Automated Analysis Methods for the Assessment of Bicycle Infrastructure and Demand

A first phase of the research activity has been related to the study of the state of art of the infrastructures for cycling, bicycle use and methods for evaluation. In this part, the candidate has studied the "bicycle system" in countries with high bicycle use and in particular in the Netherlands. Has been carried out an evaluation of the questionnaires of the survey conducted within the European project BICY on mobility in general in 13 cities of the participating countries. The questionnaire was designed, tested and implemented, and was later validated by a test in Bologna. The results were corrected with information on demographic situation and compared with official data. The cycling infrastructure analysis was conducted on the basis of information from the OpenStreetMap database. The activity consisted in programming algorithms in Python that allow to extract data from the database infrastructure for a region, to sort and filter cycling infrastructure calculating some attributes, such as the length of the arcs paths. The results obtained were compared with official data where available. The structure of the thesis is as follows: 1. Introduction: description of the state of cycling in several advanced countries, description of methods of analysis and their importance to implement appropriate policies for cycling. Supply and demand of bicycle infrastructures. 2. Survey on mobility: it gives details of the investigation developed and the method of evaluation. The results obtained are presented and compared with official data. 3. Analysis cycling infrastructure based on information from the database of OpenStreetMap: describes the methods and algorithms developed during the PhD. The results obtained by the algorithms are compared with official data. 4. Discussion: The above results are discussed and compared. In particular the cycle demand is compared with the length of cycle networks within a city. 5. Conclusions

Advances in methods to detect, isolate and quantify foodborne pathogens

Foodborne diseases impact human health and economies worldwide in terms of health care and productivity loss. Prevention is necessary and methods to detect, isolate and quantify foodborne pathogens play a fundamental role, changing continuously to face microorganisms and food production evolution. Official methods are mainly based on microorganisms growth in different media and their isolation on selective agars followed by confirmation of presumptive colonies through biochemical and serological test. A complete identification requires form 7 to 10 days. Over the last decades, new molecular techniques based on antibodies and nucleic acids allow a more accurate typing and a faster detection and quantification. The present thesis aims to apply molecular techniques to improve official methods performances regarding two pathogens: Shiga-like Toxin-producing Escherichia coli (STEC) and Listeria monocytogenes. In 2011, a new strain of STEC belonging to the serogroup O104 provoked a large outbreak. Therefore, the development of a method to detect and isolate STEC O104 is demanded. The first objective of this work is the detection, isolation and identification of STEC O104 in sprouts artificially contaminated. Multiplex PCR assays and antibodies anti-O104 incorporated in reagents for immunomagnetic separation and latex agglutination were employed. Contamination levels of less than 1 CFU/g were detected. Multiplex PCR assays permitted a rapid screening of enriched food samples and identification of isolated colonies. Immunomagnetic separation and latex agglutination allowed a high sensitivity and rapid identification of O104 antigen, respectively. The development of a rapid method to detect and quantify Listeria monocytogenes, a high-risk pathogen, is the second objective. Detection of 1 CFU/ml and quantification of 10–1,000 CFU/ml in raw milk were achieved by a sample pretreatment step and quantitative PCR in about 3h. L. monocytogenes growth in raw milk was also evaluated.

Advanced decision-support methods for the design, control, and optimization of perishable products life cycle

In the last decades, global food supply chains had to deal with the increasing awareness of the stakeholders and consumers about safety, quality, and sustainability. In order to address these new challenges for food supply chain systems, an integrated approach to design, control, and optimize product life cycle is required. Therefore, it is essential to introduce new models, methods, and decision-support platforms tailored to perishable products. This thesis aims to provide novel practice-ready decision-support models and methods to optimize the logistics of food items with an integrated and interdisciplinary approach. It proposes a comprehensive review of the main peculiarities of perishable products and the environmental stresses accelerating their quality decay. Then, it focuses on top-down strategies to optimize the supply chain system from the strategical to the operational decision level. Based on the criticality of the environmental conditions, the dissertation evaluates the main long-term logistics investment strategies to preserve products quality. Several models and methods are proposed to optimize the logistics decisions to enhance the sustainability of the supply chain system while guaranteeing adequate food preservation. The models and methods proposed in this dissertation promote a climate-driven approach integrating climate conditions and their consequences on the quality decay of products in innovative models supporting the logistics decisions. Given the uncertain nature of the environmental stresses affecting the product life cycle, an original stochastic model and solving method are proposed to support practitioners in controlling and optimizing the supply chain systems when facing uncertain scenarios. The application of the proposed decision-support methods to real case studies proved their effectiveness in increasing the sustainability of the perishable product life cycle. The dissertation also presents an industry application of a global food supply chain system, further demonstrating how the proposed models and tools can be integrated to provide significant savings and sustainability improvements.

