Home About us Contact
|
Home About us Contact | ||
|
|
||
Mahalanobis Distance (Mahalanobi + distance)
Selected AbstractsAssessing ecosystem threats from global and regional change: hierarchical modeling of risk to sagebrush ecosystems from climate change, land use and invasive species in Nevada, USAECOGRAPHY, Issue 1 2010Bethany A. Bradley Global change poses significant challenges for ecosystem conservation. At regional scales, climate change may lead to extensive shifts in species distributions and widespread extirpations or extinctions. At landscape scales, land use and invasive species disrupt ecosystem function and reduce species richness. However, a lack of spatially explicit models of risk to ecosystems makes it difficult for science to inform conservation planning and land management. Here, I model risk to sagebrush (Artemisia spp.) ecosystems in the state of Nevada, USA from climate change, land use/land cover change, and species invasion. Risk from climate change is based on an ensemble of 10 atmosphere-ocean general circulation model (AOGCM) projections applied to two bioclimatic envelope models (Mahalanobis distance and Maxent). Risk from land use is based on the distribution of roads, agriculture, and powerlines, and on the spatial relationships between land use and probability of cheatgrass Bromus tectorum invasion in Nevada. Risk from land cover change is based on probability and extent of pinyon-juniper (Pinus monophylla; Juniperus spp.) woodland expansion. Climate change is most likely to negatively impact sagebrush ecosystems at the edges of its current range, particularly in southern Nevada, southern Utah, and eastern Washington. Risk from land use and woodland expansion is pervasive throughout Nevada, while cheatgrass invasion is most problematic in the northern part of the state. Cumulatively, these changes pose major challenges for conservation of sagebrush and sagebrush obligate species. This type of comprehensive assessment of ecosystem risk provides managers with spatially explicit tools important for conservation planning. [source] Glutathione S -transferase detoxification as a potential pyrethroid resistance mechanism in the maize weevil, Sitophilus zeamaisENTOMOLOGIA EXPERIMENTALIS ET APPLICATA, Issue 1 2003Daniel B. Fragoso Abstract Insecticide resistance patterns among 16 Brazilian populations of the maize weevil, Sitophilus zeamais Motschulsky (Coleoptera: Curculionidae), were recognized by surveying resistance to three organophosphates (chlorpyrifos-methyl, malathion, and pirimiphos-methyl) and three pyrethroids (cypermethrin, deltamethrin, and permethrin). Two population clusters were obtained: one with three populations (Bragança Paulista, Cristalina, and Nova Andradina) showing low frequency of cypermethrin resistance (13,36%) and negligible frequency of deltamethrin resistance (2,9%); and another with six populations (Campos dos Goytacazes, Ivinhema, Patos de Minas, Penápolis, Uberlândia, and Venda Nova) showing low to negligible levels of pyrethroid resistance (0,23%). The remaining seven populations, including a susceptible, and a DDT- and pyrethroid-resistant reference populations (Sete Lagoas and Jacarezinho, respectively), were significantly different from each other and from the two recognized clusters. In contrast with pyrethroid resistance, organophosphate resistance was negligible except for chlorpyrifos-methyl in two populations (Fátima do Sul and Penápolis). There was no correlation between geographic distance and the Mahalanobis distance estimated from the resistance pattern ordination of the populations by canonical variate analysis, suggesting local selection and/or broad dispersal of resistant populations by grain trade. The results of biochemical in vitro studies measuring the activity of detoxification enzymes (esterases and glutathion S -transferases) in conjunction with canonical correlation analysis suggest a major involvement of enhanced conjugation by glutathione S -transferases (> 2-fold increase) in pyrethroid resistance and, in the case of cypermethrin resistance, enhanced phosphotriesterase activity. [source] Clustering composition vectors using uncertainty informationENVIRONMETRICS, Issue 8 2007William F. Christensen Abstract In the biological and environmental sciences, interest often lies in using multivariate observations to discover natural clusters of objects. In this manuscript, the incorporation of measurement uncertainty information into a cluster analysis is discussed. This study is motivated by a problem involving the clustering of composition vectors associated with each of several chemical species. The observed abundance of each component is available along with its estimated uncertainty (measurement error standard deviation). An approach is proposed for converting the abundance vectors into composition (relative abundance) vectors, obtaining the covariance matrix associated with each composition vector, and defining a Mahalanobis distance between composition vectors that are suitable for cluster analysis. The approach is illustrated using particle size distributions obtained near Houston, Texas in 2000. Computer simulation is used to compare the performance of Mahalanobis-distance-based