Learning representations for graph-structured socio-technical systems

The recent widespread use of social media platforms and web services has led to a vast amount of behavioral data that can be used to model socio-technical systems. A significant part of this data can be represented as graphs or networks, which have become the prevalent mathematical framework for studying the structure and the dynamics of complex interacting systems. However, analyzing and understanding these data presents new challenges due to their increasing complexity and diversity. For instance, the characterization of real-world networks includes the need of accounting for their temporal dimension, together with incorporating higher-order interactions beyond the traditional pairwise formalism. The ongoing growth of AI has led to the integration of traditional graph mining techniques with representation learning and low-dimensional embeddings of networks to address current challenges. These methods capture the underlying similarities and geometry of graph-shaped data, generating latent representations that enable the resolution of various tasks, such as link prediction, node classification, and graph clustering. As these techniques gain popularity, there is even a growing concern about their responsible use. In particular, there has been an increased emphasis on addressing the limitations of interpretability in graph representation learning. This thesis contributes to the advancement of knowledge in the field of graph representation learning and has potential applications in a wide range of complex systems domains. We initially focus on forecasting problems related to face-to-face contact networks with time-varying graph embeddings. Then, we study hyperedge prediction and reconstruction with simplicial complex embeddings. Finally, we analyze the problem of interpreting latent dimensions in node embeddings for graphs. The proposed models are extensively evaluated in multiple experimental settings and the results demonstrate their effectiveness and reliability, achieving state-of-the-art performances and providing valuable insights into the properties of the learned representations.

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.

Real-time anomaly detection of gamma-ray bursts for the Cherenkov Telescope Array using deep learning

The Cherenkov Telescope Array (CTA) will be the next-generation ground-based observatory to study the universe in the very-high-energy domain. The observatory will rely on a Science Alert Generation (SAG) system to analyze the real-time data from the telescopes and generate science alerts. The SAG system will play a crucial role in the search and follow-up of transients from external alerts, enabling multi-wavelength and multi-messenger collaborations. It will maximize the potential for the detection of the rarest phenomena, such as gamma-ray bursts (GRBs), which are the science case for this study. This study presents an anomaly detection method based on deep learning for detecting gamma-ray burst events in real-time. The performance of the proposed method is evaluated and compared against the Li&Ma standard technique in two use cases of serendipitous discoveries and follow-up observations, using short exposure times. The method shows promising results in detecting GRBs and is flexible enough to allow real-time search for transient events on multiple time scales. The method does not assume background nor source models and doe not require a minimum number of photon counts to perform analysis, making it well-suited for real-time analysis. Future improvements involve further tests, relaxing some of the assumptions made in this study as well as post-trials correction of the detection significance. Moreover, the ability to detect other transient classes in different scenarios must be investigated for completeness. The system can be integrated within the SAG system of CTA and deployed on the onsite computing clusters. This would provide valuable insights into the method's performance in a real-world setting and be another valuable tool for discovering new transient events in real-time. Overall, this study makes a significant contribution to the field of astrophysics by demonstrating the effectiveness of deep learning-based anomaly detection techniques for real-time source detection in gamma-ray astronomy.

Thermal and air quality modeling of an electric vehicle cabin with low-cost sensors and reinforcement learning

The design process of any electric vehicle system has to be oriented towards the best energy efficiency, together with the constraint of maintaining comfort in the vehicle cabin. Main aim of this study is to research the best thermal management solution in terms of HVAC efficiency without compromising occupant’s comfort and internal air quality. An Arduino controlled Low Cost System of Sensors was developed and compared against reference instrumentation (average R-squared of 0.92) and then used to characterise the vehicle cabin in real parking and driving conditions trials. Data on the energy use of the HVAC was retrieved from the car On-Board Diagnostic port. Energy savings using recirculation can reach 30 %, but pollutants concentration in the cabin builds up in this operating mode. Moreover, the temperature profile appeared strongly nonuniform with air temperature differences up to 10° C. Optimisation methods often require a high number of runs to find the optimal configuration of the system. Fast models proved to be beneficial for these task, while CFD-1D model are usually slower despite the higher level of detail provided. In this work, the collected dataset was used to train a fast ML model of both cabin and HVAC using linear regression. Average scaled RMSE over all trials is 0.4 %, while computation time is 0.0077 ms for each second of simulated time on a laptop computer. Finally, a reinforcement learning environment was built in OpenAI and Stable-Baselines3 using the built-in Proximal Policy Optimisation algorithm to update the policy and seek for the best compromise between comfort, air quality and energy reward terms. The learning curves show an oscillating behaviour overall, with only 2 experiments behaving as expected even if too slow. This result leaves large room for improvement, ranging from the reward function engineering to the expansion of the ML model.

