On the length of bank-firm relationships: an empirical application to a major French bank

NIPE - WP 01/ 2016

Using data mining for prediction of hospital length of stay: an application of the CRISP-DM Methodology

Hospitals are nowadays collecting vast amounts of data related with patient records. All this data hold valuable knowledge that can be used to improve hospital decision making. Data mining techniques aim precisely at the extraction of useful knowledge from raw data. This work describes an implementation of a medical data mining project approach based on the CRISP-DM methodology. Recent real-world data, from 2000 to 2013, were collected from a Portuguese hospital and related with inpatient hospitalization. The goal was to predict generic hospital Length Of Stay based on indicators that are commonly available at the hospitalization process (e.g., gender, age, episode type, medical specialty). At the data preparation stage, the data were cleaned and variables were selected and transformed, leading to 14 inputs. Next, at the modeling stage, a regression approach was adopted, where six learning methods were compared: Average Prediction, Multiple Regression, Decision Tree, Artificial Neural Network ensemble, Support Vector Machine and Random Forest. The best learning model was obtained by the Random Forest method, which presents a high quality coefficient of determination value (0.81). This model was then opened by using a sensitivity analysis procedure that revealed three influential input attributes: the hospital episode type, the physical service where the patient is hospitalized and the associated medical specialty. Such extracted knowledge confirmed that the obtained predictive model is credible and with potential value for supporting decisions of hospital managers.

Time-dependent flexural behaviour of cracked steel fibre reinforced self-compacting concrete panels

In the present work are described and discussed the results of an extensive experimental program that aims to study the long-term behaviour of cracked steel fibre reinforced self-compacting concrete, SFRSCC, applied in laminar structures. In a first stage, the influence of the initial crack opening level (wcr = 0.3 and 0.5 mm), applied stress level, fibre orientation/dispersion and distance from the casting point, on the flexural creep behaviour of SFRSCC was investigated. Moreover, in order to evaluate the effects of the creep phenomenon on the residual flexural strength, a series of monotonic tests were also executed. It was found that wcr = 0.5 mm series showed a higher creep coefficient comparing to the series with a lower initial crack opening. Furthermore, the creep performance of the SFRSCC was influenced by the orientation of the extracted prismatic specimens regarding the direction of the concrete flow within the cast panel.

Dispersion and re-agglomeration of graphite nanoplates in polypropylene melts under controlled flow conditions

The kinetics of GnP dispersion in polypropylene melt was studied using a prototype small scale modular extensional mixer. Its modular nature enabled the sequential application of a mixing step, melt relaxation, and a second mixing step. The latter could reproduce the flow conditions on the first mixing step, or generate milder flow conditions. The effect of these sequences of flow constraints upon GnP dispersion along the mixer length was studied for composites with 2 and 10 wt.% GnP. The samples collected along the first mixing zone showed a gradual decrease of number and size of GnP agglomerates, at a rate that was independent of the flow conditions imposed to the melt, but dependent on composition. The relaxation zone induced GnP re-agglomeration, and the application of a second mixing step caused variable dispersion results that were largely dependent on the hydrodynamic stresses generated.

The role of Pep4p, the vacuolar yeast protease ortholog of human cathepsin D, in mitochondria-dependent apoptosis

Doctoral Thesis (PhD Programm on Molecular and Environmental Biology)

Structure-property relationships in polymer nanocomposites

Tese de Doutoramento em Ciência e Engenharia de Polímeros e Compósitos

Ion exchange dependent electroactive phase content and electrical properties of poly(vinylidene fluoride)/Na(M)Y composites

Different metal-ion exchanged NaY zeolite, Na(M)Y, were used to prepare poly(vinylidene fluoride) based composites by solvent casting and melting crystallization. The effect of different metal ion-exchanged zeolites on polymer crystallization and electrical properties was reported. Cation-framework interactions and hydration energy of the cations determined that K+ is the most efficient exchanged ion in NaY zeolite, followed by Cs+ and Li+. The electroactive phase crystallization strongly depends on the ions present in the zeolite, leading to variations of the surface energy characteristics of the Na(M)Y zeolites and the polymer chain ability of penetration in the zeolite. Thus, Na(Li)Y and NaY induces the complete electroactive -phase crystallization of the crystalline phase of PVDF, while Na(K)Y only induces it partly and Na(Cs)Y is not able to promote the crystallization of the electroactive phase. Furthermore, different ion size/weigh and different interaction with the zeolite framework results in significant variations in the electrical response of the composite. In this way, iinterfacial polarization effects in the zeolite cavities and zeolite-polymer interface, leads to strong increases of the dielectric constant on the composites with lightest ions weakly bound to the zeolite framework. Polymer composite with Na(Li)Y show the highest dielectric response, followed by NaY and Na(K)Y. Zeolite Na(Cs)Y contribute to a decrease of the dielectric constant of the composite. The results show the relevance of the materials for sensor development.

