Hybrid Artificial Intelligence to Extract Patterns and Rules from Argumentative and Legal Texts

This Thesis is composed of a collection of works written in the period 2019-2022, whose aim is to find methodologies of Artificial Intelligence (AI) and Machine Learning to detect and classify patterns and rules in argumentative and legal texts. We define our approach “hybrid”, since we aimed at designing hybrid combinations of symbolic and sub-symbolic AI, involving both “top-down” structured knowledge and “bottom-up” data-driven knowledge. A first group of works is dedicated to the classification of argumentative patterns. Following the Waltonian model of argument and the related theory of Argumentation Schemes, these works focused on the detection of argumentative support and opposition, showing that argumentative evidences can be classified at fine-grained levels without resorting to highly engineered features. To show this, our methods involved not only traditional approaches such as TFIDF, but also some novel methods based on Tree Kernel algorithms. After the encouraging results of this first phase, we explored the use of a some emerging methodologies promoted by actors like Google, which have deeply changed NLP since 2018-19 — i.e., Transfer Learning and language models. These new methodologies markedly improved our previous results, providing us with best-performing NLP tools. Using Transfer Learning, we also performed a Sequence Labelling task to recognize the exact span of argumentative components (i.e., claims and premises), thus connecting portions of natural language to portions of arguments (i.e., to the logical-inferential dimension). The last part of our work was finally dedicated to the employment of Transfer Learning methods for the detection of rules and deontic modalities. In this case, we explored a hybrid approach which combines structured knowledge coming from two LegalXML formats (i.e., Akoma Ntoso and LegalRuleML) with sub-symbolic knowledge coming from pre-trained (and then fine-tuned) neural architectures.

Design and testing of innovative, artificial intelligence-based techniques to model and control the combustion process and to reduce the Co2 emissions in modern, high-performance, gasoline direct injection engines

This work deals with the development of calibration procedures and control systems to improve the performance and efficiency of modern spark ignition turbocharged engines. The algorithms developed are used to optimize and manage the spark advance and the air-to-fuel ratio to control the knock and the exhaust gas temperature at the turbine inlet. The described work falls within the activity that the research group started in the previous years with the industrial partner Ferrari S.p.a. . The first chapter deals with the development of a control-oriented engine simulator based on a neural network approach, with which the main combustion indexes can be simulated. The second chapter deals with the development of a procedure to calibrate offline the spark advance and the air-to-fuel ratio to run the engine under knock-limited conditions and with the maximum admissible exhaust gas temperature at the turbine inlet. This procedure is then converted into a model-based control system and validated with a Software in the Loop approach using the engine simulator developed in the first chapter. Finally, it is implemented in a rapid control prototyping hardware to manage the combustion in steady-state and transient operating conditions at the test bench. The third chapter deals with the study of an innovative and cheap sensor for the in-cylinder pressure measurement, which is a piezoelectric washer that can be installed between the spark plug and the engine head. The signal generated by this kind of sensor is studied, developing a specific algorithm to adjust the value of the knock index in real-time. Finally, with the engine simulator developed in the first chapter, it is demonstrated that the innovative sensor can be coupled with the control system described in the second chapter and that the performance obtained could be the same reachable with the standard in-cylinder pressure sensors.

Computational modelling of human stem cell-derived cardiomyocytes - Texture descriptors for biological image processing

This thesis investigates two distinct research topics. The main topic (Part I) is the computational modelling of cardiomyocytes derived from human stem cells, both embryonic (hESC-CM) and induced-pluripotent (hiPSC-CM). The aim of this research line lies in developing models of the electrophysiology of hESC-CM and hiPSC-CM in order to integrate the available experimental data and getting in-silico models to be used for studying/making new hypotheses/planning experiments on aspects not fully understood yet, such as the maturation process, the functionality of the Ca2+ hangling or why the hESC-CM/hiPSC-CM action potentials (APs) show some differences with respect to APs from adult cardiomyocytes. Chapter I.1 introduces the main concepts about hESC-CMs/hiPSC-CMs, the cardiac AP, and computational modelling. Chapter I.2 presents the hESC-CM AP model, able to simulate the maturation process through two developmental stages, Early and Late, based on experimental and literature data. Chapter I.3 describes the hiPSC-CM AP model, able to simulate the ventricular-like and atrial-like phenotypes. This model was used to assess which currents are responsible for the differences between the ventricular-like AP and the adult ventricular AP. The secondary topic (Part II) consists in the study of texture descriptors for biological image processing. Chapter II.1 provides an overview on important texture descriptors such as Local Binary Pattern or Local Phase Quantization. Moreover the non-binary coding and the multi-threshold approach are here introduced. Chapter II.2 shows that the non-binary coding and the multi-threshold approach improve the classification performance of cellular/sub-cellular part images, taken from six datasets. Chapter II.3 describes the case study of the classification of indirect immunofluorescence images of HEp2 cells, used for the antinuclear antibody clinical test. Finally the general conclusions are reported.

CT perfusion image processing: analysis of liver tumors

Perfusion CT imaging of the liver has potential to improve evaluation of tumour angiogenesis. Quantitative parameters can be obtained applying mathematical models to Time Attenuation Curve (TAC). However, there are still some difficulties for an accurate quantification of perfusion parameters due, for example, to algorithms employed, to mathematical model, to patient’s weight and cardiac output and to the acquisition system. In this thesis, new parameters and alternative methodologies about liver perfusion CT are presented in order to investigate the cause of variability of this technique. Firstly analysis were made to assess the variability related to the mathematical model used to compute arterial Blood Flow (BFa) values. Results were obtained implementing algorithms based on “ maximum slope method” and “Dual input one compartment model” . Statistical analysis on simulated data demonstrated that the two methods are not interchangeable. Anyway slope method is always applicable in clinical context. Then variability related to TAC processing in the application of slope method is analyzed. Results compared with manual selection allow to identify the best automatic algorithm to compute BFa. The consistency of a Standardized Perfusion Index (SPV) was evaluated and a simplified calibration procedure was proposed. At the end the quantitative value of perfusion map was analyzed. ROI approach and map approach provide related values of BFa and this means that pixel by pixel algorithm give reliable quantitative results. Also in pixel by pixel approach slope method give better results. In conclusion the development of new automatic algorithms for a consistent computation of BFa and the analysis and definition of simplified technique to compute SPV parameter, represent an improvement in the field of liver perfusion CT analysis.

Inverse Static Analysis of Massive Parallel Arrays of Three-State Actuators via Artificial Intelligence

Massive parallel robots (MPRs) driven by discrete actuators are force regulated robots that undergo continuous motions despite being commanded through a finite number of states only. Designing a real-time control of such systems requires fast and efficient methods for solving their inverse static analysis (ISA), which is a challenging problem and the subject of this thesis. In particular, five Artificial intelligence methods are proposed to investigate the on-line computation and the generalization error of ISA problem of a class of MPRs featuring three-state force actuators and one degree of revolute motion.

Anticancer drug discovery using artificial intelligence: an application in pharmacological activity prediction

Hematological cancers are a heterogeneous family of diseases that can be divided into leukemias, lymphomas, and myelomas, often called “liquid tumors”. Since they cannot be surgically removable, chemotherapy represents the mainstay of their treatment. However, it still faces several challenges like drug resistance and low response rate, and the need for new anticancer agents is compelling. The drug discovery process is long-term, costly, and prone to high failure rates. With the rapid expansion of biological and chemical "big data", some computational techniques such as machine learning tools have been increasingly employed to speed up and economize the whole process. Machine learning algorithms can create complex models with the aim to determine the biological activity of compounds against several targets, based on their chemical properties. These models are defined as multi-target Quantitative Structure-Activity Relationship (mt-QSAR) and can be used to virtually screen small and large chemical libraries for the identification of new molecules with anticancer activity. The aim of my Ph.D. project was to employ machine learning techniques to build an mt-QSAR classification model for the prediction of cytotoxic drugs simultaneously active against 43 hematological cancer cell lines. For this purpose, first, I constructed a large and diversified dataset of molecules extracted from the ChEMBL database. Then, I compared the performance of different ML classification algorithms, until Random Forest was identified as the one returning the best predictions. Finally, I used different approaches to maximize the performance of the model, which achieved an accuracy of 88% by correctly classifying 93% of inactive molecules and 72% of active molecules in a validation set. This model was further applied to the virtual screening of a small dataset of molecules tested in our laboratory, where it showed 100% accuracy in correctly classifying all molecules. This result is confirmed by our previous in vitro experiments.