Ethics in the flesh: formalizing moral values in embodied cognition

Values are beliefs or principles that are deemed significant or desirable within a specific society or culture, serving as the fundamental underpinnings for ethical and socio-behavioral norms. The objective of this research is to explore the domain encompassing moral, cultural, and individual values. To achieve this, we employ an ontological approach to formally represent the semantic relations within the value domain. The theoretical framework employed adopts Fillmore’s frame semantics, treating values as semantic frames. A value situation is thus characterized by the co-occurrence of specific semantic roles fulfilled within a given event or circumstance. Given the intricate semantics of values as abstract entities with high social capital, our investigation extends to two interconnected domains. The first domain is embodied cognition, specifically image schemas, which are cognitive patterns derived from sensorimotor experiences that shape our conceptualization of entities in the world. The second domain pertains to emotions, which are inherently intertwined with the realm of values. Consequently, our approach endeavors to formalize the semantics of values within an embodied cognition framework, recognizing values as emotional-laden semantic frames. The primary ontologies proposed in this work are: (i) ValueNet, an ontology network dedicated to the domain of values; (ii) ISAAC, the Image Schema Abstraction And Cognition ontology; and (iii) EmoNet, an ontology for theories of emotions. The knowledge formalization adheres to established modeling practices, including the reuse of semantic web resources such as WordNet, VerbNet, FrameNet, DBpedia, and alignment to foundational ontologies like DOLCE, as well as the utilization of Ontology Design Patterns. These ontological resources are operationalized through the development of a fully explainable frame-based detector capable of identifying values, emotions, and image schemas generating knowledge graphs from from natural language, leveraging the semantic dependencies of a sentence, and allowing non trivial higher layer knowledge inferences.

Data surveillance for infectious diseases: models, complex networks and machine learning

In this thesis, we investigate the role of applied physics in epidemiological surveillance through the application of mathematical models, network science and machine learning. The spread of a communicable disease depends on many biological, social, and health factors. The large masses of data available make it possible, on the one hand, to monitor the evolution and spread of pathogenic organisms; on the other hand, to study the behavior of people, their opinions and habits. Presented here are three lines of research in which an attempt was made to solve real epidemiological problems through data analysis and the use of statistical and mathematical models. In Chapter 1, we applied language-inspired Deep Learning models to transform influenza protein sequences into vectors encoding their information content. We then attempted to reconstruct the antigenic properties of different viral strains using regression models and to identify the mutations responsible for vaccine escape. In Chapter 2, we constructed a compartmental model to describe the spread of a bacterium within a hospital ward. The model was informed and validated on time series of clinical measurements, and a sensitivity analysis was used to assess the impact of different control measures. Finally (Chapter 3) we reconstructed the network of retweets among COVID-19 themed Twitter users in the early months of the SARS-CoV-2 pandemic. By means of community detection algorithms and centrality measures, we characterized users’ attention shifts in the network, showing that scientific communities, initially the most retweeted, lost influence over time to national political communities. In the Conclusion, we highlighted the importance of the work done in light of the main contemporary challenges for epidemiological surveillance. In particular, we present reflections on the importance of nowcasting and forecasting, the relationship between data and scientific research, and the need to unite the different scales of epidemiological surveillance.

Integrated communication and learning towards autonomous mobile radio networks

The integration of distributed and ubiquitous intelligence has emerged over the last years as the mainspring of transformative advancements in mobile radio networks. As we approach the era of “mobile for intelligence”, next-generation wireless networks are poised to undergo significant and profound changes. Notably, the overarching challenge that lies ahead is the development and implementation of integrated communication and learning mechanisms that will enable the realization of autonomous mobile radio networks. The ultimate pursuit of eliminating human-in-the-loop constitutes an ambitious challenge, necessitating a meticulous delineation of the fundamental characteristics that artificial intelligence (AI) should possess to effectively achieve this objective. This challenge represents a paradigm shift in the design, deployment, and operation of wireless networks, where conventional, static configurations give way to dynamic, adaptive, and AI-native systems capable of self-optimization, self-sustainment, and learning. This thesis aims to provide a comprehensive exploration of the fundamental principles and practical approaches required to create autonomous mobile radio networks that seamlessly integrate communication and learning components. The first chapter of this thesis introduces the notion of Predictive Quality of Service (PQoS) and adaptive optimization and expands upon the challenge to achieve adaptable, reliable, and robust network performance in dynamic and ever-changing environments. The subsequent chapter delves into the revolutionary role of generative AI in shaping next-generation autonomous networks. This chapter emphasizes achieving trustworthy uncertainty-aware generation processes with the use of approximate Bayesian methods and aims to show how generative AI can improve generalization while reducing data communication costs. Finally, the thesis embarks on the topic of distributed learning over wireless networks. Distributed learning and its declinations, including multi-agent reinforcement learning systems and federated learning, have the potential to meet the scalability demands of modern data-driven applications, enabling efficient and collaborative model training across dynamic scenarios while ensuring data privacy and reducing communication overhead.

