Biomedical subjects

Hideyuki Shinzawa

Publications and source records attributed to Hideyuki Shinzawa.

3 recordsLinked to original sources

PubMed2006

Perturbation-correlation moving-window two-dimensional correlation spectroscopy.

A new method of analysis, perturbation-correlation moving-window two-dimensional (PCMW2D) correlation spectroscopy, is proposed. For a spectral data set collected under an external perturbation, this method provides a pair of synchronous and asynchronous two-dimensional correlation spectra plotted on a plane between a spectral variable (e.g., wavenumber) axis and a perturbation variable (e.g., temperature) axis. One of the advantages of this new correlation analysis method is that complicated spectral variation along the perturbation direction can be monitored. It has been found that the synchronous and asynchronous PCMW2D correlation spectra are similar to the first perturbation derivative and negative second perturbation derivative spectra of the original data, respectively. To demonstrate the potential of PCMW2D correlation spectroscopy, it has been applied to temperature-dependent infrared (IR) spectra of a poly(vinyl alcohol) (PVA) film. The thermal behavior of the PVA film has been revealed by the PCMW2D correlation analysis. Two characteristic cross-peaks are observed in the synchronous PCMW2D correlation spectra generated from the temperature-dependent IR spectra between the crystalline phase C-O stretching band at 1141 cm-1 and the melting temperature of 209 degrees C and between the amorphous phase C-O stretching band at 1095 cm-1 and another specific temperature of 233 degrees C. This specific temperature of 233 degrees C corresponds to the thermal degradation temperature due to the elimination of the hydroxyl group attached to the main chain.

Journal Article↗

PubMed2006

Multi-objective genetic algorithm-based sample selection for partial least squares model building with applications to near-infrared spectroscopic data.

In this study, multi-objective genetic algorithms (GAs) are introduced to partial least squares (PLS) model building. This method aims to improve the performance and robustness of the PLS model by removing samples with systematic errors, including outliers, from the original data. Multi-objective GA optimizes the combination of these samples to be removed. Training and validation sets were used to reduce the undesirable effects of over-fitting on the training set by multi-objective GA. The reduction of the over-fitting leads to accurate and robust PLS models. To clearly visualize the factors of the systematic errors, an index defined with the original PLS model and a specific Pareto-optimal solution is also introduced. This method is applied to three kinds of near-infrared (NIR) spectra to build PLS models. The results demonstrate that multi-objective GA significantly improves the performance of the PLS models. They also show that the sample selection by multi-objective GA enhances the ability of the PLS models to detect samples with systematic errors.

Algorithms↗

PubMed2006

New method for spectral data classification: two-way moving window principal component analysis.

Two-way moving window principal component analysis (TMWPCA), which considers all possible variable regions by using variable and sample moving windows, is proposed as a new spectral data classification method. In TMWPCA, the similarity between model function and the index obtained by variable and sample moving windows is defined as "fitness". For each variable region selected by a variable moving window, the fitness is obtained through the use of a model function. By maximizing the fitness, an optimal variable region can be searched. A remarkable advantage of TMWPCA is that it offers an optimal variable region for the classification. To demonstrate the potential of TMWPCA, it has been applied to the classification of visible-near-infrared (Vis-NIR) spectra of mastitic and healthy udder quarters of cows measured in a nondestructive manner. The misclassification rate of TMWPCA has been compared with those of other chemometric methods, such as principal component analysis (PCA), soft independent modeling of class analogies (SIMCA), and principal discriminant variate (PDV). TMWPCA has yielded the lowest misclassification rate. The result indicates that TMWPCA is a powerful tool for the classification of spectral data.

Journal Article↗