T-pattern Tree

A T-pattern Tree is a decision tree that follows a trajectory pattern.

• AKA: Trajectory Pattern Tree.
• See: Decision Tree, Decision Function, Trajectory Pattern.

---

---

References

2009

• (Monreale et al., 2009) ⇒ Anna Monreale, Fabio Pinelli, Roberto Trasarti, and Fosca Giannotti. (2009). “WhereNext: A Location Predictor on Trajectory Pattern Mining.” In: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2009). doi:10.1145/1557019.1557091
  • QUOTE: A decision tree, named T-pattern Tree, is built and evaluated with a formal training and test process. The tree is learned from the Trajectory Patterns that hold a certain area and it may be used as a predictor of the next location of a new trajectory finding the best matching path in the tree. ...

    ...

T-pattern Tree Building: the extracted local models, T-patterns, are combined in a prefix tree called T-pattern Tree. The nodes of the tree are regions frequently visited and the edges represent travel among regions and are annotated with the typical travel time. Each common prefix of T-patterns becomes common path on the tree. This tree may be viewed as a global model of the underlying mobility data, once augmented with a default path which represents all infrequent trajectories. This method is similar to the use of association rules as predictive rules in rule based classifiers.

---