Identificazione e classificazione delle lesioni endocavitarie uterine dalle immagini isteroscopiche con il deep learning

Anche se l'isteroscopia con la biopsia endometriale è il gold standard nella diagnosi della patologia intracavitaria uterina, l'esperienza dell’isteroscopista è fondamentale per una diagnosi corretta. Il Deep Learning (DL) come metodica di intelligenza artificiale potrebbe essere un aiuto per superare questo limite. Sono disponibili pochi studi con risultati preliminari e mancano ricerche che valutano le prestazioni dei modelli di DL nell'identificazione delle lesioni intrauterine e il possibile aiuto derivato dai fattori clinici. Obiettivo: Sviluppare un modello di DL per identificare e classificare le patologie endocavitarie uterine dalle immagini isteroscopiche. Metodi: È stato eseguito uno studio di coorte retrospettivo osservazionale monocentrico su una serie consecutiva di casi isteroscopici di pazienti con patologia intracavitaria uterina confermata all’esame istologico eseguiti al Policlinico S. Orsola. Le immagini isteroscopiche sono state usate per costruire un modello di DL per la classificazione e l'identificazione delle lesioni intracavitarie con e senza l'aiuto di fattori clinici (età, menopausa, AUB, terapia ormonale e tamoxifene). Come risultati dello studio abbiamo calcolato le metriche diagnostiche del modello di DL nella classificazione e identificazione delle lesioni uterine intracavitarie con e senza l'aiuto dei fattori clinici. Risultati: Abbiamo esaminato 1.500 immagini provenienti da 266 casi: 186 pazienti avevano lesioni focali benigne, 25 lesioni diffuse benigne e 55 lesioni preneoplastiche/neoplastiche. Sia per quanto riguarda la classificazione che l’identificazione, le migliori prestazioni sono state raggiunte con l'aiuto dei fattori clinici, complessivamente con precision dell'80,11%, recall dell'80,11%, specificità del 90,06%, F1 score dell’80,11% e accuratezza dell’86,74% per la classificazione. Per l’identificazione abbiamo ottenuto un rilevamento complessivo dell’85,82%, precision 93,12%, recall del 91,63% ed F1 score del 92,37%. Conclusioni: Il modello DL ha ottenuto una bassa performance nell’identificazione e classificazione delle lesioni intracavitarie uterine dalle immagini isteroscopiche. Anche se la migliore performance diagnostica è stata ottenuta con l’aiuto di fattori clinici specifici, questo miglioramento è stato scarso.

Directly training spiking neural networks for cyber-physical systems: from supervised to reinforcement learning

Spiking Neural Networks (SNNs) are bio-inspired Artificial Neural Networks (ANNs) utilizing discrete spiking signals, akin to neuron communication in the brain, making them ideal for real-time and energy-efficient Cyber-Physical Systems (CPSs). This thesis explores their potential in Structural Health Monitoring (SHM), leveraging low-cost MEMS accelerometers for early damage detection in motorway bridges. The study focuses on Long Short-Term SNNs (LSNNs), although their complex learning processes pose challenges. Comparing LSNNs with other ANN models and training algorithms for SHM, findings indicate LSNNs' effectiveness in damage identification, comparable to ANNs trained using traditional methods. Additionally, an optimized embedded LSNN implementation demonstrates a 54% reduction in execution time, but with longer pre-processing due to spike-based encoding. Furthermore, SNNs are applied in UAV obstacle avoidance, trained directly using a Reinforcement Learning (RL) algorithm with event-based input from a Dynamic Vision Sensor (DVS). Performance evaluation against Convolutional Neural Networks (CNNs) highlights SNNs' superior energy efficiency, showing a 6x decrease in energy consumption. The study also investigates embedded SNN implementations' latency and throughput in real-world deployments, emphasizing their potential for energy-efficient monitoring systems. This research contributes to advancing SHM and UAV obstacle avoidance through SNNs' efficient information processing and decision-making capabilities within CPS domains.

