Knowledge management in intelligent tutoring systems

In the last years, Intelligent Tutoring Systems have been a very successful way for improving learning experience. Many issues must be addressed until this technology can be defined mature. One of the main problems within the Intelligent Tutoring Systems is the process of contents authoring: knowledge acquisition and manipulation processes are difficult tasks because they require a specialised skills on computer programming and knowledge engineering. In this thesis we discuss a general framework for knowledge management in an Intelligent Tutoring System and propose a mechanism based on first order data mining to partially automate the process of knowledge acquisition that have to be used in the ITS during the tutoring process. Such a mechanism can be applied in Constraint Based Tutor and in the Pseudo-Cognitive Tutor. We design and implement a part of the proposed architecture, mainly the module of knowledge acquisition from examples based on first order data mining. We then show that the algorithm can be applied at least two different domains: first order algebra equation and some topics of C programming language. Finally we discuss the limitation of current approach and the possible improvements of the whole framework.

Modeling systems and vis/NIR device to improve peach and nectarine pre and post-harvest fruit maturity management

During the last decade peach and nectarine fruit have lost considerable market share, due to increased consumer dissatisfaction with quality at retail markets. This is mainly due to harvesting of too immature fruit and high ripening heterogeneity. The main problem is that the traditional used maturity indexes are not able to objectively detect fruit maturity stage, neither the variability present in the field, leading to a difficult post-harvest management of the product and to high fruit losses. To assess more precisely the fruit ripening other techniques and devices can be used. Recently, a new non-destructive maturity index, based on the vis-NIR technology, the Index of Absorbance Difference (IAD), that correlates with fruit degreening and ethylene production, was introduced and the IAD was used to study peach and nectarine fruit ripening from the “field to the fork”. In order to choose the best techniques to improve fruit quality, a detailed description of the tree structure, of fruit distribution and ripening evolution on the tree was faced. More in details, an architectural model (PlantToon®) was used to design the tree structure and the IAD was applied to characterize the maturity stage of each fruit. Their combined use provided an objective and precise evaluation of the fruit ripening variability, related to different training systems, crop load, fruit exposure and internal temperature. Based on simple field assessment of fruit maturity (as IAD) and growth, a model for an early prediction of harvest date and yield, was developed and validated. The relationship between the non-destructive maturity IAD, and the fruit shelf-life, was also confirmed. Finally the obtained results were validated by consumer test: the fruit sorted in different maturity classes obtained a different consumer acceptance. The improved knowledge, leaded to an innovative management of peach and nectarine fruit, from “field to market”.

Supporting requirement elicitation and ontology testing in knowledge graph engineering

Knowledge graphs and ontologies are closely related concepts in the field of knowledge representation. In recent years, knowledge graphs have gained increasing popularity and are serving as essential components in many knowledge engineering projects that view them as crucial to their success. The conceptual foundation of the knowledge graph is provided by ontologies. Ontology modeling is an iterative engineering process that consists of steps such as the elicitation and formalization of requirements, the development, testing, refactoring, and release of the ontology. The testing of the ontology is a crucial and occasionally overlooked step of the process due to the lack of integrated tools to support it. As a result of this gap in the state-of-the-art, the testing of the ontology is completed manually, which requires a considerable amount of time and effort from the ontology engineers. The lack of tool support is noticed in the requirement elicitation process as well. In this aspect, the rise in the adoption and accessibility of knowledge graphs allows for the development and use of automated tools to assist with the elicitation of requirements from such a complementary source of data. Therefore, this doctoral research is focused on developing methods and tools that support the requirement elicitation and testing steps of an ontology engineering process. To support the testing of the ontology, we have developed XDTesting, a web application that is integrated with the GitHub platform that serves as an ontology testing manager. Concurrently, to support the elicitation and documentation of competency questions, we have defined and implemented RevOnt, a method to extract competency questions from knowledge graphs. Both methods are evaluated through their implementation and the results are promising.

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.

Cultura "Open" e nuovi modelli normativi per la gestione della conoscenza

L'obiettivo della ricerca è di compiere un'analisi dell'impatto della cosiddetta cultura "open" alla luce dell'attuale condizione del World Wide Web. Si prenderà in considerazione, in particolare, la genesi del movimento a partire dalle basi di cultura hacker e la relativa evoluzione nella filosofia del software libero, con il fine ultimo di identificare il ruolo attuale del modello open source nello scenario esistente. L'introduzione al concetto di Open Access completerà la ricerca anche considerando la recente riaffermazione della conoscenza come bene comune all'interno della Società dell'Informazione