Statistical learning of random probability measures

The study of random probability measures is a lively research topic that has attracted interest from different fields in recent years. In this thesis, we consider random probability measures in the context of Bayesian nonparametrics, where the law of a random probability measure is used as prior distribution, and in the context of distributional data analysis, where the goal is to perform inference given avsample from the law of a random probability measure. The contributions contained in this thesis can be subdivided according to three different topics: (i) the use of almost surely discrete repulsive random measures (i.e., whose support points are well separated) for Bayesian model-based clustering, (ii) the proposal of new laws for collections of random probability measures for Bayesian density estimation of partially exchangeable data subdivided into different groups, and (iii) the study of principal component analysis and regression models for probability distributions seen as elements of the 2-Wasserstein space. Specifically, for point (i) above we propose an efficient Markov chain Monte Carlo algorithm for posterior inference, which sidesteps the need of split-merge reversible jump moves typically associated with poor performance, we propose a model for clustering high-dimensional data by introducing a novel class of anisotropic determinantal point processes, and study the distributional properties of the repulsive measures, shedding light on important theoretical results which enable more principled prior elicitation and more efficient posterior simulation algorithms. For point (ii) above, we consider several models suitable for clustering homogeneous populations, inducing spatial dependence across groups of data, extracting the characteristic traits common to all the data-groups, and propose a novel vector autoregressive model to study of growth curves of Singaporean kids. Finally, for point (iii), we propose a novel class of projected statistical methods for distributional data analysis for measures on the real line and on the unit-circle.

Evaluation of the real nutritional value of processed food to improve their effect on health and increase their sustainability

Cured meats and dairy products are criticized for their salt content and synthetic additives. This has led to the development of strategies to reduce and replace these ingredients. Since the food matrix and technological processes can affect the bioaccessibility of nutrients, it is necessary to study their release during digestion to determine the real nutritional value of foods. In the first part of this PhD project, the impact on the nutritional quality of the reduction of sodium content and of the replacement of synthetic nitrates/nitrites with a combination of innovative formulations was evaluated in Parmigiano Reggiano Cheese and salami. For this purpose, an in vitro digestion model combined with different analytical techniques was used. The results showed that fatty acids and proteins release increased over time during digestion. At the end of digestion, the innovative formulation/processing did not negatively affect fatty acids release and protein hydrolysis, and led to the formation of bioactive peptides. The excessive intake of sugars is correlated with metabolic diseases. After the intestinal uptake, their release in the blood stream depends on their metabolic fate within the enterocyte. In the second part of this PhD project, the absorption and metabolism of glucose, fructose and sucrose was evaluated using intestinal cell line. A faster absorption of fructose than glucose was observed, and a different modulation of the synthesis/transport of other metabolites by monosaccharides was shown. Intestinal cells were also used to verify the stability and intestinal uptake of vitamins (A and D3) delivered to cells through two vehicles. It was shown that the presence of lipids protected the vitamin from external factors such as light, heat and oxygen, and improved their bioavailability Overall, the results obtained in this PhD project confirmed that considering only the chemical composition of foods is not sufficient to determine their nutritional value.

Media activism on and off line by Italian adolescents and young adults

From several researchers it appears that Italian adolescents and young people are grown up with commercial television which is accused to contain too much violence, sex, reality shows, advertising, cartoons which are watched from 1 to 4 hours daily. Adolescents are also great users of mobile phones and spend a lot of time to use it. Their academic results are below the average of Ocse States. However the widespread use of communication technology and social networks display also another side of adolescents who engage in media activism and political movement such as Ammazzateci tutti!, Indymedia, Movimento 5 Stelle, Movimento No Tav. In which way does the world economic crisis -with the specific problems of Italy as the cutting founds for school, academic research and welfare, the corruption of political class, mafia and camorra organisation induce a reaction in our adolescents and young people? Several researches inform us about their use of internet in terms of spending time but, more important, how internet, and the web 2.0, could be an instrument for their reaction? What do they do online? How they do it? Which is the meaning of their presence online? And, has their online activity a continuity offline? The research aims are: 1. Trough a participant observation of Social Network profiles opened by 10 young active citizens, I would seek to understand which kind of social or political activities they engage in online as individuals and which is the meaning of their presence online. 2. To observe and understand if adolescents and young people have a continuity of their socio-political engagement online in offline activities and which kind of experiences it is. 3. Try to comprehend which was (or which were) the significant, learning experiences that convinced them about the potential of the web as tool for their activism.