Factorial Discriminant Analysis Research Articles

Using an Online Image Analysis Technique to Characterize Sucrose Crystal Morphology during a Crystallization Run

The morphological forms and habits of crystals and agglomeration are important properties on crystallization processes. Online techniques for realtime measurement of these properties are mandatory for a better comprehension of crystal growth phenomenon. The present paper presents and describes a new online method to determine the complexity level of a crystal or a population of crystals during a crystallization process. An image analysis technique is combined with discriminant factorial analysis leading to results that allow the computation of the complexity of crystals through the parameter agglomeration degree of crystals. With this methodology, it has been possible to distinguish online and automatically among three different classes of crystals according to their complexity. It further describes the application of such methodology on the study of CaCl2, d-fructose, and d-glucose influence on the crystallization of sucrose, namely, on crystal size, morphology, and complexity. The effect of supersaturat...

Stable production rhythms across languages for bilingual speakers.

There has been a great deal of work on classifying spoken languages according to their perceived or acoustically‐measured rhythmic structures. The current study examined the speech of 12 Spanish‐English bilinguals producing sentences in both languages using rhythmic measures based on the amplitude envelopes extracted from different frequency regions—the envelope modulation spectrum (EMS). Using discriminant factor analysis, EMS variables demonstrated a moderate ability to classify the language being spoken suggesting that rhythmic differences between languages survive even when speaker is controlled. More interesting is the fact that EMS variables could reliably classify which speaker produced each sentence even across languages. This result suggests that there are stable rhythmic structures in an individual talker’s speech that are apparent above and beyond the structural constraints of the language spoken. The EMS appears capable of describing systematic characteristics of both the talker and the language spoken. [Work supported by NIH‐NIDCD].

High performance size-exclusion chromatography analysis of polar compounds applied to refined, mild deodorized, extra virgin olive oils and their blends: An approach to their differentiation

An investigation was carried out to evaluate the use of High Performance Size-Exclusion Chromatography (HPSEC) of polar compounds of refined, mild deodorized, extra virgin olive oils as well as of their blends, in attempting to reveal significant differences in the amounts of the substance classes constituting polar compounds among these oils. Two sets of blends were prepared by mixing an extra virgin olive oil with both refined and mild deodorized olive oils in increasing amounts. The obtained data highlighted that the triacylglycerol oligopolymers were absent or present in traces in the extra virgin olive oil, while their mean amount was equal to 0.04g/100g and 0.72g/100g in mild deodorized and refined olive oils, respectively. Oxidized triacylglycerols and diacylglycerols were more abundant in mild deodorized oil and refined oil than in extra virgin olive oil. The Factorial Discriminant Analysis of the data showed that the HPSEC analysis could reveal the presence of refined/mild deodorized oils in extra virgin olive oils. In particular, the classification functions obtained allowed designation of mixtures containing at least 30g/100g of mild deodorized oil and all those containing refined olive oil as deodorized oil, therefore as oils subjected to at least a mild refining treatment.

Monitoring groundwater in the discharge area of a complex karst aquifer to assess the role of the saturated and unsaturated zones

The hydrochemical response at springs in the drainage area of the Sierra del Rey—Los Tajos carbonate aquifer (province of Malaga, southern Spain) was monitored in order to determine the hydrogeological functioning of this aquifer. Analysis of the most important chemical parameters, using methodologies such as the temporal evolution of chemical components, principal component analysis and discriminant factorial analysis revealed that the high level of hydrochemical heterogeneity to be found in this discharge zone, in addition to particular spatial and temporal factors, is responsible for the mineralisation of the spring water. Sampling in karst systems where discharge occurs by several springs should take into account the hydrochemical variability of them; otherwise conclusions about the hydrological functioning of aquifers deduced from mixture of spring waters can be inaccurate.

