Wood identification using pressure DSC data (pages 475–487)
Javier Tarrío-Saavedra, Mario Francisco-Fernández, Salvador Naya, Jorge López-Beceiro, Carlos Gracia-Fernández and Ramón Artiaga
Article first published online: 24 OCT 2013 | DOI: 10.1002/cem.2561
Pressure differential scanning calorimetry (PDSC) represents a new way to obtain thermo-oxidative information from wood species. A supervised classification problem of wood species, applying functional data analysis (FDA) and multivariate techniques to PDSC data, is performed. The FDA techniques are competitive with respect to partial linear squares (PLS) and principal component analysis (PCA) approaches. New PDSC fit model parameters and six estimators of the fractal dimension were proposed as an alternative to PLS/PCA features extraction. The supervised classification by PDSC curves has been shown to be feasible, fast, and robust.