Search

Computing is moving towards pervasive, ubiquitous environments in which devices, software agents and services are all expected to seamlessly integrate and cooperate in support of human objectives. An important next step for pervasive computing is the integration of intelligent agents that employ knowledge and reasoning to understand the local context and share this information in support of intelligent applications and interfaces. Such scenarios, characterised by "computation everywhere around us", require on the one hand software components with intelligent behaviour in terms of objectives and context, and on the other their integration so as to produce social intelligence. Logic Programming (LP) has been recognised as a natural paradigm for addressing the needs of distributed intelligence. Yet, the development of novel architectures, in particular in the context Internet of Things (IoT), and the emergence of new domains and potential applications, are creating new research opportunities where LP could be exploited, when suitably coupled with agent technologies and methods so that it can fully develop its potential in the new context. In particular, the LP and its extensions can act as micro-intelligence sources for the IoT world, both at the individual and the social level, provided that they are reconsidered in a renewed architectural vision. Such micro-intelligence sources could deal with the local knowledge of the devices taking into account the domain specificity of each environment. The goal of this thesis is to re-contextualise LP and its extensions in these new domains as a source of micro-intelligence for the IoT world, envisioning a large number of small computational units distributed and situated in the environment, thus promoting the local exploitation of symbolic languages with inference capabilities. The topic is explored in depth and the effectiveness of novel LP models and architectures -and of the corresponding technology- expressing the concept o

Computing is moving towards pervasive, ubiquitous environments in which devices, software agents and services are all expected to seamlessly integrate and cooperate in support of human objectives. An important next step for pervasive computing is the integration of intelligent agents that employ knowledge and reasoning to understand the local context and share this information in support of intelligent applications and interfaces. Such scenarios, characterised by "computation everywhere around us", require on the one hand software components with intelligent behaviour in terms of objectives and context, and on the other their integration so as to produce social intelligence. Logic Programming (LP) has been recognised as a natural paradigm for addressing the needs of distributed intelligence. Yet, the development of novel architectures, in particular in the context Internet of Things (IoT), and the emergence of new domains and potential applications, are creating new research opportunities where LP could be exploited, when suitably coupled with agent technologies and methods so that it can fully develop its potential in the new context. In particular, the LP and its extensions can act as micro-intelligence sources for the IoT world, both at the individual and the social level, provided that they are reconsidered in a renewed architectural vision. Such micro-intelligence sources could deal with the local knowledge of the devices taking into account the domain specificity of each environment. The goal of this thesis is to re-contextualise LP and its extensions in these new domains as a source of micro-intelligence for the IoT world, envisioning a large number of small computational units distributed and situated in the environment, thus promoting the local exploitation of symbolic languages with inference capabilities. The topic is explored in depth and the effectiveness of novel LP models and architectures -and of the corresponding technology- expressing the concept o

As Artificial Intelligence (AI) progressively conquers the software industry at a fast pace, the demand for more transparent and pervasive technologies increases accordingly. In this scenario, novel approaches to Logic Programming (LP) and symbolic AI have the potential to satisfy the requirements of modern software environments. However, traditional logic-based approaches often fail to match present-day planning and learning workflows, which natively deal with uncertainty. Accordingly, Probabilistic Logic Programming (PLP) is emerging as a modern research field that investigates the combination of LP with the probability theory. Although research efforts at the state of the art demonstrate encouraging results, they are usually either developed as proof of concepts or bound to specific platforms, often having inconvenient constraints. In this dissertation, we introduce an elastic and platform-agnostic approach to PLP aimed to surpass the usability and portability limitations of current proposals. We design our solution as an extension of the 2P-Kt symbolic AI ecosystem, thus endorsing the mission of the project and inheriting its multi-platform and multi-paradigm nature. Additionally, our proposal comprehends an object-oriented and pure-Kotlin library for manipulating Binary Decision Diagrams (BDDs), which are notoriously relevant in the context of probabilistic computation. As a Kotlin multi-platform architecture, our BDD module aims to surpass the usability constraints of existing packages, which typically rely on low level C/C++ bindings for performance reasons. Overall, our project explores novel directions towards more usable, portable, and accessible PLP technologies, which we expect to grow in popularity both in the research community and in the software industry over the next few years.

Child marriage is still a great issue in developing countries and even if the interventions to prevent it are having results, they are not enough to eliminate the problem. Among the strategies that seem to work most to fight child marriage, there is the empowerment of girls with information combined with education of parents and community. As smartphones are more accessible year after year in developing countries, this thesis wants to investigate if a mobile app could be effective in fighting child marriage and which characteristics such an app should have. The research was organized in four phases and used design and creation and case study methodologies. Firstly, the literature was analyzed and an initial design was proposed. Secondly, expert interviews were performed to gain feedback on the proposed design, and afterwards prototype was built. Thirdly, a case study in the Democratic Republic of Congo (DRC) was performed to test the prototype, gaining insights and improvements through group interviews with 26 girls aged 15-19. Finally, a first version of the app was developed and a second phase of the case study was run in the DRC to understand if the girls were able to use the app. This phase included 14 girls of which 6 had participated in the prototype testing and used questionnaires as a data generation method. The app was built following the Principles for Digital Development. Even if this app is built based on the case study in DRC is modular and easily adaptable to other contexts as it is not content-specific. It was shown that is worth continuing to study this topic and it was defined a conceptual framework for designing learning apps for developing countries, in particular, to fight child, early, and forced marriage.

