Dairy DigiD: An Edge-Cloud Framework for Real-Time Cattle Biometrics and Health Classification
Bibliographic record
Abstract
The advancement of precision livestock farming hinges not only on breakthroughs in artificial intelligence (AI), but also on overcoming practical challenges in deploying these technologies within real-world farm environments. To bridge this gap, we present Dairy DigiD, an integrated edge-cloud AI framework designed for real-time cattle biometric identification and physiological classification. Central to the system is the lightweight YOLOv11 model, optimized for deployment on NVIDIA Jetson devices through INT8 quantization and TensorRT acceleration, achieving 94.2% classification accuracy and 24 FPS in resource-constrained settings. Complementing this, a DenseNet121-based classifier enables accurate categorization of physiological states under varying farm conditions. A key innovation of Dairy DigiD lies in its active learning pipeline, powered by Roboflow, which enhances model adaptability by prioritizing low-confidence cases for annotation—reducing labeling overhead while maintaining model accuracy. The system also features a Gradio-based user interface that reduces technician onboarding time by 84%, improving accessibility for non-technical users. Validated across ten commercial dairy farms in Atlantic Canada, the framework addresses key barriers to AI adoption in agriculture—including hardware limitations, connectivity variability, and user training—while supporting energy-efficient, continuous monitoring. Rather than introducing new algorithms, Dairy DigiD demonstrates a replicable, systems-level integration of existing AI tools, offering a practical pathway for scalable, welfare-oriented livestock monitoring in commercial dairy operations.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.008 | 0.004 |
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".