and Euclidean-distance-based clustering approaches. The use of a modified Mahalanobis distance along with Ward's method is recommended for use. Copyright © 2007 John Wiley & Sons, Ltd. [source] Robust principal component analysis and outlier detection with ecological dataENVIRONMETRICS, Issue 2 2004Donald A. Jackson Abstract Ecological studies frequently involve large numbers of variables and observations, and these are often subject to various errors. If some data are not representative of the study population, they tend to bias the interpretation and conclusion of an ecological study. Because of the multivariate nature of ecological data, it is very difficult to identify atypical observations using approaches such as univariate or bivariate plots. This difficulty calls for the application of robust statistical methods in identifying atypical observations. Our study provides a comparison of a standard method, based on the Mahalanobis distance, used in multivariate approaches to a robust method based on the minimum volume ellipsoid as a means of determining whether data sets contain outliers or not. We evaluate both methods using simulations varying conditions of the data, and show that the minimum volume ellipsoid approach is superior in detecting outliers where present. We show that, as the sample size parameter, h, used in the robust approach increases in value, there is a decrease in the accuracy and precision of the associated estimate of the number of outliers present, in particular as the number of outliers increases. Conversely, where no outliers are present, large values for the parameter provide the most accurate results. In addition to the simulation results, we demonstrate the use of the robust principal component analysis with a data set of lake-water chemistry variables to illustrate the additional insight available. We suggest that ecologists consider that their data may contain atypical points. Following checks associated with normality, bivariate linearity and other traditional aspects, we advocate that ecologists examine their data sets using robust multivariate methods. Points identified as being atypical should be carefully evaluated based on background information to determine their suitability for inclusion in further multivariate analyses and whether additional factors explain their unusual characteristics. Copyright © 2004 John Wiley & Sons, Ltd. [source] Mahalanobis distance-based traffic matrix estimationEUROPEAN TRANSACTIONS ON TELECOMMUNICATIONS, Issue 3 2010Dingde Jiang This letter studies large-scale IP traffic matrix (TM) estimation problem and proposes a novel method called the Mahalanobis distance-based regressive inference (MDRI). By using Mahalanobis distance as an optimal metric, we can get rid of the highly ill-posed nature of this problem. We describe the TM estimation into an optimal process, and then by optimising the regularised equation about this problem, TM's estimation can accurately obtained. Testing results are shown to be promising. Copyright © 2010 John Wiley & Sons, Ltd. [source] Not everything is everywhere: the distance decay of similarity in a marine host,parasite systemJOURNAL OF BIOGEOGRAPHY, Issue 2 2009Ana Pérez-del-Olmo Abstract Aim, We test the similarity,distance decay hypothesis on a marine host,parasite system, inferring the relationships from abundance data gathered at the lowest scale of parasite community organization (i.e. that of the individual host). Location, Twenty-two seasonal samples of the bogue Boops boops (Teleostei: Sparidae) were collected at seven localities along a coastal positional gradient from the northern North-East Atlantic to the northern Mediterranean coast of Spain. Methods, We used our own, taxonomically consistent, data on parasite communities. The variations in parasite composition and structure with geographical and regional distance were examined at two spatial scales, namely local parasite faunas and component communities, using both presence,absence (neighbour joining distance) and abundance (Mahalanobis distance) data. The influence of geographical and regional distance on faunal/community divergence was assessed through the permutation of distance matrices. Results, Our results revealed that: (1) geographical and regional distances do not affect the species composition in the system under study at the higher scales; (2) geographical distance between localities contributes significantly to the decay of similarity estimated from parasite abundance at the lowest scale (i.e. the individual host); (3) the structured spatial patterns are consistent in time but not across seasons; and (4) a restricted clade of species (the ,core' species of the bogue parasite fauna) contributes substantially to the observed patterns of both community homogenization and differentiation owing to the strong relationship between local abundance and regional distribution of species. Main conclusions, The main factors that tend to homogenize the composition of parasite communities of bogue at higher regional scales are related to the dispersal of parasite colonizers across host populations, which we denote as horizontal neighbourhood colonization. In contrast, the spatial structure