Juzzy - A Java based toolkit for type-1, interval type-2 and general type-2 fuzzy logic and fuzzy logic systems.

By Christian Wagner

 

 

>>NEW<< If you would like to explore fuzzy logic systems without programming, try the browser-based platform JuzzyOnline based on the Juzzy library.

 

Implementation of Type-2 FLSs using Java.

Note: On this website you are given access to Juzzy (and its source code) - a java based toolkit for the development of fuzzy logic systems. You are free to use the code/toolkit for your own work as long as you cite its use with the following reference:

C. Wagner, "Juzzy – A Java based Toolkit for Type-2 Fuzzy Logic", Proceedings of the IEEE Symposium Series on Computational Intelligence, Singapore, April 2013.

Also, be aware that Juzzy is still being tested and may still contain bugs, i.e. verify your results!

Note that there are two options, you can either download a precompiled version of Juzzy which you can test from the command line or you can download the complete project inclusive of the source code.

What you need:

  1. Java JDK:
    Please make sure you have a recent Java JDK installed on your system (not just the JRE).
    The current JDK is available here: http://www.oracle.com/technetwork/java/javase/downloads/index.html.
  2. Netbeans IDE (optional – alternatively use an IDE of your choice such as Eclipse, etc.):
    Download it here: http://netbeans.org/.
  3. Java Fuzzy Logic Toolkit (jar files – include jMathPlot jar):
    Download it here.
  4. Source Code, Javadoc and Visualisation library:

Download the source code here.

Download the javadoc here.

Download jmathplot.jar here: http://code.google.com/p/jmathplot/downloads/list

Note: after unzipping and setting up the project in Netbeans you will have to add the jmathplot.jar library to your project path (click  resolve references or Project properties )

To get started without looking at source code / without Netbeans:

  1. Unzip the toolkit, creating a Juzzy directory.
  2. Test your setup:
    Open a command prompt (in Windows, run CMD) and navigate to your Juzzy directory.
    Run one or more of the examples using the commands below. All examples are based on the standard "How much to tip a waiter?" problem and are based on two inputs (food quality & service level) and a single output: the amount of tip in percent. All examples will produce the output for sample calculations, the rulebase employed as well as visualisations of the control surface and all fuzzy sets. Some example contain multiple styles of visualisation for the fuzzy sets.
  3. If the examples are running fine you should be good to go!