Real-time classification of Serengeti wildebeest behaviour with edge machine learning and a long-range IoT network
Bibliographic record
Abstract
Globally, animal populations are facing increasing levels of environmental disturbance. Human activity, land-use change, and global warming are altering migration routes, space use, activity budgets, and the behaviour of many wildlife species. Understanding impacts on wildlife at a fine scale is essential to identify locations of increased disturbance, mitigate its effects, and predict potential population level outcomes. In this work, we introduce a low-cost animal tracking system that integrates open-source electronics, edge machine learning, and an Internet of Things network, to provide real-time information on the location and behaviour of animals. The system employs an on-board machine learning algorithm to identify distinct behaviours and then transmits classification outputs along with location data over a long-range network. We deployed the system on wildebeest ( Connochaetes taurinus (Burchell, 1823)), in Serengeti National Park, Tanzania, a highly social migratory ungulate population that is ecologically and economically vital to the region. Analysis of the transmitted data showed activity readings were consistent with location data and revealed biologically meaningful fluctuations in daily activity patterns. Our system introduces a new dimension to studying animal behaviour and movement ecology by offering immediate insights into the behaviour and location of collared animals.
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 | 0.000 | 0.000 |
| 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 | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".