Trajectory cleaning is essential for pre-processing GPS data. GPS data might be wrong because sometimes signals transmitted by satellites cannot be recorded accurately by GPS receivers because of the interference, weak signal, and malfunction of sensor. Therefore, the recorded GPS point can be far from the actual location of the receiver. This inaccurate location can make strong affect to some decision-making processes based on the GPS data. In order to eliminate wrong GPS data points from the trajectory, some trajectory cleaning processes: detecting stop points, interpolating missing segments and removing inaccurate points are proposed in this paper. Moreover, the results show that pre-processing trajectory cleaning approach helps to improve the quality of trajectory clustering.
Reference
1. L. O. Alvares, G. Oliveira, C. A. Heuser, and V. Bogorny (2009). A framework for trajectory data preprocessing for data mining. Int. Conf. on Software Engineering and Knowledge Engineering, 698 – 702.
2. G. Andrienko, N. Andrienko, S. Rinzivillo, M. Nanni, D. Pedreschi, and F. Giannotti (2009). Interactive visual clustering of large collections of trajectories. Visual Analytics Science and Technology, 3 –10.
3. M. Ankerst, M. M. Breunig, H.-P. Krie gel, and J. Sander (1999). Optics: ordering points to identify the clustering structure. Proceedings of SIGMOD Int. Conf. on Management of Data, 49 – 60.
4. D. J. Berndt and J. Clifford (1994). Using Dynamic Time Warping to Find Patterns in Time Series. Proceedings of KDD-94: AAAI Workshop on Knowledge Discovery in Databases, 359 – 370.