Impacto de la resiliencia en pacientes con Artritis Reumatoide

Introducción: La artritis reumatoide (AR) es una enfermedad autoinmune-inflamatoria, que compromete las articulaciones diartrodiales. Tiene una importante repercusión sistémica que incluye la depresión; por lo tanto, tiene un severo impacto sobre la calidad de vida. Es posible que mecanismos de defensa, tales como la resiliencia, puedan amortiguar dicho impacto. Metodología: estudio de corte transversal, multicéntrico (análisis inicial dentro del grupo AR, con muestra no probabilística de 66 pacientes, posterior selección aleatoria simple de 16 pacientes de la muestra inicial y selección de 16 individuos sanos pareados). Posteriormente, se comparó la resiliencia entre sujetos con AR y sujetos sanos, mediante las escalas RS y CD-RISC25. Adicionalmente, se aplicaron las escalas EEAE, EADZ, SF-36 y PANAS. Los datos fueron evaluados mediante el coeficiente de correlación de Spearman, las pruebas U Mann-Whitney, Kruskall-Wallis, T de Student y análisis de varianza. Resultados: se encontraron diferencias significativas en las estrategias de afrontamiento no espirituales en grupos de resiliencia baja, media y alta; diferencias en las medianas de resiliencia en los grupos de depresión por EAZD en los pacientes. No se encontraron resultados significativos en las variables clínicas de la AR ni en la comparación con sujetos sanos. Conclusiones: el uso de estrategias de afrontamiento no espirituales y la ausencia de depresión, se asoció a mayores niveles de resiliencia en los pacientes con AR, por lo cual, los componentes emocionales y cognitivos se asocian a la resiliencia.

Prevalencia de síntomas de fatiga crónica / encefalomielitis miálgica (SFC/EM) y su relación con factores ocupacionales en trabajadores en una empresa de vigilancia en Bogotá, Colombia, 2016

Antecedentes: El síndrome de fatiga crónica/encefalomielitis miálgica (SFC/EM), un trastorno debilitante y complejo que se caracteriza por un cansancio intenso, ha sido estudiado en población general, sin embargo, su exploración en población trabajadora ha sido limitada. Objetivo: Determinar la prevalencia de síntomas asociados a SFC/EM y su relación con factores ocupacionales en personal de una empresa de vigilancia en Bogotá, durante el año 2016. Materiales y métodos: Estudio de corte transversal en una empresa de vigilancia, utilizando como instrumento para la recolección de datos la historia clínica-ocupacional. En las variables cualitativas se obtuvieron frecuencias simples y porcentajes y en las variables cuantitativas medidas de tendencia central y de dispersión. Se determinaron asociaciones entre variables (Ji-cuadrado de Pearson o test exacto de Fisher, valores esperados <5), (mann-whitney.y un modelo de regresión logística incondicional (p<0.05)). Resultados: Se evaluaron 162 trabajadores, los síntomas de SFC/EM con mayor prevalencia fueron sueño no reparador (38,3%) y dolor muscular (30,2%). Se encontró asociación estadísticamente significativa entre fatiga severa y crónica por al menos 6 meses con alteración en sistema nervioso (p=0,016) y consumo de medicamentos (p=0,043), así mismo entre el sueño no reparador con el número de horas de sueño de 5 a 7 horas (p=0,002). Conclusión: En los vigilantes el síntoma de SFC/EM más prevalente fue sueño no reparador y este se asoció con el número de horas de sueño de 5 a 7 horas. Con el estudio se pudieron determinar los casos probables de SFC/EM los cuales se beneficiarían de una valoración médica integral para un diagnóstico oportuno.

