Charles River Analytics BNet™.News
In This Issue: July/August 2007 
•   BNet Innovations Presented at UAI 2007
•   BNet™.EngineKit User Tip: Cpt Indices
•   BNet™.Builder Used in Computational Approaches to Situation Assessment and Decision Support
•   View Back Issues of BNet™.News
•   BNet™.Builder User Tip: Cut/Copy/Paste
•   Publicize Your Belief Network Success Story
BNet Innovations Presented at UAI 2007
CAMBRIDGE, MA - Charles River Analytics presented research on Bayesian belief networks at the Fifth Bayesian Modeling Applications Workshop during the 23rd Conference on Uncertainty in Artificial Intelligence (UAI 2007). The conference took place from July 19-22, 2007, at the University of British Columbia in Vancouver, BC, Canada. The theme of this year's Bayesian Modeling Applications Workshop was Bayesian Model Views.

Charles River's Zach Cox presented a talk during the session on Tools for Building Bayesian Network Models. "I presented some innovations we've made to our BNet products recently, which help users build and test Bayesian networks much faster, and they were very well received by the audience. I'm also very excited that they will be included in the next release of our BNet products."

The abstract of his presentation appears below.

Abstract
Bayesian networks (BN) are particularly well suited to capturing vague and uncertain knowledge. However, the capture of this knowledge and associated reasoning from human domain experts often requires specialized knowledge engineers and computational modelers responsible for creating BN-based models. Through our experiences in applying BN modeling techniques across application domains, we have analyzed how these models are constructed, refined, and validated with domain experts. From this analysis, we have identified potential simplifying assumptions and used these to guide the design of computational and user interface methods that support the rapid creation and validation of BN models.

For more information on the conference, click here.

BNet™.Builder Used in Computational Approaches to Situation Assessment and Decision Support
Dr. Subrata Das, Chief Scientist at Charles River Analytics, presented a tutorial on "Computational Approaches to Situation Assessment and Decision Support," including the use of BNet.Builder, at Information Fusion 2007. Fusion 2007 is the world's premiere conference on information fusion for industry, academia, and defense organizations. The conference took place from July 9-12, 2007, in Quebec, Canada.

Dr. Das was also involved in a number of capacities during the conference. On July 9, he presented a tutorial on Computational Approaches to Situation Assessment and Decision Support. The following day, he presented a panel discussion on Agent Based Information Fusion. Dr. Das also presented two papers, "Disease outbreak detection and tracking for biosurveillance: A data fusion approach" and "Envelope of human cognition for battlefield information processing."

To read more about Dr. Das's tutorial or the conference, click here

BNet™.Builder User Tip: Cut/Copy/Paste
BNet.Builder supports cut, copy, and paste operations on an individual node and a group of nodes. Simply select the node(s) you want to cut or copy, click the Cut or Copy toolbar buttons (or use the Ctrl+X or Ctrl+C keyboard shortcuts), and then click the Paste toolbar button to paste (or use the Ctrl+V keyboard shortcut).

If you cut or copy a single node, pasting will create a copy of that node and its CPT, as well as any edges directed into it. If you cut or copy a group of nodes, pasting will create copies of all those nodes and their CPTs, as well as any edges between them.

To learn more about BNet.Builder, click here.

BNet.Builder
BNet™.EngineKit User Tip: Cpt Indices
The Cpt class provides get(int, int[]) and set(int, int[], double) methods for obtaining and changing individual CPT entries. The int parameter to these methods is the index of the child state (think of it as the column in the CPT view of BNet.Builder). The int[] parameter specifies one state for each parent (think of it as the row in the CPT view). The parent states in the int[] should be ordered the same as the parents returned by the Node.getParents() method. For nodes without parents, you can use the Cpt.EMPTY_PARENT_INDICES field as the int[] parameter.

To learn more about Engine.Kit, click here.

Bnet.EngineKit
View Back Issues of BNet™.News
We have back issues of BNet™.News posted on our Web site. If you're a new subscriber or are looking for more articles and tips, come visit our Web site.

To visit the BNet.News archive, click here.

Publicize Your Belief Network Success Story
Want to show off your applications of belief networks to others using them in their research? Send us your success stories. We would like to include at least one in each edition of BNet.News.

To send us your story, please contact lcordeiro@cra.com or zcox@cra.com.

BNet™.News is published by Charles River Analytics™, the company that brings you BNet.Builder™ and BNet.EngineKit™.  View our Privacy Policy