Partial Least Squares Discriminant Analysis Analysis Research Articles

1H NMR-based metabonomic and pattern recognition analysis for detection of oral squamous cell carcinoma

Background Metabonomic analysis has been increasingly used to monitor metabolic abnormalities in cells and their microenvironment in order to detect the cancer markers recently. We evaluated the feasibility of applying 1H nuclear magnetic resonance ( 1H NMR) based metabonomic method in the early detection of the differences in the plasma from 3 groups, which were patients with oral squamous cell carcinoma (OSCC), patients with oral leukoplakia (OLK), and the healthy control group. Methods 1H NMR spectra were obtained from human plasma samples prior to spectral analysis. The obtained data were processed by both the unsupervised principal component analysis (PCA) and the supervised partial least squares discriminant analysis (PLS-DA) to find out the differences among the three groups. Results PLS-DA analysis has revealed a good model to detect the NMR data that can differentiate the OSCC patients from the OLK patients and the controls using a test set. Conclusion The results indicated that the 1H NMR-based metabonomic approach is a feasible and efficient method for differentiating the OSCC patient's plasma from the healthy controls. As a potential novel strategy and a more convenient technique, it deserves a further evaluation for an early detection of oral cancer.

Data fusion in the wavelet domain by means of fuzzy aggregation connectives

Dual-domain classification analysis is proposed to identify pigments used in works of art studied by Raman spectroscopy and X-ray fluorescence spectrometry. By means of this methodology, Raman and X-ray fluorescence data are jointly processed by a high-level fusion approach. The system proposed aims to avoid the pre-processing stage and directly process raw data obtained from the instrument. The system is tested with spectra contaminated with background components of different shapes and intensities and with those with the background removed by line segment correction. The benefits of the approach were well demonstrated in a study of an ochre pigment classification. The approach is based on the main advantage of wavelet transform, which is multiresolution. Each spectrum is split into blocks, according to a specific frequency, to form a wavelet prism. Partial least squares-discriminant analysis (PLS-DA) is then applied to those blocks which contain the deterministic part of the signal and are not influenced by noise and background signal components. At the end, to obtain the final classification assignment, high-level data fusion of the classifications results (decision levels) obtained from PLS-DA analysis is done by means of fuzzy aggregation connective operators. Our study showed that fuzzy aggregation may be suitable for performing high-level data fusion on dual-domain data. This method can be automated so that classification can be rapid. It can handle classifications with different levels of difficulty and requires no prior knowledge of sample composition.