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

Repository Web            Google
View ALL Data Sets

× Check out the beta version of the new UCI Machine Learning Repository we are currently testing! Contact us if you have any issues, questions, or concerns. Click here to try out the new site.

Swarm Behaviour Data Set
Download: Data Folder, Data Set Description

Abstract: This dataset achieved from an online survey, which is run by UNSW, Australia. It contains three data of ' Flocking - Not Flocking', 'Aligned - Not Aligned', and 'Grouped - Not Grouped'.

Data Set Characteristics:  


Number of Instances:




Attribute Characteristics:


Number of Attributes:


Date Donated


Associated Tasks:


Missing Values?


Number of Web Hits:



Dr Shadi Abpeikar- s.abpeikar '@', University of New South Wales, Australia.
A/Prof Kathryn Kasmarik- kathryn.kasmarik '@', University of New South Wales, Australia.
A/Prof Michael Barlow- m.barlow '@', University of New South Wales, Australia.
Md Mohiuddin Khan- mohiuddin.khan '@', University of New South Wales, Australia.

Data Set Information:

To access the survey, please use the following link:
[Web Link]

Attribute Information:

The attributes are xm, ym as the (X,Y) position of each boid, xVeln, yVeln as the velocity vector, xAm, yAm as the alignment vector, xSm, ySm as the separation vector, xCm, yCm as the cohesion vector, nACm as the number of boids in the radius of Alignment/Cohesion, and nSm as the number of boids in the radius of Separation. These attributes are repeated for all m boids, where m=1,...,200. Also, class labels are binary, which 1 refers to flocking, grouped, and aligned, and 0 refers to not flocking, not grouped, and not aligned.

Relevant Papers:


Citation Request:

Please refer to the Machine Learning Repository's citation policy

Supported By:

 In Collaboration With:

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