Application of Redundancy Analysis for Aerobiological Data

An aerobiological survey was conducted through five consecutive years (2006–2010) at Worcester (England).The concentration of 20 allergenic fungal spore types was measured using a 7-day volumetric spore trap. The relationship between investigated fungal spore genera and selected meteorological parameters (maximum, minimum, mean and dew point temperatures, rainfall, relative humidity, air pressure,wind direction) was examined using an ordination method(redundancy analysis) to determine which environmental factors favoured their most abundance in the air and whether it would be possible to detect similarities between different genera in their distribution pattern. Redundancy analysis provided additional information about the biology of the studied fungi through the results of the Spearman’s rank correlation. Application of the variance inflation factor in canonical correspondence analysis indicated which explanatory variables were auto-correlated and needed to be excluded from further analyses. Obtained information will be consequently implemented in the selection of factors that will be a foundation for forecasting models for allergenic fungal spores in the future.

ON THE UTILITY OF CANONICAL CORRELATION ANALYSIS FOR DOMAIN ADAPTATION IN MULTI-VIEW HEADPOSE ESTIMATION

The utility of canonical correlation analysis (CCA) for domain adaptation (DA) in the context of multi-view head pose estimation is examined in this work. We consider the three problems studied in 1], where different DA approaches are explored to transfer head pose-related knowledge from an extensively labeled source dataset to a sparsely labeled target set, whose attributes are vastly different from the source. CCA is found to benefit DA for all the three problems, and the use of a covariance profile-based diagonality score (DS) also improves classification performance with respect to a nearest neighbor (NN) classifier.

Deflation based nonlinear canonical correlation analysis

This paper introduces two new techniques for determining nonlinear canonical correlation coefficients between two variable sets. A genetic strategy is incorporated to determine these coefficients. Compared to existing methods for nonlinear canonical correlation analysis (NLCCA), the benefits here are that the nonlinear mapping requires fewer parameters to be determined, consequently a more parsimonious NLCCA model can be established which is therefore simpler to interpret. A further contribution of the paper is the investigation of a variety of nonlinear deflation procedures for determining the subsequent nonlinear canonical coefficients. The benefits of the new approaches presented are demonstrated by application to an example from the literature and to recorded data from an industrial melter process. These studies show the advantages of the new NLCCA techniques presented and suggest that a nonlinear deflation procedure should be considered. (c) 2006 Elsevier B.V. All rights reserved.

The use of ensemble empirical mode decomposition with canonical correlation analysis as a novel artifact removal technique

Biosignal measurement and processing is increasingly being deployed in ambulatory situations particularly in connected health applications. Such an environment dramatically increases the likelihood of artifacts which can occlude features of interest and reduce the quality of information available in the signal. If multichannel recordings are available for a given signal source, then there are currently a considerable range of methods which can suppress or in some cases remove the distorting effect of such artifacts. There are, however, considerably fewer techniques available if only a single-channel measurement is available and yet single-channel measurements are important where minimal instrumentation complexity is required. This paper describes a novel artifact removal technique for use in such a context. The technique known as ensemble empirical mode decomposition with canonical correlation analysis (EEMD-CCA) is capable of operating on single-channel measurements. The EEMD technique is first used to decompose the single-channel signal into a multidimensional signal. The CCA technique is then employed to isolate the artifact components from the underlying signal using second-order statistics. The new technique is tested against the currently available wavelet denoising and EEMD-ICA techniques using both electroencephalography and functional near-infrared spectroscopy data and is shown to produce significantly improved results. © 1964-2012 IEEE.

Applications of redundancy analysis for the detection of chemical response patterns to air pollution in lichen

The lichens Ramalina celastri (Spreng.) Krog & Swinsc., Punctelia microsticta (Müll. Arg.) Krog and Canomaculina pilosa (Stizenb.) Elix & Hale were transplanted simultaneously to 17 urban-industrial sites in a northwestern area of Córdoba city, Argentina. The transplantation sites were set according to different environmental conditions: traffic, industries, tree cover, building height, topographic level, position in the block and distances from the river and from the power plant. Three months later, chlorophyll a, chlorophyll b, phaeophytin a, soluble proteins, hydroperoxy conjugated dienes, malondialdehyde concentration and sulfur accumulation were determined, and a pollution index was calculated for each sampling site. Redundancy analysis was applied to detect the variation pattern of the lichen variables that can be 'best' explained by the environmental variables considered. The present study provides information about both the specific pattern response of each species to atmospheric pollution, and environmental conditions that determine it. As regards pollutants emission sources R. celastri showed a chemical response associated mainly with pollutant released by the power plant and traffic. P. microsticta and C. pilosa responded mainly to industrial sources. Regarding environmental conditions that affect the spreading of air pollutants and their incidence on the bioindicator, the topographic level and tree cover surrounding the sampling site were found to be important for R. celastri, tree cover surrounding the sampling site and the building height affected P. microsticta, while building height did so for C. pilosa.

