Abstract. Deformationanalysis is one of the main research fields in geodesy. Deformationanalysis process comprises measurement and analysis phases. Measurements can be collected using several techniques. The output of the eval- uation of the measurements is mainly point positions. In the deformationanalysis phase, the coordinate changes in the point positions are investigated. Several models or ap- proaches can be employed for the analysis. One approach is based on a Helmert or similarity coordinate transforma- tion where the displacements and the respective covariance matrix are transformed into a unique datum. Traditionally a LeastSquares (LS) technique is used for the transforma- tion procedure. Another approach that could be introduced as an alternative methodology is the TotalLeastSquares (TLS) that is considerably a new approach in geodetic applications. In this study, in order to determine point displacements, 3-D coordinate transformations based on the Helmert transforma- tion model were carried out individually by the LeastSquares (LS) and the TotalLeastSquares (TLS), respectively. The data used in this study was collected by GPS technique in a landslide area located nearby Istanbul. The results obtained from these two approaches have been compared.
Statistical analysis was performed using multivariate techniques, specifically principal component analysis (PCA), followed by partial leastsquares discriminant analysis (PLS – DA). SIMCA – P+ version 12 (Umetrics, Umea, Sweden) was used to identify principal components which accounted for the majority of the variation within the dataset. PCA is an unsupervised method and a data reduction technique that allows the major sources of variation in a multi-dimensional dataset to be analysed without introducing inherent bias. PLS – DA is a regression extension of the principal component analysis that uses class information to maximize the separation between various groups of observations. To estimate the number of PCA and PLS-DA components, cross-validation was used . Data for each cytokine was mean centred and variance scaled to unit variance. SIMCA-P+ uses NIPALS (non- linear iterative partial leastsquares) algorithm to calculate the first few principal components and inherently compensates for missing data values. This has been suggested as a more accurate, though computationally more complex method for deriving eigenvalues . Cross validation was carried out by dividing the data into seven parts and comparing models with each of the seven parts left in or out in turn. Predicted Residual Sum of Squares are calculated for the whole dataset and scaled to provide the Q2 statistic.
Being able to merge high quality and complete building models with parcel data is of a paramount importance for any application dealing with urban planning. However since parcel boundaries often stand for the legal reference frame, the whole correction will be exclusively done on building features. Then a major task is to identify spatial relationships and properties that buildings should keep through the conflation process. The purpose of this paper is to describe a method based on leastsquares approach to ensure that buildings fit consistently into parcels while abiding by a set of standard constraints that may concern most of urban applications. An important asset of our model is that it can be easily extended to comply with more specific constraints. In addition, results analysis also demonstrates that it provides significantly better output than a basic algorithm relying on an individual correction of features, especially regarding conservation of metrics and topological relationships between buildings. In the future, we would like to include more specific constraints to retrieve the actual positions of buildings relatively to parcel borders and we plan to assess the contribution of our algorithm on the quality of urban application outputs.
(Received 27 February, revised 2 August, accepted 3 August 2015) Abstract: The application of interval partial leastsquares (IPLS) and moving window partial leastsquares (MWPLS) for the enantiomeric analysis of tryp- tophan (Trp) was investigated. A UV–Vis spectroscopic method for deter- mining the enantiomeric composition of Trp was developed. The calibration model was built using partial leastsquares (PLS), IPLS and MWPLS, respect- ively. Leave-one-out cross validation and external test validation were used to assess the prediction performance of the established models. The validation result demonstrated the established full-spectrum PLS model is impractical for quantifying the relationship between the spectral data and enantiomeric com- position of L-Trp. On the contrary, the developed IPLS and MWPLS models are both practicable for modeling this relationship. For the IPLS model, the root mean square relative error (RMSRE) values of the external test validation and leave-one-out cross validation were 4.03 and 6.50, respectively. For the MWPLS model, the RMSRE values of the external test validation and leave- -one-out cross validation were 2.93 and 4.73, respectively. Obviously, the pre- diction accuracy of the MWPLS model was higher than that of the IPLS model. It was demonstrated that UV–Vis spectroscopy combined with MWPLS is a commendable method for determining the enantiomeric composition of Trp. MWPLS was superior to IPLS for selecting the spectral region in the UV–Vis spectroscopy analysis.
