Seif Ben Chaabene | Searcharxiv

arXiv2021

Proposition d'approches de déploiement des unités de bord de route dans les réseaux véhiculaires

Road Side Units (RSUs) have a crucial role in maintaining Vehicular Ad-hoc Networks (VANETs) connectivity and coverage, especially, for applications gathering or disseminating non-safety information. In big cities with complex road network topology, a huge number of costly RSUs must be deployed to collect data gathered by all moving vehicles. In this respect, several research works focusing on RSUs deployment have been proposed. The thriving challenge would be to (i) reduce the deployment cost by minimizing as far as possible the number of used RSUs; and (ii) to maximize the coverage ratio. In this thesis, we introduce a spatio-temporal RSU deployment framework including three methods namely SPaCov/SPaCov+, HeSPic and MIP. SPaCov starts by mining frequent mobility patterns of moving vehicles from their trajectories then it computes the best RSU locations that cover the extracted patterns. Nonetheless, SPaCov+ extracts the frequent mobility patterns as well as the rare ones to enhance the coverage ratio. HeSiC is a budget-constrained spatio-temporal coverage method that aims to maximize the coverage ratio subject to a budget constraint, which is defined in terms of RSUs number. MIP is a spatio-temporal coverage method that aims to finding representative transactions from the sequential database and computing coverage. Performed simulations highlight the efficiency and the effectiveness of the proposed RSU deployment framework in terms of coverage ratio, deployment cost, network latency and overhead.

cs.NI↗

arXiv2020

Nouvelles représentations concises exactes des motifs rares

Until a present, the majority of work in data mining were interested in the extraction of the frequent itemsets and the generation of the frequent association rules from these itemsets. Sometimes, the frequent of associations rules can revealed not-interesting in the direction where a frequent behavior is in general a normal behavior in the database. These last years, some work was focused on the exploitation and the extraction of rare itemset and shows them interest. However, the very important size of those itemset was the handicap of algorithms that exploit the rare pattern. In order to relieve this problem, the present report proposes two exact concise representations of the rare itemset, one based on the minimal generators and the other based on the closed itemset. In this context, we introduce two new algorithms called GMRare and MFRare which extract these two exact concise representations.

cs.IR↗