dropbox.com/s/cboyglx74g8sd93/width%20gauge.mp4?dl=0) when the grid and filter are applied. I would like get stable the filtered image and grid from edge detector.
    Does anyone know how to solve this?
    Thanks for the moment.
    Attachments:
    calibrcurve_ml2.xlsx ‏20 KB

  • No non-linear under voice-port to reslove hissing on NM-HDV

    Hello.
    I have a trouble with 2MFT on NM-HDV.
    I can hear hissing on call.
    So, i had configured no non-linear under voice-port, then i can't hear any hissing.
    Instead, I can hear echo on call.
    How can i fix it?
    Regard,
    john.

    Hell Venky.
    Thnak you for your helping.
    I tried to configure based on the web site what did you told me.
    But i couldn't success it to resolve echo issue.
    The voice gate have 12.4(1a) on Cisco 2851.
    So the solution to reslove echo doesn't fit in my case.
    As i mentioned, normally i can hear noise each i talk another persion. If i stop the conversation i can't hear noise. but i started to talk again, i can hear noise each time.
    Thus i tried to disable "no non-linear" parameter, i can hear echo instead noise.
    So i should choice if i can hear noise or echo.
    And also, i tried to change input gain and output attenuation from -6 to 14, but the each still can hear.
    out voip network toplolog is below.
    NEC Digital Phone---NEC PBX---Gateway---(cat6500---MSPP(WAN Area)---cat6500)---Gateway---NEC Digital Phone.
    If i make a call using Normal Phone (INot Digital Phone), I can't hear noise. Whenever i can hear noise with NEC Digital Phone.
    Here is the option on cisco 2851 with 12.4
    2851(config-voiceport)#?
    Voice-port configuration commands:
    bearer-cap Specify the bear capability
    busyout Configure busyout trigger event & procedure
    comfort-noise Use fill-silence option
    compand-type The companding type for this voice port
    connection Specify Trunking Parameters
    cptone Configure voice call progress tone locale
    default Set a command to its defaults
    description Description of what this port is connected to
    disc_pi_off close voice path when disconnect with PI received
    echo-cancel Echo-cancellation option
    exit Exit from voice-port configuration mode
    idle-detection Idle code detection for digital voice
    input Configure input gain for voice
    music-threshold Threshold for Music on Hold
    no Negate a command or set its defaults
    non-linear Use non-linear processing during echo cancellation
    output Configure output attenuation for voice
    playout-delay Configure voice playout delay buffer
    shutdown Take voice-port offline
    threshold Threshold [noise] for voice port
    timeouts Configure voice timeout parameters
    translate Translation rule
    translation-profile Translation profile
    trunk-group Configure interface to be in a trunk group
    voice-class Set voiceport voice class control parameters
    Please advise to me to reslove the problem.
    Regard,
    john.

  • Non-linear equation solution

    I have used Lev-Mar Non-Linear VI before but cannot understand how to apply to the following:
    deltaTC = R(TC)*L^2 + QS + QC(TC) +QR(TC)*dt
    where variables containing (TC) are dependent on TC.
    I have samples of change of L over time (dt).  Trying to determine dTC with variables dependent on TC (current value - which means initial T + dTC).
    Any help much appreciated.

    Hi Battler,
    I am not sure if you know this or not but Lev-Mar Non-Linear VI is not supported any more. Instead you can use Nonlinear Curve Fit.vi . It is located in function->mathematics->fitting palette.
    The functionality of both of them is the same.Next you can go LabVIEW help, search for this VI, and then look at the "Linear, Exp, and Power Fitting VI: labview\examples\math\curvefit.llb"
    example. On the block diagram go to "Time out"and "true" for the case structures.You will see the Nonlinear Curve fit.vi, you need to input your equation to the reference terminal f(x,a). So
    you need to make a subVI of your equation, and input it into f(x,a). Hope this helps!!
    Edna
    National Instruments
    Applications Engineer

  • How should I set up my VI so that I can use the linear fit coefficient data analysis program, when my values are coming from while loops within a sequence structure?