Canonical Correlation Analysis for Interpreting Airborne Laser Scanning Metrics along the Lorenz Curve of Tree Size Inequality

Canonical Correlation Analysis for Interpreting Airborne Laser Scanning Metrics along the Lorenz Curve of Tree Size Inequality

Statnote 28:Canonical Variate Analysis (CVA)

The pattern of correlation between two sets of variables can be tested using canonical variate analysis (CVA). CVA, like principal components analysis (PCA) and factor analysis (FA) (Statnote 27, Hilton & Armstrong, 2011b), is a multivariate analysis Essentially, as in PCA/FA, the objective is to determine whether the correlations between two sets of variables can be explained by a smaller number of ‘axes of correlation’ or ‘canonical roots’.

Approches transcriptomiques dans l’étude de la fibrose kystique

Les avancées en biotechnologie ont permis l’identification d’un grand nombre de mécanismes moléculaires, soulignant également la complexité de la régulation génique. Néanmoins, avoir une vision globale de l’homéostasie cellulaire, nous est pour l’instant inaccessible et nous ne sommes en mesure que d’en avoir qu’une vue fractionnée. Étant donné l’avancement des connaissances des dysfonctionnements moléculaires observés dans les maladies génétiques telles que la fibrose kystique, il est encore difficile de produire des thérapies efficaces. La fibrose kystique est causée par la mutation de gène CFTR (cystic fibrosis transmembrane conductance regulator), qui code pour un canal chlorique transmembranaire. La mutation la plus fréquente (ΔF508) induit un repliement incorrect de la protéine et sa rétention dans le réticulum endoplasmique. L’absence de CFTR fonctionnel à la membrane a un impact sur l’homéostasie ionique et sur l’hydratation de la muqueuse respiratoire. Ceci a pour conséquence un défaut dans la clairance mucocilliaire, induisant infection chronique et inflammation excessive, deux facteurs fondamentaux de la physiopathologie. L’inflammation joue un rôle très important dans l’évolution de la maladie et malgré le nombre important d’études sur le sujet, la régulation du processus inflammatoire est encore très mal comprise et la place qu’y occupe le CFTR n’est pas établie. Toutefois, plusieurs autres facteurs, tels que le stress oxydatif participent à la physiopathologie de la maladie, et considérer leurs impacts est important pour permettre une vision globale des acteurs impliqués. Dans notre étude, nous exploitons la technologie des puces à ADN, pour évaluer l’état transcriptionnel d’une cellule épithéliale pulmonaire humaine fibro-kystique. Dans un premier temps, l’analyse de notre expérience identifie 128 gènes inflammatoires sur-exprimés dans les cellules FK par rapport aux cellules non FK où apparaissent plusieurs familles de gènes inflammatoires comme les cytokines ou les calgranulines. L’analyse de la littérature et des annotations suggèrent que la modulation de ces transcripts dépend de la cascade de NF-κB et/ou des voies de signalisation associées aux interférons (IFN). En outre, leurs modulations pourraient être associées à des modifications épigénétiques de leurs loci chromosomiques. Dans un second temps, nous étudions l’activité transcriptionnelle d’une cellule épithéliale pulmonaire humaine FK en présence de DMNQ, une molécule cytotoxique. Notre but est d’identifier les processus biologiques perturbés par la mutation du gène CFTR en présence du stress oxydatif. Fondé sur une analyse canonique de redondance, nous identifions 60 gènes associés à la mort cellulaire et leur variance, observée dans notre expérience, s’explique par un effet conjoint de la mutation et du stress oxydatif. La mesure de l’activité des caspases 3/7, des effecteurs de l’apoptose (la mort cellulaire programmée), montre que les cellules porteuses de la mutation ΔF508, dans des conditions de stress oxydatif, seraient moins apoptotiques que les cellules saines. Nos données transcriptomiques suggèrent que la sous-activité de la cascade des MAPK et la sur-expression des gènes anti-apoptotiques pourraient être impliquées dans le déséquilibre de la balance apoptotique.