Nonparametric estimation of time-dependent ROC curves conditional on a continuous covariate

The receiver-operating characteristic (ROC) curve is the most widely used measure for evaluating the performance of a diagnostic biomarker when predicting a binary disease outcome. The ROC curve displays the true positive rate (or sensitivity) and the false positive rate (or 1-specificity) for different cut-off values used to classify an individual as healthy or diseased. In time-to-event studies, however, the disease status (e.g. death or alive) of an individual is not a fixed characteristic, and it varies along the study. In such cases, when evaluating the performance of the biomarker, several issues should be taken into account: first, the time-dependent nature of the disease status; and second, the presence of incomplete data (e.g. censored data typically present in survival studies). Accordingly, to assess the discrimination power of continuous biomarkers for time-dependent disease outcomes, time-dependent extensions of true positive rate, false positive rate, and ROC curve have been recently proposed. In this work, we present new nonparametric estimators of the cumulative/dynamic time-dependent ROC curve that allow accounting for the possible modifying effect of current or past covariate measures on the discriminatory power of the biomarker. The proposed estimators can accommodate right-censored data, as well as covariate-dependent censoring. The behavior of the estimators proposed in this study will be explored through simulations and illustrated using data from a cohort of patients who suffered from acute coronary syndrome.

The Warburg effect in mycobacterial granulomas is dependent on the recruitment and activation of macrophages by interferon-γ

Granulomas are the hallmark of mycobacterial disease. Here, we demonstrate that both the cell recruitment and the increased glucose consumption in granulomatous infiltrates during Mycobacterium avium infection are highly dependent on interferon-y (IFN-y). Mycobacterium avium-infected mice lacking IFN-y signalling failed to developed significant inflammatory infiltrations and lacked the characteristic uptake of the glucose analogue fluorine-18-fluorodeoxyglucose (FDG). To assess the role of macrophages in glucose uptake we infected mice with a selective impairment of IFN-y signalling in the macrophage lineage (MIIG mice). Although only a partial reduction of the granulomatous areas was observed in infected MIIG mice, the insensitivity of macrophages to IFN-y reduced the accumulation of FDG. In vivo, ex vivo and in vitro assays showed that macrophage activated by IFN-y displayed increased rates of glucose uptake and in vitro studies showed also that they had increased lactate production and increased expression of key glycolytic enzymes. Overall, our results show that the activation of macrophages by IFN-y is responsible for the Warburg effect observed in organs infected with M. avium.

Risk of multiple myeloma is associated with polymorphisms within telomerase genes and telomere length

Compelling biological and epidemiological evidences point to a key role of genetic variants of the TERT and TERC genes in cancer development. We analyzed the genetic variability of these two gene regions using samples of 2,267 multiple myeloma (MM) cases and 2,796 healthy controls. We found that a TERT variant, rs2242652, is associated with reduced MM susceptibility (OR?=?0.81; 95% CI: 0.72-0.92; p?=?0.001). In addition we measured the leukocyte telomere length (LTL) in a subgroup of 140 cases who were chemotherapy-free at the time of blood donation and 468 controls, and found that MM patients had longer telomeres compared to controls (OR?=?1.19; 95% CI: 0.63-2.24; ptrend ?=?0.01 comparing the quartile with the longest LTL versus the shortest LTL). Our data suggest the hypothesis of decreased disease risk by genetic variants that reduce the efficiency of the telomerase complex. This reduced efficiency leads to shorter telomere ends, which in turn may also be a marker of decreased MM risk.

Implementation and validation of a strain rate dependent anisotropic continuum model for masonry

A newly developed strain rate dependent anisotropic continuum model is proposed for impact and blast applications in masonry. The present model adopted the usual approach of considering different yield criteria in tension and compression. The analysis of unreinforced block work masonry walls subjected to impact is carried out to validate the capability of the model. Comparison of the numerical predictions and test data revealed good agreement. Next, a parametric study is conducted to evaluate the influence of the tensile strengths along the three orthogonal directions and of the wall thickness on the global behavior of masonry walls.