Relación entre atrofia cortical difusa y desempeño cognitivo : estudio en población mayor de 60 años en un hospital universitario en la ciudad de Bogotá

El presente trabajo tuvo como objetivo evaluar la existencia de la relación entre la atrofia cortical difusa objetivada por neuroimagenes cerebrales y desempeños cognitivos determinados mediante la aplicación de pruebas neuropsicológicas que evalúan memoria de trabajo, razonamiento simbólico verbal y memoria anterógrada declarativa. Participaron 114 sujetos reclutados en el Hospital Universitario Mayor Méderi de la ciudad de Bogotá mediante muestreo de conveniencia. Los resultados arrojaron diferencias significativas entre los dos grupos (pacientes con diagnóstico de atrofia cortical difusa y pacientes con neuroimagenes interpretadas como dentro de los límites normales) en todas las pruebas neuropsicológicas aplicadas. Respecto a las variables demográficas se pudo observar que el grado de escolaridad contribuye como factor neuroprotector de un posible deterioro cognitivo. Tales hallazgos son importantes para determinar protocoles tempranos de detección de posible instalación de enfermedades neurodegenerativas primarias.

New measures for assessing model equilibrium and prediction mismatch in species distribution models

Models based on species distributions are widely used and serve important purposes in ecology, biogeography and conservation. Their continuous predictions of environmental suitability are commonly converted into a binary classification of predicted (or potential) presences and absences, whose accuracy is then evaluated through a number of measures that have been the subject of recent reviews. We propose four additional measures that analyse observation-prediction mismatch from a different angle – namely, from the perspective of the predicted rather than the observed area – and add to the existing toolset of model evaluation methods. We explain how these measures can complete the view provided by the existing measures, allowing further insights into distribution model predictions. We also describe how they can be particularly useful when using models to forecast the spread of diseases or of invasive species and to predict modifications in species’ distributions under climate and land-use change

Model-Based validation of Driver Drowsiness Detection System for ADAS

The work described in this Master’s Degree thesis was born after the collaboration with the company Maserati S.p.a, an Italian luxury car maker with its headquarters located in Modena, in the heart of the Italian Motor Valley, where I worked as a stagiaire in the Virtual Engineering team between September 2021 and February 2022. This work proposes the validation using real-world ECUs of a Driver Drowsiness Detection (DDD) system prototype based on different detection methods with the goal to overcome input signal losses and system failures. Detection methods of different categories have been chosen from literature and merged with the goal of utilizing the benefits of each of them, overcoming their limitations and limiting as much as possible their degree of intrusiveness to prevent any kind of driving distraction: an image processing-based technique for human physical signals detection as well as methods based on driver-vehicle interaction are used. A Driver-In-the-Loop simulator is used to gather real data on which a Machine Learning-based algorithm will be trained and validated. These data come from the tests that the company conducts in its daily activities so confidential information about the simulator and the drivers will be omitted. Although the impact of the proposed system is not remarkable and there is still work to do in all its elements, the results indicate the main advantages of the system in terms of robustness against subsystem failures and signal losses.

Tensor-Train decomposition for image classification problems

In these last years a great effort has been put in the development of new techniques for automatic object classification, also due to the consequences in many applications such as medical imaging or driverless cars. To this end, several mathematical models have been developed from logistic regression to neural networks. A crucial aspect of these so called classification algorithms is the use of algebraic tools to represent and approximate the input data. In this thesis, we examine two different models for image classification based on a particular tensor decomposition named Tensor-Train (TT) decomposition. The use of tensor approaches preserves the multidimensional structure of the data and the neighboring relations among pixels. Furthermore the Tensor-Train, differently from other tensor decompositions, does not suffer from the curse of dimensionality making it an extremely powerful strategy when dealing with high-dimensional data. It also allows data compression when combined with truncation strategies that reduce memory requirements without spoiling classification performance. The first model we propose is based on a direct decomposition of the database by means of the TT decomposition to find basis vectors used to classify a new object. The second model is a tensor dictionary learning model, based on the TT decomposition where the terms of the decomposition are estimated using a proximal alternating linearized minimization algorithm with a spectral stepsize.

