Center for Machine Learning and Intelligent Systems
About  Citation Policy  Donate a Data Set  Contact

Repository Web            Google
View ALL Data Sets

GPS Trajectories Data Set
Download: Data Folder, Data Set Description

Abstract: The dataset has been feed by Android app called Go!Track. It is available at Goolge Play Store([Web Link]).

Data Set Characteristics:  


Number of Instances:




Attribute Characteristics:


Number of Attributes:


Date Donated


Associated Tasks:

Classification, Regression

Missing Values?


Number of Web Hits:



M. O. Cruz
H. T. Macedo
R. Barreto
A. P. Guimarães

Data Set Information:

The dataset is composed by two tables. The first table go_track_tracks presents general attributes and each instance has one trajectory that is represented by the table

Attribute Information:

(1) go_track_tracks.csv: a list of trajectories
id_android - it represents the device used to capture the instance;
speed - it represents the average speed (Km/H)
distance - it represent the total distance (Km)
rating - it is an evaluation parameter. Evaluation the traffic is a way to verify the volunteers perception about the traffic during the travel, in other words,
if volunteers move to some place and face traffic jam, maybe they will evaluate 'bad'. (3- good, 2- normal, 1-bad).
rating_bus - it is other evaluation parameter. (1 - The amount of people inside the bus is little, 2 - The bus is not crowded, 3- The bus is crowded.
rating_weather - it is another evaluation parameter. ( 2- sunny, 1- raining).
car_or_bus - (1 - car, 2-bus)
linha - information about the bus that does the pathway

(2) go_track_trackspoints.csv: localization points of each trajectory
id: unique key to identify each point
latitude: latitude from where the point is
longitude: longitude from where the point is
track_id: identify the trajectory which the point belong
time: datetime when the point was collected (GMT-3)

Relevant Papers:

Provide references to papers that have cited this data set in the past (if any).

Citation Request:

We have some papers that used this dataset. The first was presented in BRACIS (4th Brazilian Conference on Intelligent System).
The paper was accepted but not published yet.
The other paper was submitted to AT&T (IJCAI-16).
The last paper is about the dataset.

1 - CRUZ, M. O.; MACEDO, H.; GUIMARãES, A. P. Grouping similar trajectories for
carpooling purposes. In: Brazilian Conference on Intelligent Systems. [S.l.: s.n.], 2015. p.
234–239. ISBN 9781509000166.

Supported By:

 In Collaboration With:

About  ||  Citation Policy  ||  Donation Policy  ||  Contact  ||  CML