Modelling topological features of swarm behaviour in space and time with persistence landscapes
- Submitting institution
-
Cardiff University / Prifysgol Caerdydd
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 96793369
- Type
- D - Journal article
- DOI
-
10.1109/ACCESS.2017.2749319
- Title of journal
- IEEE Access
- Article number
- -
- First page
- 18534
- Volume
- 5
- Issue
- -
- ISSN
- 2169-3536
- Open access status
- Compliant
- Month of publication
- September
- Year of publication
- 2017
- URL
-
https://doi.org/10.1109/ACCESS.2017.2749319
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
1
- Research group(s)
-
A - Artificial intelligence and data analytics
- Citation count
- 9
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper proposes a new method for characterizing swarm behaviour in terms of topological features. The work was first published in a short form at the 2016 ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (https://doi.org/10.1145/2996913.2996949) and received the best presentation award. Previous methods had predominantly focused on characterizing swarm behaviour in terms of statistical properties. The proposed method was validated through application to real data corresponding to a swarm of fish, demonstrating that it could, in an unsupervised manner, discover significant behaviours manually identified by human experts.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -