Efficient ultrasonic signal processing techniques for aided medical diagnostics

Ultrasound imaging is widely used in medical diagnostics as it is the fastest, least invasive, and least expensive imaging modality. However, ultrasound images are intrinsically difficult to be interpreted. In this scenario, Computer Aided Detection (CAD) systems can be used to support physicians during diagnosis providing them a second opinion. This thesis discusses efficient ultrasound processing techniques for computer aided medical diagnostics, focusing on two major topics: (i) Ultrasound Tissue Characterization (UTC), aimed at characterizing and differentiating between healthy and diseased tissue; (ii) Ultrasound Image Segmentation (UIS), aimed at detecting the boundaries of anatomical structures to automatically measure organ dimensions and compute clinically relevant functional indices. Research on UTC produced a CAD tool for Prostate Cancer detection to improve the biopsy protocol. In particular, this thesis contributes with: (i) the development of a robust classification system; (ii) the exploitation of parallel computing on GPU for real-time performance; (iii) the introduction of both an innovative Semi-Supervised Learning algorithm and a novel supervised/semi-supervised learning scheme for CAD system training that improve system performance reducing data collection effort and avoiding collected data wasting. The tool provides physicians a risk map highlighting suspect tissue areas, allowing them to perform a lesion-directed biopsy. Clinical validation demonstrated the system validity as a diagnostic support tool and its effectiveness at reducing the number of biopsy cores requested for an accurate diagnosis. For UIS the research developed a heart disease diagnostic tool based on Real-Time 3D Echocardiography. Thesis contributions to this application are: (i) the development of an automated GPU based level-set segmentation framework for 3D images; (ii) the application of this framework to the myocardium segmentation. Experimental results showed the high efficiency and flexibility of the proposed framework. Its effectiveness as a tool for quantitative analysis of 3D cardiac morphology and function was demonstrated through clinical validation.

Topics in climate change risk

In this Thesis, we analyze how climate risk impacts economic players and its consequences on the financial markets. Essentially, literature unravels two main channels through which climate change poses risks to the status quo, namely physical and transitional risk, that we cover in three works. Firstly, the call for a global shift to a net-zero economy implicitly devalues assets that contribute to global warming that regulators are forcing to dismiss. On the other hand, abnormal changes in the temperatures as well as weather-related events challenge the environmental equilibrium and could directly affect operations as well as profitability. We start the analysis with the physical component, by presenting a statistical measure that generally represents shocks to the distribution of temperature anomalies. We oppose this statistic to classical physical measures and assess that it is the driver of the electricity consumption, in the weather derivatives market, and in the cross-section of equity returns. We find two transmission channels, namely investor attention, and firm operations. We then analyze the transition risk component, by associating a regulatory horizon characterization to fixed income valuation. We disentangle a risk driver for corporate bond overperformance that is tight to change in credit riskiness. After controlling a statistical learning algorithm to forecast excess returns, we include carbon emission metrics without clear evidence. Finally, we analyze the effects of change in carbon emission on a regulated market such as the EU ETS by selecting utility sector corporate bond and, after controlling for the possible risk factor, we document how a firm’s carbon profile differently affects the term structure of credit riskiness.

