BeRSTID: A Behaviour Real-Time Spatial Tracking Identification System used for Cat Behaviour Monitoring in an Animal Shelter
Bibliographic record
Abstract
Abstract The ability to efficiently track animal behaviour in an animal shelter has direct lifesaving applications. However, monitoring behaviour is a challenge as time and financial resources are often limited, and the size and needs of animal populations within shelters are commonly in flux. Individualized care and early recognition of distress in cats are often missed. Our research required a method of behavioural observation that was simple, accessible, used limited human and computer resources and allowed for real-time feedback. Here, we present BeRSTID, an open-source behaviour real-time spatial tracking identification system demonstrated on six cats in an animal shelter using unique 2D fiducial markers. The markers were attached to custom veterinary paper identification collars for feedback on individual animal behaviour over time. Our findings show BeRSTID correlated closely to human-coded data in both real-time and post-event processing modes of eating and drinking behaviours of cats in naturalistic shelter environments. By building upon a lateral concept of marker tracking for direct applied use in a new context, we present a low-barrier user-friendly solution using common technologies that can track and help improve welfare in animal care facilities such as shelters. Further extensions of BeRSTID can be generalized to track unique subjects in a range of environments for multiple use cases.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".