In addition to uncovering unobserved heterogeneity, the previous literature has also suggested different approaches to test for observed heterogeneity across groups (Hair et al., 2018). For two-group scenarios, a repeated application of unpaired sample t-tests has been proposed to identify differences between groups (Chin, 2000; Keil et al., 2000). In doing so, the test statistic is assumed to follow a t-distribution where the standard errors of the parameter estimates are obtained by the bootstrap or jackknife procedure (Keil et al., 2000). To overcome distributional assumptions, the previous literature has also provided a non-parametric test for MGA (Henseler, 2012). Although this test is similar to the former, it evaluates the bootstrap distribution of each group to analyze whether the estimates statistically differ between groups. Similarly, Chin (2003) and Chin and Dibbern (2010) propose a permutation test to evaluate group differences. Group-specific differences are compared with the corresponding reference distribution obtained by the permutation procedure. Apart from the analysis of two groups, approaches for multiple groups have been suggested, for example, the omnibus test of group differences, which is a combinatorial test comprising bootstrapping and permutation to mimic an overall F-test (Sarstedt, Henseler and Ringle, 2011).
Drug-induced torsades de pointes (TdP), a life-threatening arrhythmia associated with prolongation of the QT interval, has been a significant reason for withdrawal of several medicines from the market. Prolongation of the QT interval is considered as the best biomarker for predicting the torsadogenic risk of a new chemical entity. Because of the difficulty assessing the risk for TdP during drug development, we evaluated the metabolic phenotype for predicting QT prolongation induced by sparfloxacin, and elucidated the metabolic pathway related to the QT prolongation. We performed electrocardiography analysis and liquid chromatography–mass spectroscopy-based metabolic profiling of plasma samples obtained from 15 guinea pigs after administration of sparfloxacin at doses of 33.3, 100, and 300 mg/kg. Principal component analysis and partial leastsquares modelling were conducted to select the metabolites that substantially contributed to the prediction of QT prolongation. QTc increased significantly with increasing dose (r = 0.93). From the PLS analysis, the key metabolites that showed the highest variable importance in the projection values (.1.5) were selected, identified, and used to determine the metabolic network. In particular, cytidine-59-diphosphate (CDP), deoxycorticosterone, L-aspartic acid and stearic acid were found to be final metabolomic phenotypes for the prediction of QT prolongation. Metabolomic phenotypes for predicting drug-induced QT prolongation of sparfloxacin were developed and can be applied to cardiac toxicity screening of other drugs. In addition, this integrative pharmacometabolomic approach would serve as a good tool for predicting pharmacodynamic or toxicological effects caused by changes in dose.
variables than observations) Partial LeastSquares modeling is particularly suited . A blockwise Recursive Partial LeastSquares  allows online identification of Partial LeastSquares regression. N-way PLS (NPLS)  provides a generalization of ordinary PLS to the case of tensor variables. Similarly to the generic algorithm, NPLS combines regression analysiswith the projection of data into the low dimensional space of latent variables using tensor factorization. The blockwise Recursive PLS adapted to multi-way structured inputs (tensor-input scalar-output) was invented by the authors recently . This article presents blockwise Recursive NPLS (RNPLS) extended to the most general case of tensor-input/tensor-output, its numerical study, testing and comparison. The algorithm is addressed to a data set of huge dimensions and conducts a sequential blockwise tensor-data processing. Unlike the multi-pass blockwise Iterative NPLS , which repeatedly runs through the entire data set, the new RNPLS algorithm performs a consecutive calculation and can be applied online. Moreover, in the case of non-stationary tensor-valued processes, RNPLS allows adaptive learning by introducing the forgetting factor.
The partial leastsquares discriminant analysis (PLS-DA), a special case of regression by partial leastsquares (PLSR) for categorical variables (Pérez-Enciso and Tenenhaus 2003) was used to predict the areas damaged by T. peregrinus. Five multispectral bands were subjected to PLS-DA regression, where the collinearity effect of the model data can be reduced more effectively, and the correlation between the variables of predictor spectral band and variable response maximized (Mevik and Cederkvist 2004). The partial leastsquares regression is described by the equation, X= TP’ + E, Y= UQ’ + F, where X is the predictor matrix; Y is the response matrix; T-scores= X; U= Y-scores; P= X-loadings; Q= Y-loadings; E= X-residuals; and F= Y-residuals (Geladi and Kowalski 1986; Ye et al. 2008).
were analyzed by gas chromatography with mass spectrometry (GC-MS) and by FTIR. Principal component analysis was applied to the infrared spectra to detected different clusters, corresponding to original samples and different types of counterfeits. A partial leastsquares - discriminant analysis method was proposed to discriminate original samples from those counterfeits that were indistinguishable from the originals in the infrared analysis. A training subset comprised of one- third of the available spectra was used to establish a suitable model that correctly discriminated all samples in the test subset, resulting in 0% of false positive or negative results and 100% of efficiency rate, sensitivity and specificity. In addition to the low cost of the infrared technique, the proposed method is fast, reliable and suitable to replace GC-MS methods used in Durateston ®
The aim of this article was to chemically characterize cocaine samples seized between 2008 and 2010 by the Federal Police of the Minas Gerais State (Brazil), which is the government organization responsible for international and interstate drug traffic control. Minas Gerais is the second most populous state in Brazil, with 19.6 million inhabitants, located in the Southeast region. The qualitative analysis of adulterants and the quantitative determination of cocaine were both performed by gas chromatography coupled with mass spectrometry (GC-MS). ATR-FTIR spectra of powder samples were obtained and used in a PCA model, searching for chemical similarities and pattern recognition. Finally, these spectra were used in two supervised classification models (partial least-squares discriminant analysis (PLS-DA)), which were able to discriminate cocaine samples as a function of their content and chemical form.
