forum.hugin.com

User Forums => HUGIN API Discussion => Java => Topic started by: lauchlin on August 14, 2012, 07:22:04

Title: OOBN file format and continuous nodes
Post by: lauchlin on August 14, 2012, 07:22:04
Hi, two questions for today.

Firstly, is there a plan to enable the reading of .oobn files?  I have an OOBN with a number of associated .oobn files that I have created using the GUI. At the moment I am flattening the network and saving it as a .net file so I can read it using the  DefaultClassParseListener() class but ideally I'd just like to read in the .oobn files.

Secondly, is there any work being done on enabling true continuous nodes in OOBNs rather than being restricted to interval nodes?

Thanks,

Lauchlin
Title: Re: OOBN file format and continuous nodes
Post by: Anders L Madsen on August 14, 2012, 09:09:13
Hi,

Quote
Firstly, is there a plan to enable the reading of .oobn files?

This is supported. Please read this post: http://forum.hugin.com/index.php?topic=277.0 (http://forum.hugin.com/index.php?topic=277.0), which refers to two different examples.

Quote
is there any work being done on enabling true continuous nodes in OOBNs rather than being restricted to interval nodes?

You can use the Continuous Chance node tool in the GUI to add continuous chance nodes to a Bayesian network. A continuous chance node is assumed to follow a Normal distribution.
Title: Re: OOBN file format and continuous nodes
Post by: lauchlin on August 15, 2012, 08:46:20
Sorry, I wasn't very clear with the question regarding the continuous chance node. I mean is there any plan to add the CDTV function between continuous and interval nodes in an OOBN?

Thanks for the response on reading the OOBN files.  I'll give that a try.
Title: Re: OOBN file format and continuous nodes
Post by: Anders L Madsen on August 15, 2012, 09:42:33
Quote
I mean is there any plan to add the CDTV function between continuous and interval nodes in an OOBN?

No, not for the moment. The CDVT function is only available in the Graphical User Interface and only for "flat" Bayesian networks. This functionality has developed by request from a commercial customer.