26 datasets found

The METR-LA traffic forecasting dataset contains time series data from 16 sensors.

Traffic4cast challenge 2019 dataset contains 100 billion probe points covering 3 cities (Berlin, Istanbul and Moscow) throughout a year.

The dataset used for traffic forecasting and brain network analysis.

Traffic forecasting, which aims to predict traffic conditions based on historical observations, has been an enduring research topic and is widely recognized as an essential...

The Graph-Based U-Net model is used for traffic prediction.

The SWIN-Transformer model is used for traffic map prediction.

The Traffic4cast 2021 competition provides a unique data set derived from industrial scale trajectories of raw GPS position fixes, with latitude, longitude, time stamp, as well as...

The Seattle-Loop dataset is a highway speed dataset collected from 323 loop detectors in the Greater Seattle Area.

The Urban-core dataset is an urban speed dataset containing data collected from DTG (Digital Tacho Graph) on Seoul Taxis.

The complex spatial-temporal correlations in traffic data make the traffic forecasting problem challenging. The proposed model captures the time-varying spatial correlations by...

The dataset provided for the two tasks consists of 10 different cities from around the world over the course of 2 years. The cities have been split into 3 categories: Core...

The Traffic dataset records the occupation rate of highway systems in California, USA.

The traffic forecasting problem can be categorized into three types, namely, based on the length of prediction, i.e., short-term (less than 30 min) and long term(30 ∼ 60 min).

Traffic speed prediction is a crucial task for many key purposes in intelligent traffic systems and urban planning.

Spatio-temporal prediction plays an important role in many application areas especially in traffic domain. However, due to complicated spatio-temporal dependency and high...

Zhuzhou and Baoding are two real-world datasets used in this paper for irregular traffic forecasting.

The dataset used in this paper for stochastic time series forecasting.

The METR-LA dataset contains speed profiles, given in miles per hour (mph), of 207 sensor locations collected from the loop detector on the highways of Los Angeles County.

The dataset from the California Transportation Agency contains average traffic speed.

Ring-BJ is a real-world traffic network dataset generated by ourselves.