Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Principal component”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,351 records · Page 75Linked to original sources
PubMed1983

A method for quantification of alternate pronation and supination of forearms.

A method for quantitative evaluation of diadochokinesia test (alternate pronation and supination of forearms) has been developed. Ten parameters that quantify features of movements were established. The method was applied to a group of healthy people and a group of patients with methylmercury poisoning. Significant differences between the two groups were noted in many parameters. To interpret the parameters synthetically, principal component analysis was applied and a scatter diagram on the first two principal components indicated the difference in distribution between the two groups. Among the established parameters, there were six related to regularity. They were combined in a linear form to define a summarized measure for regularity. The measure agreed very well with visual judgment. The obtained results demonstrated the usefulness of the method in daily clinical practices.

Forearm↗
PubMed1996

Repetitive behaviors in schizophrenia: a single disturbance or discrete symptoms?

Schizophrenia patients often display multiple repetitive behaviors. We investigated relations among nine repetitive behaviors and evaluated the hypothesis that these behaviors are varied manifestations of a single underlying biobehavioral disturbance. Nine repetitive behaviors from the Elgin Behavioral Rating Scale were assessed in 400 schizophrenia patients residing at a state hospital. A majority of patients were smokers (76.3%) and very few had pica (3%). Several other repetitive behaviors showed substantial frequency. A principal components analysis revealed eight of nine behaviors shared at least 10% of their variance with a single, common component. However, a principal factor analysis suggested a five-factor model best represented the data. The five factors and items identifying them were: (1) 'oral consumption' behaviors-polydipsia and smoking; (2) 'Kluver-Bucy' behaviors-bulimia and hypersexuality; (3) 'movement' behaviors-mannerisms/postures and pacing; (4) 'bizarre use of objects'-bizarre grooming and hoarding; (5) 'Pica'. Associations among repetitive behaviors varied. Symptoms such as smoking and polydipsia appeared reliably related, and others such as pica appeared discrete and independent. Overall, the data did not support the 'single disturbance' hypothesis and suggested a multifactorial model is needed to characterize repetitive behavior disturbances in schizophrenia.

Adult↗
PubMed2006

Application and comparison of classification algorithms for recognition of Alzheimer's disease in electrical brain activity (EEG).

The early detection of subjects with probable Alzheimer's disease (AD) is crucial for effective appliance of treatment strategies. Here we explored the ability of a multitude of linear and non-linear classification algorithms to discriminate between the electroencephalograms (EEGs) of patients with varying degree of AD and their age-matched control subjects. Absolute and relative spectral power, distribution of spectral power, and measures of spatial synchronization were calculated from recordings of resting eyes-closed continuous EEGs of 45 healthy controls, 116 patients with mild AD and 81 patients with moderate AD, recruited in two different centers (Stockholm, New York). The applied classification algorithms were: principal component linear discriminant analysis (PC LDA), partial least squares LDA (PLS LDA), principal component logistic regression (PC LR), partial least squares logistic regression (PLS LR), bagging, random forest, support vector machines (SVM) and feed-forward neural network. Based on 10-fold cross-validation runs it could be demonstrated that even tough modern computer-intensive classification algorithms such as random forests, SVM and neural networks show a slight superiority, more classical classification algorithms performed nearly equally well. Using random forests classification a considerable sensitivity of up to 85% and a specificity of 78%, respectively for the test of even only mild AD patients has been reached, whereas for the comparison of moderate AD vs. controls, using SVM and neural networks, values of 89% and 88% for sensitivity and specificity were achieved. Such a remarkable performance proves the value of these classification algorithms for clinical diagnostics.

Aged↗
PubMed2004

Delphinidin accumulation is associated with abnormal flower development in petunias.

The relative floral anthocyanidin contents of 195 commercial petunias with floral colours other than white and yellow were determined using HPLC, and the presence of five anthocyanidins (cyanidin, peonidin, delphinidin, petunidin, and malvidin) was confirmed. Pelargonidin was not detected, and delphinidin was not a major component. Using a principal component analysis of the relative anthocyanidin contents, the petunias were classified into three phenotype-groups accumulating cyanidin, peonidin, or malvidin, (plus petunidin) as the major anthocyanidin. A fourth phenotype was segregated in the progeny obtained by self-pollinating an F1 hybrid of the malvidin group; this accumulated delphinidin 3-glucoside in a markedly crumpled corolla-limb (delphinidin group). Such inferior floral traits, associated with the accumulation of delphinidin 3-glucoside, are thought to be the driving force that removed the delphinidin group from commercial petunias. A comparison of flowers of the delphinidin group and those of the other groups may provide a useful tool towards a deeper understanding of how anthocyanin biosynthesis relates to normal development of the corolla.