Effect of the alkyl chain length of the ionic liquid anion on polymer electrolytes properties

New polymer electrolytes (PEs) based on chitosan and three ionic liquid (IL) families ([C2mim][CnSO3], [C2mim][CnSO4] and [C2mim][diCnPO4]) were synthesized by the solvent casting method. The effect of the length of the alkyl chain of the IL anion on the thermal, morphological and electrochemical properties of the PEs was studied. The solid polymer electrolytes (SPE) membranes were analyzed by differential scanning calorimetry (DSC), thermogravimetric analysis (TGA), X-ray diffraction (XRD), scanning electron microscopy (SEM), energy dispersive X-ray (EDX), polarized optical microscopy (POM), atomic force microscopy (AFM), complex impedance spectroscopy (ionic conductivity) and cyclic voltammetry (CV). The obtained results evidenced an influence of the alkyl chain length of the IL anion on the temperature of degradation, birefringence, surface roughness and ionic conductivity of the membranes. The DSC, XRD and CV results showed independency from the length of the IL-anion-alkyl chain. The PEs displayed an predominantly amorphous morphology, a minimum temperature of degradation of 135 °C, a room temperature (T = 25 °C) ionic conductivity of 7.78 × 10−4 S cm−1 and a wide electrochemical window of ∼ 4.0 V.

Structure dependent resistivity and dielectric characteristics of tantalum oxynitride thin films produced by magnetron sputtering

tThe main purpose of this work is to present and to interpret the change of electrical properties of TaxNyOzthin films, produced by DC reactive magnetron sputtering. Some parameters were varied during deposi-tion: the flow of the reactive gases mixture (N2and O2, with a constant concentration ratio of 17:3); thesubstrate voltage bias (grounded, −50 V or −100 V) and the substrate (glass, (1 0 0) Si or high speed steel).The obtained films exhibit significant differences. The variation of the deposition parameters inducesvariations of the composition, microstructure and morphology. These differences cause variation of theelectrical resistivity essentially correlated with the composition and structural changes. The gradualdecrease of the Ta concentration in the films induces amorphization and causes a raise of the resistivity.The dielectric characteristics of some of the high resistance TaxNyOzfilms were obtained in the sampleswith a capacitor-like design (deposited onto high speed steel, with gold pads deposited on the dielectricTaxNyOzfilms). Some of these films exhibited dielectric constant values higher than those reported forother tantalum based dielectric films.

Automatically estimating iSAX parameters

The Symbolic Aggregate Approximation (iSAX) is widely used in time series data mining. Its popularity arises from the fact that it largely reduces time series size, it is symbolic, allows lower bounding and is space efficient. However, it requires setting two parameters: the symbolic length and alphabet size, which limits the applicability of the technique. The optimal parameter values are highly application dependent. Typically, they are either set to a fixed value or experimentally probed for the best configuration. In this work we propose an approach to automatically estimate iSAX’s parameters. The approach – AutoiSAX – not only discovers the best parameter setting for each time series in the database, but also finds the alphabet size for each iSAX symbol within the same word. It is based on simple and intuitive ideas from time series complexity and statistics. The technique can be smoothly embedded in existing data mining tasks as an efficient sub-routine. We analyze its impact in visualization interpretability, classification accuracy and motif mining. Our contribution aims to make iSAX a more general approach as it evolves towards a parameter-free method.

Thermal technologies in food processing

[Excerpt] Introduction: Thermal processing is probably the most important process in food industry that has been used since prehistoric times, when it was discovered that heat enhanced the palatability and the life of the heat-treated food. Thermal processing comprehends the heating of foods at a defined temperature for a certain length of time. However, in some foods, the high thermotolerance of certain enzymes and microorganisms, their physical properties (e.g.,highviscosity),ortheircomponents(e.g.,solidfractions) require the application of extreme heat treatments that not only are energy intensive, but also will adversely affect the nutritional and organoleptic properties of the food. Technologies such as ohmic heating, dielectric heating (which includes microwave heating and radiofrequency heating), inductive heating, and infrared heating are available to replace, or complement, the traditional heat-dependent technologies (heating through superheated steam, hot air, hot water, or other hot liquid, being the heating achieved either through direct contact with those agents – mostly superheated steam – or through contact with a hot surface which is in turn heated by such agents). Given that the “traditional” heatdependent technologies are thoroughly described in the literature, this text will be mainly devoted to the so-called “novel” thermal technologies. (...)