The composition and distribution of the particulate matter in the Strait of Magellan (Chile) during the 1991 and 1995 Italian campaigns

During 1991 and 1995, the Italian National Program for Antarctic Research carried out two oceanographic campaigns in the framework of the International (Strait of) Magellan Project. In this paper, we describe the distribution, biochemical composition, and mineralogical characteristics of particulate matter and the characteristics of the water masses defining microbasins in the Strait of Magellan. The data analyses highlighted differences in quality and quantity of the suspended matter and its organic component in the basins that make up the Strait and the Pacific Ocean. The westernmost basin is subject to an eastward flow from the Pacific Ocean, and continental runoff in the surface layers, which are consequently rich in organic matter with a high C:N ratio. The central basin, Isla Carlos III–Segunda Angostura, is characterized by the mixing of Sub-Antarctic Pacific waters, continental runoff, and glacio-fluvial waters: The basin has the lowest particulate matter concentration, but at Paso Ancho showed high concentrations of organic matter with a lower C:N ratio. The easternmost basin, Segunda Angostura-Atlantic entrance, is characterized by the mixing of the water column due to strong Atlantic tides and showed high concentration of particulate matter with a high detritic component. Generally, the organic matter concentrations showed significant differences during the cruises, being higher in 1991. Using the multivariate discriminant factor analysis to determine whether statistically significant differences existed between defined sampling areas, we determined that temperature, particulate organic carbon, and total particulate matter were the variables most important for the difference between areas.

Translation and Validation of EORTC QLQ-C30 into Indonesian Version for Cancer Patients in Indonesia

Quality of life studies in Indonesia are still uncommon. This research was aimed to validate the European Organization for Research and Treatment of Cancer Quality of Life Questionnaire-C30 in Indonesian version. The standard procedure of forward-backward translation was adhered to in the translation procedures. The validity procedure included reliability, convergent and discriminant validity, known-groups validity, factor analysis and external convergent validity. Data were collected from cancer patients in the Oncology Department of Sardjito Hospital, Yogyakarta, Indonesia, who were treated with cisplatin at the dosage ≥50 mg/m(2) as monotherapy or in combinations. The Short Form-36 was used to assess the external convergent validity of our translated questionnaire. One hundred and twenty-eight patients were recruited from March 2009 to November 2009. The internal consistency with values of >0.70 was observed in the Indonesian version of the European Organization for Research and Treatment of Cancer Quality of Life Questionnaire-C30 scales. All items in the questionnaire met the criteria of convergent and discriminant validity, except for items 5. Both of the European Organization for Research and Treatment of Cancer Quality of Life Questionnaire-C30 and the Short Form-36 showed that different diagnoses were associated with a similar impact on quality of life. Factor analysis showed that only the role function and social function loaded onto the second factor together. Correlations between the Indonesian versions of both questionnaires were moderate: between 0.18 and 0.48 for the physical, emotional, social, fatigue and pain domains. The Indonesian version of the European Organization for Research and Treatment of Cancer Quality of Life Questionnaire-C30 can be used as a questionnaire to assess quality of life in Indonesian cancer patients with high-emetogenic treatments.

Mid infrared and fluorescence spectroscopies coupled with factorial discriminant analysis technique to identify sheep milk from different feeding systems

Mid infrared spectroscopy (MIR) combined with multivariate data analysis was used to discriminate between ewes milk samples according to their feeding systems (controls, ewes fed scotch bean and ewes fed soybean). The MIR spectra were scanned throughout the first 11weeks of the lactation stage. When factorial discriminant analysis (FDA) with leave one-out cross-validation was applied, separately, to the three spectral regions in the MIR (i.e. 3000–2800, 1700–1500 and 1500–900cm−1), the classification rate was not satisfactory. Therefore, the first principal component (PCs) scores (corresponding to 3, 10 and 10 for, respectively, the 3000–2800, 1700–1500 and 1500–900cm−1) of the principal component analysis (PCA) extracted from each of the data sets were pooled (concatenated) into a single matrix and analysed by FDA. Correct classification amounting to 71.7% was obtained. Finally, the same procedure was applied to the MIR and fluorescence data sets and 98% of milk samples were found to be correctly classified. Milk samples belonging to control and soybean groups were 100% correctly classified. Regarding milk samples originating from the scotch bean group, only 2 out of 33 samples were misclassified. It was concluded that concatenation of the data sets collected from the two spectroscopic techniques is an efficient tool for authenticating milk samples according to their feeding systems, regardless of the lactation stage.

