Partial least squares , pattern recognition technique

While principal components models are used mostly in an unsupervised or exploratory mode, models based on canonical variates are often applied in a supervisory way for the prediction of biological activities from chemical, physicochemical or other biological parameters. In this section we discuss briefly the methods of linear discriminant analysis (LDA) and canonical correlation analysis (CCA). Although there has been an early awareness of these methods in QSAR [7,50], they have not been widely accepted. More recently they have been superseded by the successful introduction of partial least squares analysis (PLS) in QSAR. Nevertheless, the early pattern recognition techniques have prepared the minds for the introduction of modem chemometric approaches. 

The data processing of the multivariate output data generated by the gas sensor array signals represents another essential part of the electronic nose concept. The statistical techniques used are based on commercial or specially designed software using pattern recognition routines like principal component analysis (PCA), cluster analysis (CA), partial least squares (PLSs) and linear discriminant analysis (LDA). 

Finally, feature selection is crucial to ensure a successful pattern-recognition study, since irrelevant features can introduce so much noise that a good classification of the data cannot be obtained. When these irrelevant features are removed, a clear and well-separated class structure is often found. The deletion of irrelevant variables is therefore an important goal of feature selection. For averaging techniques such as K-NN, partial least squares, or SIMCA, feature selection is vital, since signal is averaged with noise... 

Various attempts have been made to use pattern recognition [24, 25] in QSAR studies and successful applications have been reported. Soft modeling techniques, e.g. the partial least squares (PLS) method [26, 27], now offer better opportunities. With the help of this principal component-like method the explanatory power of many, even hundreds or thousands of variables can be used for a limited number of objects, a task being absolutely impossible in regression analysis in which the number of objects must always be larger than the number of variables. 

Acoustic emission power spectra are similar in many respects to optical spectra and are amenable to chemometric processing (multivariate analysis). Principal component analysis, partial least squares (PLS), neural networks, and qualitative techniques such as SIMCA (soft independent modeling of class analogy a pattern recognition technique) have been employed... 

XRF and scattering (EDXRFS) spectroscopy method for direct rapid analysis of trace bioavailable macronutrients (i.e. C, N, Na, Mg, P) in soils. Chemo-metric techniques, namely principal component analysis (PCA), partial least squares (PLS) and artificial neural networks (ANNs), were utilized for pattern recognition based on fluorescence and regions of Compton scatter peaks, and to develop multivariate quantitative calibration models based on Compton scatter peaks, respectively. 

---