Mathematical methods to analyze and interpret calcium signals of astrocytes

Astrocytes are the most numerous glial cell type in the mammalian brain and permeate the entire CNS interacting with neurons, vasculature, and other glial cells. Astrocytes display intracellular calcium signals that encode information about local synaptic function, distributed network activity, and high-level cognitive functions. Several studies have investigated the calcium dynamics of astrocytes in sensory areas and have shown that these cells can encode sensory stimuli. Nevertheless, only recently the neuro-scientific community has focused its attention on the role and functions of astrocytes in associative areas such as the hippocampus. In our first study, we used the information theory formalism to show that astrocytes in the CA1 area of the hippocampus recorded with 2-photon fluorescence microscopy during spatial navigation encode spatial information that is complementary and synergistic to information encoded by nearby "place cell" neurons. In our second study, we investigated various computational aspects of applying the information theory formalism to astrocytic calcium data. For this reason, we generated realistic simulations of calcium signals in astrocytes to determine optimal hyperparameters and procedures of information measures and applied them to real astrocytic calcium imaging data. Calcium signals of astrocytes are characterized by complex spatiotemporal dynamics occurring in subcellular parcels of the astrocytic domain which makes studying these cells in 2-photon calcium imaging recordings difficult. However, current analytical tools which identify the astrocytic subcellular regions are time consuming and extensively rely on user-defined parameters. Here, we present Rapid Astrocytic calcium Spatio-Temporal Analysis (RASTA), a novel machine learning algorithm for spatiotemporal semantic segmentation of 2-photon calcium imaging recordings of astrocytes which operates without human intervention. We found that RASTA provided fast and accurate identification of astrocytic cell somata, processes, and cellular domains, extracting calcium signals from identified regions of interest across individual cells and populations of hundreds of astrocytes recorded in awake mice.

Radio frequency communication and fault detection for railway signalling

The continuous and swift progression of both wireless and wired communication technologies in today's world owes its success to the foundational systems established earlier. These systems serve as the building blocks that enable the enhancement of services to cater to evolving requirements. Studying the vulnerabilities of previously designed systems and their current usage leads to the development of new communication technologies replacing the old ones such as GSM-R in the railway field. The current industrial research has a specific focus on finding an appropriate telecommunication solution for railway communications that will replace the GSM-R standard which will be switched off in the next years. Various standardization organizations are currently exploring and designing a radiofrequency technology based standard solution to serve railway communications in the form of FRMCS (Future Railway Mobile Communication System) to substitute the current GSM-R. Bearing on this topic, the primary strategic objective of the research is to assess the feasibility to leverage on the current public network technologies such as LTE to cater to mission and safety critical communication for low density lines. The research aims to identify the constraints, define a service level agreement with telecom operators, and establish the necessary implementations to make the system as reliable as possible over an open and public network, while considering safety and cybersecurity aspects. The LTE infrastructure would be utilized to transmit the vital data for the communication of a railway system and to gather and transmit all the field measurements to the control room for maintenance purposes. Given the significance of maintenance activities in the railway sector, the ongoing research includes the implementation of a machine learning algorithm to detect railway equipment faults, reducing time and human analysis errors due to the large volume of measurements from the field.

Novel methods of state estimation and parameter identification for high-performance motorcycles

This research activity aims at providing a reliable estimation of particular state variables or parameters concerning the dynamics and performance optimization of a MotoGP-class motorcycle, integrating the classical model-based approach with new methodologies involving artificial intelligence. The first topic of the research focuses on the estimation of the thermal behavior of the MotoGP carbon braking system. Numerical tools are developed to assess the instantaneous surface temperature distribution in the motorcycle's front brake discs. Within this application other important brake parameters are identified using Kalman filters, such as the disc convection coefficient and the power distribution in the disc-pads contact region. Subsequently, a physical model of the brake is built to estimate the instantaneous braking torque. However, the results obtained with this approach are highly limited by the knowledge of the friction coefficient (μ) between the disc rotor and the pads. Since the value of μ is a highly nonlinear function of many variables (namely temperature, pressure and angular velocity of the disc), an analytical model for the friction coefficient estimation appears impractical to establish. To overcome this challenge, an innovative hybrid solution is implemented, combining the benefit of artificial intelligence (AI) with classical model-based approach. Indeed, the disc temperature estimated through the thermal model previously implemented is processed by a machine learning algorithm that outputs the actual value of the friction coefficient thus improving the braking torque computation performed by the physical model of the brake. Finally, the last topic of this research activity regards the development of an AI algorithm to estimate the current sideslip angle of the motorcycle's front tire. While a single-track motorcycle kinematic model and IMU accelerometer signals theoretically enable sideslip calculation, the presence of accelerometer noise leads to a significant drift over time. To address this issue, a long short-term memory (LSTM) network is implemented.