Advancing digital healthcare research and machine learning-aided knowledge extraction amidst the COVID-19 pandemic

The rapid progression of biomedical research coupled with the explosion of scientific literature has generated an exigent need for efficient and reliable systems of knowledge extraction. This dissertation contends with this challenge through a concentrated investigation of digital health, Artificial Intelligence, and specifically Machine Learning and Natural Language Processing's (NLP) potential to expedite systematic literature reviews and refine the knowledge extraction process. The surge of COVID-19 complicated the efforts of scientists, policymakers, and medical professionals in identifying pertinent articles and assessing their scientific validity. This thesis presents a substantial solution in the form of the COKE Project, an initiative that interlaces machine reading with the rigorous protocols of Evidence-Based Medicine to streamline knowledge extraction. In the framework of the COKE (“COVID-19 Knowledge Extraction framework for next-generation discovery science”) Project, this thesis aims to underscore the capacity of machine reading to create knowledge graphs from scientific texts. The project is remarkable for its innovative use of NLP techniques such as a BERT + bi-LSTM language model. This combination is employed to detect and categorize elements within medical abstracts, thereby enhancing the systematic literature review process. The COKE project's outcomes show that NLP, when used in a judiciously structured manner, can significantly reduce the time and effort required to produce medical guidelines. These findings are particularly salient during times of medical emergency, like the COVID-19 pandemic, when quick and accurate research results are critical.

Effects of artificial defences and flooding on coastal habitats and assemblages

Since large stretches of European coasts are already retreating and projected scenarios are worsening, many artificial structures, such as breakwaters and seawalls, are built as tool against coastal erosion. However artificial structures produce widespread changes that alter the coastal zones and affect the biological communities. My doctoral thesis analyses the consequences of different options for coastal protection, namely hard engineering ‘artificial defences’ (i.e. impact of human-made structures) and ‘no-defence’ (i.e. impact of seawater inundation). I investigated two new aspects of the potential impact of coastal defences. The first was the effect of artificial hard substrates on the fish communities structure. In particular I was interested to test if the differences among breakwaters and natural rocky reef would change depending on the nature of the surrounding habitat of the artificial structure (prevalent sandy rather than rocky). The second was the effect on the native natural sandy habitats of the organic detritus derived from hard-bottom species (green algae and mussels) detached from breakwaters. Furthermore, I investigated the ecological implication of the “no-defend” option, which allow the inundation of coastal habitats. The focus of this study was the potential effect of seawater intrusion on the degradation process of marine, salt-marsh and terrestrial detritus, including changes on the breakdown rates and the associated macrofauna. The PhD research was conducted in three areas along European coasts: North Adriatic sea, Sicilian coast and South-West England where different habitats (coastal, estuarine), biological communities (soft-bottom macro-benthos; rocky-coastal fishes; estuarine macro-invertebrates) and processes (organic enrichment; assemblage structure; leaf-litter breakdown) were analyzed. The research was carried out through manipulative and descriptive field-experiments in which specific hypothesis were tested by univariate and multivariate analyses.

Engineering Agent-Oriented Technologies and Programming Languages for Computer Programming and Software Development

Mainstream hardware is becoming parallel, heterogeneous, and distributed on every desk, every home and in every pocket. As a consequence, in the last years software is having an epochal turn toward concurrency, distribution, interaction which is pushed by the evolution of hardware architectures and the growing of network availability. This calls for introducing further abstraction layers on top of those provided by classical mainstream programming paradigms, to tackle more effectively the new complexities that developers have to face in everyday programming. A convergence it is recognizable in the mainstream toward the adoption of the actor paradigm as a mean to unite object-oriented programming and concurrency. Nevertheless, we argue that the actor paradigm can only be considered a good starting point to provide a more comprehensive response to such a fundamental and radical change in software development. Accordingly, the main objective of this thesis is to propose Agent-Oriented Programming (AOP) as a high-level general purpose programming paradigm, natural evolution of actors and objects, introducing a further level of human-inspired concepts for programming software systems, meant to simplify the design and programming of concurrent, distributed, reactive/interactive programs. To this end, in the dissertation first we construct the required background by studying the state-of-the-art of both actor-oriented and agent-oriented programming, and then we focus on the engineering of integrated programming technologies for developing agent-based systems in their classical application domains: artificial intelligence and distributed artificial intelligence. Then, we shift the perspective moving from the development of intelligent software systems, toward general purpose software development. Using the expertise maturated during the phase of background construction, we introduce a general-purpose programming language named simpAL, which founds its roots on general principles and practices of software development, and at the same time provides an agent-oriented level of abstraction for the engineering of general purpose software systems.

