Context

Point-of-interests (POI) are used to show important locations on a map such as landmarks, bus stations, restaurants, and so on. Maps, navigation systems, recommender systems, and other services use POI information to guide their users. For instance, drivers can see gas and charging stations on their route in navigation systems, so that they can choose to stop by as needed.

Objective

This project aims to develop an algorithm to estimate public POI information such as movie theaters, libraries, grocery stores, etc.

It is important for a dataset to have ground-truth of POI information to achieve this objective. Therefore, we focus our research on the Breadcrumbs dataset (it is mandatory to work on this dataset). However, if students want to evaluate their solution on more datasets, they are encouraged to do so.

We plan a three-step plan for this project as follows:

Step 1: Students must implement the algorithm proposed by Kulkarni et al. in [1] to find geofences of users’ hotspots.

Step 2: Using a map API (Google Places API or OpenStreetMap API), POI information should be estimated for each users’ hotspots.

Step 3: Evaluate your approach using the ground-truth in the Breadcrumbs dataset.

This subject as a Semester Project is a guided project.

If you want to learn more about the Breadcrumbs Dataset, we suggest you read the Breadcrumbs Paper [1] and Breadcrumbs Dataset Description [2].

Prerequisites

Students must be confident with their algorithms, mathematics, and programming skills. Preferred programming languages are Java and Python. Note that the APIs might offer service in a different programming languages such as JavaScript.

References

[1] Vaibhav Kulkarni, Arielle Moro, Bertil Chapuis, and Benoît Garbinato. 2017. Extracting Hotspots without A-priori by Enabling Signal Processing over Geospatial Data. In Proceedings of the 25th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (SIGSPATIAL ’17). Association for Computing Machinery, New York, NY, USA, Article 79, 1–4. DOI:https://doi.org/10.1145/3139958.3140002

[2] Breadcrumbs Dataset Description, https://github.com/doplab/breadcrumbsDB/blob/main/Breadcrumbs_Dataset_Description.pdf

[3] Vaibhav Kulkarni, Arielle Moro, Bertil Chapuis, and Benoît Garbinato. 2017. Extracting Hotspots without A-priori by Enabling Signal Processing over Geospatial Data. In Proceedings of the 25th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (SIGSPATIAL ’17). Association for Computing Machinery, New York, NY, USA, Article 79, 1–4. DOI:https://doi.org/10.1145/3139958.3140002

Contact

melike.gecer@unil.ch