Longitudinal Micro CT-driven biomarkers as a tool to evaluate lung fibrosis progression and antifibrotic efficacy in a refined Bleomycin mouse model

Idiopathic pulmonary fibrosis (IPF) is a chronic progressive disease with no curative pharmacological treatment. Animal models play an essential role in revealing molecular mechanisms involved in the pathogenesis of the disease. Bleomycin (BLM)-induced lung fibrosis is the most widely used and characterized model for anti-fibrotic drugs screening. However, several issues have been reported, such as the identification of an optimal BLM dose and administration scheme as well as gender-specificity. Moreover, the balance between disease resolution, an appropriate time window for therapeutic intervention and animal welfare remains critical aspects yet to be fully elucidated. In this thesis, Micro CT imaging has been used as a tool to identify the ideal BLM dose regimen to induce sustained lung fibrosis in mice as well as to assess the anti-fibrotic effect of Nintedanib (NINT) treatment upon this BLM administration regimen. In order to select the optimal BLM dose scheme, C57bl/6 male mice were treated with BLM via oropharyngeal aspiration (OA), following either double or triple BLM administration. The triple BLM administration resulted in the most promising scheme, able to balance disease resolution, appropriate time-window for therapeutic intervention and animal welfare. The fibrosis progression was longitudinally assessed by micro-CT every 7 days for 5 weeks after BLM administration and 5 animals were sacrificed at each timepoint for the BALF and histological evaluation. The antifibrotic effect of NINT was assessed following different treatment regimens in this model. Herein, we have developed an optimized mouse model of pulmonary fibrosis, enabling three weeks of the therapeutic window to screen putative anti-fibrotic drugs. micro-CT scanning, allowed us to monitor the progression of lung fibrosis and the therapeutical response longitudinally in the same subject, drastically reducing the number of animals involved in the experiment.

Essays in political and gender economics

In the first chapter, “Political power and the influence of minorities: theory and evidence from Italy”, I analyze the relationship between minority and majority in politics, and how it can influence policy outcomes. I first present a theoretical model describing the possible consequences of an increase in a minority’s political power and show how it can increase difficulties in reaching a compromise on policy outcomes between parties. Furthermore, I empirically test these implications by exploiting the introduction in 2012 of a gender quota in Italian local elections: the increase in female politicians had heterogeneous effects on the level of funding for daycare, based on its differential effects on the share of women councillors. The second chapter, “Marriage patterns and the gender gap in labor force participation: evidence from Italy”, presents evidence highlighting a new possible determinant of the large gender gap in the Italian labor force: endogamy intensity. I argue that endogamy helps preserve social norms stigmatizing working women and reduces the probability of divorce, which disincentivizes women’s participation in the labor force. Endogamy is proxied by the degree of concentration of its surnames’ distribution, and I provide evidence that a more intense custom of endogamy contributed to enlarging gender participation gaps across Italian municipalities in 2001. The third chapter, “Information and quality of politicians: is transparency helping voters?”, studies how voting choices are affected by giving voters more personal information on candidates. I exploit the introduction of the “Spazzacorrotti” law in Italy in 2019, which imposed candidates at local elections to publish their CVs and criminal records before elections. I find no effects on elected candidates’ age, gender, educational level, or ideology. Moreover, I present anecdotal evidence that candidates with a criminal record received fewer votes on average, but only in the case of local media exposing it.

Digital 3D reconstruction as a research environment in art and architecture history: uncertainty classification and visualisation

The dissertation addresses the still not solved challenges concerned with the source-based digital 3D reconstruction, visualisation and documentation in the domain of archaeology, art and architecture history. The emerging BIM methodology and the exchange data format IFC are changing the way of collaboration, visualisation and documentation in the planning, construction and facility management process. The introduction and development of the Semantic Web (Web 3.0), spreading the idea of structured, formalised and linked data, offers semantically enriched human- and machine-readable data. In contrast to civil engineering and cultural heritage, academic object-oriented disciplines, like archaeology, art and architecture history, are acting as outside spectators. Since the 1990s, it has been argued that a 3D model is not likely to be considered a scientific reconstruction unless it is grounded on accurate documentation and visualisation. However, these standards are still missing and the validation of the outcomes is not fulfilled. Meanwhile, the digital research data remain ephemeral and continue to fill the growing digital cemeteries. This study focuses, therefore, on the evaluation of the source-based digital 3D reconstructions and, especially, on uncertainty assessment in the case of hypothetical reconstructions of destroyed or never built artefacts according to scientific principles, making the models shareable and reusable by a potentially wide audience. The work initially focuses on terminology and on the definition of a workflow especially related to the classification and visualisation of uncertainty. The workflow is then applied to specific cases of 3D models uploaded to the DFG repository of the AI Mainz. In this way, the available methods of documenting, visualising and communicating uncertainty are analysed. In the end, this process will lead to a validation or a correction of the workflow and the initial assumptions, but also (dealing with different hypotheses) to a better definition of the levels of uncertainty.