A common issue in psychological research is the problem of multicollinearity (i.e., when the predictors are highly correlated). Multicollinearity can result in redundancy and can lead to high variability in the coefficients (see Mason & Perreault Jr, 1991). One of the proposed methods for dealing with this issue is through a reduction in the dimensionality. In this case, the use of principal component regression (PCR) might be considered an appropriate choice. PCR is an extension of principal component analysis (PCA; see Dunn Iii, Scott, & Glen, 1989), in which correlated variables are grouped into sets of uncorrelated variables known as the principal components. In PCR, the same techniques that are applied in PCA are used to project predictors into its principal components, and then use this reduced dimensionality (the components) in the regression of the response variable. Through this orthogonal projection, PCR is able to deal with the problem of multicollinearity via dimension reduction and is able to generate predictive models using the principal components through regression. See Geladi and Esbensen (1991) for a more detailed description of the procedure, and Sutter, Kalivas, and Lang (1992) for information regarding the selection of principal components.
The determination of cocaine in drug samples is an important task for law enforcement agencies such as the Brazilian Federal Police (BFP). In this sense, this paper proposes a method based on infrared spectra obtained by attenuated total reflectance (ATR) and partial leastsquares regression (PLSR) to quantify cocaine hydrochloride in drug samples. The method was developed and validated with 275 actual samples of drugs seized by the BFP. The determination was performed between 35 to 99% (m/m) of cocaine in the drug samples. Results indicate that the method is able to directly analyze drug samples containing cocaine in its hydrochloride form without any sample preparation with average prediction errors of 3.00% (m/m), 1.50% (m/m) precision and 13% (m/m) of minimum detectable concentration.
Abstract: The purpose of this paper was to analyze the modeling of an artificial satellite orbit, using signals of the GPS constellation and leastsquares algorithms as the method of estimation, with the aim of analyzing the performance of the orbit estimation process. One pursues to verify how differences of modeling can affect the final accuracy of orbit determination. To accomplish that, the following effects were considered: high degree and order for the geopotential coefficients; direct solar radiation pressure; and Sun-Moon attraction. The measurements were used to feed the batch leastsquares orbit determination process, in order to yield conclusive results about the orbit modeling issue. An application has been done, using GPS data of the TOPEX/Poseidon satellite, whose accurate ephemeris are available on the Internet. It is shown that from a poor but acceptable modeling up to all effects included, the accuracy can vary from 28 to 9 m in the long-period analysis.
We would like to point out that Lee2012 was not originally developed to extract context- specific models. However, RegrEx has a form similar to that of Lee2012, which aims at improv- ing flux prediction through minimizing the absolute distance between data (e.g., RNAseq expression profiles) and flux values. For this reason, we also included Lee2012 in the compara- tive analysis. Nevertheless, RegrEx differs from Lee2012 in the inclusion of regularization and also in the treatment of reversible reactions: Lee2012 applies an iterative approach, where the optimization problem starts first with the subset of irreversible reactions, and reversible reac- tions are then added sequentially by solving additional optimization problems. This last step is time consuming because it involves two optimization problems per reversible reaction. In con- trast, RegrEx selects direction of reversible reactions at once through the use of a binary vari- able, as explained in the Methods section, thus reducing the computational time. Moreover, RegrEx is unbiased with respect to the order in which the reversible reactions are added, which is a shortcoming not resolved in Lee2012.
One sub-model of ANN is a group method data han- dling (GMDH) algorithm which was first developed by Ivakhnenko (1971). This is a multivariate analysis method for modeling and identification of complex systems. The main idea of GMDH is to build an analytical function in a feed-forward network based on a quadratic node transfer function whose coefficients are obtained by using the re- gression technique. This model has been successfully used to deal with uncertainty and linear or nonlinearity systems in a wide range of disciplines such as engineering, science, economy, medical diagnostics, signal processing and con- trol systems (Tamura and Kondo, 1980; Ivakhnenko and Ivakhnenko, 1995; Voss and Feng, 2002). In water resource, the GMDH method has received very attention and only a few applications to modeling of environmental and ecolog- ical systems (Chang and Hwang, 1999; Onwubolu et al., 2007; Wang et al., 2005) have been carried out.
