Revisiting Group Mobility Modelling: A Systematic Evaluation
Name
Mubashar Shahzad
Abstract
While human mobility modeling has been studied extensively over the years, there is still a partial understanding of the modeling of users moving together. In this thesis, we develop a method that can be used to build trajectories of users from mobile crowdsensed data. By using this method, we characterize different types of trajectories. We then perform rigorous experimental benchmarks to compare and analyze these trajectories in a systematic manner. Our results demonstrate that the optimal similarity score between trajectories is found when considering trajectories of the same type and a short length. In addition, our results also provide new insights into the level of (partial) similarity that can be found between users that move together.
Graduation Thesis language
English
Graduation Thesis type
Master - Software Engineering
Supervisor(s)
Huber Flores
Defence year
2022