Modelling and classification with quantile-based distributions

In this work, we explore and demonstrate the potential for modeling and classification using quantile-based distributions, which are random variables defined by their quantile function. In the first part we formalize a least squares estimation framework for the class of linear quantile functions, leading to unbiased and asymptotically normal estimators. Among the distributions with a linear quantile function, we focus on the flattened generalized logistic distribution (fgld), which offers a wide range of distributional shapes. A novel naïve-Bayes classifier is proposed that utilizes the fgld estimated via least squares, and through simulations and applications, we demonstrate its competitiveness against state-of-the-art alternatives. In the second part we consider the Bayesian estimation of quantile-based distributions. We introduce a factor model with independent latent variables, which are distributed according to the fgld. Similar to the independent factor analysis model, this approach accommodates flexible factor distributions while using fewer parameters. The model is presented within a Bayesian framework, an MCMC algorithm for its estimation is developed, and its effectiveness is illustrated with data coming from the European Social Survey. The third part focuses on depth functions, which extend the concept of quantiles to multivariate data by imposing a center-outward ordering in the multivariate space. We investigate the recently introduced integrated rank-weighted (IRW) depth function, which is based on the distribution of random spherical projections of the multivariate data. This depth function proves to be computationally efficient and to increase its flexibility we propose different methods to explicitly model the projected univariate distributions. Its usefulness is shown in classification tasks: the maximum depth classifier based on the IRW depth is proven to be asymptotically optimal under certain conditions, and classifiers based on the IRW depth are shown to perform well in simulated and real data experiments.

An approach to document classification using verb-object pairs

The aim of this thesis is to present a new approach to document classification using verb-object pairs. We explore one possible strategy that uses the presence of relevant verb-object pairs in documents as features and a Naive Bayes classifier as a classifier on which the model is trained. Then, we assess the results from the case study which uses a software based on the strategy and make conclusions.

Vocabulary Transfer and Knowledge Distillation for Language Model Compression

Natural Language Processing (NLP) has seen tremendous improvements over the last few years. Transformer architectures achieved impressive results in almost any NLP task, such as Text Classification, Machine Translation, and Language Generation. As time went by, transformers continued to improve thanks to larger corpora and bigger networks, reaching hundreds of billions of parameters. Training and deploying such large models has become prohibitively expensive, such that only big high tech companies can afford to train those models. Therefore, a lot of research has been dedicated to reducing a model’s size. In this thesis, we investigate the effects of Vocabulary Transfer and Knowledge Distillation for compressing large Language Models. The goal is to combine these two methodologies to further compress models without significant loss of performance. In particular, we designed different combination strategies and conducted a series of experiments on different vertical domains (medical, legal, news) and downstream tasks (Text Classification and Named Entity Recognition). Four different methods involving Vocabulary Transfer (VIPI) with and without a Masked Language Modelling (MLM) step and with and without Knowledge Distillation are compared against a baseline that assigns random vectors to new elements of the vocabulary. Results indicate that VIPI effectively transfers information of the original vocabulary and that MLM is beneficial. It is also noted that both vocabulary transfer and knowledge distillation are orthogonal to one another and may be applied jointly. The application of knowledge distillation first before subsequently applying vocabulary transfer is recommended. Finally, model performance due to vocabulary transfer does not always show a consistent trend as the vocabulary size is reduced. Hence, the choice of vocabulary size should be empirically selected by evaluation on the downstream task similar to hyperparameter tuning.