detectable in quantitative comparisons only, is related to a vertical neighbourhood colonization associated with larval dispersal on a local level. The stronger decline with distance in the spatial synchrony of the assemblages of the ,core' species indicates a close-echoing environmental synchrony that declines with distance. Our results emphasize the importance of the parasite supracommunity (i.e. parasites that exploit all hosts in the ecosystem) to the decay of similarity with distance. [source] One class classifiers for process monitoring illustrated by the application to online HPLC of a continuous processJOURNAL OF CHEMOMETRICS, Issue 3-4 2010Sila Kittiwachana Abstract In process monitoring, a representative out-of-control class of samples cannot be generated. Here, it is assumed that it is possible to obtain a representative subset of samples from a single ,in-control class' and one class classifiers namely Q and D statistics (respectively the residual distance to the disjoint PC model and the Mahalanobis distance to the centre of the QDA model in the projected PC space), as well as support vector domain description (SVDD) are applied to disjoint PC models of the normal operating conditions (NOC) region, to categorise whether the process is in-control or out-of-control. To define the NOC region, the cumulative relative standard deviation (CRSD) and a test of multivariate normality are described and used as joint criteria. These calculations were based on the application of window principal components analysis (WPCA) which can be used to define a NOC region. The D and Q statistics and SVDD models were calculated for the NOC region and percentage predictive ability (%PA), percentage model stability (%MS) and percentage correctly classified (%CC) obtained to determine the quality of models from 100 training/test set splits. Q, D and SVDD control charts were obtained, and 90% confidence limits set up based on multivariate normality (D and Q) or SVDD D value (which does not require assumptions of normality). We introduce a method for finding an optimal radial basis function for the SVDD model and two new indices of percentage classification index (%CI) and percentage predictive index (%PI) for non-NOC samples are also defined. The methods in this paper are exemplified by a continuous process studied over 105.11,h using online HPLC. Copyright © 2010 John Wiley & Sons, Ltd. [source] Clustering multivariate time-series dataJOURNAL OF CHEMOMETRICS, Issue 8 2005Ashish Singhal Abstract A new methodology for clustering multivariate time-series data is proposed. The new methodology is based on calculating the degree of similarity between multivariate time-series datasets using two similarity factors. One similarity factor is based on principal component analysis and the angles between the principal component subspaces while the other is based on the Mahalanobis distance between the datasets. The standard K -means clustering algorithm is modified to cluster multivariate time-series datasets using similarity factors. Simulation data from two nonlinear dynamic systems: a batch fermentation and a continuous exothermic chemical reactor, are clustered to demonstrate the effectiveness of the proposed technique. Comparisons with existing clustering methods show several advantages of the proposed method. Copyright © 2006 John Wiley & Sons, Ltd. [source] Color-based tumor tissue segmentation for the automated estimation of oral cancer parametersMICROSCOPY RESEARCH AND TECHNIQUE, Issue 1 2010Yung-nien Sun Abstract This article presents an automatic color-based feature extraction system for parameter estimation of oral cancer from optical microscopic images. The system first reduces image-to-image variations by means of color normalization. We then construct a database which consists of typical cancer images. The color parameters extracted from this database are then used in automated online sampling from oral cancer images. Principal component analysis is subsequently used to divide the color features into four tissue types. Each pixel in the cancer image is then classified into the corresponding tissue types based on the Mahalanobis distance. The aforementioned procedures are all fully automated; in particular, the automated sampling step greatly reduces the need for intensive labor in manual sampling and training. Experiments reveal high levels of consistency among the results achieved using the manual, semiautomatic, and fully automatic methods. Parameter comparisons between the four cancer stages are conducted, and only the mean parameters between early and late cancer stages are statistically different. In summary, the proposed system provides a useful and convenient tool for automatic segmentation and evaluation for stained biopsy samples of oral cancer. This tool can also be modified and applied to other tissue images with similar staining conditions. Microsc. Res. Tech. 2009. © 2009 Wiley-Liss, Inc. [source] Spatial patterns and evolutionary processes in southern South America: A study of dental morphometric variationAMERICAN JOURNAL OF PHYSICAL ANTHROPOLOGY, Issue 1 2010Valeria Bernal Abstract The purpose of this article is to examine the patterns of evolutionary