Search results for "Principal component analysis"
showing 10 items of 486 documents
Evaluation of Skin Melanoma in Spectral Range 450-950 nm Using Principal Component Analysis
2013
Diagnostic potential of principal component analysis (PCA) of multi-spectral imaging data in the wavelength range 450-950 nm for distant skin melanoma recognition is discussed. Processing of the measured clinical data by means of PCA resulted in clear separation between malignant melanomas and pigmented nevi.
Cardiorespiratory Coordination after Training and Detraining. A Principal Component Analysis Approach
2016
Our purpose was to study the effects of different training modalities and detraining on cardiorespiratory coordination (CRC). Thirty-two young males were randomly assigned to four training groups: aerobic (AT), resistance (RT), aerobic plus resistance (AT + RT), and control (C). They were assessed before training, after training (6 weeks) and after detraining (3 weeks) by means of a graded maximal test. A principal component (PC) analysis of selected cardiovascular and cardiorespiratory variables was performed to evaluate CRC. The first PC (PC1) coefficient of congruence in the three conditions (before training, after training and after detraining) was compared between groups. Two PCs were …
Independent component analysis on the mismatch negativity in an uninterrupted sound paradigm.
2008
We compared the efficiency of the independent component analysis (ICA) decomposition procedure against the difference wave (DW) and optimal digital filtering (ODF) procedures in the analysis of the mismatch negativity (MMN). The comparison was made in a group of 54 children aged 8-16 years. The MMN was elicited in a passive oddball protocol presenting uninterrupted auditory stimulation consisting of two frequent alternating tones (600 and 800 Hz) of 100 ms duration each. Infrequently, one of the 600 Hz tones was shortened to 50 or 30 ms. The event related potentials (ERPs) were decomposed into the MMN-like and non-MMN-like independent components (ICs) through the FastICA algorithm. The ICA …
A score model for the continuous grading of early allograft dysfunction severity
2014
Early allograft dysfunction (EAD) dramatically influences graft and patient outcomes. A lack of consensus on an EAD definition hinders comparisons of liver transplant outcomes and management of recipients among and within centers. We sought to develop a model for the quantitative assessment of early allograft function [Model for Early Allograft Function Scoring (MEAF)] after transplantation. A retrospective study including 1026 consecutive liver transplants was performed for MEAF score development. Multivariate data analysis was used to select a small number of postoperative variables that adequately describe EAD. Then, the distribution of these variables was mathematically modeled to assig…
Estradiol Stimulates Vasodilatory and Metabolic Pathways in Cultured Human Endothelial Cells
2009
Vascular effects of estradiol are being investigated because there are controversies among clinical and experimental studies. DNA microarrays were used to investigate global gene expression patterns in cultured human umbilical vein endothelial cells (HUVEC) exposed to 1 nmol/L estradiol for 24 hours. When compared to control, 187 genes were identified as differentially expressed with 1.9-fold change threshold. Supervised principal component analysis and hierarchical cluster analysis revealed the differences between control and estradiol-treated samples. Physiological concentrations of estradiol are sufficient to elicit significant changes in HUVEC gene expression. Notch signaling, actin cyt…
Rosacea assessment by erythema index and principal component analysis segmentation maps
2017
RGB images of rosacea were analyzed using segmentation maps of principal component analysis (PCA) and erythema index (EI). Areas of segmented clusters were compared to Clinician’s Erythema Assessment (CEA) values given by two dermatologists. The results show that visible blood vessels are segmented more precisely on maps of the erythema index and the third principal component (PC3). In many cases, a distribution of clusters on EI and PC3 maps are very similar. Mean values of clusters’ areas on these maps show a decrease of the area of blood vessels and erythema and an increase of lighter skin area after the therapy for the patients with diagnosis CEA = 2 on the first visit and CEA=1 on the …
Analysis of inter-atrium differences in paroxysmal and persistent atrial fibrillation using principal component analysis
2007
The pathophysiological mechanisms of atrial fibrillation (AF) are not entirely clear yet, and there is no full explanation for the development and evolution of the arrhythmia. The goal of this study is to find inter-atrium differences in electrophysiological behavior between persistent and paroxysmal AF. The database analyzed contains intra-cardiac records from 14 patients with paroxysmal AF and 10 with persistent AF. Dominant frequency and sample entropy measurements showed that in the paroxysmal group there was a left-to-right gradient. These differences were enhanced after the extraction of the main components with principal component analysis. These findings may be interpreted as a poss…
Principal component analysis and cluster analysis for measuring the local organisation of human atrial fibrillation
2001
The distribution of atrial electrogram types has been proposed to characterise human atrial fibrillation. The aim of this study was to provide computer procedures for evaluating the local organisation of intracardiac recordings during AF as an alternative to off-line manual classification. Principal components analysis (PCA) reduced the data set to a few representative activations, and cluster analysis (CA) measured the average dissimilarity between consecutive activations of an intracardiac signal. The data set consisted of 106 bipolar signals recorded on 11 patients during electrophysiological studies for catheter ablation. Performances of PCA and CA in distinguishing between organised (t…
An Emulator Toolbox to Approximate Radiative Transfer Models with Statistical Learning
2015
Physically-based radiative transfer models (RTMs) help in understanding the processes occurring on the Earth’s surface and their interactions with vegetation and atmosphere. When it comes to studying vegetation properties, RTMs allows us to study light interception by plant canopies and are used in the retrieval of biophysical variables through model inversion. However, advanced RTMs can take a long computational time, which makes them unfeasible in many real applications. To overcome this problem, it has been proposed to substitute RTMs through so-called emulators. Emulators are statistical models that approximate the functioning of RTMs. Emulators are advantageous in real practice because…