Class modeling techniques

M. Forina, C. Armanino, R. Leardi and G. Drava, A class-modelling technique based on potential functions. J. Chemom. 5 (1991) 435-453. 

Derde MP, Massart DL (1988) Comparison of the performance of the class modelling techniques UNEQ, SIMCA and PRIMA. Chemom Intell Lab Syst 4 65... 

Instead, class-modeling techniques verify whether a sample is compatible or not with the characteristics of a given class of interest. In fact. 

Nevertheless, in most of the electronic tongue applications found in the literature, classification techniques like linear discriminant analysis (LDA) and partial least squares discriminant analysis (PLS-DA) have been used in place of more appropriate class-modeling methods. Moreover, in the few cases in which a class-modeling technique such as soft independent modeling of class analogy (SIMCA) is applied, attention is frequently focused only on its classification performance (e.g., correct classification rate). Use of such a restricted focus considerably underutilizes the significant characteristics of the class-modeling approach. 

Classification and class-modeling techniques belong to three main families ... 

Two class-modeling techniques have recently been introduced multivariate range modeling (MRM) and CAIMAN analogues modelling methods (CAMM). 

CAMM is a family of powerful class-modeling techniques which builds models using distances (leverages or Mahalanobis distances from the class centroids) as predictors (Forina et ah, 2009). Such new variables may be used separately or in combination with the original predictors and, in many cases, supply models characterized by excellent efficiency values. 

Forina, M., Casale, M., Oliveri, P., and Lanteri, S. (2009). CAIMAN brothers A family of powerful classification and class modeling techniques. Chemom. Intell. Lab. Syst. 96, 239-245. 

The category correlations can be cancelled only when all the objects of the training set are in the same category, and the method is used as a class modelling technique. However, the bayesian analysis in ARTHUR-BACLASS has b n compared with the usual BA in classification problems about winra and olive oils and about the same classification and prediction abilities were observe for both methods. 

Derde, M. P., Coomans, D., Massart, D. L. Application of Class Modelling Techniques for the Classification of Olive Oils, in Food Research and Data Analysis (Martens, H., Russwurm, H., eds.), p. 427, Applied Science Publ., Barking 1983... 

Finally, a last consideration about problems with the data set representativeness. As it has been claimed in a pniblished report a LDA was applied to differentiate 12 classes of oils on the basis of the chromatographic data, where some classes contained two or three members only (and besides, the model was not validated). There is no need of being an expertise chemometrician to be aware of two or three samples are insufficient to draw any relevant conclusion about the class to which they belong. There are more sources of possible data variance than the number of samples used to estimate class variability (Daszykowski Walczak, 2006). The requirements of a sufficient number of samples for every class could be envisaged according to a class modelling technique to extract the class dimensionality and consider, for instance, a number of members within three to ten times this dimensionality. 

Olivieri et al. (2011) worked out the exploration of three different class-modelling techniques to evaluate classification abilities based on geographical origin of two PDO food products olive oil from Liguria and honey from Corsica. Authors developed the best models for both Ligurian olive oil and Corsican honey by a potential function technique (POTFUN) with values of correctly classified around 83%. 

Oliveri, P. Di Egidio, V. Woodcock, T. Downey, G. (2011). Application of class-modelling techniques to near infrared data far fjod authentication purposes. Food Chemistry Vol.125, pp. 1450-1456... 

Derde MP, Kaufman L, Massart DL. A non-parametric class-modelling technique. J Chemometr 1989 3 375. 

Forina M, Ohveri P, Lanteri S, Casale M. Class-modeling techniques, classic and new, for old and new problems. Chemranetr Intell Lab Syst 2008 93 132. 

---