Kinematic description of the rupture from strong motion data: strategies for a robust inversion

We present a non linear technique to invert strong motion records with the aim of obtaining the final slip and rupture velocity distributions on the fault plane. In this thesis, the ground motion simulation is obtained evaluating the representation integral in the frequency. The Green’s tractions are computed using the discrete wave-number integration technique that provides the full wave-field in a 1D layered propagation medium. The representation integral is computed through a finite elements technique, based on a Delaunay’s triangulation on the fault plane. The rupture velocity is defined on a coarser regular grid and rupture times are computed by integration of the eikonal equation. For the inversion, the slip distribution is parameterized by 2D overlapping Gaussian functions, which can easily relate the spectrum of the possible solutions with the minimum resolvable wavelength, related to source-station distribution and data processing. The inverse problem is solved by a two-step procedure aimed at separating the computation of the rupture velocity from the evaluation of the slip distribution, the latter being a linear problem, when the rupture velocity is fixed. The non-linear step is solved by optimization of an L2 misfit function between synthetic and real seismograms, and solution is searched by the use of the Neighbourhood Algorithm. The conjugate gradient method is used to solve the linear step instead. The developed methodology has been applied to the M7.2, Iwate Nairiku Miyagi, Japan, earthquake. The estimated magnitude seismic moment is 2.6326 dyne∙cm that corresponds to a moment magnitude MW 6.9 while the mean the rupture velocity is 2.0 km/s. A large slip patch extends from the hypocenter to the southern shallow part of the fault plane. A second relatively large slip patch is found in the northern shallow part. Finally, we gave a quantitative estimation of errors associates with the parameters.

Methodological improvement of 3D fluoroscopic analysis for the robust quantification of 3D kinematics of human joints

3D video-fluoroscopy is an accurate but cumbersome technique to estimate natural or prosthetic human joint kinematics. This dissertation proposes innovative methodologies to improve the 3D fluoroscopic analysis reliability and usability. Being based on direct radiographic imaging of the joint, and avoiding soft tissue artefact that limits the accuracy of skin marker based techniques, the fluoroscopic analysis has a potential accuracy of the order of mm/deg or better. It can provide fundamental informations for clinical and methodological applications, but, notwithstanding the number of methodological protocols proposed in the literature, time consuming user interaction is exploited to obtain consistent results. The user-dependency prevented a reliable quantification of the actual accuracy and precision of the methods, and, consequently, slowed down the translation to the clinical practice. The objective of the present work was to speed up this process introducing methodological improvements in the analysis. In the thesis, the fluoroscopic analysis was characterized in depth, in order to evaluate its pros and cons, and to provide reliable solutions to overcome its limitations. To this aim, an analytical approach was followed. The major sources of error were isolated with in-silico preliminary studies as: (a) geometric distortion and calibration errors, (b) 2D images and 3D models resolutions, (c) incorrect contour extraction, (d) bone model symmetries, (e) optimization algorithm limitations, (f) user errors. The effect of each criticality was quantified, and verified with an in-vivo preliminary study on the elbow joint. The dominant source of error was identified in the limited extent of the convergence domain for the local optimization algorithms, which forced the user to manually specify the starting pose for the estimating process. To solve this problem, two different approaches were followed: to increase the optimal pose convergence basin, the local approach used sequential alignments of the 6 degrees of freedom in order of sensitivity, or a geometrical feature-based estimation of the initial conditions for the optimization; the global approach used an unsupervised memetic algorithm to optimally explore the search domain. The performances of the technique were evaluated with a series of in-silico studies and validated in-vitro with a phantom based comparison with a radiostereometric gold-standard. The accuracy of the method is joint-dependent, and for the intact knee joint, the new unsupervised algorithm guaranteed a maximum error lower than 0.5 mm for in-plane translations, 10 mm for out-of-plane translation, and of 3 deg for rotations in a mono-planar setup; and lower than 0.5 mm for translations and 1 deg for rotations in a bi-planar setups. The bi-planar setup is best suited when accurate results are needed, such as for methodological research studies. The mono-planar analysis may be enough for clinical application when the analysis time and cost may be an issue. A further reduction of the user interaction was obtained for prosthetic joints kinematics. A mixed region-growing and level-set segmentation method was proposed and halved the analysis time, delegating the computational burden to the machine. In-silico and in-vivo studies demonstrated that the reliability of the new semiautomatic method was comparable to a user defined manual gold-standard. The improved fluoroscopic analysis was finally applied to a first in-vivo methodological study on the foot kinematics. Preliminary evaluations showed that the presented methodology represents a feasible gold-standard for the validation of skin marker based foot kinematics protocols.

