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.

Peer and group relationships in preschoolers: the role of social and linguistic skills

Being able to positively interact and build relationships with playmates in preschool years is crucial to achieve positive adjustment. An update review and two studies on such topics were provided. Study 1 is observational; it investigates the type of social experience in groups (N = 443) of children (N = 120) at preschool age in child-led vs. teacher-led contexts. The results revealed that in child-led contexts children were more likely to be alone, in dyads, and in small peer groups; groups were mostly characterized by same-gender playmates who engaged in joint interactions, with few social interactions with teachers. In teacher-led contexts, on the other hand, children were more likely to be involved in small, medium and large groups; groups were mostly characterized by other-gender playmates, involved in parallel interactions, with teachers playing a more active role. The purpose of Study 2 was to describe the development of socio-emotional competence, temperamental traits and linguistic skill. It examined the role of children’s reciprocated nominations (=RNs) with peers, assessed via sociometric interview, in relation to socio-emotional competence, temperamental traits and linguistic skill. Finally, the similarity-homophily tendency was investigated. Socio-emotional competence and temperamental traits were assessed via teacher ratings, linguistic skill via test administration. Eighty-four preschool children (M age = 62.53) were recruited within 4 preschool settings. Those children were quite representative of preschool population. The results revealed that children with higher RNs showed higher social competence (tendency), social orientation, positive emotionality, motor activity and linguistic skill. They exhibited lower anxiety-withdrawal. The results also showed that children prefer playmates with similar features: social competence, anger-aggression (tendency), social orientation, positive emotionality, inhibition to innovation, attention, motor activity (tendency) and linguistic skill. Implications for future research were suggested.

Supporting Scientific Research Through Machine and Deep Learning: Fluorescence Microscopy and Operational Intelligence Use Cases

Although the debate of what data science is has a long history and has not reached a complete consensus yet, Data Science can be summarized as the process of learning from data. Guided by the above vision, this thesis presents two independent data science projects developed in the scope of multidisciplinary applied research. The first part analyzes fluorescence microscopy images typically produced in life science experiments, where the objective is to count how many marked neuronal cells are present in each image. Aiming to automate the task for supporting research in the area, we propose a neural network architecture tuned specifically for this use case, cell ResUnet (c-ResUnet), and discuss the impact of alternative training strategies in overcoming particular challenges of our data. The approach provides good results in terms of both detection and counting, showing performance comparable to the interpretation of human operators. As a meaningful addition, we release the pre-trained model and the Fluorescent Neuronal Cells dataset collecting pixel-level annotations of where neuronal cells are located. In this way, we hope to help future research in the area and foster innovative methodologies for tackling similar problems. The second part deals with the problem of distributed data management in the context of LHC experiments, with a focus on supporting ATLAS operations concerning data transfer failures. In particular, we analyze error messages produced by failed transfers and propose a Machine Learning pipeline that leverages the word2vec language model and K-means clustering. This provides groups of similar errors that are presented to human operators as suggestions of potential issues to investigate. The approach is demonstrated on one full day of data, showing promising ability in understanding the message content and providing meaningful groupings, in line with previously reported incidents by human operators.

Populism as a battlefield Populist actors and their representation on social and legacy media during the european parliament elections 2019 in Finland, Italy and the Netherlands

The objective of the present research is to describe and explain populist actors and populism as a concept and their representation on social and legacy media during the 2019 EU elections in Finland, Italy and The Netherlands. This research tackles the topic of European populism in the context of political communication and its relation to both the legacy and digital media within the hybrid media system. Departing from the consideration that populism and populist rhetoric are challenging concepts to define, I suggest that they should be addressed and analyzed through the usage of a combination of methods and theoretical perspectives, namely Communication Studies, Corpus Linguistics, Political theory, Rhetoric and Corpus-Assisted Discourse Studies. This thesis considers data of different provenance. On the one hand, for the Legacy media part, newspapers articles were collected in the three countries under study from the 1st until the 31st of May 2019. Each country’s legacy system is represented by three different quality papers and the articles were collected according to a selection of keywords (European Union Elections and Populism in each of the three languages). On the other hand, the Digital media data takes into consideration Twitter tweets collected during the same timeframe based on particular country-specific hashtags and tweets by identified populist actors. In order to meet the objective of this study, three research questions are posed and the analysis leading to the results are exhaustively presented and further discussed. The results of this research provide valuable and novel insights on how populism as a theme and a concept is being portrayed in the context of the European elections both in legacy and digital media and political communication in general.

Understanding, defining and assessing food systems’ social and economic sustainability indicators: implementation of mixed methodologies for policy insights

Sustainability encompasses the presence of three dimensions that must coexist simultaneously, namely the environmental, social, and economic ones. The economic and social dimensions are gaining the spotlight in recent years, especially within food systems. To assess social and economic impacts, indicators and tools play a fundamental role in contributing to the achievements of sustainability targets, although few of them have deepen the focus on social and economic impacts. Moreover, in a framework of citizen science and bottom-up approach for improving food systems, citizen play a key role in defying their priorities in terms of social and economic interventions. This research expands the knowledge of social and economic sustainability indicators within the food systems for robust policy insights and interventions. This work accomplishes the following objectives: 1) to define social and economic indicators within the supply chain with a stakeholder perspective, 2) to test social and economic sustainability indicators for future food systems engaging young generations. The first objective was accomplished through the development of a systematic literature review of 34 social sustainability tools, based on five food supply chain stages, namely production, processing, wholesale, retail, and consumer considering farmers, workers, consumers, and society as stakeholders. The second objective was achieved by defining and testing new food systems social and economic sustainability indicators through youth engagement for informed and robust policy insights, to provide policymakers suggestions that would incorporate young generations ones. Future food systems scenarios were evaluated by youth through focus groups, whose results were analyzed through NVivo and then through a survey with a wider platform. Conclusion addressed the main areas of policy interventions in terms of social and economic aspects of sustainable food systems youth pointed out as in need of interventions, spanning from food labelling reporting sustainable origins to better access to online food services.

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.

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.

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.

Network analysis and machine learning assist drug repurposing and safety assessment in neurological diseases

In recent decades, two prominent trends have influenced the data modeling field, namely network analysis and machine learning. This thesis explores the practical applications of these techniques within the domain of drug research, unveiling their multifaceted potential for advancing our comprehension of complex biological systems. The research undertaken during this PhD program is situated at the intersection of network theory, computational methods, and drug research. Across six projects presented herein, there is a gradual increase in model complexity. These projects traverse a diverse range of topics, with a specific emphasis on drug repurposing and safety in the context of neurological diseases. The aim of these projects is to leverage existing biomedical knowledge to develop innovative approaches that bolster drug research. The investigations have produced practical solutions, not only providing insights into the intricacies of biological systems, but also allowing the creation of valuable tools for their analysis. In short, the achievements are: • A novel computational algorithm to identify adverse events specific to fixed-dose drug combinations. • A web application that tracks the clinical drug research response to SARS-CoV-2. • A Python package for differential gene expression analysis and the identification of key regulatory "switch genes". • The identification of pivotal events causing drug-induced impulse control disorders linked to specific medications. • An automated pipeline for discovering potential drug repurposing opportunities. • The creation of a comprehensive knowledge graph and development of a graph machine learning model for predictions. Collectively, these projects illustrate diverse applications of data science and network-based methodologies, highlighting the profound impact they can have in supporting drug research activities.