Towards Unstructured Knowledge Integration in Natural Language Processing

In the last decades, Artificial Intelligence has witnessed multiple breakthroughs in deep learning. In particular, purely data-driven approaches have opened to a wide variety of successful applications due to the large availability of data. Nonetheless, the integration of prior knowledge is still required to compensate for specific issues like lack of generalization from limited data, fairness, robustness, and biases. In this thesis, we analyze the methodology of integrating knowledge into deep learning models in the field of Natural Language Processing (NLP). We start by remarking on the importance of knowledge integration. We highlight the possible shortcomings of these approaches and investigate the implications of integrating unstructured textual knowledge. We introduce Unstructured Knowledge Integration (UKI) as the process of integrating unstructured knowledge into machine learning models. We discuss UKI in the field of NLP, where knowledge is represented in a natural language format. We identify UKI as a complex process comprised of multiple sub-processes, different knowledge types, and knowledge integration properties to guarantee. We remark on the challenges of integrating unstructured textual knowledge and bridge connections with well-known research areas in NLP. We provide a unified vision of structured knowledge extraction (KE) and UKI by identifying KE as a sub-process of UKI. We investigate some challenging scenarios where structured knowledge is not a feasible prior assumption and formulate each task from the point of view of UKI. We adopt simple yet effective neural architectures and discuss the challenges of such an approach. Finally, we identify KE as a form of symbolic representation. From this perspective, we remark on the need of defining sophisticated UKI processes to verify the validity of knowledge integration. To this end, we foresee frameworks capable of combining symbolic and sub-symbolic representations for learning as a solution.

Innovation Diffusion and Biostimulant knowledge in Moroccan agriculture

Our study focused on Morocco investigating the dissemination of PBs amongst farmers belonging to the first pillar of the GMP, located in the Fès-Meknès region. As well as to assess how innovation adoption is influenced by the network of relationships that various farmers are involved in. We adopted an “ego network” approach to identify the primary stakeholders responsible for the diffusion of PBs. We collected data through “face-to-face” interviews with 80 farmers in April and May 2021. The data were processed with the aim of: 1) analysing the total number of main and specific topics discussed between egos and egos’ alters regarding the variation of some egos attributes; 2) analysing egos’ network characteristics using E-Net software, and 3) identifying the significant variables that influence farmers to access knowledge, use and reuse of PBs a Binary Logistic Regression (LR) was applied. The first result disclosed that the main PBs topics discussed were technical positioning, the need to use PBs, knowledge of PBs, and organic PBs. We noted that farmers have specific features: they have a high school diploma and a bachelor's degree; they are specialised in fruits and cereals farming, and they are managers and members of a professional organisation. The second result showed results of SNA: 1) PBs seem to become generally a common argument for farmers who have already exchanged fertiliser information with their alters; 2) we disclosed a moderate heterogeneity in the networks, farmers have access to information mainly from acquaintances and professionals, and 3) we revealed that networks have a relatively low density and alters are not tightly connected to each other. Farmers have a brokerage position in the networks controlling the flow of information about the PBs. LR revealed that both the farmers’ attributes and the networks’ characteristics influence growers to know, use and reuse PBs.

Monitoring of Mediterranean marine benthic biodiversity through novel, standardized, and integrated approaches

Marine healthy ecosystems support life on Earth and human well-being thanks to their biodiversity, which is proven to decline mainly due to anthropogenic stressors. Monitoring how marine biodiversity changes trough space and time is needed to properly define and enroll effective actions towards habitat conservation and preservation. This is particularly needed in those areas that are very rich in species compared to their low surface extension and are characterized by strong anthropic pressures, such as the Mediterranean Sea. Subtidal rocky benthic Mediterranean habitats have a complex structural architecture, hosting a panoply of tiny organisms (cryptofauna) that inhabit crevices and caves, but that are still unknown. Different artificial standardized sampling structures (SSS) and methods have been developed and employed to characterize the cryptofauna, allowing for data replicability and comparability across regions. Organisms growing on these artificial structures can be identified coupling morphological taxonomy and DNA barcoding and metabarcoding. The metabarcoding allows for the identification of organisms in a bulk sample without morphological analysis, and it is based on comparing the genetic similarities of the assessed organisms with barcoding sequences present in online barcoding repositories. Nevertheless, barcoded species nowadays represent only a small portion of known species, and barcoding reference databases are not always curated and updated on a regular basis. In this Thesis I used an integrative approach to characterize benthic marine biodiversity, specifically coupling morphological and molecular techniques with the employment of SSS. Moreover, I upgraded the actual status of COI (cytochrome c oxidase subunit I) barcoding of marine metazoans, and I built a customized COI barcoding reference database for metabarcoding studies on temperate biogenic reefs. This work implemented the knowledge about diversity of Mediterranean marine communities, laying the groundworks for monitoring marine and environmental changes that will occur in the next future as consequences of anthropic and climate threats.

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.