Inference on copula-based correlation structures

We propose an extension of the approach provided by Kluppelberg and Kuhn (2009) for inference on second-order structure moments. As in Kluppelberg and Kuhn (2009) we adopt a copula-based approach instead of assuming normal distribution for the variables, thus relaxing the equality in distribution assumption. A new copula-based estimator for structure moments is investigated. The methodology provided by Kluppelberg and Kuhn (2009) is also extended considering the copulas associated with the family of Eyraud-Farlie-Gumbel-Morgenstern distribution functions (Kotz, Balakrishnan, and Johnson, 2000, Equation 44.73). Finally, a comprehensive simulation study and an application to real financial data are performed in order to compare the different approaches.

Employing Distances in Design-based Spatial Estimation

In the last couple of decades we assisted to a reappraisal of spatial design-based techniques. Usually the spatial information regarding the spatial location of the individuals of a population has been used to develop efficient sampling designs. This thesis aims at offering a new technique for both inference on individual values and global population values able to employ the spatial information available before sampling at estimation level by rewriting a deterministic interpolator under a design-based framework. The achieved point estimator of the individual values is treated both in the case of finite spatial populations and continuous spatial domains, while the theory on the estimator of the population global value covers the finite population case only. A fairly broad simulation study compares the results of the point estimator with the simple random sampling without replacement estimator in predictive form and the kriging, which is the benchmark technique for inference on spatial data. The Monte Carlo experiment is carried out on populations generated according to different superpopulation methods in order to manage different aspects of the spatial structure. The simulation outcomes point out that the proposed point estimator has almost the same behaviour as the kriging predictor regardless of the parameters adopted for generating the populations, especially for low sampling fractions. Moreover, the use of the spatial information improves substantially design-based spatial inference on individual values.

Diagnosis and Fault detection in Electrical Machines and Drives based on Advanced Signal Processing Techniques

In the present thesis, a new methodology of diagnosis based on advanced use of time-frequency technique analysis is presented. More precisely, a new fault index that allows tracking individual fault components in a single frequency band is defined. More in detail, a frequency sliding is applied to the signals being analyzed (currents, voltages, vibration signals), so that each single fault frequency component is shifted into a prefixed single frequency band. Then, the discrete Wavelet Transform is applied to the resulting signal to extract the fault signature in the frequency band that has been chosen. Once the state of the machine has been qualitatively diagnosed, a quantitative evaluation of the fault degree is necessary. For this purpose, a fault index based on the energy calculation of approximation and/or detail signals resulting from wavelet decomposition has been introduced to quantify the fault extend. The main advantages of the developed new method over existing Diagnosis techniques are the following: - Capability of monitoring the fault evolution continuously over time under any transient operating condition; - Speed/slip measurement or estimation is not required; - Higher accuracy in filtering frequency components around the fundamental in case of rotor faults; - Reduction in the likelihood of false indications by avoiding confusion with other fault harmonics (the contribution of the most relevant fault frequency components under speed-varying conditions are clamped in a single frequency band); - Low memory requirement due to low sampling frequency; - Reduction in the latency of time processing (no requirement of repeated sampling operation).

Machine learning as a service for high energy physics (MLaaS4HEP): a service for ML-based data analyses

With the CERN LHC program underway, there has been an acceleration of data growth in the High Energy Physics (HEP) field and the usage of Machine Learning (ML) in HEP will be critical during the HL-LHC program when the data that will be produced will reach the exascale. ML techniques have been successfully used in many areas of HEP nevertheless, the development of a ML project and its implementation for production use is a highly time-consuming task and requires specific skills. Complicating this scenario is the fact that HEP data is stored in ROOT data format, which is mostly unknown outside of the HEP community. The work presented in this thesis is focused on the development of a ML as a Service (MLaaS) solution for HEP, aiming to provide a cloud service that allows HEP users to run ML pipelines via HTTP calls. These pipelines are executed by using the MLaaS4HEP framework, which allows reading data, processing data, and training ML models directly using ROOT files of arbitrary size from local or distributed data sources. Such a solution provides HEP users non-expert in ML with a tool that allows them to apply ML techniques in their analyses in a streamlined manner. Over the years the MLaaS4HEP framework has been developed, validated, and tested and new features have been added. A first MLaaS solution has been developed by automatizing the deployment of a platform equipped with the MLaaS4HEP framework. Then, a service with APIs has been developed, so that a user after being authenticated and authorized can submit MLaaS4HEP workflows producing trained ML models ready for the inference phase. A working prototype of this service is currently running on a virtual machine of INFN-Cloud and is compliant to be added to the INFN Cloud portfolio of services.