    I'm attempting to create a calibration program, using the printer port, and a Vernier Serial Box by modifying a calibration program designed for the serial box.
    There are six calibration points, and to collect them, I have it controlled by while loops so that the numbers are taken when a button is pushed, and this is inside a sequence structure so that I can get the six different points. I feed these numbers into two different arrays (for x and y values) and then try to use the linear coefficient analysis on these points, but the values for the slope and intercepts it returns are not correc
    t.
    If I cut out the array and coefficient analysis, and feed the same numbers in directly without the while loop and sequence structures, it produces the proper values... I don't know why the numbers it is producing are different, and I'd really like to know.
    Thanks,
    Karinne.

    I would use a data manager sub-vi that would be called by each from of the sequence structure that produced a data point. The data manager sub-vi could auto append new items or could place items in a specific entry of an array. Later on when you want to calculate the linear fit, call the sub-vi to return the array of values.
    Stu

  • Asset Lease accounting -non Linear lease payment

    We are currently having a business scenario where an asset is acquired on capital lease basis.
    Different depreciation area is maintained for leasing to account for interest on leasing.
    The payments are made in monthly for lease payment.
    The lease payment amount changes every year.
    The lease tab in asset calculates Net present value on the basis on lease payment entered in the leasing tab.
    Now since the lease payment varies every year the net present value calculation will be different(not as calculated in asset master -leasing tab).
    I am not aware if the asset module can take care of any non-linear payment scenario to calculate the NPV and interest accordingly.
    Example an asset ABC is acquired as capital/finance lease basis on
    monthly lease payment  for 4 years as follows:
    The said asset is to be capitalized  with net present value and we also need to ensure that interest calculation is done accordingly.
    1st year  1000/month
    2nd year  2000/month
    3rd year  1500/month
    4th year  1900/month
    Since in lease tab only single lease payment can be entered, how the different monthly lease payment can be entered so as to calculate correct NPV.
    Next how the correct interest calculation and net present value can be calculated correctly.
    If any one has come across such situation, please reply.
    Regards,
    Manish Garg

    Hi ,
    SAp 4.7 does not support non linear lease payment. Only the Equal lease instalment can be generated automatically when you will go for opening balance at the leasing tab of the display assets(AS03).
    But the ECC6.0 support the change over the lease instalment,
    Rgds
    Satyajit

  • Magic Moves not always Magic (non-linear slide orders)

    Magic Moves opens the possibility of non-linear slide orders with animated transitions. Previously in keynote (KN '08), as far as I could ascertain, this was impossible. Now a slide with several hyper-linked objects can enjoy an animation of the on screen objects to there new positions, where-ever they may be on the on the linked slides.
    Unfortunately, as in some other things Keynote, it seems flakey. While it works most of the time for some reason, even when duplicating the linking slide and repositioning the very same objects, the Move is delayed and instantaneous: decidedly not Magic!
    The joy of being able to finally make the fully interactive Keynote presentation that will slide objects the right amount automatically according to there destination slide seems possible. The great thing is I don't have to construct all the different moves linking 26 different pages to each other via various routes (8 links on each page, which happened to be 8x26 possible linking routes = 208 move builds: too much for prescriptive build/move animations).
    But if I can't get it too work 100% I can't really show my client. Any know issues with this Magic Move stuff?
    I can replicate problem but not predict when it won't work or decode what is triggering the problem. Searching forum only revealed comment the Magic Move is work in progress. Note I am not scaling any objects. Can upload if it helps. Part of the original Presentation with a linear narrative can be seen at:
    http://www.vimeo.com/3018559
    Essentially I am endeavouring to make all the images 'clickable' so the film strip glides (against the preset order) to become the centre project. Also like to add a left and right button. All this can be theoretically done with invisible rect's with hyperlinks and Magic moves on each slide.
    Thanks for reading though all this – hope it's clearer than mud.

