IMMAN (the acronym for Information theory-based CheMoMetrics ANalysis) is a multi-platform software developed in the Java programming language, designed with a remarkably user-friendly graphical interface for the computation of a collection of information-theoretic functions adapted for rank-based unsupervised and supervised feature selection tasks.
IMMAN offers a remarkably user-friendly graphical interface stratified in sections according to the different information-theoretic concepts. IMMAN is developed in JAVA programming language and thus needs a virtual machine for its execution, and in this case requires a JDK version 1.7 or superior.
A total of 17 feature selection parameters are presented, with the unsupervised and supervised frameworks represented by 10 approaches in case.
The accepted input file formats for IMMAN are Tab and Comma Separated Value Files (.txt, .csv). In the conception of this application, we considered it useful to provide for real-time computations of multiple dataset files, and thus comparisons of features or datasets from different sources are possible.
It is important to remark that IMMAN provides the possibility of performing single parameter ranking or ensemble (multi-criteria) ranking using the former as base ranking methods. Note that the ensemble ranking procedure could be performed using the scores (values for the analyzed features)