Identificando padrões comportamentais do tipo avoidance em trajetórias de objetos móveis / Identifying avoidance behavior patterns in moving objects trajectories
AUTOR(ES)
Alisson Moscato Loy
FONTE
IBICT - Instituto Brasileiro de Informação em Ciência e Tecnologia
DATA DE PUBLICAÇÃO
2011
RESUMO
With the increasing availability and considerable price reduction of technologies that allow the collection of moving object data, the offering of trajectory data becomes abundant. The study of these trajectories has the objective to allow a better understanding of the data, as well as the extraction of new knowledge using computational techniques. One of the possible studies is the analysis of the behavior of moving objects. The study on behavior patterns in trajectories has focused on agglomeration and similarity of entities moving in space or space and time. This work proposes the formalization of a new behavior pattern that indicates when a moving object is avoiding some determined spatial region, here called avoidance. The study and identification of this behavior may be of interest in many application areas, like security, electronic games, social behavior, and so on. Initially, this work presents an heuristic based on the observations of avoidance events, and based on this heuristic we define the formalization of this new kind of trajectory behavior pattern. This work also presents an algorithm to automatically identify this behavior in trajectories of moving objects. To evaluate the effectiveness of this algorithm, experiments were performed on trajectory datasets, collected by pedestrians in a park, and by vehicles at several places in the cities of Porto Alegre and Xangri-lá.
ASSUNTO(S)
inteligência artificial moving objects trajectories behavior patterns mapa : navegação controle : trajetória kdd artificial intelligence
