Search

Different fertilization systems, methods and techniques result in differences in plant nutrition, with variations in the mineral element contents in the leaves and values of physiological, yield, and production quality indices. This results in large datasets that are often relatively difficult to interpret. Starting from these aspects, the present study analyzed data on the state of plant nutrition (N, P, K, Ca, and Mg content in leaves, in % of dry matter; Fe, Mn, Cu, and Zn content in leaves, in mg/kg of dry matter), physiological indices (chlorophyll leaf content—Chl; leaf area—LA), yield (kg/vine, t/ha), and grape berry quality (sugar and acidity content in berries) of the 'Burgund mare' grape cultivar in relation to organic, mineral and foliar fertilization. According to a PCA multivariate analysis, four groups of components were obtained: PC1 including five factors, with positive action in the case of K (r = 0.963), P (r = 0.770) and Cu (r = 0.752), and negative action in the case of Mg (r = −0.940) and Mn (r = −0.759); PC2 including three factors, with positive action for Chl (r = 0.938), LA (r = 0.938) and Ca (r = 0.722); PC3 including one factor (N), with negative action (r = −0.916); and PC4 including two factors, with positive action for Fe (r = 0.869) and Zn (r = 0.761). Based on the one-sample t test (parametric) and the Wilcoxon test (non-parametric) and a threshold value of α = 0.05, the differences between the index values for fertilization variants T2–T13 compared with those for the control variant (T1) were verified. Significant differences were recorded in PC1 for P, Mg and Cu; in PC2 for Chl, LA and Ca; and in PC3 for N. Insignificant differences were recorded in PC1 for K and Mn and in PC4 for Fe and Zn. In the case of the productivity elements and quality indices, significant differences were recorded. [ABSTRACT FROM AUTHOR]

Imaging analysis (UAV images) was used to evaluate a corn crop under hydric stress conditions. From the analysis of the series of images (June 29 - T1, July 20 - T2, year 2022) the values of the RGB parameters resulted. Suplementary the luminance (Lum), normalized values (rgb), values in the HSB system, and INT, NDI and DGCI indices, were determined. The correlation analysis identified 18 very strong correlations between the parameters considered at the time of T1, and 10 very strong correlations at the time of T2. The PCA analysis led to the classification of the components: seven components in PC1 (R = -9.93 the highest value) and three components in PC2 (Lum = 0.970 the highest value) at the time of T1; four components in PC1 (r = -0.990 the highest value) and four components in PC2 (Lum = 0.949 the highest value) at time T2. The differences between the series of parameters, at the moments T1 and T2, were confirmed by values U = 18, p = 0.017 in the case of parameter G; U = 10, p = 0.0028 in the case of the B parameter; t = 9.4202, p < 0.01 in the case of NDI; t = 9.2066, p<0.001, U = 1, p < 0.001 in the case of INT; t = 9.3176, p < 0.001 in the case of DGCI; t = 7.5581, p < 0.001, U = 3, p < 0.001 in the case of Lum. [ABSTRACT FROM AUTHOR]

Different fertilization systems, methods and techniques result in differences in plant nutrition, with variations in the mineral element contents in the leaves and values of physiological, yield, and production quality indices. This results in large datasets that are often relatively difficult to interpret. Starting from these aspects, the present study analyzed data on the state of plant nutrition (N, P, K, Ca, and Mg content in leaves, in % of dry matter; Fe, Mn, Cu, and Zn content in leaves, in mg/kg of dry matter), physiological indices (chlorophyll leaf content—Chl; leaf area—LA), yield (kg/vine, t/ha), and grape berry quality (sugar and acidity content in berries) of the ‘Burgund mare’ grape cultivar in relation to organic, mineral and foliar fertilization. According to a PCA multivariate analysis, four groups of components were obtained: PC1 including five factors, with positive action in the case of K (r = 0.963), P (r = 0.770) and Cu (r = 0.752), and negative action in the case of Mg (r = −0.940) and Mn (r = −0.759); PC2 including three factors, with positive action for Chl (r = 0.938), LA (r = 0.938) and Ca (r = 0.722); PC3 including one factor (N), with negative action (r = −0.916); and PC4 including two factors, with positive action for Fe (r = 0.869) and Zn (r = 0.761). Based on the one-sample t test (parametric) and the Wilcoxon test (non-parametric) and a threshold value of α = 0.05, the differences between the index values for fertilization variants T2–T13 compared with those for the control variant (T1) were verified. Significant differences were recorded in PC1 for P, Mg and Cu; in PC2 for Chl, LA and Ca; and in PC3 for N. Insignificant differences were recorded in PC1 for K and Mn and in PC4 for Fe and Zn. In the case of the productivity elements and quality indices, significant differences were recorded.

