Hermoupolis: A Semantic Trajectory Generator in the Data Science era
The domain of trajectory data management and mining undoubtedly contributes with interesting research problems and corresponding effective solutions to what is called data science. An interesting trend that poses new challenges in the field and has emerged especially due to the advance of location-based social networks, is that involved data cannot be considered purely spatiotemporal; trajectories of moving objects also contain additional semantic information that deserves to be further explored. On the other hand, the recently available real trajectory datasets are neither adequate nor appropriate for a wide empirical evaluation of related research proposals. As in other domains, a practical approach to overcome this limitation is developing efficient and functional synthetic trajectory generators. In this line of research, we present Hermoupolis, a pattern- and semantic-aware synthetic trajectory generator, which is able to produce realistic semantic trajectory datasets (along with their synchronized raw spatiotemporal counterparts), conforming to mobility profiles given as input by users.
Hermoupolis in Action
Case Study I: “a typical day in Athens”
Οne of the major contributions of the Hermoupolis generator, in comparison to other generators, is its ability to produce not only “raw” trajectories but also the corresponding “semantic” trajectories that are synchronized with the former. In this case study, we present in detail such a scenario, where various mobility (population) profiles, each consisting of various activities and transportation means, are simulated. The entire simulation scenario, consists of six mobility profiles:
- “young-active-workers” (orange),
- “school kids” (green),
- “young students” (turquoise),
- “middle-aged-workers” (purple),
- “middle-aged-workers-and-shoppers” (red)
- “relaxers” (light green)
More specifically, imagine a typical day of the mobility profile, called “young-active-workers” (the orange colored mobility profile in the Figure bellow) as follows: starting from their home (Stop0), they take their bicycles to a bus station (Move1) where they park their bicycles into a bicycle parking area (Stop1) and catch their bus to work (Move2). After 8 hours of work (Stop2), they catch the bus back home (Move3), arrive at the bus station (Stop3) where they change back to their bicycles and ride home (Move4). As soon as they arrive there (Stop4), they take their car in order to go for grocery shopping (Move5). After shopping (Stop5), they return back home by car (Move6) where they relax for a while (Stop6). Then, they walk to the gym (Move7) in order to work out (Stop7). Once they complete it, they return back home on foot (Move8) where they rest until the end of the day (Stop8). Here you can find the input and the output of the generator for the specific case study
Case Study II: “a big event in Athens”
This scenario simulates a big event (e.g. a concert or a football game) that takes place at Athens Olympic stadium, where lots of people from the metropolitan area around are rushing to attend. The particularity when trying to create such a scenario is that people from different areas need to have different starting times in order to reach the place of the event on time (e.g. someone that lives close to the Olympic Stadium has to start 15 minutes earlier but someone that lives very far from it needs to start 1 hour earlier). This characteristic makes it impossible to capture such a behavior by only one mobility profile. In order to bypass this problem we need to create several mobility profiles that will have different starting times depending on their proximity to the place of the event, in our case the Olympic Stadium of Athens, as illustrated in the Figure below. Here you can find the input and the output of the generator for the specific case study
Case Study III: “collective mobility behavior in Athens”
A unique feature of Hermoupolis is the ability to produce moving objects that follow a variety of mobility patterns. Consider, for instance, in the Figure underneath (left) that illustrates a mobility pattern consisting of 4 overlapping abstract Stops (depicted as rectangles) and 3 abstract Moves (depicted as arrows). It is evident that such movement simulates a flock or convoy mobility pattern. Another example is demonstrated in the Figure beneath (right), where there exist two mobility patterns; the one (green) contains 6 abstract Stops and 5 abstract Moves whereas the other (turquoise) contains 5 abstract Stops and 4 abstract Moves. Both profiles include Stops with varying spatial extent and varying speed and agility. By imposing the two profiles to meet at two specific regions – see the first and the last but one abstract Stop in Fig.3 (right) – we can simulate trajectories following a swarm pattern. Here you can find the input for the flock/convoy mobility pattern and the swarms pattern and the corresponding flock/convoy mobility pattern output and swarms pattern output of the generator for the specific case study
- N. Pelekis, C. Ntrigkogias, P. Tampakis, S. Sideridis, Y. Theodoridis. “Hermoupolis: A Trajectory Generator for Simulating Generalized Mobility Patterns”, demo paper, Proc. European Conference on Machine Learning / Principles and Practice of Knowledge Discovery in Databases, ECML/PKDD’13, Prague, Czech Republic, September 2013. [Hermoupolis Demo]
- N. Pelekis, S. Sideridis, P. Tampakis, Y. Theodoridis: “Hermoupolis: A Semantic Trajectory Generator in the Data Science era”, The SIGSPATIAL Special Newsletter of the Association for Computing Machinery, Special Interest Group on Spatial Information, Vol. 7, Number 1, March 2015.
- Nikos Pelekis, Stylianos Sideridis, Panagiotis Tampakis, and Yannis Theodoridis : “Simulating Our LifeSteps by Example” ACM Trans. Spatial Algorithms Syst. Vol. 2, Issue 3, Article 11 (October 2016), 39 pages. DOI: http://dx.doi.org/10.1145/2937753.