The CAIMAN method (Classification And Influence Matrix ANalysis) is a classification method exploiting the properties of the diagonal terms of the influence matrix, also called leverages. Depending on the classification problem, Caiman method can be used in three different ways:
– discriminant classifier (D-Caiman), i.e. as the classical classification methods, able to assign each object to one among the available classes;
– class modelling classifier (M-Caiman), which is also able to reject objects, i.e. objects can be evaluated as belonging to none of the available classes, or objects can be considered as confused, i.e. potentially belonging to at least two classes and thus not assigned;
– asymmetric classifier (A-Caiman), where the method is focused in modelling a selected class (class A) as distinct from all the other objects not belonging to that class (Not-A).
Conditions and warranty
The toolbox is freeware and may be used (but not modified) if proper reference is given to the authors. Preferably refer to the followign papers:
R.Todeschini, D.Ballabio, V.Consonni, A.Mauri and M.Pavan, CAIMAN (Classification and Influence Matrix Analysis): a new approach to the classification based on leverage-scaled functions. Chemom.Intell.Lab.Syst., 87 (2007) 3-17
In short, no guarantees, whatsoever, are given for the quality of this toolbox or for the consequences of its use. It is inevitable that there will be some bugs, but we have tried to test the algorithms thoroughly.
Download
Fill in the following form. Your personal data will be used only for notification via email of new releases of the toolbox and will not be communicated to external third parties. Once the form has been submitted, download the zip file containing the toolbox on a local folder, unzip the file and extract all the Matlab modules in a unique folder. Before starting calculations, please read the HELP files provided in HTML format. A complete guide on how to calculate models is provided.
Caiman will be available for download soon….