    Thanks for the response, Kyn.
    As it happens writing that long explanation, I thought I'd look from another angle and returned to the file – finding the answer straight away.
    Conclusion:
    Hyperlinks never use Magic Move transition, even if it is selected transition for the slide. I was getting hoodwinked by the fact that when I had forward and back arrows with hyperlinks to other slides, those slides were before and after the current slide. So they were Magic Moving with a mouse click on the Hyperlink, but only when forward one slide or backward one slide. Any other linking distance failed to Magic Move.
    I've already made the feature request but *please second it*, this would be a very powerful feature. Think Non-Linear Presentations and Info Kiosks with seamless transitions. And interaction is an area Powerpoint has decided edge on Keynote so it can and needs to be closed! (PP is such a trial of an interface after KN).
    http://www.apple.com./feedback/keynote.html
    I'll post the .keynote as requested when uploaded.

  • At the moment I have a long Griffin charging cable. Unfortunately now that I have the Smart Case this won't fit through the available hole. Is there any other make that will fit that has the none  lightening fitting that I want.

    At the moment I have a long Griffin charging cable. Unfortunately now that I have the Smart Case this won't fit through the available hole. Is there any other make that will fit that has the none  lightening fitting that I want.

    I wonder if this comment on the Amazon site is the answer to my problems?
    PLEASE NOTE: In order to provide the same power output as an original 3 ft Apple USB cable, the housing of our 6.5 ft cables need to be a bit larger. Due to the larger head size, it will not be compatible with some cases that have a smaller charger opening
    If that is the case then I am stuck with the Griffin one or just use the original.
    Thanks for your observations guys

  • [svn:fx-trunk] 10877: Fix a small syntax error in Path bounds calculations that could result in wrong bounds for edge cases involving MoveSegments .

    Revision: 10877
    Author:   [email protected]
    Date:     2009-10-05 15:23:37 -0700 (Mon, 05 Oct 2009)
    Log Message:
    Fix a small syntax error in Path bounds calculations that could result in wrong bounds for edge cases involving MoveSegments.
    Thanks go to Min for noticing the bug!
    QE notes: None
    Doc notes: None
    Bugs: None
    Reviewer: Deepa
    Tests run: checkintests
    Is noteworthy for integration: No
    Modified Paths:
        flex/sdk/trunk/frameworks/projects/spark/src/spark/primitives/Path.as

    orangekay wrote:
    That is absolutely unreadable.
    I agree completely. How about also providing a link to a set of input files so that we could actually run the code ourselves? Otherwise, there is no chance to debug the source code, it is just a mess.
    You might have better luck with an older version of the file. To quote the comments:
    // Modified on March 31, 2005. Initialized maxchange in nonlinvoltra() as
    // INFTY. Replaced crnmbr() by a similar, but faster routine interior().
    // Many thanks to Stuart Anderson for pointing out this shortcut.
    I suspect that the "interior" function is just plain incorrect. It doesn't matter if it runs on some other OS. Something about it is wrong and the code is so cryptic that it can't be deciphered.

  • Linear fit between two cursors from a signal from a NI-instruments via DAQ-Assistant

    Hi ! 
    I'm currently having som problem with my labview code. I'm trying to make regression on a specific part of my graph. The graph consist of a signal gathered from a NI cDAQ-9178. Currently I can get the live data in a graph (Raw Signal) and then  "zoom in" to the part of the graph that im intrested in by two cursors and then display the results in a new graph (Adjusted Signal). Now a want to make regresion in the new graph. How can i do this the best way ? 
    To be noted I'm a beginner of labview so my code maybe a bit off.
    Best regards Maurlind
    Solved!
    Go to Solution.
    Attachments:
    Rawsignal test.vi ‏245 KB
    rawsignal test.png ‏64 KB

    Hi maurlind,
    I got it, the function that derived the linear fit couldn't handle that large numbers on the x-axis. I edited the VI so that the large number is suctracted for the fit, i.e. the array will now begin at zero time for the fit. It will not affect your plots though, only the algorithm .
    Try it now with the files I provided. The file "pm_mod2_Rawsignal test.vi" should be used with "test3.lvm" (your data). The file "pm_mod3_Rawsignal test.vi" is the same as "pm_mod2_Rawsignal test.vi", but it is arranged to work with the simulated data. The file "test3.lvm" is your data, but the file is slightly edited to work on my system.
    Edit "pm_mod3_Rawsignal test.vi" to fit with your acquired signal as you did with the first file you got from me.
    Attachments:
    1412794.zip ‏483 KB

