Agent-based simulation for renewable energy incentive design

In this thesis, we propose a novel approach to model the diffusion of residential PV systems. For this purpose, we use an agent-based model where agents are the families living in the area of interest. The case study is the Emilia-Romagna Regional Energy plan, which aims to increase the produc- tion of electricity from renewable energy. So, we study the microdata from the Survey on Household Income and Wealth (SHIW) provided by Bank of Italy in order to obtain the characteristics of families living in Emilia-Romagna. These data have allowed us to artificial generate families and reproduce the socio-economic aspects of the region. The families generated by means of a software are placed on the virtual world by associating them with the buildings. These buildings are acquired by analysing the vector data of regional buildings made available by the region. Each year, the model determines the level of diffusion by simulating the installed capacity. The adoption behaviour is influenced by social interactions, household’s economic situation, the environmental benefits arising from the adoption and the payback period of the investment.

Modelling and simulating in systems biology: an approach based on multi-agent systems

Systems Biology is an innovative way of doing biology recently raised in bio-informatics contexts, characterised by the study of biological systems as complex systems with a strong focus on the system level and on the interaction dimension. In other words, the objective is to understand biological systems as a whole, putting on the foreground not only the study of the individual parts as standalone parts, but also of their interaction and of the global properties that emerge at the system level by means of the interaction among the parts. This thesis focuses on the adoption of multi-agent systems (MAS) as a suitable paradigm for Systems Biology, for developing models and simulation of complex biological systems. Multi-agent system have been recently introduced in informatics context as a suitabe paradigm for modelling and engineering complex systems. Roughly speaking, a MAS can be conceived as a set of autonomous and interacting entities, called agents, situated in some kind of nvironment, where they fruitfully interact and coordinate so as to obtain a coherent global system behaviour. The claim of this work is that the general properties of MAS make them an effective approach for modelling and building simulations of complex biological systems, following the methodological principles identified by Systems Biology. In particular, the thesis focuses on cell populations as biological systems. In order to support the claim, the thesis introduces and describes (i) a MAS-based model conceived for modelling the dynamics of systems of cells interacting inside cell environment called niches. (ii) a computational tool, developed for implementing the models and executing the simulations. The tool is meant to work as a kind of virtual laboratory, on top of which kinds of virtual experiments can be performed, characterised by the definition and execution of specific models implemented as MASs, so as to support the validation, falsification and improvement of the models through the observation and analysis of the simulations. A hematopoietic stem cell system is taken as reference case study for formulating a specific model and executing virtual experiments.

New markov chain based methods for single and cross-domain sentiment classification

Nowadays communication is switching from a centralized scenario, where communication media like newspapers, radio, TV programs produce information and people are just consumers, to a completely different decentralized scenario, where everyone is potentially an information producer through the use of social networks, blogs, forums that allow a real-time worldwide information exchange. These new instruments, as a result of their widespread diffusion, have started playing an important socio-economic role. They are the most used communication media and, as a consequence, they constitute the main source of information enterprises, political parties and other organizations can rely on. Analyzing data stored in servers all over the world is feasible by means of Text Mining techniques like Sentiment Analysis, which aims to extract opinions from huge amount of unstructured texts. This could lead to determine, for instance, the user satisfaction degree about products, services, politicians and so on. In this context, this dissertation presents new Document Sentiment Classification methods based on the mathematical theory of Markov Chains. All these approaches bank on a Markov Chain based model, which is language independent and whose killing features are simplicity and generality, which make it interesting with respect to previous sophisticated techniques. Every discussed technique has been tested in both Single-Domain and Cross-Domain Sentiment Classification areas, comparing performance with those of other two previous works. The performed analysis shows that some of the examined algorithms produce results comparable with the best methods in literature, with reference to both single-domain and cross-domain tasks, in $2$-classes (i.e. positive and negative) Document Sentiment Classification. However, there is still room for improvement, because this work also shows the way to walk in order to enhance performance, that is, a good novel feature selection process would be enough to outperform the state of the art. Furthermore, since some of the proposed approaches show promising results in $2$-classes Single-Domain Sentiment Classification, another future work will regard validating these results also in tasks with more than $2$ classes.

