Nowadays, the analysis of vehicular ad hoc networks for the evaluation of traffic conditions is a hot research field. One of the most significant process in VANETs is the vehicle clusterization. Indeed, in order to optimize the information exchange in such a network, an opportune criterion to aggregate vehicles is needed. The main goal of this work is to propose an innovative strategy to perform such an aggregation, by not considering only the punctual position of vehicles in a given instant, but by taking into account the behavior of vehicles over the time, so that a cluster contains vehicles that behave the same. To this aim, we propose a model that processes information about nodes of the network, and extracts a similarity measure between pair of vehicles to establish if they should belong to the same cluster. © 2020, Springer Nature Switzerland AG.
Behavioral Clustering: A New Approach for Traffic Congestion Evaluation / Balzano, W.; Murano, A.; Sorrentino, L.; Stranieri, S.. - 1150 AISC:(2020), pp. 1418-1427. (Intervento presentato al convegno Workshops of the 34th International Conference on Advanced Information Networking and Applications, WAINA 2020;) [10.1007/978-3-030-44038-1_129].
Behavioral Clustering: A New Approach for Traffic Congestion Evaluation
Balzano, W.;Murano, A.
;Sorrentino, L.;Stranieri, S.
2020
Abstract
Nowadays, the analysis of vehicular ad hoc networks for the evaluation of traffic conditions is a hot research field. One of the most significant process in VANETs is the vehicle clusterization. Indeed, in order to optimize the information exchange in such a network, an opportune criterion to aggregate vehicles is needed. The main goal of this work is to propose an innovative strategy to perform such an aggregation, by not considering only the punctual position of vehicles in a given instant, but by taking into account the behavior of vehicles over the time, so that a cluster contains vehicles that behave the same. To this aim, we propose a model that processes information about nodes of the network, and extracts a similarity measure between pair of vehicles to establish if they should belong to the same cluster. © 2020, Springer Nature Switzerland AG.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