The assessment of nonlinear relationships in the context of Partial LeastSquares Path Modelling (PLS-PM) has received a growing interest in recent years. One important contribution to this subject has been the work of Henseler, Fassot, Dijkstra and Wilson (2012) on the analysis of four different approaches to quadratic effects. The Smooth Partial LeastSquares (PLSs) estimation technique studied in this work removes any assumptions on the structure of the nonlinear relationships between latent variables, by applying smoothing spline techniques to the structural model. Performance results of the PLSs show that it is a powerful tool in the context of predictive research, for instance to support the definition of targeted policies. Building from the hybrid approach to the PLS algorithm introduced by Wold (1982), we compare the performance of alternative spline designs, including natural cubic splines, P-Splines and Thin Plate Regression Splines (TPRS). For this purpose, Monte-Carlo simulations are carried with a conceptual model drawn from a comprehensive set of nonlinear relationships, in different sample sizes. All model configurations are compared using Root Mean Squared Error (RMSE) and absolute bias results. The benchmarking exercise shows that, in most contexts, P-Splines perform slightly better than TPRS and natural cubic splines.
Lg (Figures 2 and 8) and lower levels of m-Ins in all tumor groups with the exception of Lg group (Figure 9) compared to control samples, a characteristic that was more evident in the aggressive ones, Hg and metastasis (Figures 2, 6, 7, and 8). In addition to changes related to tumor metabolism, such as anti-apoptotic activity (12), protection against nutrient starvation and hyperosmolarity, regulation of mitochondrial permeability transition (13), and participation in tricarboxylic acid cycle, Gly levels decrease less than those of other metabolites in the areas of tissue necrosis in aggressive tumors (14). On the other hand, m-Ins is present in glial cell cultures and its levels increase according to the number of normal glial cells (15). Therefore, m-Ins reduction or absence in Hg, NN and metastasis groups indirectly indicates the absence or reduction of normal glial cells. In this study, the increase of Gly and the decrease of m-Ins were a general tendency in aggressive tumors, as recently described in in vivo and in vitro studies (16,17). However, at low magnetic fields with TEs of 135-270 ms, in vivo studies have shown a marked signal overlapping of m-Ins with Gly methylene at δ 3.56 ppm and these two metabolites are usually evaluated together, limiting their diagnostic value. Guided by these findings, the observation of the signal decay from short to long TE at lower fields, where m-Ins decays faster, and the use of TEs as low as 30 ms at 7 T in vivo, which are able to differentiate these peaks (18), could be useful for the clinical investigation of aggressive tumors.
MULTIVARIATE CURVE RESOLUTION WITH ALTERNATING LEASTSQUARES: DESCRIPTION, OPERATION AND APLICATIONS. Multivariate Curve Resolution with Alternating LeastSquares (MCR-ALS) is a resolution method that has been efficiently applied in many different fields, such as process analysis, environmental data and, more recently, hyperspectral image analysis. When applied to second order data (or to three-way data) arrays, recovery of the underlying basis vectors in both measurement orders (i.e. signal and concentration orders) from the data matrix can be achieved without ambiguities if the trilinear model constraint is considered during the ALS optimization. This work summarizes different protocols of MCR-ALS application, presenting a case study: near-infrared image spectroscopy.
to 7 grams of coffee powder (w for weight) for each 100 ml of water (v for volume), with the same for 0.10 - the experiments were evaluated together, considering the compositions described in (Table 2). The blends were identified in the joint analysis using coded samples (k = 1, ..., 36), which referred to the blends analysed in experiments 1, 2, 3 and 4. The blends included a commercial product, coffee from the species Canephora, henceforth referred to as Conilon, as shown by the description in Table 2 for process type.
This paper tries to define the effect of air cargo traffic on the local employment in terms of industries and occupations by using econometric models. To overcome the problem of causality between air cargo traffic and local employment levels, this study employed two- stage least-squares (2SLS) estimation. The most significant advantage of this study is that it includes so many occupations and industries through which a wide range of analyses and interpretations can be made. Comparable studies focus on specific sectors (such as manufacturing, wholesale trade, retail and finance, insurance and real estate) or focus on macroeconomic parameters (such as GDP, per capita GDP, and economic growth). In contrast, this paper is able to identify and analyze 16 different groups of occupations and industries, which provides us a large room for conclusions. The results of 2SLS estimations show that air cargo traffic fosters employment in finance, insurance, real estate and business services and increases the total number of (i) administrative and managerial workers and (ii) clerical and related workers. Meanwhile it tends to reduce employment in agriculture, hunting, forestry and fishing activities and the total number of agricultural, animal husbandry, forestry workers, fishermen and hunters. The following section briefly summarizes the current condition of Turkish air cargo industry. Section 3 describes the methodology of the analysis and the data used. Section 4 discusses the results of the analysis. The conclusion includes the summary of the results, the limitations of the study, and the policy implications.