Classification algorithms for Intelligent Transport Systems

Intelligent Transport Systems (ITS) consists in the application of ICT to transport to offer new and improved services to the mobility of people and freights. While using ITS, travellers produce large quantities of data that can be collected and analysed to study their behaviour and to provide information to decision makers and planners. The thesis proposes innovative deployments of classification algorithms for Intelligent Transport System with the aim to support the decisions on traffic rerouting, bus transport demand and behaviour of two wheelers vehicles. The first part of this work provides an overview and a classification of a selection of clustering algorithms that can be implemented for the analysis of ITS data. The first contribution of this thesis is an innovative use of the agglomerative hierarchical clustering algorithm to classify similar travels in terms of their origin and destination, together with the proposal for a methodology to analyse drivers’ route choice behaviour using GPS coordinates and optimal alternatives. The clusters of repetitive travels made by a sample of drivers are then analysed to compare observed route choices to the modelled alternatives. The results of the analysis show that drivers select routes that are more reliable but that are more expensive in terms of travel time. Successively, different types of users of a service that provides information on the real time arrivals of bus at stop are classified using Support Vector Machines. The results shows that the results of the classification of different types of bus transport users can be used to update or complement the census on bus transport flows. Finally, the problem of the classification of accidents made by two wheelers vehicles is presented together with possible future application of clustering methodologies aimed at identifying and classifying the different types of accidents.

ABC transporters of the A subfamily: potential prognostic markers and candidates for antibody selection from phage-display libraries for therapeutic use in Ewing sarcoma

The prognostic value of ABC transporters in Ewing sarcoma is still poorly explored and controversial. We described for the first time the impact of various ABCs on Ewing sarcoma prognosis by assessment of their gene expression in two independent cohorts of patients. Unexpected associations with favourable outcomes were observed for two ABCs of the A-subfamily, ABCA6 and ABCA7, whereas no associations with the canonical multidrug ABC transporters were identified. The ABCs of the A-subfamily are involved in cholesterol/phospholipids transportation and efflux from cells. Our clinical data support the drug-efflux independent contribution to cancer progression of the ABCAs, which has been confirmed in PDX-derived cell lines. The impact of these ABCA transporters on tumor progression seems to be mediated by lowering intracellular cholesterol, supporting the role of these proteins in lipid transport. In addition, the gene expression of ABCA6 and ABCA7 is regulated by transcription factors which control lipid metabolism: ABCA6 was induced by the binding of FoxO1/FoxO3a to its promoter and repressed by IGF1R/Akt signaling, whereas the expression of ABCA7 was regulated by p53. The data point to ABCA6 and ABCA7 as potential prognostic markers in Ewing sarcoma and suggest the IGF1/ABCA/lipid axis as an intriguing therapeutic target. Agonist monoclonal antibodies towards ABCA6/7 or inhibitors of cholesterol biosynthesis, such as statins or aminobiphoshonates, may be investigated as therapeutic options in combination with chemotherapy. Considering that no monoclonal antibodies selectively targeting extracellular domains of ABCA6/7 are available, the second part of the project has been dedicated to the generation of human antibody phage-display libraries as tools for selecting monoclonal antibodies. A novel synthetic human antibody phage-display library has been designed, cloned and characterized. The library takes advantages of the high variability of a designed naïve repertoire to be a useful tool for isolating antibodies towards all potential antigens, including the ABCAs.