768 research outputs found
EPB892599 Supplemental Material - Supplemental material for Graph input representations for machine learning applications in urban network analysis
No full textSupplemental material, EPB892599 Supplemental Material for Graph input representations for machine learning applications in urban network analysis by Alessio Pagani, Abhinav Mehrotra and Mirco Musolesi in EPB: Urban Analytics and City Science</p
Didactics and Self-Assessment: An Innovative Proposal for The University of Trento
No full textThe university institution is called today to face challenges concerning the ability to recognize and pursue new formative goals (Grion et al., 2018). In the light of this, the research wants to reflect on the reality of the University of Trento, so far, the only Italian university, among the 35 evaluated, to have obtained the highest rating assignable by the Anvur. The aim is to highlight both the primary nodes in which the University requires renewal and its hinges points, and report in detail the results of quantitative analysis, commissioned and drafted by the Joint Committee of the Department of Civil, Environmental and Mechanical Engineering (DICAM), which saw the need to further analyze the reality of students of the individual courses of the Department. The contribution links, in conclusion, the points emerged from the direct observation of the students to a consistent response to the emerging literature review. Specifically, reflecting the field of post-compulsory education paths, with a strong connection with self-assessment (SA). The results seem to show that self-assessment (SA) can be a new key to the promotion of an education capable of experimenting, through participatory and innovative teaching, knowledge, autonomy, responsibility and soft skills: fundamental elements that the University of Trento needs to improve to achieve European and international standards
Knowledge Discovery from Car Sharing Data for Traffic Flows Estimation
No full textThe newly introduced car sharing services are an unexploited source of data that could be used to estimate the state of the road network as well as to provide new interesting analysis on urban mobility. In this paper we propose a Knowledge Discovery System that first gathers information from car sharing sites and applications, and then processes it to estimate interesting metrics such as travel time and vehicle flows in the urban areas at different times and in different days. We further argue that the information gathered can be processed in real-time, to estimate instant traffic, and can be exploited to perform deeper analysis, using historical data. Finally, we analyze vehicle availability as a function of time in different zones and show how the results can be applied to travel time estimation, car stockout forecast and multimodal travel planning
Graph input representations for machine learning applications in urban network analysis
No full textUnderstanding and learning the characteristics of network paths has been of particular interest for decades and has led to several successful applications. Such analysis becomes challenging for urban networks as their size and complexity are significantly higher compared to other networks. The state-of-the-art machine learning techniques allow us to detect hidden patterns and, thus, infer the features associated with them. However, very little is known about the impact on the performance of such predictive models by the use of different input representations. In this paper, we design and evaluate six different graph input representations (i.e. representations of the network paths), by considering the network’s topological and temporal characteristics, for being used as inputs for machine learning models to learn the behavior of urban network paths. The representations are validated and then tested with a real-world taxi journeys dataset predicting the tips of using a road network of New York. Our results demonstrate that the input representations that use temporal information help the model to achieve the highest accuracy (root mean-squared error of 1.42$)
Ancora San Giorgio con Santa Maria Maddalena in Friuli: postilla su una 'singolare', perduta Crocifissione altomedievale a Aquileia
No full textNuova proposta di lettura iconografica e agiografica dell'affresco già presente nella demolita 'chiesa dei pagani' presso la Basilica di Aquilei
Reconstruction of public transport state
No full textInterest towards the applications of ICT in public and private urban transport has grown significantly over the last few years. In the field of the user interfaces with transportation, however, continuous, highly context-Aware, real time interaction can still be found only in a very limited number of cases, mostly in private transportation. One of the main issues in actually developing an assistive, portable, continuously interacting application is getting to know the transports system state (equations of motion of the means, position of the users on the means). In most cities the most temporally accurate data available is the estimated departure time of the next train or bus at the stops. In this paper, we propose a state-based Bayesian approach to the reconstruction of the transit system state from limited available knowledge (estimated departure time at the stops, data from users phone). The system is general and effective also in the presence of various real-world kinds of noise, such as information blackouts. In addition, we propose an extension to seamlessly exploit location of users to estimate which means they're on-board, and describe some scenarios in which such information would be of great value for the transit agencies, and would enable innovative social applications and interactions
The Pottesman Collection in the British Museum. Early Dynastic and Sargonic administrative texts. With an Appendix on a Palmyrene Inscription
No full textEdizione, trascrizione, traduzione e commento di un frammento di iscrizione palmirena inedita presente nella collezione Pottesman del British Museum (Appendice Agostini).The British Museum houses a small collection of six cuneiform tablets and a Palmyrene dedicatory inscription purchased in 1987 from the private collection of Solomon Pottesman. The aim of the present contribution is to provide a catalog of this lot and an edition of the so far unpublished cuneiform texts. In the appendix, Alessio Agostini added the edition of the Palmyrene inscription, which would have otherwise gone beyond the capabilities of the present author
A Linux-based support for developing real-time applications on heterogeneous platforms with dynamic FPGA reconfiguration
No full text- …