Reverse Engineering tools: development and experimentation of innovative methods for physical and geometrical data integration and post-processing

In recent years, the use of Reverse Engineering systems has got a considerable interest for a wide number of applications. Therefore, many research activities are focused on accuracy and precision of the acquired data and post processing phase improvements. In this context, this PhD Thesis deals with the definition of two novel methods for data post processing and data fusion between physical and geometrical information. In particular a technique has been defined for error definition in 3D points’ coordinates acquired by an optical triangulation laser scanner, with the aim to identify adequate correction arrays to apply under different acquisition parameters and operative conditions. Systematic error in data acquired is thus compensated, in order to increase accuracy value. Moreover, the definition of a 3D thermogram is examined. Object geometrical information and its thermal properties, coming from a thermographic inspection, are combined in order to have a temperature value for each recognizable point. Data acquired by an optical triangulation laser scanner are also used to normalize temperature values and make thermal data independent from thermal-camera point of view.

Continual learning for computer vision applications

One of the most visionary goals of Artificial Intelligence is to create a system able to mimic and eventually surpass the intelligence observed in biological systems including, ambitiously, the one observed in humans. The main distinctive strength of humans is their ability to build a deep understanding of the world by learning continuously and drawing from their experiences. This ability, which is found in various degrees in all intelligent biological beings, allows them to adapt and properly react to changes by incrementally expanding and refining their knowledge. Arguably, achieving this ability is one of the main goals of Artificial Intelligence and a cornerstone towards the creation of intelligent artificial agents. Modern Deep Learning approaches allowed researchers and industries to achieve great advancements towards the resolution of many long-standing problems in areas like Computer Vision and Natural Language Processing. However, while this current age of renewed interest in AI allowed for the creation of extremely useful applications, a concerningly limited effort is being directed towards the design of systems able to learn continuously. The biggest problem that hinders an AI system from learning incrementally is the catastrophic forgetting phenomenon. This phenomenon, which was discovered in the 90s, naturally occurs in Deep Learning architectures where classic learning paradigms are applied when learning incrementally from a stream of experiences. This dissertation revolves around the Continual Learning field, a sub-field of Machine Learning research that has recently made a comeback following the renewed interest in Deep Learning approaches. This work will focus on a comprehensive view of continual learning by considering algorithmic, benchmarking, and applicative aspects of this field. This dissertation will also touch on community aspects such as the design and creation of research tools aimed at supporting Continual Learning research, and the theoretical and practical aspects concerning public competitions in this field.

Movement analysis on the field in young football players: biomechanical patterns of performance and injury prevention

The integration of quantitative data from movement analysis technologies is reshaping the analysis of athletes’ performances and injury mitigation, e.g., anterior cruciate ligament (ACL) rupture. Most of the movement assessments are performed in laboratory environments. Recent progress provides the chance to shift the paradigm to a more ecological approach with sport-specific elements and a closer examination of “real” movement patterns associated with performance and (ACL) injury risk. The present PhD thesis aimed at investigating the on-field motion patterns related to performance and injury prevention in young football players. The objectives of the thesis were: (I) in-lab measures of high-dynamics movements were used to validate wearable inertial sensors technology; (II) in-laboratory and on-field agility movement tasks were compared to inspect the effect of football-specific environment; (III) on-field analysis was conducted to challenge wearable sensors technology in the assessment of dangerous movement patterns towards the ACL rupture; (IV) an overview of technologies that could shape present and future assessment of ACL injury risk in daily practice was presented. The validity of wearables in the assessment of high-dynamics movements was confirmed. Relevant differences emerged between the movements performed in a laboratory setting and on the football pitch, supporting the inclusion of an ecological dynamics approach in preventive protocols. The on-field analysis of football-specific movement tasks demonstrated good reliability of wearable sensors and the presence of residual dangerous patterns in the injured players. A tool to inspect at-risk movement patterns on the field through objective measurements was presented. It discussed how potential alternatives to wearable inertial sensors embrace artificial intelligence and closer collaboration between clinical and technical expertise. The present thesis was meant to contribute to setting the basis for data-driven prevention protocols. A deeper comprehension of injury-related principles and counteractions will contribute to preserving athletes’ careers and health over time.