Classifying tree and non-tree farmers for improving of agroforestry systems using a discriminant analytical approach

Non-industrial private forestry owners (NIPFo) represent the most forest and wooded lands, as well as timber supply in several forest European regions. In Galicia, a Northwest Spanish community, there are registered more than 670000 NIPFo on a total area around 1200000 ha. Farmers to main title, although they are experimented a notable decline during the last years, constitute the main profile of Galician NIPFo. This article presents a statistical model and empirical evidences of the factors that determine forest behaviour and management by farmers. From 245 variables collected by a personal survey questionnaire to more than 4300 Galician farmers, a factorial discriminant analysis was used in the empirical study for classifying significant farmer groups by forestland owned. The results suggest that variables associated with geographical location of the farm, the pattern of land acquisition, the economic dependence of farm activity and the agroforestry size are key determinants of the forest behaviour, management and relevance for the farmers. Moreover, the study provides useful information and recommendations to new actuation patterns and allocation aids by the public Administration in the future development of the agroforestry activities by individual tree farmers.

Optical fiber-based synchronous fluorescence spectroscopy for bacterial discrimination directly from colonies on agar plates.

The development of experimental conditions for rapid bacterial discrimination using fluorescence spectroscopy fingerprinting is presented. Colonies of Pseudomonas and related reference strains on agar plates were analyzed directly using an optic fiber coupled to a laboratory spectrofluorimeter. Spectra were collected using either classic fluorescence spectroscopy after excitation at 250 nm and 340 nm for aromatic amino acids and nucleic acids (AAA + NA) and nicotinamide adenine dinucleotide (NADH) respectively, or synchronous scanning in the excitation wavelength range 250-500 nm. Factorial discriminant analysis (FDA) showed 100% correct classification at the genus and species level from NADH spectra and 100% correct classification at the genus and species level for λ = 30, 70, 90 and 110 nm (cross-validation). Analysis of variance (ANOVA) confirmed that culture time (48 or 72 h) colony and optic fiber positioning had non-significant impacts on differences between species. The use of optical fiber-fluorescence spectroscopy for bacterial discrimination directly on colonies is fast, simple and reliable. The results are independent of culture growth phase and neither need reagent addition nor prior manual preparation of cells, thus eliminating all risk of human error or contamination during sample work-up.

Comparative evaluation of spectroscopic models using different multivariate statistical tools in a multicancer scenario

Cancer is now recognized as one of the major causes of morbidity and mortality. Histopathological diagnosis, the gold standard, is shown to be subjective, time consuming, prone to interobserver disagreement, and often fails to predict prognosis. Optical spectroscopic methods are being contemplated as adjuncts or alternatives to conventional cancer diagnostics. The most important aspect of these approaches is their objectivity, and multivariate statistical tools play a major role in realizing it. However, rigorous evaluation of the robustness of spectral models is a prerequisite. The utility of Raman spectroscopy in the diagnosis of cancers has been well established. Until now, the specificity and applicability of spectral models have been evaluated for specific cancer types. In this study, we have evaluated the utility of spectroscopic models representing normal and malignant tissues of the breast, cervix, colon, larynx, and oral cavity in a broader perspective, using different multivariate tests. The limit test, which was used in our earlier study, gave high sensitivity but suffered from poor specificity. The performance of other methods such as factorial discriminant analysis and partial least square discriminant analysis are at par with more complex nonlinear methods such as decision trees, but they provide very little information about the classification model. This comparative study thus demonstrates not just the efficacy of Raman spectroscopic models but also the applicability and limitations of different multivariate tools for discrimination under complex conditions such as the multicancer scenario.

Diversité morphologique et teneur en hyoscyamine/scopolamine de douze provenances algériennes de Datura stramonium L.