A numerical methodology for the multi-objective optimization of the DI Diesel engine combustion

DI Diesel engine are widely used both for industrial and automotive applications due to their durability and fuel economy. Nonetheless, increasing environmental concerns force that type of engine to comply with increasingly demanding emission limits, so that, it has become mandatory to develop a robust design methodology of the DI Diesel combustion system focused on reduction of soot and NOx simultaneously while maintaining a reasonable fuel economy. In recent years, genetic algorithms and CFD three-dimensional combustion simulations have been successfully applied to that kind of problem. However, combining GAs optimization with actual CFD three-dimensional combustion simulations can be too onerous since a large number of calculations is usually needed for the genetic algorithm to converge, resulting in a high computational cost and, thus, limiting the suitability of this method for industrial processes. In order to make the optimization process less time-consuming, CFD simulations can be more conveniently used to generate a training set for the learning process of an artificial neural network which, once correctly trained, can be used to forecast the engine outputs as a function of the design parameters during a GA optimization performing a so-called virtual optimization. In the current work, a numerical methodology for the multi-objective virtual optimization of the combustion of an automotive DI Diesel engine, which relies on artificial neural networks and genetic algorithms, was developed.

Development of numerical methodologies to predict the liquid fuel sprays - wall interaction to optimize the mixing process of direct injection spark ignition engines

Nowadays the development of new Internal Combustion Engines is mainly driven by the need to reduce tailpipe emissions of pollutants, Green-House Gases and avoid the fossil fuels wasting. The design of dimension and shape of the combustion chamber together with the implementation of different injection strategies e.g., injection timing, spray targeting, higher injection pressure, play a key role in the accomplishment of the aforementioned targets. As far as the match between the fuel injection and evaporation and the combustion chamber shape is concerned, the assessment of the interaction between the liquid fuel spray and the engine walls in gasoline direct injection engines is crucial. The use of numerical simulations is an acknowledged technique to support the study of new technological solutions such as the design of new gasoline blends and of tailored injection strategies to pursue the target mixture formation. The current simulation framework lacks a well-defined best practice for the liquid fuel spray interaction simulation, which is a complex multi-physics problem. This thesis deals with the development of robust methodologies to approach the numerical simulation of the liquid fuel spray interaction with walls and lubricants. The accomplishment of this task was divided into three tasks: i) setup and validation of spray-wall impingement three-dimensional CFD spray simulations; ii) development of a one-dimensional model describing the liquid fuel – lubricant oil interaction; iii) development of a machine learning based algorithm aimed to define which mixture of known pure components mimics the physical behaviour of the real gasoline for the simulation of the liquid fuel spray interaction.