Anthocyanins↗
PubMed1998

Comparative analysis of two methods used to show interspecific associations in naturally acquired parasite nematode communities from the abomasum of ewes.

The aim of our study was to compare a multivariate and a univariate method to evaluate the associations between nematode species in natural infections. We used a data set based on the 3-year study of the community of abomasal nematodes in ewes of the middle-Atlas region of Morocco. Frequency data (percentage of each species in the individual host community) were processed by principal component analysis. Euclidean distances between species (D2) were calculated from projections of principal component analysis on three axes and compared to a bivariate estimate (1 - correlation coefficient R). Low distances were recorded between morphs of the same species (Teladorsagia circumcincta and T. trifurcata, for example), which indicates a positive association. Only two species, Trichostrongylus axei and T. circumcincta, were negatively associated having D2 values much over 1. The distances D2, i.e., multivariate measure of association intensity were similar in most cases to 1- R estimates, indicating probably the absence of strong multispecies association. The D2 fitted a Motomura geometric progression model indicating that associations were arranged in a continuum from low to high values, but they did not depart much from what could be expected from random associations for most species. The D2 interest is mostly to relate associations with environmental variables, and comparing with 1 - R, to assess the degree of interaction in the community.

Abomasum↗
PubMed2003

Chemical fingerprinting of unevaporated automotive gasoline samples.

The comparison of two or more samples of liquid gasoline (petrol) to establish a common origin is a difficult problem in the forensic investigation of arsons and suspicious fires. A total of 35 randomly collected samples of unevaporated gasoline, covering three different grades (regular unleaded, premium unleaded and lead replacement), were examined. The high-boiling fraction of the gasoline was targeted with a view to apply the techniques described herein to evaporated gasoline samples in the future.A novel micro solid phase extraction (SPE) technique using activated alumina was developed to isolate the polar compounds and the polycyclic aromatic hydrocarbons (PAHs) from a 200microl sample of gasoline. Samples were analysed using full-scan gas chromatography-mass spectrometry (GC-MS) and potential target compounds identified. Samples were then re-analysed directly, without prior treatment, using GC-MS in selected ion monitoring (SIM) mode for target compounds that exhibited variation between gasoline samples. Principal component analysis (PCA) was applied to the chromatographic data. The first two principal components (PCs) accounted for 91.5% of the variation in the data. Linear discriminant analysis (LDA) performed on the PCA results showed that the 35 samples tested could be classified into 32 different groups.

Journal Article↗
PubMed2005

[Application of a dietary pattern approach in the Belgium context].

BACKGROUND: Dietary pattern analysis has recently emerged as a new direction and a complementary approach to study the relationship between diet and morbidity or mortality. At present, two methods have been developed to construct dietary patterns: "a priori" method and "a posteriori" method. OBJECTIVE: This paper presents the two methods and their application based on dietary data from the "Belgium Interuniversity on Nutrition and Health Study". METHODS: A prospective study was conducted (1979-1984) in a sample of 5,225 males and 4,476 females from the Belgian population aged 25 to 74 years at the initial survey and followed for 10 years for all causes and specific mortality. Dietary data was collected by a 24-hour recall and for a sub-sample also by a 7 day-diet record. The "a priori" method was used by calculating an index based on the national dietary guidelines. We used the principal component analysis to identify dietary patterns a posteriori. We conducted a first principal component analysis using the data from the 24-hour recall and a second on the data collected by the 7 day-record. RESULTS: Both of the currently used approaches for extracting dietary patterns have advantages and limitations. We applied first the "a priori" approach by calculating an Index (IAR) which measures the adherence of the sample to the Belgian dietary guidelines. We obtained an index that ranged from 0 to 8, a higher score represented a "healthier diet". The index mean (sd) was 3.7 (+/- 1.2) for the entire sample with a significantly higher IAR for women. Using factor analysis, we identified 8 dietary patterns for men and for women. These were difficult to translate in terms of dietary intake profile. Inversely, with the factors identified with the 7 day record, we could find a "western" dietary profile and a "prudent" profile. CONCLUSION: Dietary pattern analysis offers the opportunity to evaluate the overall quality of the diet. The dietary profiles constructed by the two approaches should be related to morbidity or mortality in order to evaluate their predictive capacity.

