GeNIe & SMILE

Category Intelligent Software>Bayesian Network Systems/Tools

Abstract SMILE (Structural Modeling, Inference, and Learning Engine) is a fully platform independent portable library of C++ classes implementing graphical decision-theoretic methods, such as ‘Bayesian networks’ and influence diagrams and structural equation models, directly amenable to inclusion in intelligent systems.

Its Windows user interface, GeNIe is a versatile and user-friendly development environment for graphical decision-theoretic models.

The GeNIe (Graphical Network Interface) software package can be used to create ‘decision theoretic’ models intuitively using the graphical click- and-drop interface.

GeNIe is the graphical interface to SMILE, a fully portable ‘Bayesian inference engine’ developed by the Decision Systems Laboratory and thoroughly tested in the field since 1998.

GeNIe 2.0 is the latest version of GeNIe.

GeNIe Primary features/capabilities include:

1) Graphical editor to create and modify network models.

2) Uses the SMILE Engine. You may develop models in GeNIe and create a custom interface for them using SMILE.

3) Supports chance nodes with General, Noisy OR/MAX and Noisy AND distribution.

4) Open multiple networks and cut and paste sections of models between them.

5) Complete integration with MS. Excel, cut and paste data into the internal spreadsheet view of GeNIe.

6) Cross compatibility with other software. It supports all major file types [e.g. Hugin (see G6G Abstract Number 20163) and Netica (see G6G Abstract Number 20213)].

7) Support for handling observation costs of nodes.

8) Support for diagnostic case management.

SMILE individual classes, defined in the SMILE API (Application Programming Interface), allows you to create, edit, save, and load graphical models, and use them for probabilistic reasoning and decision making under uncertainty.

SMILE directly supports object-oriented (OO) methodology. SMILE is implemented in C++ in a platform independent fashion.

Individual classes of SMILE are accessible from C++ or (as functions) from C programming languages.

As most implementations of programming languages define a C interface, this makes SMILE accessible from practically any language on any system.

SMILE can be embedded in programs that use graphical probabilistic models as their reasoning engines.

Models developed in GeNIe can be equipped with a user interface which utilizes SMILE as the back-end engine.

SMILE is released as a dynamic link library (DLL).

There are also several SMILE wrappers, such as SMILE.NET (.NET interface), SMILEX (Active X), jSMILE (Java interface), etc.

SMILE Primary features/capabilities include:

1) Graphical editor to create and modify network models.

2) Platform independent, versions available for Windows, UNIX (Solaris), Linux, Mac, Pocket PC, etc.

3) SMILE.NET is available for use with the .NET framework. It is compatible with all .NET languages, including C# and VB.NET.

It can be used to create web-based applications of ‘Bayesian networks’.

4) Thorough and complete documentation.

5) Robust and running successfully in the field since 1997.

6) Responsive development team support, they will compile SMILE for your platform on demand.

What's new in GeNIe 2 --

GeNIe 2.0 has a lot of new features. The manufacturer has included a lot of graphical elements, cleaner graphics and a lot more decision tools.

GeNIe 2.0 now incorporates all the features of Diagnostic GeNIe [DGeNIe] within it, so you can perform diagnosis from within GeNIe.

A list of all the major added features is as follows:

1) Open multiple networks at the same time.

2) Support for Diagnosis.

3) Support for KI (Knowledge Industries, Inc.) file type.

4) Text formatting support, now you can change the font type, size and color for the text displayed in the Graph 4 View.

5) Layout features like Snap to Grid, Bring to Front, Distribute Horizontally, Graph Layout and many more.

6) New and improved Find command.

7) New Zoom tool for magnifying the network.

8) New full-screen view mode for presentations.

9) View nodes as bar charts, showing probabilities of each state graphically.

10) Spreadsheet View for displaying properties of all nodes in a spreadsheet.

11) Observation Cost.

12) Support for controlling values of states.

13) EPIS and AIS sampling algorithms for 'Bayesian networks' are now available.

14) Supports Annotation for nodes and individual states of a node.

Note: The manufacturer maintains a web based network repository (examples) of various public domain networks available. They are all in the xdsl (GeNIe 2.0) format.

System Requirements

Contact manufacturer.

Manufacturer

Decision Systems Laboratory is a research group within the Department of Information Science and Telecommunications and the Intelligent Systems Program at the University of Pittsburgh.

Manufacturer Web Site GeNIe & SMILE

Price Contact manufacturer.

G6G Abstract Number 20363

G6G Manufacturer Number 104012