HIGHLIGHTS
- who: Xinyi Liu from the University of have published the research: Graph-based representation for identifying individual travel activities with spatiotemporal trajectories and POI data, in the Journal: Scientific Reports Scientific Reports
- what: The authors evaluate how node features and edge weights contribute to identifying different individual travel activity types.
- how: The comparison results are analyzed in the discussion section. It shows that NL=2 receives the highest F1 score for identifying most activity types especially Work Visiting Others` Home and Health (Fig 5d) thus is used in the model for tuning other . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.