Adult↗
PubMed2003

Energy transfer--a tool for probing micellar media.

The non-ionic polyoxyethylene chain-containing surfactant Triton X-100 (TX-100) forms well-defined micelles and reverse micelles in aqueous and hydrocarbon media, respectively. Nonradiative energy transfer between two charged fluorescent dyes, fluorescein (FL) and acridine orange (AO) has been used to probe the micelles and reverse micelles of TX-100. In the energy transfer system employed, FL acts as the donor and AO as the acceptor. This is borne out by the fluorescence spectral data. Time-resolved studies further corroborate the steady-state results. As the fluorescence emission spectra of the two dyes show a considerable amount of overlap, they are resolved into individual donor and acceptor components using the principal component analysis (PCA) method. This study also focuses on the more important role played by hydrophobic forces (compared with electrostatic interactions) in promoting energy transfer between charged species in micellar media.

Acridine Orange↗
PubMed1997

Flexibility and repeatability of finger movements during typing: analysis of multiple degrees of freedom.

The kinematics of the hand and fingers were studied during various keystrokes in typing. These movements were defined by 17 degrees of freedom of motion, and methods were developed to identify simplifying strategies in the execution of the task. Most of the analysis was restricted to the 11 degrees of freedom of the fingers, neglecting thumb and wrist motion. Temporal characteristics of the motion were defined by computing principal components, and it was found that only a few (two to four) principal components were needed to characterize motion of each of the degrees of freedom. Hierarchical relationships among patterns within and between different degrees of freedom were identified using cluster analysis. There was a considerable amount of consistency each time a given keystroke was executed by a subject, and this repeatability may imply a reduction in the number of degrees of freedom independently controlled by the nervous system. However, there also appears to be considerable flexibility in the coordination of the many joints of the hand when examined across different keys and across different subjects.

Biomechanical Phenomena↗
PubMed2004

Impact of educational attainment on the quality of young women's diets.

OBJECTIVE: New findings, that relate poor foetal growth to long-term outcomes, highlight the need to understand more about the nature of women's diets before and during pregnancy. This study examines the influence of sociodemographic and anthropometric factors on the quality of the diets of young women in the UK. DESIGN: Diet was assessed by an interviewer-administered food frequency questionnaire. A single diet score was calculated for each woman using the first component defined by principal components analysis. SETTING: Southampton, UK. SUBJECTS: A total of 6125 non pregnant women aged 20-34 y. RESULTS: The diets of women with low diet scores were characterised by low intakes of fruit and vegetables, wholemeal bread, rice and pasta, yogurt, and breakfast cereals, but high intakes of chips and roast potatoes, sugar, white bread, red, and processed meat and full-fat dairy products. Educational attainment was the most important factor related to the diet score. In all, 55% (95% CI 50-59%) of women with no educational qualifications had scores in the lowest quarter of the distribution, compared with only 3% (95% CI 2-4%) of those who had a degree. Smoking, watching television, lack of strenuous exercise, and living with children were also associated with lower diet scores. After taking these factors into account, no other factor including social class, the deprivation score of the neighbourhood, or receipt of benefits added more than 1% to the variance in the diet score. CONCLUSIONS: Poor achievement at school defines a substantial group of women in the UK who may be vulnerable. Many of these women have poor diets that are not simply a result of the level of deprivation in their neighbourhood, or of living at a level of poverty that entitles them to benefits. We suggest that it is a priority to identify and to address the barriers that prevent these women from improving the quality of their diets. SPONSORSHIP: The study was funded by the Dunhill Medical Trust, the University of Southampton and the Medical Research Council.

Adult↗
PubMed2004

Variability of personal chemical exposure in eight office buildings in Sweden.