Study of the tracking performance of a liquid Argon detector based on a novel optical imaging concept

The Deep Underground Neutrino Experiment (DUNE) is a long-baseline accelerator experiment designed to make a significant contribution to the study of neutrino oscillations with unprecedented sensitivity. The main goal of DUNE is the determination of the neutrino mass ordering and the leptonic CP violation phase, key parameters of the three-neutrino flavor mixing that have yet to be determined. An important component of the DUNE Near Detector complex is the System for on-Axis Neutrino Detection (SAND) apparatus, which will include GRAIN (GRanular Argon for Interactions of Neutrinos), a novel liquid Argon detector aimed at imaging neutrino interactions using only scintillation light. For this purpose, an innovative optical readout system based on Coded Aperture Masks is investigated. This dissertation aims to demonstrate the feasibility of reconstructing particle tracks and the topology of CCQE (Charged Current Quasi Elastic) neutrino events in GRAIN with such a technique. To this end, the development and implementation of a reconstruction algorithm based on Maximum Likelihood Expectation Maximization was carried out to directly obtain a three-dimensional distribution proportional to the energy deposited by charged particles crossing the LAr volume. This study includes the evaluation of the design of several camera configurations and the simulation of a multi-camera optical system in GRAIN.

Hierarchical active inference for cognitive architectures

This thesis explores the methods based on the free energy principle and active inference for modelling cognition. Active inference is an emerging framework for designing intelligent agents where psychological processes are cast in terms of Bayesian inference. Here, I appeal to it to test the design of a set of cognitive architectures, via simulation. These architectures are defined in terms of generative models where an agent executes a task under the assumption that all cognitive processes aspire to the same objective: the minimization of variational free energy. Chapter 1 introduces the free energy principle and its assumptions about self-organizing systems. Chapter 2 describes how from the mechanics of self-organization can emerge a minimal form of cognition able to achieve autopoiesis. In chapter 3 I present the method of how I formalize generative models for action and perception. The architectures proposed allow providing a more biologically plausible account of more complex cognitive processing that entails deep temporal features. I then present three simulation studies that aim to show different aspects of cognition, their associated behavior and the underlying neural dynamics. In chapter 4, the first study proposes an architecture that represents the visuomotor system for the encoding of actions during action observation, understanding and imitation. In chapter 5, the generative model is extended and is lesioned to simulate brain damage and neuropsychological patterns observed in apraxic patients. In chapter 6, the third study proposes an architecture for cognitive control and the modulation of attention for action selection. At last, I argue how active inference can provide a formal account of information processing in the brain and how the adaptive capabilities of the simulated agents are a mere consequence of the architecture of the generative models. Cognitive processing, then, becomes an emergent property of the minimization of variational free energy.

Seemingly unrelated linear regression for contaminated data based on Gaussian mixtures

In this thesis, new classes of models for multivariate linear regression defined by finite mixtures of seemingly unrelated contaminated normal regression models and seemingly unrelated contaminated normal cluster-weighted models are illustrated. The main difference between such families is that the covariates are treated as fixed in the former class of models and as random in the latter. Thus, in cluster-weighted models the assignment of the data points to the unknown groups of observations depends also by the covariates. These classes provide an extension to mixture-based regression analysis for modelling multivariate and correlated responses in the presence of mild outliers that allows to specify a different vector of regressors for the prediction of each response. Expectation-conditional maximisation algorithms for the calculation of the maximum likelihood estimate of the model parameters have been derived. As the number of free parameters incresases quadratically with the number of responses and the covariates, analyses based on the proposed models can become unfeasible in practical applications. These problems have been overcome by introducing constraints on the elements of the covariance matrices according to an approach based on the eigen-decomposition of the covariance matrices. The performances of the new models have been studied by simulations and using real datasets in comparison with other models. In order to gain additional flexibility, mixtures of seemingly unrelated contaminated normal regressions models have also been specified so as to allow mixing proportions to be expressed as functions of concomitant covariates. An illustration of the new models with concomitant variables and a study on housing tension in the municipalities of the Emilia-Romagna region based on different types of multivariate linear regression models have been performed.