Characterization of microplastics ingested by marine benthos - a methodological and field-experimental study

Microplastics have become ubiquitous pollutants in the marine environment. Ingestion of microplastics by a wide range of marine organisms has been recorded both in laboratory and field studies. Despite growing concern for microplastics, few studies have evaluated their concentrations and distribution in wild populations. Further, there is a need to identify cost-effective standardized methodologies for microplastics extraction and analysis in organisms. In this thesis I present: (i) the results of a multi-scale field sampling to quantify and characterize microplastics occurrence and distribution in 4 benthic marine invertebrates from saltmarshes along the North Adriatic Italian coastal lagoons; (ii) a comparison of the effects and cost-effectiveness of two extraction protocols for microplastics isolation on microfibers and on wild collected organisms; (iii) the development of a novel field- based technique to quantify and characterize the microplastic uptake rates of wild and farmed populations of mussels (Mytilus galloprovincialis) through the analysis of their biodeposits. I found very low and patchy amounts of microplastics in the gastrointestinal tracts of sampled organisms. The omnivorous crab Carcinus aestuarii was the species with the highest amounts of microplastics, but there was a notable variation among individuals. There were no substantial differences between enzymatic and alkaline extraction methods. However, the alkaline extraction was quicker and cheaper. Biodeposit traps proved to be an effective method to estimate mussel ingestion rates. However their performance differed significantly among sites, suggesting that the method, as currently designed, is sensible to local environmental conditions. There were no differences in the ingestion rates of microplastics between farmed and wild mussels. The estimates of microplastic ingestion and the validated procedures for their extraction provide a strong basis for future work on microplastic pollution.

Galactic fountain flows in high-resolution hydrodynamical simulations of galaxy disks

Feedback from the most massive components of a young stellar cluster deeply affects the surrounding ISM driving an expanding over-pressured hot gas cavity in it. In spiral galaxies these structures may have sufficient energy to break the disk and eject large amount of material into the halo. The cycling of this gas, which eventually will fall back onto the disk, is known as galactic fountains. We aim at better understanding the dynamics of such fountain flow in a Galactic context, frame the problem in a more dynamic environment possibly learning about its connection and regulation to the local driving mechanism and understand its role as a metal diffusion channel. The interaction of the fountain with a hot corona is hereby analyzed, trying to understand the properties and evolution of the extraplanar material. We perform high resolution hydrodynamical simulations with the moving-mesh code AREPO to model the multi-phase ISM of a Milky Way type galaxy. A non-equilibrium chemical network is included to self consistently follow the evolution of the main coolants of the ISM. Spiral arm perturbations in the potential are considered so that large molecular gas structures are able to dynamically form here, self shielded from the interstellar radiation field. We model the effect of SN feedback from a new-born stellar cluster inside such a giant molecular cloud, as the driving force of the fountain. Passive Lagrangian tracer particles are used in conjunction to the SN energy deposition to model and study diffusion of freshly synthesized metals. We find that both interactions with hot coronal gas and local ISM properties and motions are equally important in shaping the fountain. We notice a bimodal morphology where most of the ejected gas is in a cold $10^4$ K clumpy state while the majority of the affected volume is occupied by a hot diffuse medium. While only about 20\% of the produced metals stay local, most of them quickly diffuse through this hot regime to great scales.

Near Real-Time Detection Of Pipe Bursts in Water Distribution Systems

The research work presented in the thesis describes a new methodology for the automated near real-time detection of pipe bursts in Water Distribution Systems (WDSs). The methodology analyses the pressure/flow data gathered by means of SCADA systems in order to extract useful informations that go beyond the simple and usual monitoring type activities and/or regulatory reporting , enabling the water company to proactively manage the WDSs sections. The work has an interdisciplinary nature covering AI techniques and WDSs management processes such as data collection, manipulation and analysis for event detection. Indeed, the methodology makes use of (i) Artificial Neural Network (ANN) for the short-term forecasting of future pressure/flow signal values and (ii) Rule-based Model for bursts detection at sensor and district level. The results of applying the new methodology to a District Metered Area in Emilia- Romagna’s region, Italy have also been reported in the thesis. The results gathered illustrate how the methodology is capable to detect the aforementioned failure events in fast and reliable manner. The methodology guarantees the water companies to save water, energy, money and therefore enhance them to achieve higher levels of operational efficiency, a compliance with the current regulations and, last but not least, an improvement of customer service.