This study focuses on the variability in chemical exposures for individuals working in office buildings. The study involved eight office buildings with 79 participants, and exposures were measured using personal samplers for volatile organic compounds, aldehydes, amines, nitrogen dioxide, ozone, and particles. Ventilation was assessed in each individual office. "Variability among buildings" and "variability among individuals" were evaluated for any component (of the 123) measured in samples from at least 20 persons, using variance component analysis and principal component analysis. Interpersonal differences explained the major part of the variance for 78% of the compounds versus between-buildings differences for 14% of the compounds. For 8% of compounds, the variation was explained in equal amounts by the differences among individuals and among buildings. This study illustrates the necessity for individualised measurements (versus stationary measurements in building) to estimate personal exposures. These results also support the conclusion that in case-referent studies of "sick building syndrome" (SBS), referents to SBS cases can be randomised for building location.

Air Pollution, Indoor↗
PubMed1992

Event related potentials and EEG components in a semantic memory search task.

This study examined the effects of memory search and related processes on both time and frequency domain components of electroencephalographic activity. More specifically, we were interested in the relationship between EEG and event-related potential (ERP) components as a function of memory load and response type. Subjects performed a semantic memory search task in which they matched word probes to category labels. Consistent with previous studies, reaction time increased and accuracy decreased with increasing memory loads. A negative component of the ERP (N400) was found to reflect semantic mismatch: N400s were larger for the nontargets than for the targets. Two ERP components were found to be reciprocally related to memory load. P300 decreased and Negative Slow Wave increased in amplitude with increases in the size of the memory set. These two ERP components were reflected by different components in a Principal Components Analysis. The power in the theta band (5-7 Hz) also increased as a function of memory load and appears to be functionally and topographically related to the Negative Slow Wave in the ERP. It is argued that both measures are jointly determined and reflect the difficulty of the conceptual operations during memory search.

Adult↗
PubMed2005

Discrimination efficacy of fecal pollution detection in different aquatic habitats of a high-altitude tropical country, using presumptive coliforms, Escherichia coli, and Clostridium perfringens spores.

The performance of rapid and practicable techniques that presumptively identify total coliforms (TC), fecal coliforms (FC), Escherichia coli, and Clostridium perfringens spores (CP) by testing them on a pollution gradient in differing aquatic habitats in a high-altitude tropical country was evaluated during a 12-month period. Site selection was based on high and low anthropogenic influence criteria of paired sites including six spring, six stream, and four lakeshore sites spread over central and eastern parts of Uganda. Unlike the chemophysical water quality, which was water source type dependent (i.e., spring, lake, or stream), fecal indicators were associated with the anthropogenic influence status of the respective sites. A total of 79% of the total variability, including all the determined four bacteriological and five chemophysical parameters, could be assigned to either a pollution, a habitat, or a metabolic activity component by principal-component analysis. Bacteriological indicators revealed significant correlations to the pollution component, reflecting that anthropogenic contamination gradients were followed. Discrimination sensitivity analysis revealed high ability of E. coli to differentiate between high and low levels of anthropogenic influence. CP also showed a reasonable level of discrimination, although FC and TC were found to have worse discrimination efficacy. Nonpoint influence by soil erosion could not be detected during the study period by correlation analysis, although a theoretical contamination potential existed, as investigated soils in the immediate surroundings often contained relevant concentrations of fecal indicators. The outcome of this study indicates that rapid techniques for presumptive E. coli and CP determination may be reliable for fecal pollution monitoring in high-altitude tropical developing countries such as those of Eastern Africa.

Altitude↗
PubMed2005

Inequalities in neighbourhood socioeconomic characteristics: potential evidence-base for neighbourhood health planning.

