Data Mining in Clinical Practice for the Quantification of Motor Impairment in Parkinson's Disease

Advances in biomedical signal acquisition systems for motion analysis have led to lowcost and ubiquitous wearable sensors which can be used to record movement data in different settings. This implies the potential availability of large amounts of quantitative data. It is then crucial to identify and to extract the information of clinical relevance from the large amount of available data. This quantitative and objective information can be an important aid for clinical decision making. Data mining is the process of discovering such information in databases through data processing, selection of informative data, and identification of relevant patterns. The databases considered in this thesis store motion data from wearable sensors (specifically accelerometers) and clinical information (clinical data, scores, tests). The main goal of this thesis is to develop data mining tools which can provide quantitative information to the clinician in the field of movement disorders. This thesis will focus on motor impairment in Parkinson's disease (PD). Different databases related to Parkinson subjects in different stages of the disease were considered for this thesis. Each database is characterized by the data recorded during a specific motor task performed by different groups of subjects. The data mining techniques that were used in this thesis are feature selection (a technique which was used to find relevant information and to discard useless or redundant data), classification, clustering, and regression. The aims were to identify high risk subjects for PD, characterize the differences between early PD subjects and healthy ones, characterize PD subtypes and automatically assess the severity of symptoms in the home setting.

Reconstruction of Etna recent flank eruptions for assessing diversion barrier project

The thesis contributed to the volcanic hazard assessment through the reconstruction of some historical flank eruptions of Etna in order to obtain quantitative data (volumes, effusion rates, etc.) for characterizing the recent effusive activity, quantifying the impact on the territory and defining mitigation actions for reducing the volcanic risk as for example containment barriers. The reconstruction was based on a quantitative approach using data extracted from aerial photographs and topographic maps. The approach allows to obtain the temporal evolution of the lava flow field and estimating the Time Average Discharge Rate (TADR) by dividing the volume emplaced over a given time interval for the corresponding duration. The analysis concerned the 2001, 1981 and 1928 Etna eruptions. The choice of these events is linked to their impact on inhabited areas. The results of the analysis showed an extraordinarily high effusion rate for the 1981 and 1928 eruptions (over 600 m^3/s), unusual for Etna eruptions. For the 1981 Etna eruption an eruptive model was proposed to explain the high discharge rate. The obtained TADRs were used as input data for simulations of the propagation of the lava flows for evaluating different scenarios of volcanic hazard and analyse different mitigation actions against lava flow invasion. It was experienced how numerical simulations could be adopted for evaluating the effectiveness of barrier construction and for supporting their optimal design. In particular, the gabions were proposed as an improvement for the construction of barriers with respect to the earthen barriers. The gabion barriers allow to create easily modular structures reducing the handled volumes and the intervention time. For evaluating operational constrain an experimental test was carried out to test the filling of the gabions with volcanic rock and evaluating their deformation during transport and placement.

Formazione e Competenze Professionali: una ricerca empirica sui Cassaintegrati in deroga della regione Emilia Romagna

The general theme of the present inquiry concerns the role of training and continuous updating of knowledge and skills in relation to the concept of employability and social vulnerability. The empirical research has affected the entire calendar year 2010, namely from 13 February 2010 to December 31, 2010: data refer to a very specific context or to the course funded by the Emilia Romagna region and targeted to employees in cassintegrazione notwithstanding domiciled in the region. The investigations were performed in a vocational training scheme accredited by the Emilia Romagna for the provision of publicly funded training courses. The quantitative data collected are limited to the region and distributed in all the provinces of Emilia Romagna; It addressed the issue of the role of continuing education throughout life and the importance of updating knowledge and skills, such as privileged instruments to address the instability of the labor market and what strategy to reduce the risk unemployment. Based on the different strategies that the employee puts in place during their professional careers, we introduce two concepts that are more common in the so-called knowledge society, namely the concept of social vulnerability and employability. In modern organizations becomes relevant knowledge they bring workers and the relationships that develop between people and allowing exponentially and disseminate such knowledge and skills. The knowledge thus becomes the first productive force, defined by Davenport and Prusak (1998) as "fluid combination of experience, values, contextual information and specialist knowledge that provides a framework for the evaluation and assimilation of new experience and new information ". Learning at work is a by stable explicit and conscious, and even enjoyable for everyone, especially outside of a training intervention. It then goes on to address the specific issue of training, under the current labor market increasingly deconstructed.

Lo spreco alimentare domestico in Italia: stime, cause ed impatti

Non esiste una definizione standard di spreco alimentare, così come non esistono metodologie uniformi per calcolarlo. Gli studi finora realizzati sullo spreco sono carenti, i dati raccolti spesso insufficienti. Il cibo viene sprecato ad ogni stadio della filiera alimentare, dal campo alla tavola. Nei Paesi Membri dell’Unione Europea, le famiglie – secondo dati elaborati da Eurostat- sono le principali responsabili dello spreco. Secondo la FAO, ogni europeo spreca ogni anno 179 chili di alimenti. Last Minute Market, spin off accademico che si occupa di ridurre e recuperare lo spreco, ha stimato che a livello domestico in Italia si sprecano mediamente il 17% dei prodotti ortofrutticoli acquistati, il 15% di pesce, il 28% di pasta e pane, il 29% di uova, il 30% di carne e il 32% di latticini. Da un punto di vista economico, lo sperpero alimentare significa una perdita di 1.693 euro l’anno per famiglia. Per inquadrare lo spreco alimentare domestico in Italia e gettare luce su dati contrastanti emersi da diversi studi finora realizzati, la tesi – dopo aver presentato stime a livello globale, europeo e italiano – si concentra sull’analisi dei dati emersi da un questionario sullo spreco domestico, compilato da 3.087 italiani tra il mese di novembre e quello di dicembre 2012. L’indagine socio-economica è stata realizzata in collaborazione con la Commissione Europea (DG JCR, Istituto per la Tutela della Salute dei Consumatori) e il Karlsruhe Institut für Technologie. Il questionario è stato posto sulla piattaforma online surveymonkey. La tesi ha avuto come obiettivi l’identificazione di dati quantitativi circa “quanto si spreca” , “cosa si spreca”, l’individuazione delle cause sociali, valoriali, comportamentali e di stile di vita, dello spreco alimentare delle famiglie italiane, l’impatto economico dello spreco sul budget domestico e l’elaborazione di profili di consumatori attraverso la cluster analysis.