Search results for "partial least square"
showing 10 items of 152 documents
Quantitative Transfer Function Approaches in Palaeoclimatic Reconstruction Using Quaternary Ostracods
2012
Abstract Quantifying (palaeo-)environmental changes is a key challenge for aquatic biological proxies, but the number of published transfer functions is increasing rapidly for the main palaeoecologically relevant groups such as diatoms and chironomids, and several transfer functions have also been developed during the past decades based on ostracod findings. The main environmental variables influencing the species assemblage composition in ostracod training sets are specific ion concentrations or ratios, salinity, water temperature and/or water depth. The available transfer functions and training sets are globally scattered, but often regionally restricted in their application. The most com…
Multivariate Methods Based Soft Measurement for Wine Quality Evaluation
2014
Published version of an article in the journal: Abstract and Applied Analysis. Also available from the publisher at: http://dx.doi.org/10.1155/2014/740754 Open Access Soft measurement is a new, developing, and promising industry technology and has been widely used in the industry nowadays. This technology plays a significant role especially in the case where some key variables are difficult to be measured by traditional measurement methods. In this paper, the quality of the wine is evaluated given the wine physicochemical indexes according to multivariate methods based soft measurement. The multivariate methods used in this paper include ordinary least squares regression (OLSR), principal c…
Engagement with Travel Web Sites and the Influence of Online Comparative Behaviour
2015
We propose a Web site engagement measurement, and study the influence of potential antecedents and consequences. Utilising partial least squares path modeling, we contrast a model with data obtained from respondents choosing a holiday in the Seychelles, on a Web site capable of tracing online within-page and within-site behaviour.
Categorization of chlordecone potential transformation products to predict their environmental fate
2016
EABIOmE; Chlordecone (C10Cl10O; CAS number 143-50-0) has been used extensively as an organochlorine insecticide but is nowadays banned and listed on annex A in The Stockholm Convention on Persistent Organic Pollutants (POPs). Although experimental evidences of biodegradation of this compound are scarce, several dechlorination products have been proposed by Dolfing et al. (2012) using Gibbs free energy calculations to explore different potential transformation routes. We here present the results of an in silico classification (TyPol similar to Typology of Pollutants) of chlordecone transformation products (TPs) based on statistical analyses combining several environmental endpoints and struc…
Analyse des effets direct et indirect des pratiques agricoles sur les adventices et la production de blé tendre d’hiver
2016
Analysis of direct and indirect effects of farming practices on weeds and winter wheat yield. Farmers implement farming practices to maximize production by limiting biotic (e.g. weeds) and abiotic (e.g. nutrient) growth factors. Our study aimed to quantify direct and indirect (through a change of weed pressure) effects of farming practices on yield. We analysed the relationships between farming practices, weeds and yield of 152 wheat fields located in the study site of Fénay (UMR Agroécologie, Dijon) using partial least square path modelling (PLS-PM). Our results showed that farming practices had a positive direct effect on crop productivity (β = 0.32). Farming practices decreased weed pres…
Semisupervised kernel orthonormalized partial least squares
2012
This paper presents a semisupervised kernel orthonormalized partial least squares (SS-KOPLS) algorithm for non-linear feature extraction. The proposed method finds projections that minimize the least squares regression error in Hilbert spaces and incorporates the wealth of unlabeled information to deal with small size labeled datasets. The method relies on combining a standard RBF kernel using labeled information, and a generative kernel learned by clustering all available data. The positive definiteness of the kernels is proven, and the structure and information content of the derived kernels is studied. The effectiveness of the proposed method is successfully illustrated in standard UCI d…
Use of pH gradients in continuous-flow systems and multivariate regression techniques applied to the determination of methionine and cysteine in phar…
1997
Abstract The simultaneous spectrophotometric determination of methionine and cysteine in presence of cystine and other compounds in pharmaceuticals, using a multivariate calibration method, was studied. The method is based on the reaction between the analytes and the o- phthalaldehyde -N- acetyl - l - cysteine (OPA-NAC) reagent performed in a continuous-flow system (FI). The FI system allows the generation of a local pH gradient in order to produce spectral and/or kinetic changes in the UV-Vis spectra of the amino acid-OPA-NAC derivatives. This information is used to improve the prediction ability of the Partial Least-Squares (PLS) models. The performance of two FI assemblies, the selection…
Determination of fatty acids and lipid classes in salmon oil by near infrared spectroscopy
2017
International audience; Near-infrared (NIR) spectroscopy was evaluated as a rapid method for the determination of oleic, palmitic, linoleic and linolenic acids as well as omega-3, omega-6, and to predict polyunsaturated, monounsaturated and saturated fatty acids, together with triacylglycerides, diglycerides, free fatty acids and ergosterol in salmon oil. To do it, Partial Least Squares (PLS) regression models were applied to correlate NIR spectra with aforementioned fatty acids and lipid classes. Results obtained were validated in front of reference procedures based on high performance thin layer and gas chromatography. PLS-NIR has a good predictive capability with relative root mean squar…
Analysis of Caffeine, Sweeteners, and Other Additives in Beverages by Vibrational Spectroscopy
2001
This chapter presents a review of the scientific literature on the use of vibrational spectroscopy, near-infrared (NIR), mid-infrared (mid-IR), and Raman, for the analysis of caffeine, sweeteners, and other additives in beverages and related products. Direct analysis procedures of coffee and tea, for both classification according to precedence or variety and quantitative determination of caffeine, are available. For beverage analysis, caffeine has been determined by direct attenuated total reflection (ATR) measurement or by transmission spectroscopy in the mid-IR region after extraction with chloroform. Different strategies have been employed for the analysis of sweeteners in beverages and …
Fusion of the 1H NMR data of serum, urine and exhaled breath condensate in order to discriminate chronic obstructive pulmonary disease and obstructiv…
2015
Chronic obstructive pulmonary disease, COPD, affects the condition of the entire human organism and causes multiple comorbidities. Pathological lung changes lead to quantitative changes in the composition of the metabolites in different body fluids. The obstructive sleep apnea syndrome, OSAS, occurs in conjunction with chronic obstructive pulmonary disease in about 10–20 % of individuals who have COPD. Both conditions share the same comorbidities and this makes differentiating them difficult. The aim of this study was to investigate whether it is possible to diagnose a patient with either COPD or the OSA syndrome using a set of selected metabolites and to determine whether the metabolites t…