  • [request] [non-linear video editing] PiTiVi

    i have had a lot of trouble attempting to get this working, particularly with the dependencies
    PiTiVi allows users to easily edit audio/video projects based on the GStreamer framework: Capture audio and video; mix, resize, cut, apply effects to audio/video sources; Render/Save the projects to any format supported by the GStreamer framework. PiTiVi is still in a very early stage of development, and contributions are much welcome.
    *  Gstreamer 0.8.10
              o GST-FFMpeg 0.8.4
              o GST-Plugins 0.8.8
        * Python 2.3.0
              o PyGTK 2.6.0
              o GNOME-Python 2.6.0
              o GST-Python CVS
        * Gnonlin CVS
    The dependencies are on date of July 5th, 2005. The numbers are there to give an indication, there might be higher needs.
    sourceforge homepage
    screenshot

    gst-ffmpeg, pygtk, gstreamer, gst-plugins, gnome-python and python  are in extra
    gst-python is in community, but is behind one version (as required by pitivi .1.10) but currently the aur won't let me at the PKGBUILD ..so here's a shotty one
    pkgname=gst-python
    pkgver=0.8.2
    pkgrel=1
    pkgdesc="err um.. it does python stuff for gstreamer"
    url="http://gstreamer.freedesktop.org/src/gst-python/"
    license="GPL"
    depends=('gstreamer' 'python')
    makedepends=('gstreamer' 'python')
    source=(http://gstreamer.freedesktop.org/src/gst-python/$pkgname-$pkgver.tar.gz)
    md5sums=('35a735711f43551722b0dbcfc7895f3e')
    build() {
    cd $startdir/src/$pkgname-$pkgver
    ./configure --prefix=/usr --sysconfdir=/etc
    make || return 1
    make DESTDIR=$startdir/pkg install
    template gnonlin PKGBUILD  -can you tell i don't really know what im doing-
    pkgname=gnonlin
    pkgver=0.2.2
    pkgrel=1
    pkgdesc="Gnonlin is a library built on top of GStreamer which provides support
    for writing non-linear audio and video editing applications. It introduces the
    concept of a timeline"
    url="http://gnonlin.sourceforge.net/"
    license="GPL"
    depends=('gstreamer')
    makedepends=('gstreamer')
    source=(http://peterhost.dl.sourceforge.net/sourceforge/gnonlin/$pkgname-$pkgver
    .tar.bz2)
    md5sums=('7ff9f2e58463a3bb783a1c77445e9863')
    build() {
    cd $startdir/src/$pkgname-$pkgver
    ./configure --prefix=/usr --sysconfdir=/etc
    make || return 1
    make DESTDIR=$startdir/pkg install
    it seems to work -- though i donno what it would do if it didn't
    to be used from cvs, pitivi requires gstreamer .9, current version in repos is 8.10
    pitivi .1.10 builds but does not seem to work well (though the screenshots may say more for it than the actual program does) it could be a bad gnonlin
    if i build without a pkgbuild it runs but ugly EDIT: i didn't have gst-ffmpeg, now i get the same error either way
    if i build with this pkgbuild i get
    "PyGTK couldn't be found !"
    pkgname=pitivi
    pkgver=0.1.10
    pkgdesc="python non linear video/audio editor"
    url="http://pitivi.sourceforge.net"
    license="?"
    depends=('gnonlin' 'gst-python' 'gst-ffmpeg' 'gst-plugins' 'pygtk' 'gnome-python' )
    source=(http://peterhost.dl.sourceforge.net/sourceforge/pitivi/$pkgname-$pkgver.tar.gz)
    md5sums=('c311f801206aca77ab50e853c7c7c81c')
    build() {
    cd $startdir/src/$pkgname-$pkgver
    ./autogen.sh
    ./configure --prefix=/usr --sysconfdir=/etc
    make || return 1
    make DESTDIR=$startdir/pkg install

Maybe you are looking for