relationships between human populations from the later Late Holocene (1,500,100 years BP) of southern South America on the basis of dental morphometric data. We tested the hypotheses that the variation observed in this region would be explained by the existence of populations with different phylogenetic origin or differential action of gene flow and genetic drift. In this study, we analyzed permanent teeth from 17 samples of male and female adult individuals from throughout southern South America. We measured mesiodistal and buccolingual diameters at the base of the crown, along the cement,enamel junction. The results of multiple regression analysis and a mantel correlogram indicate the existence of spatial structure in dental shape variation, as the D2 Mahalanobis distance between samples increases with increasing geographical distance between them. In addition, the correlation test results show a trend toward reduction of the internal variation of samples with increasing latitude. The detected pattern of dental variation agrees with the one expected as an outcome of founder serial effects related to an expansion of range during the initial occupation of southern South America. Am J Phys Anthropol, 2010. © 2009 Wiley-Liss, Inc. [source] The Diagnostic Utility of an Electronic Nose: Rhinologic ApplicationsTHE LARYNGOSCOPE, Issue 9 2002Erica R. Thaler MD Abstract Objective/Hypothesis The thesis explores the applicability of electronic nose technology in medical decision-making. Specifically, the studies undertaken in the thesis were designed to test the ability of the electronic nose to assist in diagnostic questions encountered in the field of rhinology. Study Design Three separate studies were undertaken. All involved analysis of specimens by the electronic nose, obtained either in vitro or in vivo: known matched sets of cerebrospinal fluid and serum, bacterial samples from known plated specimens, and culture swabs taken from patients suspected of having rhinosinusitis who also had a matched standard bacterial culture taken from the same site. The goal of analysis was to determine whether the electronic nose was able to identify or categorize specimens or groups of specimens. Methods Each specimen was tested using the organic semiconductor-based Cyranose 320 electronic nose. Data from the 32-element sensor array were subjected to principal-component analysis to depict differences in odorant patterns. Distinction of specimens was identified by calculation of Mahalanobis distance. Results The electronic nose was able to distinguish serum from cerebrospinal fluid in pure isolates as well as in isolates collected on small cottonoid pledgets at amounts of 0.2 mL or greater. It was also able to distinguish between control swabs and bacterial samples as well as among bacterial samples collected in vitro. Preliminary work suggests that it may be able to distinguish between presence and absence of bacterial infection in specimens collected on nasal swabs. Conclusions The electronic nose is able to distinguish reliably between cerebrospinal fluid and serum sampled in small amounts, may be able to identify presence and type of bacterial pathogen in vitro, and is able to identify presence or absence of bacteria on nasal swabs. Because this information is available immediately, the electronic nose may be a powerful new technology for diagnostic use, not only for rhinologic purposes but in many other aspects of medicine as well. [source] Pattern of geographical variation in petal shape in wild populations of Primula sieboldii E. MorrenPLANT SPECIES BIOLOGY, Issue 2 2007YOSUKE YOSHIOKA Abstract The petal shape of Primula sieboldii E. Morren (Primulaceae) is diverse in wild populations. In this study, we investigated population differentiation in the petal shape of P. sieboldii using image analysis. Flowers were sampled from 160 genets from eight wild populations in the western to north-eastern parts of the Japanese archipelago. Principal component (PC) analysis of 40 coefficients of elliptic Fourier descriptors (EFDs) detected three major characteristics of petal shape variation: the ratio of length to width (PC1), the depth of the head notch (PC2) and the position of the center of gravity (PC3). To test the association between divergence in petal shape and geographical and genetic distances, we calculated two types of pairwise population distances for petal shape: Mahalanobis distances for the 40 EFD coefficients and for the first three PCs. The existence of an association between neutral genetic markers and petal shape was revealed by the Mahalanobis distances based on the 40 EFD coefficients, suggesting that evolutionary forces, such as founder effect and isolation by distance effect, are probably the main causes of differentiation in petal shape. In contrast, we found no association between Mahalanobis distances for the first three PCs and geographical and genetic distances. The discrepancy between the two petal shape distances indicated that the population differentiation promoted by the founder effects and isolation by distance effect appears mainly as subtle changes in petal shape rather than in major characteristics of petal shape variation. [source] | |||||||||||||