Mining Frequent Moving Patterns of Objects in Sensor Networks

Aiming at the issue of mining frequent moving patterns with two dimensional attributes including locations and time in sensor networks, a novel method named OMP-mine is proposed in this paper, OMP-mine is based on a novel data structure named OMP-tree and a scheme of conditional search. The OMP-tree can efficiently store large numbers of original moving patterns compactly and the method of conditional search can efficiently narrow the search space. OMP-mine adopts the idea of pattern growth, recursively fetches frequent prefix patterns from the conditional pattern bases directly, and joints the suffix to make a pattern grow. Simulation results show OMP-mine can efficiently discover frequent moving patterns with two dimensional attributes in sensor networks and decreases its complexity in time and space simultaneously.