simulation in "Space- and Time- Invariant Trajectory Clustering via Deep Representation Learning"
##Required Packages:
Tensorflow = 0.11.0rc0, pandas = 0.19.0, sklearn = 0.17.1 traj_dist = https://github.com/maikol-solis/trajectory_distance
##Useage: ###simulate_data.py: Generating the synthetic trajectories 'sim_trajectories' in /simulated_data/. Here, we only generate 30 trajectories as the sample. ###tmb2vec.py: Embed each trajectory to a fixed-length vector utiziling our framework. Five files is generated in /simulated_data/
- sim_trajectories_complete : Trajectories after attributes completion.
- sim_trajectories_feas : Elementary features computed by each pair of continuous records
- sim_behavior_sequences : Behavior sequence generated sliding windows and Feature Extraction Layer
- sim_normal_behavior_sequences : Moving behavior sequence after normalizaion
- sim_traj_vec_normal_reverse : Vector of trajectories generated by Seq2Seq Auto-Encoder Layer
###compared_methods.py: Four distance based trajectory clustering methods(DTW, EDR, LCSS, Hausdorff) were compared with our framwork. After compution, distance matrixs are generated in /distances/.
##Reference: Besse P, Guillouet B, Loubes J M, et al. Review and perspective for distance based trajectory clustering[J]. arXiv preprint arXiv:1508.04904, 2015.