Evaluating the effect of compressing algorithms for trajectory similarity and classification problems

Abstract During the last few years volumes of data that synthesize trajectories have expanded to unparalleled quantities. This growth is challenging traditional trajectory analysis approaches and solutions are sought in other domains. In this work, we focus on compression techniques with intention minimize size data, while, at same time, minimizing impact methods. To extent, evaluate five lossy algorithms: Douglas-Peucker (DP), Time Ratio (TR), Speed Based (SP), (TR_SP) (SP_TR). The comparison performed using four distinct real world datasets against six different dynamically assigned thresholds. effectiveness evaluated classification similarity measures. results showed there a trade-off between rate achieved quality. no “best algorithm” for every case choice proper algorithm an application-dependent process.