Adaptive Neural Translation for Enterprises (ANTE). La traduzione automatica neurale a sostegno delle imprese emiliano-romagnole

Il progetto ANTE riguarda i nuovi sistemi di traduzione automatica (TA) e la loro applicazione nel mondo delle imprese. Lo studio prende spunto dai recenti sviluppi legati all’intelligenza artificiale e ai Big Data che negli ultimi anni hanno permesso alla TA di raggiungere livelli qualitativi molto elevati, al punto tale da essere impiegata da grandi multinazionali per raggiungere nuove quote di mercato. La TA può rispondere positivamente anche ai bisogni delle imprese di piccole dimensioni e a basso tenore tecnologico, migliorando la qualità delle comunicazioni multilingue attraverso delle traduzioni in tempi brevi e a costi contenuti. Lo studio si propone quindi di contribuire al rafforzamento della competitività internazionale delle piccole e medie imprese (PMI) emiliano- romagnole, migliorando la loro capacità di comunicazione in una o più lingue straniere attraverso l’introduzione e l’utilizzo efficace e consapevole di soluzioni ICT di ultima generazione e fornire, così, nuove opportunità di internazionalizzazione.

How to explain: from theory to practice

Today we live in an age where the internet and artificial intelligence allow us to search for information through impressive amounts of data, opening up revolutionary new ways to make sense of reality and understand our world. However, it is still an area of improvement to exploit the full potential of large amounts of explainable information by distilling it automatically in an intuitive and user-centred explanation. For instance, different people (or artificial agents) may search for and request different types of information in a different order, so it is unlikely that a short explanation can suffice for all needs in the most generic case. Moreover, dumping a large portion of explainable information in a one-size-fits-all representation may also be sub-optimal, as the needed information may be scarce and dispersed across hundreds of pages. The aim of this work is to investigate how to automatically generate (user-centred) explanations from heterogeneous and large collections of data, with a focus on the concept of explanation in a broad sense, as a critical artefact for intelligence, regardless of whether it is human or robotic. Our approach builds on and extends Achinstein’s philosophical theory of explanations, where explaining is an illocutionary (i.e., broad but relevant) act of usefully answering questions. Specifically, we provide the theoretical foundations of Explanatory Artificial Intelligence (YAI), formally defining a user-centred explanatory tool and the space of all possible explanations, or explanatory space, generated by it. We present empirical results in support of our theory, showcasing the implementation of YAI tools and strategies for assessing explainability. To justify and evaluate the proposed theories and models, we considered case studies at the intersection of artificial intelligence and law, particularly European legislation. Our tools helped produce better explanations of software documentation and legal texts for humans and complex regulations for reinforcement learning agents.

Anatomical biomarkers of body composition in oncological population: application and development of artificial intelligences

In the Era of precision medicine and big medical data sharing, it is necessary to solve the work-flow of digital radiological big data in a productive and effective way. In particular, nowadays, it is possible to extract information “hidden” in digital images, in order to create diagnostic algorithms helping clinicians to set up more personalized therapies, which are in particular targets of modern oncological medicine. Digital images generated by the patient have a “texture” structure that is not visible but encrypted; it is “hidden” because it cannot be recognized by sight alone. Thanks to artificial intelligence, pre- and post-processing software and generation of mathematical calculation algorithms, we could perform a classification based on non-visible data contained in radiological images. Being able to calculate the volume of tissue body composition could lead to creating clasterized classes of patients inserted in standard morphological reference tables, based on human anatomy distinguished by gender and age, and maybe in future also by race. Furthermore, the branch of “morpho-radiology" is a useful modality to solve problems regarding personalized therapies, which is particularly needed in the oncological field. Actually oncological therapies are no longer based on generic drugs but on target personalized therapy. The lack of gender and age therapies table could be filled thanks to morpho-radiology data analysis application.