Time filter

Source Type

Gnecco G.,Institute for Advanced Studies IMT | Morisi R.,Institute for Advanced Studies IMT | Roth G.,University of Genoa | Sanguineti M.,University of Genoa | Taramasso A.C.,University of Genoa
Soft Computing | Year: 2016

Supervised and semi-supervised machine-learning techniques are applied and compared for the recognition of the flood hazard. The learning goal consists in distinguishing between flood-exposed and marginal-risk areas. Kernel-based binary classifiers using six quantitative morphological features, derived from data stored in digital elevation models, are trained to model the relationship between morphology and the flood hazard. According to the experimental outcomes, such classifiers are appropriate tools when one is interested in performing an initial low-cost detection of flood-exposed areas, to be possibly refined in successive steps by more time-consuming and costly investigations by experts. The use of these automatic classification techniques is valuable, e.g., in insurance applications, where one is interested in estimating the flood hazard of areas for which limited labeled information is available. The proposed machine-learning techniques are applied to the basin of the Italian Tanaro River. The experimental results show that for this case study, semi-supervised methods outperform supervised ones when—the number of labeled examples being the same for the two cases—only a few labeled examples are used, together with a much larger number of unsupervised ones. © 2016 Springer-Verlag Berlin Heidelberg Source

Mureddu M.,University of Cagliari | Scala A.,Institute for Advanced Studies IMT | Scala A.,Complex Systems Computational Laboratory | Chessa A.,Institute for Advanced Studies IMT | And 5 more authors.
2014 IEEE International Electric Vehicle Conference, IEVC 2014 | Year: 2014

In the present paper an agent based approach, addressed to simulate the behaviour of a Plug-in Electric Vehicles (PEV) fleet into a Smart City, is presented. Considering the traffic data-set available from mobility plans, a spatial and time model, representing the evolution of travel patterns, can be developed considering each vehicle as an agent. The following statistical analysis in space and time of the agent behaviours is used to plan the PEV charging infrastructure of municipalities. The proposed planning methodology has been tested on an European city in order to evaluate the effectiveness of the proposed procedure. Such charging infrastructure, defined according to the mobility needs, has been tested and used to evaluate the customer satisfaction of PEV users in term of charging demand. The proposed charging system has been implemented to estimate the average daily energy profiles for charging the smart city PEV fleet during a typical workday. This has been finally used as one day ahead energy reference profile to develop a market-oriented EV charging strategies. The performance of the proposed smart charging strategies has been finally simulated and compared. © 2014 IEEE. Source

Discover hidden collaborations