On the prediction of large-scale road-network constrained trajectories

Autor(es)

de Sousa, Roniel S. ; Boukerche, Azzedine ; Loureiro, Antonio A. F.

• Tipo de documento: Artigo Científico
• Fonte: Computer Networks; v. 206, p. 13-pg., 2022-02-05.

Resumo

Trajectory data mining-based applications benefit from the increasing availability of vehicle trajectory and road network datasets. For instance, the application of trajectory prediction makes it possible to design more efficient routing protocols for vehicular networks. This paper proposes a novel cluster-based framework for the long-term prediction of road-network constrained trajectories. The framework employs a new hierarchical agglomerative clustering algorithm and trains prediction models from historical trajectory datasets. Experimental results show the framework's effectiveness and efficiency to predict trajectories with different characteristics in a new real-world, large-scale scenario. Furthermore, the framework outperformed the related work in terms of prediction accuracy and time complexity. (AU)

• Processo FAPESP: 18/23064-8 - Mobilidade na computação urbana: caracterização, modelagem e aplicações (MOBILIS)
• Beneficiário: Antonio Alfredo Ferreira Loureiro
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 15/24494-8 - Comunicação e processamento de big data em nuvens e névoas computacionais
• Beneficiário: Nelson Luis Saldanha da Fonseca
• Modalidade de apoio: Auxílio à Pesquisa - Temático