Higher-order Mobility Flow Data
Authors/Creators
- 1. York University
Description
This dataset is a collection of higher-order mobility datasets, primarily aimed at trajectory data mining applications. These datasets have been created using the Point2Hex tool, allowing us to transform traditional GPS-based geolocations and check-in data into sequences of higher-order geometric elements, particularly hexagons. This transformation has various advantages, including reduced sparsity, analysis at different levels of granularity, improved compatibility with common machine learning architectures, enhanced generalization and overfitting reduction, and efficient visualization.
Seven popular mobility datasets, typically utilized in various trajectory-related tasks and technical problems, were subjected to this transformation process. These include applications like trajectory prediction, classification, clustering, imputation, and anomaly detection, among others.
To foster the culture of reusability and reproducibility, we are providing not only the transformed higher-order mobility flow datasets but also the source code for the Point2Hex tool and comprehensive documentation. This offering aims to streamline the generation process, ensuring that users have clear guidance on how to reproduce curated or customized versions of these datasets. The material is stored in publicly accessible repositories, ensuring its widespread accessibility.
Notes
Files
Restricted
The record is publicly accessible, but files are restricted. Log in to check if you have access.
Request access
If you would like to request access to these files, please fill out the form below.
You need to satisfy these conditions in order for this request to be accepted:
Our collection of transformed and preprocessed mobility datasets is now available to the public. However, it's essential to note that these datasets—T-Drive, GeoLife, Rome Taxi, NYC Taxi, Foursquare Check-in Dataset for NYC and TKY, and Porto Dataset—have been sourced from various providers and their original licenses apply.
We have transformed and preprocessed the data; we do not own it.
Each dataset retains its original license from the respective data provider.
The use of these datasets should respect the conditions set forth by the original data providers, whether these conditions pertain to acknowledgment, non-commercial use, or any other stipulations as specified by the data providers.
You are currently not logged in. Do you have an account? Log in here