10-26-2010 05:09 AM
Hi there,
I would like to know if there is a simple algorithm to find the equation of a line that best separate two sets of points.
I have found some hints when reading documentation about SVM and clustering. I have found some algorithms to find a hyperplane (wich is a line in 2D problems) maximising the margin between the sets of points.
I know that classifiers in Ni Vision are based on this kind of things, but there is no simple function concerning 2D problems.
Just let me know if you have some ideas/solutions//VIs
Thanks
10-29-2010 03:25 AM - edited 10-29-2010 03:33 AM
HelloToto26,
Which version/edition of LabVIEW are you using ?
Have you tried the Linear Programming functions in the Mathematics VIs ? You have few functions that should help on this :
http://zone.ni.com/reference/en-XX/help/371361G-01/gmath/curve_fitting_vis/
http://zone.ni.com/reference/en-XX/help/371361G-01/gmath/linear_fit/
You also have and advanced functions sub-palette
http://zone.ni.com/reference/en-XX/help/371361G-01/gmath/advanced_curve_fitting_vis/
Here is also a tutorial with an overview of curve fitting models and methods in LabVIEW
http://zone.ni.com/devzone/cda/tut/p/id/6954
Is that answering to your question ?
Regards,
Yannick D.
National Instruments France