Robust Adaptive Control with Applications to Multi-Agent Systems and Mobile Robotics

This thesis deals with robust adaptive control and its applications, and it is divided into three main parts. The first part is about the design of robust estimation algorithms based on recursive least squares. First, we present an estimator for the frequencies of biased multi-harmonic signals, and then an algorithm for distributed estimation of an unknown parameter over a network of adaptive agents. In the second part of this thesis, we consider a cooperative control problem over uncertain networks of linear systems and Kuramoto systems, in which the agents have to track the reference generated by a leader exosystem. Since the reference signal is not available to each network node, novel distributed observers are designed so as to reconstruct the reference signal locally for each agent, and therefore decentralizing the problem. In the third and final part of this thesis, we consider robust estimation tasks for mobile robotics applications. In particular, we first consider the problem of slip estimation for agricultural tracked vehicles. Then, we consider a search and rescue application in which we need to drive an unmanned aerial vehicle as close as possible to the unknown (and to be estimated) position of a victim, who is buried under the snow after an avalanche event. In this thesis, robustness is intended as an input-to-state stability property of the proposed identifiers (sometimes referred to as adaptive laws), with respect to additive disturbances, and relative to a steady-state trajectory that is associated with a correct estimation of the unknown parameter to be found.

Methods for integrating machine learning and constrained optimization

In the framework of industrial problems, the application of Constrained Optimization is known to have overall very good modeling capability and performance and stands as one of the most powerful, explored, and exploited tool to address prescriptive tasks. The number of applications is huge, ranging from logistics to transportation, packing, production, telecommunication, scheduling, and much more. The main reason behind this success is to be found in the remarkable effort put in the last decades by the OR community to develop realistic models and devise exact or approximate methods to solve the largest variety of constrained or combinatorial optimization problems, together with the spread of computational power and easily accessible OR software and resources. On the other hand, the technological advancements lead to a data wealth never seen before and increasingly push towards methods able to extract useful knowledge from them; among the data-driven methods, Machine Learning techniques appear to be one of the most promising, thanks to its successes in domains like Image Recognition, Natural Language Processes and playing games, but also the amount of research involved. The purpose of the present research is to study how Machine Learning and Constrained Optimization can be used together to achieve systems able to leverage the strengths of both methods: this would open the way to exploiting decades of research on resolution techniques for COPs and constructing models able to adapt and learn from available data. In the first part of this work, we survey the existing techniques and classify them according to the type, method, or scope of the integration; subsequently, we introduce a novel and general algorithm devised to inject knowledge into learning models through constraints, Moving Target. In the last part of the thesis, two applications stemming from real-world projects and done in collaboration with Optit will be presented.

A machine learning based method to detect genomic imbalances exploiting X chromosome exome reads

Whole Exome Sequencing (WES) is rapidly becoming the first-tier test in clinics, both thanks to its declining costs and the development of new platforms that help clinicians in the analysis and interpretation of SNV and InDels. However, we still know very little on how CNV detection could increase WES diagnostic yield. A plethora of exome CNV callers have been published over the years, all showing good performances towards specific CNV classes and sizes, suggesting that the combination of multiple tools is needed to obtain an overall good detection performance. Here we present TrainX, a ML-based method for calling heterozygous CNVs in WES data using EXCAVATOR2 Normalized Read Counts. We select males and females’ non pseudo-autosomal chromosome X alignments to construct our dataset and train our model, make predictions on autosomes target regions and use HMM to call CNVs. We compared TrainX against a set of CNV tools differing for the detection method (GATK4 gCNV, ExomeDepth, DECoN, CNVkit and EXCAVATOR2) and found that our algorithm outperformed them in terms of stability, as we identified both deletions and duplications with good scores (0.87 and 0.82 F1-scores respectively) and for sizes reaching the minimum resolution of 2 target regions. We also evaluated the method robustness using a set of WES and SNP array data (n=251), part of the Italian cohort of Epi25 collaborative, and were able to retrieve all clinical CNVs previously identified by the SNP array. TrainX showed good accuracy in detecting heterozygous CNVs of different sizes, making it a promising tool to use in a diagnostic setting.