Intelligent Transportation Systems (ITS) built using Deep Neural Network (DNN) models offer an effective solution for handling short-term traffic flow, which greatly assists drivers, travellers or public security and safety in their decision-making. In particular, Spatio-Temporal Graph Neural Networks (STGNNs) have gained popularity as a powerful tool for effectively modelling spatio-temporal dependencies in diverse real-world urban applications, including intelligent transportation and public safety. However, the black-box nature of these models prevents a true understanding of the results and a trustworthy adoption by their users. The research field of eXplainable Artificial Intelligence (XAI) addresses this concern by developing systems that help users trust non-transparent AI. Non-expert ITS users are primarily interested in the non-technical reasons behind model predictions. Hence, leveraging Natural Language Generation (NLG), verbal descriptions of the reasons behind model outcomes are a peculiar tool to provide an easy and clear illustration of the process. This work focuses on developing an XAI system to explain short-term speed forecasts in traffic networks obtained from STGNNs. The primary emphasis lies in explaining the reasons behind predicted traffic congestions or free flows. Key information justifying these predictions is extracted from the input traffic network in the form of a significant subgraph. The information of the subgraph is finally summarized and it is then converted into text using a template-based approach. This thesis makes a dual contribution. First, it delves into explaining short-term traffic predictions by STGNNs, an underexplored area in current literature. Second, it leverages NLG techniques uniquely, using them to verbally translate XAI explanations into a coherent narrative, following a data-to-sequence template-based approach.

The ability to create hybrid systems that blend different paradigms has now become a requirement for complex AI systems usually made of more than a component. In this way, it is possible to exploit the advantages of each paradigm and exploit the potential of different approaches such as symbolic and non-symbolic approaches. In particular, symbolic approaches are often exploited for their efficiency, effectiveness and ability to manage large amounts of data, while symbolic approaches are exploited to ensure aspects related to explainability, fairness, and trustworthiness in general. The thesis lies in this context, in particular in the design and development of symbolic technologies that can be easily integrated and interoperable with other AI technologies. 2P-Kt is a symbolic ecosystem developed for this purpose, it provides a logic-programming (LP) engine which can be easily extended and customized to deal with specific needs. The aim of this thesis is to extend 2P-Kt to support constraint logic programming (CLP) as one of the main paradigms for solving highly combinatorial problems given a declarative problem description and a general constraint-propagation engine. A real case study concerning school timetabling is described to show a practical usage of the CLP(FD) library implemented. Since CLP represents only a particular scenario for extending LP to domain-specific scenarios, in this thesis we present also a more general framework: Labelled Prolog, extending LP with labelled terms and in particular labelled variables. The designed framework shows how it is possible to frame all variations and extensions of LP under a single language reducing the huge amount of existing languages and libraries and focusing more on how to manage different domain needs using labels which can be associated with every kind of term. Mapping of CLP into Labeled Prolog is also discussed as well as the benefits of the provided approach.

Child marriage is still a great issue in developing countries and even if the interventions to prevent it are having results, they are not enough to eliminate the problem. Among the strategies that seem to work most to fight child marriage, there is the empowerment of girls with information combined with education of parents and community. As smartphones are more accessible year after year in developing countries, this thesis wants to investigate if a mobile app could be effective in fighting child marriage and which characteristics such an app should have. The research was organized in four phases and used design and creation and case study methodologies. Firstly, the literature was analyzed and an initial design was proposed. Secondly, expert interviews were performed to gain feedback on the proposed design, and afterwards prototype was built. Thirdly, a case study in the Democratic Republic of Congo (DRC) was performed to test the prototype, gaining insights and improvements through group interviews with 26 girls aged 15-19. Finally, a first version of the app was developed and a second phase of the case study was run in the DRC to understand if the girls were able to use the app. This phase included 14 girls of which 6 had participated in the prototype testing and used questionnaires as a data generation method. The app was built following the Principles for Digital Development. Even if this app is built based on the case study in DRC is modular and easily adaptable to other contexts as it is not content-specific. It was shown that is worth continuing to study this topic and it was defined a conceptual framework for designing learning apps for developing countries, in particular, to fight child, early, and forced marriage.

As Artificial Intelligence (AI) progressively conquers the software industry at a fast pace, the demand for more transparent and pervasive technologies increases accordingly. In this scenario, novel approaches to Logic Programming (LP) and symbolic AI have the potential to satisfy the requirements of modern software environments. However, traditional logic-based approaches often fail to match present-day planning and learning workflows, which natively deal with uncertainty. Accordingly, Probabilistic Logic Programming (PLP) is emerging as a modern research field that investigates the combination of LP with the probability theory. Although research efforts at the state of the art demonstrate encouraging results, they are usually either developed as proof of concepts or bound to specific platforms, often having inconvenient constraints. In this dissertation, we introduce an elastic and platform-agnostic approach to PLP aimed to surpass the usability and portability limitations of current proposals. We design our solution as an extension of the 2P-Kt symbolic AI ecosystem, thus endorsing the mission of the project and inheriting its multi-platform and multi-paradigm nature. Additionally, our proposal comprehends an object-oriented and pure-Kotlin library for manipulating Binary Decision Diagrams (BDDs), which are notoriously relevant in the context of probabilistic computation. As a Kotlin multi-platform architecture, our BDD module aims to surpass the usability constraints of existing packages, which typically rely on low level C/C++ bindings for performance reasons. Overall, our project explores novel directions towards more usable, portable, and accessible PLP technologies, which we expect to grow in popularity both in the research community and in the software industry over the next few years.