Phylogenetic position of the acariform mites: sensitivity to homology assessment under total evidence

Background: Mites (Acari) have traditionally been treated as monophyletic, albeit composed of two major lineages: Acariformes and Parasitiformes. Yet recent studies based on morphology, molecular data, or combinations thereof, have increasingly drawn their monophyly into question. Furthermore, the usually basal (molecular) position of one or both mite lineages among the chelicerates is in conflict to their morphology, and to the widely accepted view that mites are close relatives of Ricinulei. Results: The phylogenetic position of the acariform mites is examined through employing SSU, partial LSU sequences, and morphology from 91 chelicerate extant terminals (forty Acariformes). In a static homology framework, molecular sequences were aligned using their secondary structure as guide, whereby regions of ambiguous alignment were discarded, and pre-aligned sequences analyzed under parsimony and different mixed models in a Bayesian inference. Parsimony and Bayesian analyses led to trees largely congruent concerning infraordinal, well-supported branches, but with low support for inter-ordinal relationships. An exception is Solifugae + Acariformes (P. P = 100%, J. = 0.91). In a dynamic homology framework, two analyses were run: a standard POY analysis and an analysis constrained by secondary structure. Both analyses led to largely congruent trees; supporting a (Palpigradi (Solifugae Acariformes)) clade and Ricinulei as sister group of Tetrapulmonata with the topology (Ricinulei (Amblypygi (Uropygi Araneae))). Combined analysis with two different morphological data matrices were run in order to evaluate the impact of constraining the analysis on the recovered topology when employing secondary structure as a guide for homology establishment. The constrained combined analysis yielded two topologies similar to the exclusively molecular analysis for both morphological matrices, except for the recovery of Pedipalpi instead of the (Uropygi Araneae) clade. The standard (direct optimization) POY analysis, however, led to the recovery of trees differing in the absence of the otherwise well-supported group Solifugae + Acariformes. Conclusions: Previous studies combining ribosomal sequences and morphology often recovered topologies similar to purely morphological analyses of Chelicerata. The apparent stability of certain clades not recovered here, like Haplocnemata and Acari, is regarded as a byproduct of the way the molecular homology was previously established using the instrumentalist approach implemented in POY. Constraining the analysis by a priori homology assessment is defended here as a way of maintaining the severity of the test when adding new data to the analysis. Although the strength of the method advocated here is keeping phylogenetic information from regions usually discarded in an exclusively static homology framework; it still has the inconvenience of being uninformative on the effect of alignment ambiguity on resampling methods of clade support estimation. Finally, putative morphological apomorphies of Solifugae + Acariformes are the reduction of the proximal cheliceral podomere, medial abutting of the leg coxae, loss of sperm nuclear membrane, and presence of differentiated germinative and secretory regions in the testis delivering their products into a common lumen.

Inverse aerodynamic design applications using the MGM hybrid formulation

The well-known modified Garabedian-Mcfadden (MGM) method is an attractive alternative for aerodynamic inverse design, for its simplicity and effectiveness (P. Garabedian and G. Mcfadden, Design of supercritical swept wings, AIAA J. 20(3) (1982), 289-291; J.B. Malone, J. Vadyak, and L.N. Sankar, Inverse aerodynamic design method for aircraft components, J. Aircraft 24(2) (1987), 8-9; Santos, A hybrid optimization method for aerodynamic design of lifting surfaces, PhD Thesis, Georgia Institute of Technology, 1993). Owing to these characteristics, the method has been the subject of several authors over the years (G.S. Dulikravich and D.P. Baker, Aerodynamic shape inverse design using a Fourier series method, in AIAA paper 99-0185, AIAA Aerospace Sciences Meeting, Reno, NV, January 1999; D.H. Silva and L.N. Sankar, An inverse method for the design of transonic wings, in 1992 Aerospace Design Conference, No. 92-1025 in proceedings, AIAA, Irvine, CA, February 1992, 1-11; W. Bartelheimer, An Improved Integral Equation Method for the Design of Transonic Airfoils and Wings, AIAA Inc., 1995). More recently, a hybrid formulation and a multi-point algorithm were developed on the basis of the original MGM. This article discusses applications of those latest developments for airfoil and wing design. The test cases focus on wing-body aerodynamic interference and shock wave removal applications. The DLR-F6 geometry is picked as the baseline for the analysis.