In recent years, automatic lineament extraction has gained huge popularity as it circumvents the issues such as errors and time constraints associated with manual extraction procedure. Another impediment in the lineament extraction process is that linear features existing near sub-surface or occluded due to vegetation cover cannot be identified solely by optical data. To mitigate these issues, a multi-sensor fusion-based automatic extraction process using EO-based optical and SAR data is proposed. Use of moderate resolution optical data such as ASTER minimizes erroneous identification and misclassification of anthropogenic features as geological features. In addition to this, a component loading-based band selection approach is proposed to select the most informative bands from the available optical bands for improved extraction of lineament features. Finally, a new HSV-based mapping method for visualization and directional analysis of the extracted linear features is discussed. The results are validated using the published seismo-tectonic map of the region and field investigation studies which corroborates that the proposed algorithm can successfully extract most of the geological lineaments in the study area with minimum errors. Research highlights: This research sheds light on the use of multi-sensor data for understanding the tectonic setup of an area. This research is highly useful for the practices such as geological mapping and weak zone demarcation using EO data of the denied areas Further, the outcome of the results can also be used in mass movement vulnerability assessment of the area for mitigation and planning purposes. Further, this also increases robustness in band selection procedure for lineament extraction. [ABSTRACT FROM AUTHOR]

Band selection and feature extraction are the two paradigms of hyperspectral dimensionality reduction. While feature extraction methods have many desirable properties, band selection methods keep the actual reflectances intact, which results in better interpretation of the behavior of the materials. Keeping this in mind, several feature extraction-based band selection methods have been proposed in the past, which can bridge the gap between these two approaches and combine their salient advantages. In this article, a feature extraction-based, clustering-ranking type band selection method is proposed in which the band selection is performed in two stages. In the clustering stage, a new and improved representation of bands using their component loadings for the top principal components is introduced, which is employed to cluster similar bands into groups using sparse subspace clustering. In the ranking stage, a new metric called combined divergence-correlation index is introduced to elect the most discriminative as well as least correlated bands as cluster representatives. Experimental results indicate that the proposed method can proficiently select a set of distinct and discriminative bands, which can help in effective hyperspectral classification. Additionally, it was also shown that the selected bands show rich information content, low interband correlation and high-class separabilities.

Dimensionality reduction strategies can be broadly categorized as band selection and feature extraction. Researchers and analysts from the remote sensing community give greater preference to band selection over feature extraction as the latter modifies the original reflectance values of hyperspectral data, making it difficult to understand the behavior of the materials in terms of their reflectance values. However, feature extraction strategies have their own advantages which cannot be ignored. Thus, a two-level, PCA-based band selection framework is proposed to unify the two dimensionality reduction strategies so that benefits of both the strategies can be derived. The proposed approach selects bands based on their relationship with a given set of principal components explained in terms of component loadings, thus keeping the original bands intact. Additionally, contrary to the popular notion that the complete information of all bands is adequately coalesced in the top principal components, middle principal components play a far stronger discriminative role when the competing classes are spectrally confusing to each other. Thus, for each level of classification, a different range of principal components is used to select the bands, on the basis of the level of spectral similarity expected between the classes at each level. Experimental results indicate that the proposed two-level band selection algorithm can select bands with varying levels of discriminative capabilities to effectively classify hyperspectral images consisting of classes spectrally very similar in nature. [ABSTRACT FROM AUTHOR]