Morphological diversity and hyoscyamine/scopolamine contents in twelve Algerian samples of Datura stramonium L. of different origin. Morphological diversity was estimated on 15 phenotypic characters of Datura stramonium from twelve samples of different origin ; the Algerian distribution of that species extends from Nedroma (extreme western Algeria : semi-arid bioclimatic stage) to El Kala (at the Algerian-Tunisian border : humid bioclimatic stage). Seeds from these twelve samples were collected and then grown in similar pedoclimatic conditions. Measurements were carried out 60 days after sowing. Results show that these twelve samples were significantly different for the measured traits (leaf area, length of the flowers, number of ramifications, number and biometrics of the capsules and height of the plants). Principal component analysis (PCA) and Factorial discriminant analysis (FDA) were used to discriminate the origins of the samples from their studied characters. The canonical averages of the twelve samples were significantly different, especially in the biometric traits including mature plants, capsules and seeds. The alkaloid content (hyoscyamine and scopolamine) of the twelve samples seems to be influenced by the geographical and bioclimatic distribution. In addition, the most alkaloid productive samples were generally those that invest more in biomass production (leaf area, height and collar diameter of plants).

Body Shape and Life Style of the Extinct Balearic Dormouse Hypnomys (Rodentia, Gliridae): New Evidence from the Study of Associated Skeletons

Hypnomys is a genus of Gliridae (Rodentia) that occurred in the Balearic Islands until Late Holocene. Recent finding of a complete skeleton of the chronospecies H. morpheus (Late Pleistocene-Early Holocene) and two articulated skeletons of H. cf. onicensis (Late Pliocene) allowed the inference of body size and the calculation of several postcranial indexes. We also performed a Factorial Discriminant Analysis (FDA) in order to evaluate locomotory behaviour and body shape of the taxa. Using allometric models based on skull and tooth measurements, we calculated a body weight between 173 and 284 g for H. morpheus, and direct measurements of articulated skeletons yielded a Head and Body Length (HBL) of 179 mm and a Total Body Length of 295 mm for this species. In addition to the generally higher robustness of postcranial bones already recorded by previous authors, H. morpheus, similar to Canariomys tamarani, another extinct island species, displayed elongated zygopodium bones of the limbs and a wider distal humerus and femur than in an extant related taxon, Eliomys quercinus. Indexes indicated that Hypnomys was more terrestrial and had greater fossorial abilities than E. quercinus. This was also corroborated by a Discriminant Analysis, although no clear additional inference of locomotory abilities could be calculated.

Insights into chiral recognition mechanisms in supercritical fluid chromatography. II. Factors contributing to enantiomer separation on tris-(3,5-dimethylphenylcarbamate) of amylose and cellulose stationary phases

In this second part of our work on enantioselective supercritical fluid chromatography (SFC), we investigate the factors participating in the chiral recognition process on tris-(3,5-dimethylphenylcarbamate) of amylose and cellulose chiral stationary phases (CSPs). 135 racemates with diverse structures were analysed under identical SFC conditions on both stationary phases. The possibility of identifying the differential interactions of an enantiomer pair within the chromatographic system is assessed using a modified version of the solvation parameter model and factorial discriminant analysis. It is illustrated that one relationship of intermolecular interactions is insufficient to express the enantioseparation of different groups of racemates. An innovative approach is used in unravelling the interactions taking part in the enantiorecognition process. Different intermolecular interactions participating in the enantiomeric separation are demonstrated between the two stationary phases.

Attempted Confirmation of the Provenance of Corsican PDO Honey Using FT-IR Spectroscopy and Multivariate Data Analysis

This study investigated the potential of Fourier-transform infrared (FT-IR) spectroscopy and chemometric techniques to produce a mathematical model that would confirm or refute the provenance of honeys claiming to be Corsican. Authentic honey samples from two harvest seasons (2004/2005 and 2005/2006) were collected from Ireland (n=2), Italy (n=30), Austria (n=40), Germany (n=36), mainland France (n=46), and Corsica (n=219). Prior to scanning, samples were diluted with distilled water to a standard solids content (70 degrees Brix). Spectra (2500-12500 nm) were recorded at room temperature using a FT-IR spectrometer equipped with a germanium attenuated total reflectance (ATR) accessory. Standard normal variate (SNV) and first- and second-derivative data pretreatments were applied to the recorded spectra, which were processed using factorial discriminant analysis (FDA) and partial least-squares (PLS) regression analysis. Overall correct classification figures of 82% (FDA) and 87% (PLS) were obtained for a separate validation set comprising samples from both harvests.