BACKGROUND: Population health planning aims to improve the health of the entire population and to reduce health inequities among population groups. Socioeconomic factors are increasingly being recognized as major determinants of many aspects of health and causes of health inequities. Knowledge of socioeconomic characteristics of neighbourhoods is necessary to identify their unique health needs and enhance identification of socioeconomically disadvantaged populations. Careful integration of this knowledge into health planning activities is necessary to ensure that health planning and service provision are tailored to unique neighbourhood population health needs. In this study, we identify unique neighbourhood socioeconomic characteristics and classify the neighbourhoods based on these characteristics. Principal components analysis (PCA) of 18 socioeconomic variables was used to identify the principal components explaining most of the variation in socioeconomic characteristics across the neighbourhoods. Cluster analysis was used to classify neighbourhoods based on their socioeconomic characteristics. RESULTS: Results of the PCA and cluster analysis were similar but the latter were more objective and easier to interpret. Five neighbourhood types with distinguishing socioeconomic and demographic characteristics were identified. The methodology provides a more complete picture of the neighbourhood socioeconomic characteristics than when a single variable (e.g. income) is used to classify neighbourhoods. CONCLUSION: Cluster analysis is useful for generating neighbourhood population socioeconomic and demographic characteristics that can be useful in guiding neighbourhood health planning and service provision. This study is the first of a series of studies designed to investigate health inequalities at the neighbourhood level with a view to providing evidence-base for health planners, service providers and policy makers to help address health inequity issues at the neighbourhood level. Subsequent studies will investigate inequalities in health outcomes both within and across the neighbourhood types identified in the current study.

Journal Article↗
PubMed2006

An illustration of issues in factor extraction and identification of dimensionality in psychological assessment data.

Structural validity has long been regarded as critical to psychological measurement. However, in practical application, issues central to structural validity are often neglected. The purpose of this study was to illustrate the importance of several crucial choices that face researchers attempting to evaluate the structure of data from a given scale. In this study, I compared the structural solutions derived via principal components analysis and principal axis factoring using eigenvalues, scree plots, and traditional parallel analyses with data from the Purpose in Life Test (Crumbaugh & Maholick, 1964). I discuss the importance of structural validity for overall construct validity and the importance of carefully considering factor analytic methodology. I provide recommendations for uses of factor analysis.

Adult↗
PubMed2006

Factorial coding of natural images: how effective are linear models in removing higher-order dependencies?

The performance of unsupervised learning models for natural images is evaluated quantitatively by means of information theory. We estimate the gain in statistical independence (the multi-information reduction) achieved with independent component analysis (ICA), principal component analysis (PCA), zero-phase whitening, and predictive coding. Predictive coding is translated into the transform coding framework, where it can be characterized by the constraint of a triangular filter matrix. A randomly sampled whitening basis and the Haar wavelet are included in the comparison as well. The comparison of all these methods is carried out for different patch sizes, ranging from 2x2 to 16x16 pixels. In spite of large differences in the shape of the basis functions, we find only small differences in the multi-information between all decorrelation transforms (5% or less) for all patch sizes. Among the second-order methods, PCA is optimal for small patch sizes and predictive coding performs best for large patch sizes. The extra gain achieved with ICA is always less than 2%. In conclusion, the edge filters found with ICA lead to only a surprisingly small improvement in terms of its actual objective.

Algorithms↗
PubMed2000

Using social indicators to inform community drug and alcohol prevention policy.

In recent years, the federal government has begun to require state agencies to allocate drug prevention resources according to the needs of local communities. The methods by which this is to be accomplished have not been described, and most published social indicator studies in the field of drug abuse research have used county-level data which are too insensitive to local needs to be of use in resource allocation decisions. The present study describes a needs assessment in drug abuse prevention in the state of New Jersey using municipal-level social indicator data. In addition, it examines the extent to which the resource allocation of one state prevention agency can be predicted by the municipal-level social indicators. Thirty-six social indicators pertaining to 508 municipalities were used in the study, and data were analyzed using principal component analysis and hierarchical regression analysis. Five factors were extracted from the principal component analysis, two of which clearly describe "high risk" municipalities and one of which clearly describes "low risk" municipalities. The regression analysis showed that these factors explained very little of the variance in the state agency's drug prevention spending. The study shows that social indicators can be used to distinguish between different levels of need for drug prevention services at a municipal level, and that these data can be used to inform decisions concerning resource allocation.

Alcoholism↗
PubMed2000

Cardiac arrhythmia classification using neural networks.

In this paper, ECG arrhythmia classification using principal component analysis is proposed. Hebbian neural networks are used for computing the principal components of an ECG signal. This provides an unsupervised feature extraction, dimension reduction and an improved computing efficiency. Results from 14 pathological records obtained from the MIT ECG database demonstrate the capability of this method in differentiating between five different types of arrhythmia despite the variations in signal morphology. An average value for classification sensitivity and positive predictivity were found to be Se% = 98.1% and +P% = 94.7% respectively.

Algorithms↗