Motor Unit Spike Trains Recontruction from sEMG Signals for Gesture Classification on a Low-Power Processing Platform

Hand gesture recognition based on surface electromyography (sEMG) signals is a promising approach for the development of intuitive human-machine interfaces (HMIs) in domains such as robotics and prosthetics. The sEMG signal arises from the muscles' electrical activity, and can thus be used to recognize hand gestures. The decoding from sEMG signals to actual control signals is non-trivial; typically, control systems map sEMG patterns into a set of gestures using machine learning, failing to incorporate any physiological insight. This master thesis aims at developing a bio-inspired hand gesture recognition system based on neuromuscular spike extraction rather than on simple pattern recognition. The system relies on a decomposition algorithm based on independent component analysis (ICA) that decomposes the sEMG signal into its constituent motor unit spike trains, which are then forwarded to a machine learning classifier. Since ICA does not guarantee a consistent motor unit ordering across different sessions, 3 approaches are proposed: 2 ordering criteria based on firing rate and negative entropy, and a re-calibration approach that allows the decomposition model to retain information about previous sessions. Using a multilayer perceptron (MLP), the latter approach results in an accuracy up to 99.4% in a 1-subject, 1-degree of freedom scenario. Afterwards, the decomposition and classification pipeline for inference is parallelized and profiled on the PULP platform, achieving a latency < 50 ms and an energy consumption < 1 mJ. Both the classification models tested (a support vector machine and a lightweight MLP) yielded an accuracy > 92% in a 1-subject, 5-classes (4 gestures and rest) scenario. These results prove that the proposed system is suitable for real-time execution on embedded platforms and also capable of matching the accuracy of state-of-the-art approaches, while also giving some physiological insight on the neuromuscular spikes underlying the sEMG.

Meta-learning for informed model searches in Automated Machine Learning

Day by day, machine learning is changing our lives in ways we could not have imagined just 5 years ago. ML expertise is more and more requested and needed, though just a limited number of ML engineers are available on the job market, and their knowledge is always limited by an inherent characteristic of theirs: they are humans. This thesis explores the possibilities offered by meta-learning, a new field in ML that takes learning a level higher: models are trained on other models' training data, starting from features of the dataset they were trained on, inference times, obtained performances, to try to understand the relationship between a good model and the way it was obtained. The so-called metamodel was trained on data collected by OpenML, the largest ML metadata platform that's publicly available today. Datasets were analyzed to obtain meta-features that describe them, which were then tied to model performances in a regression task. The obtained metamodel predicts the expected performances of a given model type (e.g., a random forest) on a given ML task (e.g., classification on the UCI census dataset). This research was then integrated into a custom-made AutoML framework, to show how meta-learning is not an end in itself, but it can be used to further progress our ML research. Encoding ML engineering expertise in a model allows better, faster, and more impactful ML applications across the whole world, while reducing the cost that is inevitably tied to human engineers.

SynBA: A contextualized Synonim-Based adversarial Attack for text classification

With the advent of high-performance computing devices, deep neural networks have gained a lot of popularity in solving many Natural Language Processing tasks. However, they are also vulnerable to adversarial attacks, which are able to modify the input text in order to mislead the target model. Adversarial attacks are a serious threat to the security of deep neural networks, and they can be used to craft adversarial examples that steer the model towards a wrong decision. In this dissertation, we propose SynBA, a novel contextualized synonym-based adversarial attack for text classification. SynBA is based on the idea of replacing words in the input text with their synonyms, which are selected according to the context of the sentence. We show that SynBA successfully generates adversarial examples that are able to fool the target model with a high success rate. We demonstrate three advantages of this proposed approach: (1) effective - it outperforms state-of-the-art attacks by semantic similarity and perturbation rate, (2) utility-preserving - it preserves semantic content, grammaticality, and correct types classified by humans, and (3) efficient - it performs attacks faster than other methods.