Protein discrimination by fluorescent sensor array constituted of variously charged dendritic phenylene–ethynylene fluorophores

A protein fluorescent sensor array based on variously charged dendritic fluorophores is developed. The variation of charge is achieved by different combinations of cationic trimethylammonium, anionic carboxylate and non-ionic methyl ester or N,N-dimethylamino on the peripheries of the fluorophores. Nine phenylene–ethynylene dendritic fluorophores, seven zeroth generation bearing charges varied from −3 to +3 and two first generation bearing −6 and +6 charges, are synthesized from triiodotriphenylamine through series of Sonogashira coupling. In phosphate buffer saline pH 7.4, five out of these nine compounds fluorogenically response to eight protein analytes distinctively. The data set of fluorescent intensities obtained from 5 fluorophores × 8 proteins × 9 replicated measurements can be statistically sorted into eight clusters corresponding to each protein by principal component analysis (PCA). Factorial discriminant analysis (FDA) cross-validation is applied to locate the optimum detection wavelength and reduce the number of sensing elements from nine to two with 100% discriminating accuracy. The method described should be generally practical for the development of electronic tongue for protein related food analysis and medical diagnosis.

Morphometric and Allozyme Variation inCulex tritaeniorhynchusMosquito Populations from India

Four populations of Culex tritaeniorhynchus (Giles) (Diptera: Culicidae), collected from Bellary, Cuddalore, Pune, and the Microbial Containment Complex laboratory culture in India were analyzed for morphological and allozyme variation. Multivariate analysis based on eight morphological characteristics and three morphometric indices was used to investigate the morphological variations among the four populations. Principal component analysis of the data suggested that siphon, saddle, and anal gills related variables were most important. Discriminant factor analysis of morphological data revealed that the four populations form significantly different clusters which can be differentiated from each other based on siphon, saddle, and pectin teeth related variables. Allozyme electrophoresis of the four populations revealed that the mean heterozygosity per locus value had high variation, ranging from 0.0879 to 1.794. Fst values between 0 and 0.519 suggested genetic differentiation within these populations. Fis values ranged from 0 to 1 with most of the values closer to 1. The allelic frequencies and Nei's genetic identity values showed that genetic differences between populations were small, but significant. Some of the morphological and allozyme variations in the Cx. tritaeniorhynchus populations could be partly attributed to the environmental conditions. The findings suggested that transition of morphological characters and allozyme variations in Cx. tritaeniorhynchus populations seem to be consequences of influence and selection by the environmental conditions. These results indicated that populations of Cx. tritaeniorhynchus in non-endemic areas of Japanese encephalitis (JE) virus infection have higher adaptability as compared to endemic areas of JE infection.

Utilisation of attenuated total reflectance MIR and front-face fluorescence spectroscopies for the identification of Saint-Nectaire cheeses varying by manufacturing conditions

Twelve samples of cheeses (three types of Saint-Nectaire PDO cheeses and Savaron cheeses) differing by manufacturing and ripening conditions, from 12 different producers, were characterised by attenuated total reflectance mid-infrared (MIR) and front-face fluorescence spectroscopies, dynamic testing rheology and physico-chemical analysis. Fluorescence spectra (tryptophan residues, vitamin A and riboflavin) and MIR (3,000–2,800 (fat region), 1,700–1,500 (protein region) and 1,500–900 cm−1 (fingerprint region)) spectra were recorded on cheese samples. The potential of the data tables was investigated for discriminating the four different groups of cheeses. The results of factorial discriminant analysis (FDA) performed on the fluorescence and mid-infrared spectra showed a good discrimination of the four cheese groups. Considering cross-validation results, the best classifications (100%) were achieved from mid-infrared and fluorescence spectra, while only 91.7 and 72.2% of correct classification were obtained by applying FDA to rheology and physico-chemical data, respectively. Spectroscopic techniques could provide useful fingerprints and allow the identification of investigated cheeses according to manufacturing conditions. Simple and rapid spectroscopic methods offer a promising approach to the authentication of cheeses.

