Abstract

'''The improvements in monitoring devices result in databases of increasing size showing dam behaviour. Advanced tools are required to extract useful information from such large amounts of data. Machine learning is increasingly used for that purpose worldwide: data-based models are built to estimate the dam response in front of a given combination of loads. The results of the comparison between model predictions and actual measurements can be used for decision support in dam safety evaluations. However, most of the works to date consider each device separately. A different approach is used in this contribution: a set of displacement records are jointly considered to identify patterns using a classification model. First, potential anomaly scenarios are defined and the response of the dam for each of them is obtained with numerical models under a realistic load combination. Then, the resulting displacements are used to generate a machine learning classifier. This model is later used to predict the most probable class of dam behavior corresponding to a new set of records. The methodology is applied to a double-curvature arch dam, showing great potential for anomaly detection.

Abstract

Computational fluid dynamics is a cornerstone for the modern aerospace industry, providing important insights on aerodynamic analysis while reducing the need of expensive experiments and tests. Nevertheless, simulations of complex geometries are often performed on a discrete spatial domain too coarse to capture all relevant physical phenomena for the sake of lowering the computational cost. A consistent spatial discretization on so-called grids approximates the analytical solution of the partial differential equation with increasing number of discrete points. Such a grid refinement study is an expensive method to assess the general grid quality. This work shows that machine learning as a post-processing tool is capable of improving coarse grid simulations, even if not converged. The results show that three machine learning models varying in their complexity, namely the random forest, the neural network, and the graph neural network, are capable of finding patterns in coarse grid simulations. These patterns are used to predict the discretization error to approximate the field variables of interest of the corresponding fine grid simulation mapped onto the coarse grid. Initial training and testing is performed on the RAE2822 airfoil leading to corrected flow fields, improved surface integrals and coefficients, even when shocks are present. Additional tests are performed on the RAE5212 airfoil, showing the generalization limits of the trained models. The proposed method promises to reduce computational expenses while increasing the accuracy of the coarse grid results which works locally, e.g. it corrects the error for each cell individually and is therefore not restricted by the number of grid points. The presented results obtained by the machine learning models during post-processing are a promising baseline for more integrated developments, where the models will interact in a dynamic fashion with the flow solver to further improve coarse grid simulations.

Abstract

Abstract

Aquest treball investiga la problemàtica de la manipulació comptable. En concret, té l'objectiu d'identificar variables quantitatives i qualitatives que permetin distingir a les empreses maquilladores de les no maquilladores. Per a això, s'utilitza la metodologia Random Forest. A partir d'una mostra equilibrada de 80 empreses, la meitat de les quals han estat identificades com a manipuladores comptables i l'altra meitat identificades com a susceptibles de no haver manipulat els seus estats comptables, s'analitzen un total de 47 senyals d'alerta, tant quantitatives com qualitatives. D'aquesta forma, es determinen quines són les més rellevants a l'hora de discriminar entre tots dos grups. Els resultats permeten tenir més coneixement sobre els senyals d'alerta relacionades amb la manipulació comptable. Aquesta recerca pot ser de gran interès per als usuaris de la informació financera de les empreses, entre els quals podem destacar a: directius, accionistes, inversors, creditors, competidors, analistes bancaris, analistes d'inversió, auditors… així com per a organismes supervisors.

Abstract

Conventional concrete is the most common material used in civil construction, and its behavior is highly nonlinear, mainly because of its heterogeneous characteristics. Compressive strength is one of the most critical parameters when designing concrete structures, and it is widely used by engineers. This parameter is usually determined through expensive laboratory tests, causing a loss of resources, materials, and time. However, artificial intelligence and its numerous applications are examples of new technologies that have been used successfully in scientific applications. Artificial neural network (ANN) and support vector machine (SVM) models are generally used to resolve engineering problems. In this work, three models are designed, implemented, and tested to determine the compressive strength of concrete: random forest, SVM, and ANNs. Pre-processing data, statistical methods, and data visualization techniques are also employed to gain a better understanding of the database. Finally, the results obtained show high efficiency and are compared with other works, which also captured the compressive strength of the concrete.

Abstract

Abstract

Abstract

Abstract

Eix 10: La contribució dels professionals de l’economia

Justificació del seu interès

La incidència del frau i maquillatge comptable en els estats financers és un tema d'alta rellevància tant en l'àmbit acadèmic com en el professional, donant lloc a significatives pèrdues econòmiques i afectant la credibilitat de les empreses. La metodologia Random Forest ha demostrat ser una eina potent en la identificació de patrons de maquillatge comptable, oferint una nova perspectiva en la detecció de fraus.

Objectius

1.     Identificar els senyals d'alerta més efectius per a la detecció de maquillatge comptable.

2.     Validar l'eficàcia de la metodologia Random Forest en l'anàlisi de dades comptables.

3.     Contribuir a la millora de la transparència i la integritat financera en el sector empresarial.

Resultats que s'espera obtenir

S'espera identificar de manera fiable els senyals més importants a l´hora d'alerta de maquillatge comptable. conjunt de 55 variables analitzades.

Conclusions que s'espera assolir

Amb aquesta recerca es preveu demostrar per una banda,  l'aplicabilitat i l'eficiència del Random Forest en la detecció de maquillatge comptable, oferint eines robustes per a auditors i reguladors. Per altra banda, identificar quins són els senyals que tenen més poder predictiu per a la identificació de les empreses que cometen engany comptable dintre d´un conjunt de 55 variables quantitatives i qualitatives.

Es tracta d’una proposta que pot ser d’utilitat per a auditors, analistes i organismes supervisors i qualsevol persona interessada en la informació econòmica financera i no financera proporcionada per les empreses, afavorint un entorn empresarial més ètic i transparent.

Abstract