Emily Kame Kngwarreye and the undeconstructible space of justice

Selected as part of an anthology featuring best or most representative of 20th century art writing. Other authors in anthology included Benjamin, Greenberg, Krauss, T.j. Clark, Roger Fry, Stuart Hall, etc. Intended as US textbook. My essay featured as part of study day on globalism in art at Tate Modern. Essay itself subject of PhD thesis by Sally Butler of EMSAH and other subsequent commentaries.

Infiltration effects on sediment mobility under waves

Sediment mobility measurements with a horizontal sand bed under non-breaking waves are reported. Conditions include no seepage and steady downward seepage corresponding to head gradients up to 2.5. The results indicate that infiltration tends to inhibit sediment mobility for a horizontal bcd of 0.2 mm quartz sand exposed to moderated wave induced bed shear stresses. The effect is weak for the parameter range of the present study. The two opposing effects of shear stress increase due to boundary layer thinning and the stabilizing downward drag are successfully accounted for through the modified Shields parameter of Nielsen [Nielsen, P., 1997. Coastal groundwater dynamics. Proc. Coastal Dynamics '97, Plymouth, ASCE, Dp, 546-555] using coefficients derived from independent studies. That is, from the shear stress experiments of Conley [Conley, D.C., 1993. Ventilated oscillatory boundary layers. PhD Thesis, University of California, San Diego, 74 pp.] and the slope stability experiments of Martin and Aral [Martin, C.S. and M.M. Aral, 1971. Seepage force on interfacial bed particles. J. Hydraulics Div., proc. ASCE, Vol. 97, No. Hy7, pp. 1081-1100]. (C) 2001 Elsevier Science B.V. All rights reserved.

Intellectual Capital in a Seaport Context

This poster, which is the result of an ongoing PhD thesis project, illustrates how and why the Intellectual Capital (IC) concept can be applied to a seaport. As far as the authors are aware, most of the research in IC has been focused on individual firms. Although some recent papers examine macro-level organizations, such as regions, none exist on seaports. Also, there is a lack of research related to the ways IC is created and maintained as a dynamic process. In addition, there is a paucity of management sciences’ research on to maritime transportation and seaports. Several research questions are thus pertinent, whose answers can have important strategic and managerial implications for the seaport and its stakeholders.

Mulheres em morte-cor: os objetos que fazem e desfazem corpos e cancros metastáticos

Este texto sintetiza o último capítulo da investigação de doutoramento – Objetos feitos de cancro: a cultura material como pedaço de doença em histórias de mulheres contadas pela arte. Através de uma reflexão em torno dos objetos e materialidades que ganham forma e relevo em projetos artísticos referentes à experiência feminina do cancro, esta tese propõe conceitos alternativos de cultura material e de doença oncológica. Rejeita-se uma separação ou diferenciação entre dimensões materiais e intangíveis na doença, entendendo-se os objetos de cultura material como pedaços de cancro, ou seja, enquanto partes constitutivas das ideias, sensações, emoções e gestos que fazem a experiência do corpo doente. Objetos hospitalares, domésticos e pessoais, de uso coletivo ou individual, onde se incluem materialidades descartáveis, vestuário, mobiliário, equipamento e máquinas, compõem uma lista de realidades que se encastram nas experiências do corpo em diagnóstico, internamento, tratamento, reconstrução, remissão, recorrência, metastização e morte. Dando nome a esta continuidade indivisa, propus os conceitos “objeto nosoencastrável” e “doença modular”, pretendendo, na forma como defino as coisas, os mesmos encaixes que existem na realidade vivida. Para compreender a ação, os usos e os sentidos dos objetos que fazem e são pedaços de cancro(s), o campo de trabalho desta investigação abrangeu as imagens e os textos explicativos de cento e cinquenta projetos artísticos produzidos por ou com mulheres que viveram a experiência desta doença. Expostos na Internet, os exercícios criativos, amadores ou profissionais, de fotografia comercial e artística, pintura, desenho, colagem, modelagem, escultura, costura e tricô serviram de terreno narrativo e visual, permitindo-me encontrar a versão émica dos encaixes entre cultura material e doença. Tocar a continuidade entre objetos e cancros, juntando os saberes do corpo, da arte e da antropologia, assentou numa abordagem teórica e metodológica onde ensaiei o potencial heurístico daquilo a que chamo a “terceira metade das coisas e do conhecimento”.