Achromobacter xylosoxidans Genomic Characterization and Correlation of Randomly Amplified Polymorphic DNA Profiles with Relevant Clinical Features of Cystic Fibrosis Patients

Achromobacter xylosoxidans is an emerging pathogen increasingly being isolated from respiratory samples of cystic fibrosis (CF) patients. Its role and clinical significance in lung pathogenesis have not yet been clarified. The aim of the present study was to genetically characterize A. xylosoxidans strains isolated from CF patients by use of randomly amplified polymorphic DNA (RAPD) profiles and to look for a possible correlation between RAPD profiles and the patients' clinical features, such as their spirometry values, the presence of concomitant chronic bacterial flora at the time of isolation, and the persistent or intermittent presence of A. xylosoxidans strains. A set of 106 strains of A. xylosoxidans were typed by RAPD analysis, and their profiles were analyzed by agglomerative hierarchical classification (AHC) and associated with the patient characteristics mentioned above by factorial discriminant analysis (FDA). The overall results obtained in this study showed that (i) there is a marked genetic relationship between strains isolated from the same patients at different times, (ii) characteristic RAPD profiles are associated with different predicted classes for forced expiratory volume in 1 s (FEV1%), (iii) some characteristic RAPD profiles are associated with different concomitant chronic flora (CCF) profiles, and (iv) there is a significant division of RAPD profiles into "persistent strains" and "intermittent strains" of A. xylosoxidans. These findings seem to imply that the lung habitats found in CF patients are capable of shaping and selecting the colonizing bacterial flora, as seems to be the case for the A. xylosoxidans strains studied.

Identification of Saccharomyces cerevisiae strains for alcoholic fermentation by discriminant factorial analysis on electronic nose signals

An electronic nose (E-nose) coupled to gas chromatography was tested to monitor alcoholic fermentation by Saccharomyces cerevisiae ICV-K1 and Saccharomyces cerevisiae T306, two strains well-known for their use in oenology. The biomass and ethanol concentrations and conductance changes were measured during cultivations and allowed to observe the standard growth phases for both yeast strains. The two strains were characterized by a very similar tendency in biomass or ethanol production during the fermentation. E-nose was able to establish a kinetic of the production of aroma compounds production and which was then easy to associate with the fermentation phases. Principal Component Analysis (PCA) showed that the data collected by E-nose during the fermentation mainly contained cultivation course information. Discriminant factorial analysis (DFA) was able to clearly identify differences between the two strains using the four main principal components of PCA as input data. Nevertheless, the electronic nose responses being mainly influenced by cultivation course, a specific data treatment limiting the time influence on data was carried out and permitted to achieve an overall performance of 83.5%.

Supercritical fluid extracts from the Brazilian cherry ( Eugenia uniflora L.): Relationship between the extracted compounds and the characteristic flavour intensity of the fruit

Supercritical carbon dioxide (SC-CO 2) extractions of Brazilian cherry ( Eugenia uniflora L.) were carried out under varied conditions of pressure and temperature, according to a central composite 2 2 experimental design, in order to produce flavour-rich extracts. The composition of the extracts was evaluated by gas chromatography coupled with mass spectrometry (GC/MS). The abundance of the extracted compounds was then related to sensory analysis results, assisted by principal component and factorial discriminant analysis (PCA and FDA, respectively). The identified sesquiterpenes and ketones were found to strongly contribute to the characteristic flavour of the Brazilian cherry. The extracts also contained a variety of other volatile compounds, and part of the fruit wax contained long-chain hydrocarbons that according to multivariate analysis, contributed to the yield of the extracts, but not the flavour. Volatile phenolic compounds, to which antioxidant properties are attributed, were also present in the extracts in high proportion, regardless of the extraction conditions.