A Comparative Analysis of Dynamical Models for Tidal Dissipation in Natural Satellite Ephemerides

The study of the tides of a celestial bodies can unveil important information about their interior as well as their orbital evolution. The most important tidal parameter is the Love number, which defines the deformation of the gravity field due to an external perturbing body. Tidal dissipation is very important because it drives the secular orbital evolution of the natural satellites, which is even more important in the case of the the Jupiter system, where three of the Galilean moons, Io, Europa and Ganymede, are locked in an orbital resonance where the ratio of their mean motions is 4:2:1. This is called Laplace resonance. Tidal dissipation is described by the dissipation ratio k2/Q, where Q is the quality factor and it describes the dampening of a system. The goal of this thesis is to analyze and compare the two main tidal dynamical models, Mignard's model and gravity field variation model, to understand the differences between each model with a main focus on the single-moon case with Io, which can help also understanding better the differences between the two models without over complicating the dynamical model. In this work we have verified and validated both models, we have compared them and pinpointed the main differences and features that characterize each model. Mignard's model treats the tides directly as a force, while the gravity field variation model describes the tides with a change of the spherical harmonic coefficients. Finally, we have also briefly analyzed the difference between the single-moon case and the two-moon case, and we have confirmed that the governing equations that describe the change of semi-major axis and eccentricity are not good anymore when more moons are present.

Graph-based Vision-Language Model for Multi-Modal Retrieval of Fashion Products

Artificial Intelligence is reshaping the field of fashion industry in different ways. E-commerce retailers exploit their data through AI to enhance their search engines, make outfit suggestions and forecast the success of a specific fashion product. However, it is a challenging endeavour as the data they possess is huge, complex and multi-modal. The most common way to search for fashion products online is by matching keywords with phrases in the product's description which are often cluttered, inadequate and differ across collections and sellers. A customer may also browse an online store's taxonomy, although this is time-consuming and doesn't guarantee relevant items. With the advent of Deep Learning architectures, particularly Vision-Language models, ad-hoc solutions have been proposed to model both the product image and description to solve this problems. However, the suggested solutions do not exploit effectively the semantic or syntactic information of these modalities, and the unique qualities and relations of clothing items. In this work of thesis, a novel approach is proposed to address this issues, which aims to model and process images and text descriptions as graphs in order to exploit the relations inside and between each modality and employs specific techniques to extract syntactic and semantic information. The results obtained show promising performances on different tasks when compared to the present state-of-the-art deep learning architectures.

Model-Based Contrastive Explanations for XAIP: Towards a General Model and Prototype

Planning is an important sub-field of artificial intelligence (AI) focusing on letting intelligent agents deliberate on the most adequate course of action to attain their goals. Thanks to the recent boost in the number of critical domains and systems which exploit planning for their internal procedures, there is an increasing need for planning systems to become more transparent and trustworthy. Along this line, planning systems are now required to produce not only plans but also explanations about those plans, or the way they were attained. To address this issue, a new research area is emerging in the AI panorama: eXplainable AI (XAI), within which explainable planning (XAIP) is a pivotal sub-field. As a recent domain, XAIP is far from mature. No consensus has been reached in the literature about what explanations are, how they should be computed, and what they should explain in the first place. Furthermore, existing contributions are mostly theoretical, and software implementations are rarely more than preliminary. To overcome such issues, in this thesis we design an explainable planning framework bridging the gap between theoretical contributions from literature and software implementations. More precisely, taking inspiration from the state of the art, we develop a formal model for XAIP, and the software tool enabling its practical exploitation. Accordingly, the contribution of this thesis is four-folded. First, we review the state of the art of XAIP, supplying an outline of its most significant contributions from the literature. We then generalise the aforementioned contributions into a unified model for XAIP, aimed at supporting model-based contrastive explanations. Next, we design and implement an algorithm-agnostic library for XAIP based on our model. Finally, we validate our library from a technological perspective, via an extensive testing suite. Furthermore, we assess its performance and usability through a set of benchmarks and end-to-end examples.