The kernel construction for the biomedical data classification using Support Vector Machine based on Green function for Ornstein-Uhlenbeck equation is presented. Quantitative estimates of classification quality of exhaled air samples absorption spectra for patients with chronic obstructive pulmonary disease and healthy volunteers were carried out.
The ability to diagnose oral lichen planus (OLP) based on saliva analysis using THz time-domain spectroscopy and chemometrics is discussed. The study involved 30 patients (2 male and 28 female) with OLP. This group consisted of two subgroups with the erosive form of OLP (n = 15) and with the reticular and papular forms of OLP (n = 15). The control group consisted of six healthy volunteers (one male and five females) without inflammation in the mucous membrane in the oral cavity and without periodontitis. Principal component analysis was used to reveal informative features in the experimental data. The one-versus-one multiclass classifier using support vector machine binary classifiers was used. The two-stage classification approach using several absorption spectra scans for an individual saliva sample provided 100% accuracy of differential classification between OLP subgroups and control group.
The ability of diagnostics of oral lichen planus (OLP) based on spectral analysis of saliva using the THz spectroscopy is presented. The study included 8 patients with clinically proven OLP. The comparison group consisted of 8 healthy volunteers. Absorption spectra of the saliva was measured using time-domain spectrometer T-spec (EXPLA) in the range 0.2-3THz and have been considered as the feature vectors of the state. The spatial distribution of the objects under study in the feature space was analyzed using principle component analysis. The groups under study were shown to separate in full. Thus, the saliva analysis by the THz spectroscopy technique can be potentially used as a method of noninvasive diagnostics of the OLP.
In this work we studied applicability of the laser spectroscopy for fixing differences in composition of exhaled air depending on the position of the body in different physical states. Using principal component analysis we show that the use of the laser spectroscopy methods is sufficiently effective to solve this problem and provide additional opportunities for the comprehensive study of the human condition.
We examined possibilities of the Kalman filter for reducing the noise effects in the analysis of absorption spectra of gas samples, in particular, for samples of the exhaled air. It has been shown that when comparing groups of patients with broncho-pulmonary diseases on the basis of the absorption spectra analysis of exhaled air samples the data preprocessing with the Kalman filtering can improve the classification sensitivity using a support vector kernel with mpl.
We explore the problem of thermal interaction of nanoparticles heated by laser radiation with a biological tissue after particle flow entering the cell. The solution of the model equations is obtained numerically under the following assumptions: a single particle is located in a neighborhood exceeding the particle size; the environment surrounding the particle is water with the conventional thermal characteristics. The model equations are deduced from the particle and the environment energy conditions taking into account the heat transfer in the particle and in its environment by conduction. We also assume that at the boundary between the particle and the surrounding water the perfect thermal contact takes place.
The numerical solution of the problem is carried out with the use of an implicit difference scheme and the sweep method. Two cases of the laser pulse action on a particle are considered: a single pulse and a series of pulses. The dynamics of the temperature isoline propagation is obtained at which protein denaturation occurs in the space around the metal nanoparticle in the cases when the particles are heated by a single pulse and a series of pulses. The dependence of the heating rate and the heating depth of the medium on the laser pulse repetition frequency is found.
KEYWORDS: Principal component analysis, Canonical correlation analysis, Statistical modeling, Gases, Simulation of CCA and DLA aggregates, Absorption, Carbon dioxide, Carbon monoxide, NOx, Databases
We consider the problem of finding concentrations of molecular gases in the models of exhaled air samples in terms of their absorption spectra. We introduce model spectra describing the exhaled air samples as linear combinations of the absorption spectra of individual molecular gases with given coefficients. The absorption spectra are calculated on the basis of the database HITRAN. The concentrations are determined using Principal Component Analysis and Canonical Correlation Analysis.
The results of numerical simulation of application principal component analysis to absorption spectra of breath air of patients with pulmonary diseases are presented. Various methods of experimental data preprocessing are analyzed.
Canonical correlation analysis is adapted to the problem of determining the concentration of molecular components contained in samples of exhaled air. To solve this problem dealt with model spectra in form of linear combination of the absorption spectra of molecular components with unknown coefficients. The absorption spectra were calculated on the basis of databases HITRAN, HITEMP, GEISA. Application of canonical correlation analysis allows us to represent the spectrum of the mixture in the form of a vector whose coordinates are the proportion of the individual components in the mixture.
The results of comparison of quality of two classificators – SVM (support vector machine) and SIMCA (soft independent modelling of class analogies) on model data contained profiles of absorbtion specra of exhalted air are presented. It is shown, that SVM classification results can be improved by preprocessing if input data with principal component analysis method.
The possibility of the inverse spectroscopic problem solution for multicomponent gas mixtures based on the use of principal component analysis is discussed. The analysis revealed usefulness of principal component analysis to estimate the parameters of the components in a case of investigation of exhaled air samples from various groups of patients.
An approach to the reduction of the space of the absorption spectra, based on the original criterion for profile analysis of the spectra, was proposed. This criterion dates back to the known statistics chi-square test of Pearson. Introduced criterion allows to quantify the differences of spectral curves.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.