K-Nearest Neighbour Searching

[M.Babai]

Hi,

Thank you for your fast response.
Any suggestions on how to determine the best value for range when using 
find_within_range()?

Regards,
/AB

Willi Richert wrote:
> Hi,
> 
> this topic was discussed some days ago. At the moment you have to stick 
> with find_within_range().
> 
> Alternatively, you might use find_nearest_if() and provide it with a 
> predicate that internally stores the k nearest points. You are actually 
> abusing it as a visitor pattern which Paul Harris is thinking about 
> supporting it directly in the future.
> 
> Regards,
> 
> wr
> 
> Am Donnerstag 23 Oktober 2008 15:36:06 schrieb M.Babai:
> 
>  > Dear all,
> 
>  >
> 
>  > For a multi-dimensional (6 - 11) classification problem I was searching
> 
>  > for a fast data structure and found this implementation on WikiPedia.
> 
>  > In our application we need to find K-Nearest Neighbours of a given query
> 
>  > point q. I have played around using the provided example program and
> 
>  > think I can understand the basics of how the library works. But I was
> 
>  > not able to perform the search such a way that only the list of the
> 
>  > K-Nearest neighbouring points is returned.
> 
>  > Anybody any suggestion how to use this library to perform K-Nearest
> 
>  > Neighbour Searching?
> 
>  >
> 
>  >
> 
>  > Thanks in advance,
> 
>  > Kind wishes,
> 
>  > Arya.
> 
>  >
> 
>  > _______________________________________________
> 
>  > libkdtree-devel mailing list
> 
>  > libkdtree-devel at lists.alioth.debian.org
> 
>  > http://lists.alioth.debian.org/mailman/listinfo/libkdtree-devel
> 

-- 
Arya Babai
   M.Babai at rug.nl	
   KVI, Groningen, Netherlands
   Tel: (+31)50-3638102