The objective of the present study was to assess the reproducibility of data-driven dietary patterns in different samples extracted from similar populations. Dietary patterns were extracted by applying principal component analyses to the dietary information collected from a sample of 3550 women recruited from seven screening centres belonging to the Spanish breast cancer (BC) screening network (Determinants of Mammographic Density in Spain (DDM-Spain) study). The resulting patterns were compared with three dietary patterns obtained from a previous Spanish case–control study on female BC (Epidemiological study of the Spanish group for breast cancer research (GEICAM: grupo Español de investigación en cáncer de mama)) using the dietary intake data of 973 healthy participants. The level of agreement between patterns was determined using both the congruence coefficient (CC) between the pattern loadings (considering patterns with a CC≥0·85 as fairly similar) and the linear correlation between patterns scores (considering as fairly similar those patterns with a statistically significant correlation). The conclusions reached with both methods were compared. This is the first study exploring the reproducibility of data-driven patterns from two studies and the first using the CC to determine pattern similarity. We were able to reproduce the EpiGEICAM Western pattern in the DDM-Spain sample (CC=0·90). However, the reproducibility of the Prudent (CC=0·76) and Mediterranean (CC=0·77) patterns was not as good. The linear correlation between pattern scores was statistically significant in all cases, highlighting its arbitrariness for determining pattern similarity. We conclude that the reproducibility of widely prevalent dietary patterns is better than the reproducibility of more population-specific patterns. More methodological studies are needed to establish an objective measurement and threshold to determine pattern similarity. [ABSTRACT FROM PUBLISHER]

In this paper, the statistical significance of the contribution of variables to the principal components in principal components analysis (PCA) is assessed nonparametrically by the use of permutation tests. We compare a new strategy to a strategy used in previous research consisting of permuting the columns (variables) of a data matrix independently and concurrently, thus destroying the entire correlational structure of the data. This strategy is considered appropriate for assessing the significance of the PCA solution as a whole, but is not suitable for assessing the significance of the contribution of single variables. Alternatively, we propose a strategy involving permutation of one variable at a time, while keeping the other variables fixed. We compare the two approaches in a simulation study, considering proportions of Type I and Type II error. We use two corrections for multiple testing: the Bonferroni correction and controlling the False Discovery Rate (FDR). To assess the significance of the variance accounted for by the variables, permuting one variable at a time, combined with FDR correction, yields the most favorable results. This optimal strategy is applied to an empirical data set, and results are compared with bootstrap confidence intervals. [ABSTRACT FROM AUTHOR]

When the factor analysis model holds, component loadings are linear combinations of factor loadings, and vice versa. This interrelation permits us to define new optimization criteria and estimation methods for exploratory factor analysis. Although this article is primarily conceptual in nature, an illustrative example and a small simulation show the methodology to be promising. [ABSTRACT FROM AUTHOR]

Relationships between the results of factor analysis and component analysis are derived when oblique factors have independent clusters with equal variances of unique factors. The factor loadings are analytically shown to be smaller than the corresponding component loadings while the factor correlations are shown to be greater than the corresponding component correlations. The condition for the inequality of the factor/component contributions is derived in the case with different variances for unique factors. Further, the asymptotic standard errors of parameter estimates are obtained for a simplified model with the assumption of multivariate normality, which shows that the component loading estimate is more stable than the corresponding factor loading estimate. [ABSTRACT FROM AUTHOR]

Concise formulas for the asymptotic standard errors of component loading estimates were derived. The formulas cover the cases of principal component analysis for unstandardized and standardized variables with orthogonal and oblique rotations. The formulas can be used under any distributions for observed variables as long as the asymptotic covariance matrix for sample covariances/correlations is available. The estimated standard errors in numerical examples were shown to be equivalent to those by the methods using information matrices. [ABSTRACT FROM AUTHOR]

The asymptotic correlations between the estimates of factor and component loadings are obtained for the exploratory factor analysis model with the assumption of a multivariate normal distribution for manifest variables. The asymptotic correlations are derived for the cases of unstandardized and standardized manifest variables with orthogonal and oblique rotations. Based on the above results, the asymptotic standard errors for estimated correlations between factors and components are derived. Further, the asymptotic standard error of the mean squared canonical correlation for factors and components, which is an overall index for the closeness of factors and components, is derived. The results of a Monte Carlo simulation are presented to show the usefulness of the asymptotic results in the data with a finite sample size. [ABSTRACT FROM AUTHOR]