The three-dimensional single-bin-size bin packing problem: combining metaheuristic and machine learning approaches

The Three-Dimensional Single-Bin-Size Bin Packing Problem is one of the most studied problem in the Cutting & Packing category. From a strictly mathematical point of view, it consists of packing a finite set of strongly heterogeneous “small” boxes, called items, into a finite set of identical “large” rectangles, called bins, minimizing the unused volume and requiring that the items are packed without overlapping. The great interest is mainly due to the number of real-world applications in which it arises, such as pallet and container loading, cutting objects out of a piece of material and packaging design. Depending on these real-world applications, more objective functions and more practical constraints could be needed. After a brief discussion about the real-world applications of the problem and a exhaustive literature review, the design of a two-stage algorithm to solve the aforementioned problem is presented. The algorithm must be able to provide the spatial coordinates of the placed boxes vertices and also the optimal boxes input sequence, while guaranteeing geometric, stability, fragility constraints and a reduced computational time. Due to NP-hard complexity of this type of combinatorial problems, a fusion of metaheuristic and machine learning techniques is adopted. In particular, a hybrid genetic algorithm coupled with a feedforward neural network is used. In the first stage, a rich dataset is created starting from a set of real input instances provided by an industrial company and the feedforward neural network is trained on it. After its training, given a new input instance, the hybrid genetic algorithm is able to run using the neural network output as input parameter vector, providing as output the optimal solution. The effectiveness of the proposed works is confirmed via several experimental tests.

Statistical learning of random probability measures

The study of random probability measures is a lively research topic that has attracted interest from different fields in recent years. In this thesis, we consider random probability measures in the context of Bayesian nonparametrics, where the law of a random probability measure is used as prior distribution, and in the context of distributional data analysis, where the goal is to perform inference given avsample from the law of a random probability measure. The contributions contained in this thesis can be subdivided according to three different topics: (i) the use of almost surely discrete repulsive random measures (i.e., whose support points are well separated) for Bayesian model-based clustering, (ii) the proposal of new laws for collections of random probability measures for Bayesian density estimation of partially exchangeable data subdivided into different groups, and (iii) the study of principal component analysis and regression models for probability distributions seen as elements of the 2-Wasserstein space. Specifically, for point (i) above we propose an efficient Markov chain Monte Carlo algorithm for posterior inference, which sidesteps the need of split-merge reversible jump moves typically associated with poor performance, we propose a model for clustering high-dimensional data by introducing a novel class of anisotropic determinantal point processes, and study the distributional properties of the repulsive measures, shedding light on important theoretical results which enable more principled prior elicitation and more efficient posterior simulation algorithms. For point (ii) above, we consider several models suitable for clustering homogeneous populations, inducing spatial dependence across groups of data, extracting the characteristic traits common to all the data-groups, and propose a novel vector autoregressive model to study of growth curves of Singaporean kids. Finally, for point (iii), we propose a novel class of projected statistical methods for distributional data analysis for measures on the real line and on the unit-circle.

Big Data approaches as a support for precision livestock farming techniques

With the advent of new technologies it is increasingly easier to find data of different nature from even more accurate sensors that measure the most disparate physical quantities and with different methodologies. The collection of data thus becomes progressively important and takes the form of archiving, cataloging and online and offline consultation of information. Over time, the amount of data collected can become so relevant that it contains information that cannot be easily explored manually or with basic statistical techniques. The use of Big Data therefore becomes the object of more advanced investigation techniques, such as Machine Learning and Deep Learning. In this work some applications in the world of precision zootechnics and heat stress accused by dairy cows are described. Experimental Italian and German stables were involved for the training and testing of the Random Forest algorithm, obtaining a prediction of milk production depending on the microclimatic conditions of the previous days with satisfactory accuracy. Furthermore, in order to identify an objective method for identifying production drops, compared to the Wood model, typically used as an analytical model of the lactation curve, a Robust Statistics technique was used. Its application on some sample lactations and the results obtained allow us to be confident about the use of this method in the future.