Abstract:
GPS and wireless technology generate massive trajectory data. LBSN activity trajectory adds user semantic activities like visiting work/home/entertainment places to traditional trajectory data. Comparing activity trajectories in time, location, and semantics measures their similarity. We can use implicit user preference for route planning, POI recommendation, and other online tasks. Comparing activity trajectories (i.e., computing similarity) has two main challenges. The time-space sampling rate is uneven. Individual activities vary. Trajectory complements, which only provide spatial-temporal information, solve the uneven sampling rate problem. This paper proposes learning a representation for one activity trajectory using spatio-temporal characteristics and activity semantics. Weighting trajectory points and contextual features with multi-level attention mechanisms calculates trajectory similarity. We propose a point-level and feature-level attention mechanism to adaptively select critical elements and contextual factors for learning trajectory representation. At2vec outperforms baselines in extensive experimental evaluation on real trajectory databases.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
